system

Abstract

A system is provided.SOLUTION: The system includes a means for inputting data, a means for preprocessing the data, a means for performing data analysis on the basis of the preprocessed data, a means for extracting a problem of UI / UX from an analysis result, a means for proposing an improvement plan to the extracted problem, and a means for providing the improvement plan and the analysis result to a user.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] The purpose of this invention is to efficiently identify issues in the company's services that web service professionals are responsible for and propose improvement plans. Conventional methods require SQL and advanced data analysis skills, which takes a lot of time and effort, making it difficult to quickly and effectively identify issues and implement improvement plans. In addition, problem extraction and improvement plans from a UI / UX perspective are often insufficient, which has led to problems that do not lead to improvements in service quality. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for inputting data, a means for preprocessing the data, a means for performing data analysis based on the preprocessed data, a means for extracting UI / UX issues from the analysis results, a means for proposing improvement proposals for the extracted issues, and a means for providing the improvement proposals and analysis results to users. This allows users to quickly and efficiently extract issues and obtain specific improvement proposals without requiring advanced data analysis skills. Furthermore, the system applies a rule-based algorithm to identify UI / UX issues and generate improvement proposals based on past success stories and industry best practices, which is expected to improve the quality of service.

[0006] "Data" refers to the information to be input for analysis, including log data, access data, and user behavior data related to the web service.

[0007] "Preprocessing" is the process of verifying the format of the input data, processing missing or invalid values, and normalizing the data.

[0008] "Data analysis" is the process of calculating indicators such as bounce rate, duration of visit, page transition patterns, and feature usage rate based on preprocessed data to evaluate the performance of a service.

[0009] "UI / UX issues" refer to problems related to the user interface (UI) or user experience (UX), such as pages with high bounce rates or unused functions.

[0010] "Improvement proposals" are specific suggestions for improvement to the identified UI / UX issues, based on past success stories and industry best practices.

[0011] "Means for making proposals" refers to the functions and methods for generating improvement proposals for the extracted issues and presenting them to the user.

[0012] "Means for providing to the user" refers to the functions and interfaces for providing the generated improvement proposals and analysis results in a form that can be viewed by the user.

[0013] A "rule-based algorithm" is a method for automatically identifying UI / UX issues by analyzing data based on predefined rules.

[0014] "Past success stories" refer to past achievements and examples of successful solutions to similar issues, which can serve as references for proposed improvements.

[0015] "Industry best practices" are generally accepted best practices or methods in an industry that are referenced to increase the effectiveness of improvement proposals. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention is a system that efficiently identifies issues in the company's services that web service workers are responsible for and proposes improvement plans. This system automates the process of having the server preprocess data entered by users, performing data analysis, identifying UI / UX issues, and proposing improvement plans.

[0038] Program processing

[0039] Data Input

[0040] 1. The user prepares log data and access data related to their company's service in CSV or JSON format.

[0041] 2. The user logs in to the dedicated web portal and opens the data upload page.

[0042] 3. The user selects the data file in the upload interface and clicks the submit button.

[0043] 4. The terminal reads the selected data file and sends it to the server.

[0044] 5. The server stores the received data file in temporary storage.

[0045] Data Preprocessing

[0046] 1. The server reads the data file from temporary storage and validates the file format and content.

[0047] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[0048] 3. The server normalizes the data to make it consistent.

[0049] 4. The server stores the preprocessed data in the main database.

[0050] Data analysis

[0051] 1. The server loads the preprocessed data from the main database and starts data analysis.

[0052] 2. The server executes queries to calculate key metrics such as bounce rate, time on site, page navigation patterns, and feature usage.

[0053] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[0054] Identifying UI / UX issues

[0055] 1. Based on the analysis results, the server applies a rule-based algorithm to extract UI / UX issues.

[0056] 2. The server identifies pages with high drop-off rates or pages where users tend to get lost, and analyzes related factors, such as scrolling and click patterns on specific pages.

[0057] 3. The server generates a list of issues and stores it with the evidence.

[0058] Proposal of improvement plan

[0059] 1. Based on the list of issues, the server generates improvement proposals by referencing past success stories and industry best practices.

[0060] 2. The server creates specific suggestions, such as "To reduce the bounce rate on this page, place the main information at the top and make the CTA button more prominent."

[0061] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[0062] Providing reports to users

[0063] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[0064] 2. The device requests the latest analysis results and improvement suggestions from the server.

[0065] 3. The server reads the saved report and sends it to the device.

[0066] 4. The device displays the received report on the dashboard so that the user can check it.

[0067] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[0068] Specific examples

[0069] Example 1: Identifying and improving pages with high bounce rates

[0070] 1. The user uploads website log data in CSV file format.

[0071] 2. The server validates the data format and performs preprocessing.

[0072] 3. The server analyzes the log data and identifies pages with high bounce rates.

[0073] 4. The server analyzes the user behavior data for this page and identifies the reason for abandonment.

[0074] 5. The server extracts issues such as "key information is at the bottom of the page and difficult for users to find."

[0075] 6. The server will suggest improvements such as "move the main information to the top of the page and make the CTA button more prominent."

[0076] 7. Users can view suggested improvements on their dashboard and receive detailed guidelines for implementation.

[0077] Example 2: Improving a dashboard with low feature usage

[0078] 1. The user uploads dashboard usage logs in JSON file format.

[0079] 2. The server pre-processes the file and stores it in a database.

[0080] 3. The server analyzes the usage log and identifies functions with low usage rates.

[0081] 4. The server analyzes user feedback and survey data to identify the causes of low usage.

[0082] 5. The server extracts issues such as, "This function is located in a location that is difficult for users to understand."

[0083] 6. The server suggests improvements such as "move this feature to the top menu and add a tooltip."

[0084] 7. The user checks the proposed changes on the dashboard and implements the improvements by referring to the implementation procedures.

[0085] This allows users to quickly and efficiently identify and improve issues without having advanced data analysis skills. This system is expected to greatly contribute to improving the performance of web services.

[0086] The processing flow will be explained below.

[0087] Step 1:

[0088] Users prepare log data and access data for their services and save them as CSV or JSON format files.

[0089] Step 2:

[0090] Users log in to a dedicated web portal and open the data upload page.

[0091] Step 3:

[0092] The user selects the prepared data file in the upload interface and clicks the upload button.

[0093] Step 4:

[0094] The terminal reads the selected data file and transmits its contents to the server.

[0095] Step 5:

[0096] The server stores the received data file in temporary storage.

[0097] Step 6:

[0098] The server reads the data file from temporary storage, validates the data format and content, and corrects any invalid data format, missing values, or invalid values.

[0099] Step 7:

[0100] The server performs preprocessing of the data, specifically cleaning the data (removing missing or invalid values) and normalizing it.

[0101] Step 8:

[0102] The server stores the pre-processed data in the main database.

[0103] Step 9:

[0104] The server reads the pre-processed data from the main database and begins data analysis.

[0105] Step 10:

[0106] The server executes queries to analyze the data and calculates the following metrics:

[0107] Exit rate (number of exits on a specific page divided by total number of sessions)

[0108] Duration of visit (average time spent by users on each page)

[0109] Page transition patterns (analyzing the user's transition sequence between pages)

[0110] Feature usage rate (number of times a specific feature is used divided by the total number of accesses)

[0111] Step 11:

[0112] The server stores the calculation results in temporary storage in preparation for the next process.

[0113] Step 12:

[0114] The server applies a rule-based algorithm based on the analysis results to extract UI / UX issues.

[0115] Step 13:

[0116] The server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[0117] Step 14:

[0118] The server uses heat map analysis and user behavior data (click patterns, scrolling volume, etc.) to reveal details of UI / UX issues.

[0119] Step 15:

[0120] The server lists the extracted issues and stores them together with the associated evidence.

[0121] Step 16:

[0122] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[0123] Step 17:

[0124] The server creates a report detailing the generated improvement proposals and the reasons for them, and stores it in temporary storage.

[0125] Step 18:

[0126] The user logs into the web portal and opens the analysis results dashboard.

[0127] Step 19:

[0128] The device retrieves the latest analysis results and improvement suggestions from the server in response to a user request.

[0129] Step 20:

[0130] The server reads the saved report and sends it to the user's terminal.

[0131] Step 21:

[0132] The terminal displays the received report on a dashboard so that the user can check it.

[0133] Step 22:

[0134] Users can review the suggested improvements on the dashboard and download or print the report if desired.

[0135] Example 1

[0136] 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."

[0137] Optimizing the user experience (UI / UX) is extremely important for modern web services. However, the process of data analysis and UX improvement is complex and requires specialized skills. Furthermore, many web service professionals lack the time and resources to efficiently identify issues and propose appropriate improvement plans. This can lead to poor service performance and reduced user satisfaction. Therefore, there is a need for a system that can easily and efficiently analyze data and improve the user experience.

[0138] 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.

[0139] In this invention, the server includes means for uploading data input by a user and transmitting it to the server, means for preprocessing the data and saving it in temporary storage, means for saving the preprocessed data in a main database, means for performing data analysis based on the preprocessed data, means for calculating key indicators based on data from the database, means for algorithmically extracting UI / UX issues based on the analysis results, means for generating improvement plans for the extracted issues by referring to past success stories and best practices, and means for providing the generated improvement plans and analysis results to the user's device. This makes it possible for even web service professionals without specialized knowledge to perform advanced data analysis and quickly and effectively improve UI / UX.

[0140] "User" refers to an end user who uses the system to upload data and receive analysis results and improvement suggestions.

[0141] "Server" is a central system that processes data sent by users, analyzes it and makes suggestions for improvement.

[0142] A "terminal" is a device that allows a user to access the server to upload data and check analysis results.

[0143] "Data input" is the process by which a user inputs information such as log data and access data into the system.

[0144] "Preprocessing" refers to a series of operations performed by the server to prepare the data it receives into an analyzable format, and specifically includes verifying the data format, filling in missing values, and processing invalid values.

[0145] "Data analysis" is the process of calculating indicators such as bounce rate, dwell time, and feature usage rate based on preprocessed data, and extracting meaningful information.

[0146] "UI / UX issues" refer to problems or factors that may degrade the user experience in a web service.

[0147] "Improvement proposals" are specific proposals and strategies generated by the server to solve the extracted UI / UX issues.

[0148] "Temporary storage" is a storage area for temporarily storing received data and analysis results.

[0149] The "main database" is a central storage area for storing pre-processed data and important data that needs to be stored for a long period of time.

[0150] A "rule-based algorithm" is a computational method for analyzing data based on predefined rules and extracting UI / UX issues.

[0151] "Past success stories" refer to improvement measures and methods whose effectiveness has been confirmed based on past performance.

[0152] "Best practices" refer to methods or techniques that are widely accepted across an industry.

[0153] A "dashboard" is a graphical user interface that allows users to visually check analysis results and improvement proposals.

[0154] A "query" is a search command executed against a database to retrieve specific indicators or information.

[0155] A "prompt sentence" is an input sentence that instructs a generative AI model to perform a specific analysis or generate a suggestion.

[0156] MODE FOR CARRYING OUT THE INVENTION

[0157] This invention is a system that efficiently identifies issues in the company's services that web service workers are responsible for and proposes improvement plans. This system automates the process of having the server preprocess data entered by users, performing data analysis, identifying UI / UX issues, and proposing improvement plans.

[0158] Hardware and software used

[0159] server:

[0160] A server is a computer equipped with sufficient computing resources and storage to perform high-performance data processing.

[0161] Software includes database management systems (e.g., MySQL, PostgreSQL), libraries for data analysis (e.g., Python's pandas, SciPy), and scripts for applying rule-based algorithms.

[0162] Device:

[0163] Terminals are devices that users use to access the web portal to upload data and check analysis results, such as PCs, smartphones, and tablets.

[0164] User:

[0165] Users are end users who operate and want to improve web services.

[0166] Specific operating procedures

[0167] 1. Data Input:

[0168] Users prepare log data and access data related to their website in CSV or JSON format, including access logs and click data.

[0169] Users log in to a dedicated web portal and open the data upload page, which provides an interface for users to select data files and click the submit button.

[0170] The terminal reads the selected data file and transmits it to the server.

[0171] The server stores the received data file in temporary storage.

[0172] 2. Data Preprocessing:

[0173] The server loads the data file from temporary storage and performs file format and content validation, including checking the CSV format and parsing JSON.

[0174] The server detects missing or invalid values ​​and handles them appropriately, for example, by filling in the missing values ​​with the mean value and deleting or correcting invalid values.

[0175] The server performs data normalization, scaling numeric data and encoding categorical data.

[0176] The server stores the pre-processed data in the main database.

[0177] 3. Data Analysis:

[0178] The server loads the pre-processed data from the main database and begins analyzing it, using SQL queries and Python libraries to calculate metrics such as bounce rates, time spent, page navigation patterns, and feature usage.

[0179] The server stores the calculation results in temporary storage in preparation for the next process.

[0180] 4. UI / UX issue extraction:

[0181] Based on the analysis results, the server applies a rule-based algorithm to identify UI / UX issues. For example, if a particular page has a high bounce rate, it analyzes the user behavior data for that page.

[0182] The server examines click patterns, scrolling depth, and other factors to generate a list of issues. For example, specific problems such as "key information is at the bottom of the page, making it difficult for users to find" are extracted.

[0183] 5. Suggestions for improvement:

[0184] The server then generates improvement suggestions based on the list of issues, referencing past success stories and industry best practices, such as "place key information at the top of the page and make the CTA button more prominent."

[0185] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[0186] 6. Providing reports to users:

[0187] The user logs in to the web portal again and opens the analysis results dashboard.

[0188] The device requests the latest analysis results and improvement suggestions from the server.

[0189] The server reads the saved report and sends it to the terminal.

[0190] The terminal displays the received report on a dashboard so that the user can check it.

[0191] Users can review the proposed improvements on the dashboard and download the report if necessary.

[0192] Examples of concrete examples and prompts

[0193] Example 1: Identifying and improving pages with high exit rates:

[0194] Users upload website log data in CSV file format.

[0195] The server verifies the data format, performs preprocessing, and then analyzes the log data to identify pages with high bounce rates.

[0196] The server analyzes user behavior data for this page, extracts issues such as "the main information is at the bottom of the page, making it difficult for users to find," and proposes improvements.

[0197] Example 2: Improving dashboards with low usage:

[0198] Users upload dashboard usage logs in JSON file format.

[0199] The server preprocesses the files, stores them in a database, and then analyzes the usage logs to identify underused features.

[0200] The server extracts issues such as "This function is located in a location that is difficult for users to understand" and proposes improvements.

[0201] Example prompt sentence:

[0202] "Please analyze the contents of this CSV file and summarize the issues and specific suggestions for improving the UI / UX of the website."

[0203] This system allows users to quickly and efficiently identify and improve issues without having advanced data analysis skills, and is expected to significantly contribute to improving the performance of web services.

[0204] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0205] Step 1:

[0206] Preparing and uploading data

[0207] Users prepare log data and access data related to their company's services in CSV or JSON format, including access logs and click data.

[0208] Users log in to a dedicated web portal and open the data upload page.

[0209] The user selects a data file in the upload interface and clicks the submit button.

[0210] Input: Log data in CSV or JSON format

[0211] Output: Data file sent to the server

[0212] Step 2:

[0213] Receiving and temporarily storing data

[0214] The terminal reads the selected data file and transmits it to the server.

[0215] The server stores the contents of the received data file in temporary storage.

[0216] Input: Data file submitted by the user

[0217] Output: Data file saved in temporary storage

[0218] Step 3:

[0219] Data validation and preprocessing

[0220] The server reads the data file from temporary storage and validates the file format and content, specifically checking the CSV format and parsing JSON.

[0221] The server detects missing or invalid data values ​​based on the verification results and takes appropriate action.

[0222] Input: Data file for temporary storage

[0223] Output: Validated and processed preprocessed data

[0224] Step 4:

[0225] Data normalization

[0226] The server normalizes the preprocessed data, specifically scaling numeric data and encoding categorical data.

[0227] The server stores the normalized data in a main database.

[0228] Input: Preprocessed data

[0229] Output: Main database with normalized data

[0230] Step 5:

[0231] Calculating key indicators

[0232] The server reads the pre-processed data from the main database and executes the necessary queries.

[0233] The server calculates important metrics such as bounce rate, time spent, page transition patterns, and feature usage.

[0234] Input: Data in the main database

[0235] Output: Analysis results including calculated key indicators

[0236] Step 6:

[0237] Identifying UI / UX issues

[0238] Based on the calculated analysis results, the server applies a rule-based algorithm to extract UI / UX issues.

[0239] Specifically, the server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[0240] Input: Analysis results

[0241] Output: Issue list

[0242] Step 7:

[0243] Generate improvement proposals

[0244] Based on the list of issues, the server generates improvement proposals by referencing past success stories and industry best practices.

[0245] The server generates specific recommendations (e.g., "Place key information at the top of the page and make the CTA button prominent").

[0246] Input: Issue list, past success stories, best practices

[0247] Output: A report with concrete improvement suggestions

[0248] Step 8:

[0249] Providing reports

[0250] The user logs in to the web portal again and opens the analysis results dashboard.

[0251] The device requests the latest analysis results and improvement suggestions from the server.

[0252] The server reads the saved report and sends it to the terminal.

[0253] The terminal displays the received report on a dashboard so that the user can check it.

[0254] Input: Analysis results and improvement proposal request

[0255] Output: Report provided to the user

[0256] Through this series of processes, users can quickly and efficiently extract UI / UX issues and obtain appropriate improvement proposals, even without specialized knowledge.

[0257] (Application example 1)

[0258] 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."

[0259] In recent years, improving the user interface (UI) and user experience (UX) has become increasingly important in e-commerce (mail order) sites. However, identifying UI / UX issues and efficiently improving them requires advanced data analysis skills and a great deal of effort from site operators. Furthermore, they are required to not only provide analysis results but also propose specific improvement plans. Therefore, there is a need for a system that allows site operators to easily input data and receive analysis results and improvement proposals.

[0260] 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.

[0261] In this invention, the server includes means for inputting data, means for preprocessing data, means for performing data analysis based on the preprocessed data, means for extracting issues with the user interface and user experience from the analysis results, means for proposing improvement plans for the extracted issues, means for providing the improvement plans and analysis results to users, means for calculating multiple indicators, means for an online shopping site operator to upload data using a smartphone and receive the analysis results and improvement proposals, means for generating improvement plans based on past success stories and best practices, and means for saving and reading data using temporary storage and a main database. This enables operators to quickly and efficiently extract and improve issues using their smartphones, even without advanced data analysis skills.

[0262] 1. "Data input means" refers to the overall interface and process by which a user inputs data into the system.

[0263] 2. "Preprocessing measures" refers to measures to prepare data in an appropriate state before proceeding to the next step, such as data format verification, missing value imputation, invalid value processing, and data standardization.

[0264] 3. "Data analysis tools" refers to a set of processes and algorithms that calculate various indicators based on pre-processed data.

[0265] 4. "UI / UX issue extraction method" refers to the method for identifying issues and problems related to the user interface and user experience based on the analysis results.

[0266] 5. "Means for proposing improvements" refers to the means for generating specific improvement proposals based on the issues identified, with reference to past success stories and industry best practices.

[0267] 6. "Means for providing improvement proposals and analysis results" refers to the means for providing the generated improvement proposals and analysis results to the user.

[0268] 7. "Means for calculating indicators" refers to the means for calculating important indicators such as bounce rate, duration of visit, page transition patterns, and function usage rate.

[0269] 8. "Smartphone uploading means" refers to the means by which the operator of an online shopping site uploads data using a smartphone.

[0270] 9. "Means for referring to past success stories and best practices" refers to means for referring to past success stories and industry best practices when generating improvement proposals.

[0271] 10. "Temporary storage and main database means" refers to the storage means used temporarily to store and retrieve data and the main database for long-term data storage.

[0272] This invention relates to a data analysis and improvement proposal system that can be used by online shopping site operators. The system aims to enable operators to efficiently identify and improve UI / UX issues by automating a series of processes from data input to preprocessing, analysis, problem extraction, improvement proposal proposals, and result provision.

[0273] System Configuration

[0274] Data Input

[0275] Users use their smartphones to prepare log data and access data related to online shopping sites in CSV or JSON format, and then upload it to a cloud server using a dedicated application. The uploaded data is then stored in temporary storage.

[0276] Data Preprocessing

[0277] The server reads the data from the temporary storage, performs formal validation, and if the data contains missing or invalid values, it imputes or removes them appropriately and standardizes the data. The preprocessed data is then stored in the main database.

[0278] Data analysis

[0279] The server reads pre-processed data from the main database and calculates various metrics (e.g., exit rate, visit duration, page navigation patterns, feature usage rate) using multiple SQL queries and data processing algorithms.

[0280] Identifying UI / UX issues

[0281] Based on the data analysis results, the server identifies issues such as high bounce rates and low conversion rates for specific pages and functions, and uses rule-based algorithms to extract issues related to the user interface and user experience.

[0282] Improvement proposal

[0283] The server then generates specific improvement proposals for the identified issues, referencing past success stories and best practices, such as "place key information at the top of the page and make the CTA button more prominent."

[0284] Report provision

[0285] The server creates a report summarizing the generated improvement proposals and analysis results and provides it to the user, who can then check the report on their smartphone app and download it as needed.

[0286] Hardware and software used

[0287] The system consists of the following hardware and software:

[0288] Cloud Server: Responsible for storing and processing data.

[0289] Smartphone: Used by users to upload data and check results. Dedicated applications are installed.

[0290] Temporary storage and main database: Used for data storage.

[0291] Pandas and SQL: Used for data preprocessing and analysis.

[0292] Specific examples

[0293] The user prepares log data from an online shopping site in CSV format and uploads it to a cloud server via a smartphone app. The server stores the received data in temporary storage, performs formal validation, and processes missing values. The preprocessed data is then stored in the main database and indicators are calculated. Based on the calculation results, pages with high bounce rates are identified and issues on those pages are extracted. The server then proposes specific improvement plans, such as "moving key information to the top," and generates a report to provide to the user.

[0294] Prompt Sentence Examples

[0295] You can request specific analysis and improvement suggestions for your generative AI model using the following prompts:

[0296] Request Type: Analysis

[0297] Data format: CSV

[0298] Data Path: ecommerce_log.csv

[0299] Analysis type: Exit rate analysis, Conversion rate analysis

[0300] Proposal criteria: Past success stories, industry best practices

[0301] This prompt allows the system to take appropriate action based on the specified data format and analysis type.

[0302] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0303] Step 1:

[0304] A user uses a smartphone to prepare log data and access data related to an online shopping site in CSV or JSON format, and uploads it to a cloud server using a dedicated application. The input is a data file prepared by the user (e.g., ecommerce_log.csv), and the output is the uploaded data stored in temporary storage on the cloud server.

[0305] Step 2:

[0306] The server reads the uploaded data from temporary storage and verifies the data format. The input is the data file in temporary storage, and the output is the data file after format verification. Once verification is complete, it proceeds to the next process.

[0307] Step 3:

[0308] The server performs data preprocessing, such as missing value imputation, invalid value handling, and data standardization. The input is a data file that has been format-validated, and the output is a preprocessed data file. The preprocessed data is stored in the main database.

[0309] Step 4:

[0310] The server reads preprocessed data from the main database and analyzes and calculates various indicators (e.g., exit rate, duration of visit, page transition patterns, feature usage rate, etc.). The input is the preprocessed data, and the output is the calculated indicator results. The calculation results are saved in temporary storage.

[0311] Step 5:

[0312] The server extracts user interface and user experience related issues based on the analysis results. The input is the calculated metrics and the output is a list of extracted issues. Specific problems and issues are extracted using a rule-based algorithm.

[0313] Step 6:

[0314] The server generates specific improvement proposals for the extracted issues by referencing past success stories and industry best practices. The input is a list of issues, and the output is specific improvement proposals. For example, suggestions include "Place key information at the top of the page and make the CTA button more prominent."

[0315] Step 7:

[0316] The server creates a report that summarizes the generated improvement proposals and analysis results. The inputs are the improvement proposals and analysis results, and the output is a report. The report is saved in temporary storage and formatted so that it can be provided to the user.

[0317] Step 8:

[0318] Users check the reports using a smartphone app. The input is the report provided by the server, and the output is confirmation or download of the report contents. Users can check the details of the report generated in the smartphone app and obtain specific implementation procedures if necessary.

[0319] 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.

[0320] This invention is a system that enables web service professionals to efficiently identify issues in their company's services and propose improvement proposals. By combining it with an emotion engine that recognizes user emotions, it achieves more accurate issue identification and improvement proposal proposals. This system automates a series of processes: the server preprocesses data input by the user, performs data analysis, identifies UI / UX issues, and proposes improvement proposals for those issues. Furthermore, the emotion engine makes it possible to analyze and propose proposals that take into account user emotion data.

[0321] Program processing

[0322] Data Input

[0323] 1. The user prepares log data and access data related to their company's services in CSV or JSON format.

[0324] 2. The user logs in to the dedicated web portal and opens the data upload page.

[0325] 3. The user selects the prepared data file in the upload interface and clicks the Upload button.

[0326] 4. The terminal reads the selected data file and sends its contents to the server.

[0327] 5. The server stores the received data file in temporary storage.

[0328] Data Preprocessing

[0329] 1. The server reads the data file from temporary storage and verifies the data format and content.

[0330] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[0331] 3. The server normalizes the data to make it consistent.

[0332] 4. The server stores the preprocessed data in the main database.

[0333] Data analysis

[0334] 1. The server loads the preprocessed data from the main database and starts data analysis.

[0335] 2. The server executes queries to analyze the data and calculates the following metrics:

[0336] Abandonment rate

[0337] Stay time

[0338] Page Transition Pattern

[0339] Function usage rate

[0340] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[0341] Emotion data collection and analysis

[0342] 1. Users use dedicated tools and applications to collect emotional data during use.

[0343] 2. The device sends the emotion data to the server.

[0344] 3. The server analyzes the received emotion data and recognizes emotion patterns.

[0345] Identifying UI / UX issues

[0346] 1. The server applies a rule-based algorithm based on the analysis results and emotion data to extract UI / UX issues.

[0347] 2. The server identifies pages with high bounce rates and pages where users are likely to get lost, and analyzes the related factors.

[0348] 3. The server analyzes how specific UI elements affect emotions based on the user's emotional data.

[0349] 4. The server lists the extracted issues and stores them together with the associated evidence.

[0350] Proposal of improvement plan

[0351] 1. The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[0352] 2. The server compares the generated improvement proposals with the user's emotional data and makes suggestions that are appropriate for each individual user.

[0353] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[0354] Providing reports to users

[0355] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[0356] 2. The device requests the latest analysis results and improvement suggestions from the server.

[0357] 3. The server reads the saved report and sends it to the device.

[0358] 4. The device displays the received report on the dashboard so that the user can check it.

[0359] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[0360] Specific examples

[0361] Example 1: Identifying and improving pages with high bounce rates

[0362] 1. The user uploads the website log data in CSV format.

[0363] 2. The server validates the data format and performs preprocessing.

[0364] 3. The server analyzes the log data and identifies pages with high bounce rates.

[0365] 4. The server analyzes the user behavior and emotion data for this page to identify the cause of abandonment.

[0366] 5. The server extracts issues such as "key information is at the bottom of the page and difficult for users to find."

[0367] 6. The server will suggest improvements such as "move the main information to the top of the page and make the CTA button more prominent."

[0368] 7. Users can view suggested improvements on their dashboard and receive detailed guidelines for implementation.

[0369] Example 2: Improving a dashboard with low feature usage

[0370] 1. The user uploads dashboard usage logs in JSON format.

[0371] 2. The server preprocesses the data and stores it in a database.

[0372] 3. The server analyzes usage logs and sentiment data to identify features with low usage rates.

[0373] 4. The server analyzes user feedback and survey data to identify the causes of low usage.

[0374] 5. The server extracts issues such as, "This function is located in a location that is difficult for users to understand."

[0375] 6. The server suggests improvements such as "move this feature to the top menu and add a tooltip."

[0376] 7. The user checks the proposed changes on the dashboard and implements the improvements by referring to the implementation procedures.

[0377] As described above, this system enables even users without advanced data analysis skills to quickly and efficiently identify issues and obtain improvement proposals that take into account the emotions of individual users. This system is expected to make a significant contribution to improving the performance of web services and optimizing the user experience.

[0378] The processing flow will be explained below.

[0379] Step 1:

[0380] Users prepare log data and access data related to their services in CSV or JSON format.

[0381] Step 2:

[0382] Users log in to a dedicated web portal and open the data upload page.

[0383] Step 3:

[0384] The user selects the prepared data file in the upload interface and clicks the upload button.

[0385] Step 4:

[0386] The terminal reads the selected data file and transmits its contents to the server.

[0387] Step 5:

[0388] The server stores the received data file in temporary storage.

[0389] Step 6:

[0390] The server reads the data file from temporary storage, validates the data format and content, and corrects any invalid data format, missing values, or invalid values.

[0391] Step 7:

[0392] The server performs preprocessing of the data, specifically cleaning the data (removing missing or invalid values) and normalizing it.

[0393] Step 8:

[0394] The server stores the pre-processed data in the main database.

[0395] Step 9:

[0396] The server reads the pre-processed data from the main database and begins data analysis.

[0397] Step 10:

[0398] The server executes queries to analyze the data and calculates the following metrics:

[0399] Exit rate (number of exits on a specific page divided by total number of sessions)

[0400] Duration of visit (average time spent by users on each page)

[0401] Page transition patterns (analyzing the user's transition sequence between pages)

[0402] Feature usage rate (number of times a specific feature is used divided by the total number of accesses)

[0403] Step 11:

[0404] The server stores the calculation results in temporary storage in preparation for the next process.

[0405] Step 12:

[0406] Users use dedicated tools and applications to collect emotion data during use.

[0407] Step 13:

[0408] The terminal transmits the collected emotion data to the server.

[0409] Step 14:

[0410] The server analyzes the received emotion data and recognizes emotion patterns.

[0411] Step 15:

[0412] Based on the analysis results and emotional data, the server applies a rule-based algorithm to extract UI / UX issues.

[0413] Step 16:

[0414] The server identifies pages with high drop-off rates and pages where users tend to get lost, analyzes the associated factors, and takes sentiment data into account.

[0415] Step 17:

[0416] The server uses heat map analysis and user behavior data (click patterns, scrolling volume, etc.) to reveal details of UI / UX issues.

[0417] Step 18:

[0418] The server lists the extracted issues and stores them together with the associated evidence.

[0419] Step 19:

[0420] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[0421] Step 20:

[0422] The server compares the generated improvement proposals with the user's emotional data and makes suggestions that are appropriate for each individual user.

[0423] Step 21:

[0424] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[0425] Step 22:

[0426] The user logs in to the web portal again and opens the analysis results dashboard.

[0427] Step 23:

[0428] The device requests the latest analysis results and improvement suggestions from the server.

[0429] Step 24:

[0430] The server reads the saved report and sends it to the terminal.

[0431] Step 25:

[0432] The terminal displays the received report on a dashboard so that the user can check it.

[0433] Step 26:

[0434] Users can review the suggested improvements on the dashboard and download or print the report if desired.

[0435] Through this process, users can quickly and efficiently identify issues and obtain improvement proposals that take into account the emotions of individual users, even without advanced data analysis skills. This system is expected to make a significant contribution to improving the performance of web services and optimizing the user experience.

[0436] Example 2

[0437] 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."

[0438] With conventional web services, it was difficult to efficiently identify issues with the user interface and user experience and propose improvement proposals. Furthermore, the effectiveness of improvement proposals was limited because they did not take user emotions into consideration. This meant that service performance improvements and optimization of the user experience could not be fully achieved.

[0439] The identification process 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 inputting data, means for preprocessing data, means for performing data analysis based on the preprocessed data, means for extracting issues in the user interface and user experience, means for proposing improvement plans for the extracted issues, means for collecting and analyzing user emotion data, means for adjusting the issues and improvement plans based on the emotion data, means for providing the improvement plans and analysis results to the user, and means for generating a report to be provided to the user. This makes it possible to accurately extract issues and propose effective improvement plans that take user emotions into consideration.

[0440] "Data input" refers to a user providing log data and access data to the system.

[0441] "Data preprocessing" refers to the process of filling in missing values, correcting invalid values, and normalizing the data to make it consistent, in order to make the collected data easier to analyze.

[0442] "Data analysis" refers to the process of calculating metrics and identifying issues related to the user interface and user experience based on pre-processed data.

[0443] "Identifying issues in the user interface and user experience" refers to using data analysis results and user emotion data to identify problems in the user interface and user experience of web services.

[0444] "Proposing improvements" refers to presenting specific methods for correcting or improving the identified issues based on past success stories and best practices.

[0445] "Collection and analysis of emotional data" refers to the process of collecting emotional data from users while they are using the service and analyzing that data to understand the user's emotional state.

[0446] "Adjustment of issues and improvement proposals" refers to optimizing identified issues and proposed improvement proposals for individual users based on collected and analyzed emotional data.

[0447] "Report generation" refers to the process of creating a report detailing the analysis results and improvement proposals and providing it to the user.

[0448] This invention is a system that allows users of web services to efficiently identify issues with their own services and propose improvement plans. The system includes the following main components:

[0449] 1. Data input method

[0450] Users prepare log data and access data related to their services in CSV or JSON format.

[0451] Users log in to a dedicated web portal and upload data files from the data upload page.

[0452] The terminal reads the uploaded data file and transmits its contents to the server.

[0453] The server stores the received data file in temporary storage.

[0454] 2. Data preprocessing methods

[0455] The server reads the data file from the temporary storage and verifies the data format and content.

[0456] The server identifies missing, invalid, and outlier values ​​and takes appropriate action (e.g., imputing the mean value of missing values).

[0457] The server normalizes the data to ensure consistency.

[0458] The server stores the pre-processed data in the main database.

[0459] 3. Data Analysis Methods

[0460] The server reads the pre-processed data from the main database and runs queries to perform data analysis.

[0461] The server calculates the following metrics: exit rate, visit duration, page transition patterns, and feature usage rate.

[0462] The server stores the calculation results in temporary storage in preparation for the next process.

[0463] 4. Methods for collecting and analyzing emotion data

[0464] Users collect emotion data during use using dedicated tools and applications.

[0465] The terminal transmits the emotion data to the server.

[0466] The server analyzes the received emotion data and recognizes emotion patterns.

[0467] 5. Methods for extracting UI / UX issues

[0468] The server applies a rule-based algorithm to extract issues based on the analysis results and emotion data.

[0469] The server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[0470] The server analyzes how specific UI elements affect emotions.

[0471] The server lists the extracted issues and stores them together with the associated evidence.

[0472] 6. Means of proposing improvements

[0473] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[0474] The server compares the proposed improvement plan with the user's emotional data and makes suggestions that are appropriate for each individual user.

[0475] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[0476] 7. Report Generation Methods

[0477] The server has means for generating and providing reports to the user.

[0478] Specific examples

[0479] For example, when uploading a website's log data in CSV format, a user selects and uploads the file from the data upload page. This data is then sent to the server, where it is validated and pre-processed. Data analysis identifies pages with high drop-off rates and user sentiment data, and UI / UX issues are extracted. Improvement proposals are then proposed based on past success stories and industry best practices. Finally, the proposals are provided to the user in the form of a detailed report.

[0480] The specific hardware or software used

[0481] Temporary storage: Amazon S3, etc.

[0482] Main database: PostgreSQL, etc.

[0483] Data analysis libraries: Python Pandas, TensorFlow, etc.

[0484] Prompt Sentence Examples

[0485] "If a particular page has a high bounce rate, identify the cause and suggest appropriate improvements."

[0486] The above is an embodiment of the present invention, which contributes greatly to improving the performance of Web services and optimizing the user experience.

[0487] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0488] Step 1: Data Input

[0489] 1. The user prepares log data and access data related to their company's services in CSV or JSON format.

[0490] Input: User-prepared CSV or JSON file

[0491] What happens: A user accesses a web portal in their browser to select and upload a data file.

[0492] 2. The user logs in to the dedicated web portal and opens the data upload page.

[0493] Input: Portal login information

[0494] Specific behavior: The user enters their authentication information and clicks the login button.

[0495] 3. The user selects the prepared data file in the upload interface and clicks the Upload button.

[0496] Input: Selected data file

[0497] Specific behavior: The user clicks the "Choose File" button, selects a CSV file from local storage, and clicks the "Upload" button.

[0498] 4. The terminal reads the selected data file and sends its contents to the server.

[0499] Input: Selected data file

[0500] Output: Sending the data file to the server

[0501] Specific operation: The device sends a data file to the server using an HTTP POST request.

[0502] 5. The server stores the received data file in temporary storage.

[0503] Input: Received data file

[0504] Output: Data file saved in temporary storage

[0505] Specific operation: The server stores the received file in temporary storage such as an Amazon S3 bucket.

[0506] Step 2: Data Preprocessing

[0507] 1. The server reads the data file from temporary storage and verifies the data format and content.

[0508] Input: Data file saved in temporary storage

[0509] Output: Validated data file

[0510] Specific operation: The server checks the data format (such as the CSV header row) and validates the contents.

[0511] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[0512] Input: Validated data file

[0513] Output: Preprocessed data

[0514] Specific operation: Uses the Pandas library to perform operations such as filling in NaN (missing values) with the average value of the column.

[0515] 3. The server normalizes the data to make it consistent.

[0516] Input: Data file with missing, invalid, and outlier processed

[0517] Output: Normalized data file

[0518] Specific operation: Scales numerical data and normalizes it to the range 0 to 1.

[0519] 4. The server stores the preprocessed data in the main database.

[0520] Input: Normalized data file

[0521] Output: Preprocessed data stored in the main database

[0522] Specific operation: Insert the preprocessed data into a PostgreSQL database.

[0523] Step 3: Data analysis

[0524] 1. The server loads the preprocessed data from the main database and starts data analysis.

[0525] Input: Preprocessed data stored in the main database

[0526] Output: Analysis results

[0527] Specific behavior: Executes an SQL query to retrieve the required data from the database.

[0528] 2. The server executes queries to analyze the data and calculates the following metrics:

[0529] Abandonment rate

[0530] Stay time

[0531] Page Transition Pattern

[0532] Function usage rate

[0533] Input: Data retrieved from the database

[0534] Output: Calculation results for each indicator

[0535] Specific operation: Calculate each metric using SQL queries or Python scripts.

[0536] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[0537] Input: Calculated indicator data

[0538] Output: Calculation results saved in temporary storage

[0539] Specific operation: The calculation results are saved as a JSON format file on Amazon S3.

[0540] Step 4: Collect and analyze emotion data

[0541] 1. Users use dedicated tools and applications to collect emotional data during use.

[0542] Input: Data from emotion data collection tools

[0543] Output: Collected emotion data

[0544] What it does: Collects facial expression data from users using emotion recognition apps and browser extensions.

[0545] 2. The device sends the emotion data to the server.

[0546] Input: Collected emotion data

[0547] Output: Emotion data sent to the server

[0548] Specific operation: Emotion data is sent to the server in real time using a REST API.

[0549] 3. The server analyzes the received emotion data and recognizes emotion patterns.

[0550] Input: Emotion data sent to the server

[0551] Output: Parsed emotion patterns

[0552] What it does: Analyzes emotional patterns using deep learning models (e.g., TensorFlow or PyTorch).

[0553] Step 5: Identify UI / UX issues

[0554] 1. The server applies a rule-based algorithm to extract issues based on the analysis results and emotion data.

[0555] Input: Data analysis results and emotion data

[0556] Output: Extracted issues

[0557] Specific behavior: Applying rule-based algorithms to identify issues from specific indicator values ​​and sentiment patterns.

[0558] 2. The server identifies pages with high bounce rates and pages where users are likely to get lost, and analyzes the related factors.

[0559] Input: Extracted issues

[0560] Output: Identified high exit rate pages and pages where users are likely to get lost

[0561] Specific actions: Correlate and analyze user behavioral data and sentiment data to identify problematic pages.

[0562] 3. The server analyzes how specific UI elements affect emotions.

[0563] Input: User behavioral and emotional data

[0564] Output: UI elements that affect emotions

[0565] Specific behavior: Analyze how clicking a specific button or link affects a user's emotions.

[0566] 4. The server lists the extracted issues and stores them together with the associated evidence.

[0567] Input: Clarified issue

[0568] Output: A list of issues saved with evidence

[0569] Specific action: Compile a list of issues and related data into a single report.

[0570] Step 6: Propose improvements

[0571] 1. The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[0572] Input: Extracted issues

[0573] Output: Generated improvement suggestions

[0574] Specific operation: Query past success stories from a database and generate improvement suggestions based on them.

[0575] 2. The server compares the proposed improvement plan with the user's emotional data and makes suggestions that are appropriate for each individual user.

[0576] Input: Improvement proposals and user emotion data

[0577] Output: Adjusted improvement proposal

[0578] Specific action: Check whether the generated improvement proposals can elicit positive emotions from users.

[0579] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[0580] Input: Adjusted improvement proposal

[0581] Output: Improvement suggestions saved as a report

[0582] Specific operation: The proposal and its rationale are written in Markdown format and saved in temporary storage (e.g., Amazon S3).

[0583] Step 7: Provide the report to the user

[0584] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[0585] Input: Portal login information

[0586] Output: Access to the dashboard

[0587] Specific operations: After logging in to the web portal, click the "View analysis results" button.

[0588] 2. The device requests the latest analysis results and improvement suggestions from the server.

[0589] Input: Request from the dashboard page

[0590] Output: The data requested from the server

[0591] Specific operation: Send an Ajax request to get the latest data.

[0592] 3. The server reads the saved report and sends it to the device.

[0593] Input: Saved Report

[0594] Output: Report sent to terminal

[0595] Specific operation: Download the report from Amazon S3 etc. and send it to the device.

[0596] 4. The device displays the received report on the dashboard so that the user can check it.

[0597] Input: Report sent from the server

[0598] Output: The report displayed in a dashboard

[0599] Specific operation: Renders the retrieved report data in HTML format and displays it on a dashboard.

[0600] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[0601] Input: Report displayed on dashboard

[0602] Output: Downloaded report

[0603] Specific behavior: Click the "Download Report" button and save the report in PDF format to local storage.

[0604] (Application example 2)

[0605] 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."

[0606] The present invention aims to provide an effective system for improving the quality of customer experience in brick-and-mortar stores. In particular, the system aims to support store operators in increasing customer satisfaction by extracting issues in the customer experience based on customer behavioral and emotional data and automatically proposing appropriate improvement plans.

[0607] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0608] In this invention, the server includes means for inputting data, means for preprocessing the data, means for performing data analysis based on the preprocessed data, means for extracting issues in the user interface and user experience, means for proposing improvement plans for the extracted issues, means for collecting and analyzing user emotion data, and means for providing the improvement plans and analysis results to the user. This makes it possible to identify detailed customer experience issues based on customer behavioral data and emotion data, and to provide effective improvement plans.

[0609] "Means for inputting data" is a general term for various hardware and software that input data into the system from outside.

[0610] "Means for preprocessing data" refers to functions that include processes for verifying the format and content of input data, handling missing values ​​and invalid values, and normalizing data.

[0611] "Means for performing data analysis based on preprocessed data" refers to the function of using normalized data to perform various analyses, calculate indicators, and discover patterns.

[0612] "Means for identifying issues in user interfaces and user experiences" includes algorithms and procedures for identifying problems related to the use of systems and services based on the results of data analysis.

[0613] "Means for proposing improvement plans for extracted issues" refers to the function within the system that automatically generates and proposes specific solutions to issues.

[0614] "Means for collecting and analyzing user emotional data" includes tools and algorithms for measuring and recording a user's emotional state and analyzing emotional patterns.

[0615] "Means for providing improvement proposals and analysis results to users" refers to various interfaces that visually display the improvement proposals and analysis results generated by the system and provide them to users.

[0616] A "temporary storage device" is a memory or storage device for short-term storage of data files.

[0617] The system of the present invention collects and analyzes various data, automatically extracts issues, and proposes improvement plans in order to improve the customer experience in physical stores. This system is composed of a means for inputting data, a means for preprocessing the data, a means for performing data analysis based on the preprocessed data, a means for extracting issues in the user interface and user experience, a means for proposing improvement plans for the extracted issues, a means for collecting and analyzing user emotion data, and a means for providing the user with improvement plans and analysis results.

[0618] Hardware and software used

[0619] 1. Hardware

[0620] Smartphone

[0621] camera

[0622] server

[0623] 2. Software

[0624] Python

[0625] Pandas

[0626] Scikit-learn

[0627] EmotionEngine (virtual module)

[0628] UI_UX_Analyzer (virtual module)

[0629] What the program does

[0630] Data Input

[0631] Users upload customer behavior and feedback data collected in-store to the system using their smartphones, with the data provided in CSV or JSON format.

[0632] Data Preprocessing

[0633] The server first performs formal validation of the received data and processes invalid and missing values. Specifically, it reads the data as a data frame using Pandas, removes missing values, and normalizes and standardizes the numerical data using Scikit-learn.

[0634] Data analysis

[0635] Once the data preprocessing is complete, the server analyzes the data using UI_UX_Analyzer, which calculates important metrics such as customer behavior patterns, dropout rates, and dwell time.

[0636] Emotion data collection and analysis

[0637] Customer emotional data is collected in real time via smartphones and analyzed using EmotionEngine to recognize customer emotional patterns (e.g., satisfaction, dissatisfaction, excitement, etc.).

[0638] Identifying UI / UX issues and proposing improvements

[0639] Based on the results of data analysis and sentiment data, the server extracts issues in the user interface and user experience. For any issues discovered, it generates effective improvement proposals based on past success stories and industry standards.

[0640] Providing reports to users

[0641] Finally, the analysis results and improvement recommendations are provided to the user. This information is displayed in a visually easy-to-understand report format on a dashboard, where the user can view the details of the improvement recommendations and receive guidance on how to implement them.

[0642] Examples of concrete examples and prompts

[0643] Specific examples

[0644] For example, if a problem is identified where in-store navigation is difficult for customers to understand, the server will suggest moving important information to the top of the page. This suggestion is based on customer behavioral and emotional data, reducing customer frustration when trying to find information.

[0645] Prompt Sentence Examples

[0646] Analyze customer sentiment based on the feedback below.

[0647] Feedback: "The navigation in this store is very confusing. It took me a while to find the product I wanted."

[0648] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0649] Step 1: Data Input

[0650] Users upload customer behavior and feedback data collected in physical stores to the system using their smartphones, and this data is provided in CSV or JSON format.

[0651] Input: Customer behavior and feedback data in CSV or JSON format

[0652] Output: Raw data uploaded to the server

[0653] Step 2: Receiving and storing data

[0654] The terminal receives the uploaded data file and transmits the contents to the server, which stores the received data file in a temporary storage device.

[0655] Input: Data file sent to the server

[0656] Output: Raw data file saved to temporary storage

[0657] Step 3: Data Preprocessing

[0658] The server reads the data file from temporary storage, validates the data format, handles invalid and missing values, and performs standardization and normalization. It converts the data into a data frame using Pandas, removes missing values, and normalizes the numeric data using Scikit-learn.

[0659] Input: Raw data file read from temporary storage

[0660] Output: Preprocessed data

[0661] Step 4: Data analysis

[0662] The server uses UI_UX_Analyzer to perform detailed data analysis based on the pre-processed data, and calculates key indicators such as customer behavior patterns, dropout rates, and duration of stay.

[0663] Input: Preprocessed data

[0664] Output: Analysis results (customer behavior patterns, abandonment rate, duration of stay, etc.)

[0665] Step 5: Collect and analyze emotion data

[0666] The terminal collects customer emotional data in real time via the smartphone. The server uses EmotionEngine to analyze the emotional data and recognize the customer's emotional patterns. This analysis process utilizes, for example, feedback text and facial expressions provided when customers answer questionnaires on their smartphones.

[0667] Input: Real-time collected emotion data

[0668] Output: Parsed emotion patterns

[0669] Step 6: Identify UI / UX issues

[0670] The server applies rule-based algorithms based on data analysis and sentiment data to identify issues with the user interface and user experience. For example, it can identify areas where customers are experiencing inconvenience on specific pages or operations based on customer feedback and behavioral analysis data.

[0671] Input: Data analysis results and sentiment pattern analysis results

[0672] Output: A list of extracted UI / UX issues

[0673] Step 7: Propose improvements

[0674] The server generates improvement suggestions for the extracted issues based on past best practices and industry standards, including specific suggestions such as "move important information to the top of the page" or "change the location of new features."

[0675] Input: Extracted UI / UX issue list

[0676] Output: Suggested improvements

[0677] Step 8: Generate and deliver reports

[0678] The server generates a visually easy-to-understand report of the proposed improvements and analysis results and stores it in temporary storage. Users can log in to the web portal, view the report on the dashboard, and download the report if necessary.

[0679] Input: Proposed improvements and analysis results

[0680] Output: Generated report with improvement suggestions and analysis results

[0681] 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.

[0682] 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.

[0683] 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.

[0684] [Second embodiment]

[0685] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0686] 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.

[0687] 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).

[0688] 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.

[0689] 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.

[0690] 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).

[0691] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0692] 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.

[0693] 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.

[0694] 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.

[0695] 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.

[0696] 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."

[0697] This invention is a system that efficiently identifies issues in the company's services that web service workers are responsible for and proposes improvement plans. This system automates the process of having the server preprocess data entered by users, performing data analysis, identifying UI / UX issues, and proposing improvement plans.

[0698] Program processing

[0699] Data Input

[0700] 1. The user prepares log data and access data related to their company's service in CSV or JSON format.

[0701] 2. The user logs in to the dedicated web portal and opens the data upload page.

[0702] 3. The user selects the data file in the upload interface and clicks the submit button.

[0703] 4. The terminal reads the selected data file and sends it to the server.

[0704] 5. The server stores the received data file in temporary storage.

[0705] Data Preprocessing

[0706] 1. The server reads the data file from temporary storage and validates the file format and content.

[0707] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[0708] 3. The server normalizes the data to make it consistent.

[0709] 4. The server stores the preprocessed data in the main database.

[0710] Data analysis

[0711] 1. The server loads the preprocessed data from the main database and starts data analysis.

[0712] 2. The server executes queries to calculate key metrics such as bounce rate, time on site, page navigation patterns, and feature usage.

[0713] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[0714] Identifying UI / UX issues

[0715] 1. Based on the analysis results, the server applies a rule-based algorithm to extract UI / UX issues.

[0716] 2. The server identifies pages with high drop-off rates or pages where users tend to get lost, and analyzes related factors, such as scrolling and click patterns on specific pages.

[0717] 3. The server generates a list of issues and stores it with the evidence.

[0718] Proposal of improvement plan

[0719] 1. Based on the list of issues, the server generates improvement proposals by referencing past success stories and industry best practices.

[0720] 2. The server creates specific suggestions, such as "To reduce the bounce rate on this page, place the main information at the top and make the CTA button more prominent."

[0721] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[0722] Providing reports to users

[0723] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[0724] 2. The device requests the latest analysis results and improvement suggestions from the server.

[0725] 3. The server reads the saved report and sends it to the device.

[0726] 4. The device displays the received report on the dashboard so that the user can check it.

[0727] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[0728] Specific examples

[0729] Example 1: Identifying and improving pages with high bounce rates

[0730] 1. The user uploads website log data in CSV file format.

[0731] 2. The server validates the data format and performs preprocessing.

[0732] 3. The server analyzes the log data and identifies pages with high bounce rates.

[0733] 4. The server analyzes the user behavior data for this page and identifies the reason for abandonment.

[0734] 5. The server extracts issues such as "key information is at the bottom of the page and difficult for users to find."

[0735] 6. The server will suggest improvements such as "move the main information to the top of the page and make the CTA button more prominent."

[0736] 7. Users can view suggested improvements on their dashboard and receive detailed guidelines for implementation.

[0737] Example 2: Improving a dashboard with low feature usage

[0738] 1. The user uploads dashboard usage logs in JSON file format.

[0739] 2. The server pre-processes the file and stores it in a database.

[0740] 3. The server analyzes the usage log and identifies functions with low usage rates.

[0741] 4. The server analyzes user feedback and survey data to identify the causes of low usage.

[0742] 5. The server extracts issues such as, "This function is located in a location that is difficult for users to understand."

[0743] 6. The server suggests improvements such as "move this feature to the top menu and add a tooltip."

[0744] 7. The user checks the proposed changes on the dashboard and implements the improvements by referring to the implementation procedures.

[0745] This allows users to quickly and efficiently identify and improve issues without having advanced data analysis skills. This system is expected to greatly contribute to improving the performance of web services.

[0746] The processing flow will be explained below.

[0747] Step 1:

[0748] Users prepare log data and access data for their services and save them as CSV or JSON format files.

[0749] Step 2:

[0750] Users log in to a dedicated web portal and open the data upload page.

[0751] Step 3:

[0752] The user selects the prepared data file in the upload interface and clicks the upload button.

[0753] Step 4:

[0754] The terminal reads the selected data file and transmits its contents to the server.

[0755] Step 5:

[0756] The server stores the received data file in temporary storage.

[0757] Step 6:

[0758] The server reads the data file from temporary storage, validates the data format and content, and corrects any invalid data format, missing values, or invalid values.

[0759] Step 7:

[0760] The server performs preprocessing of the data, specifically cleaning the data (removing missing or invalid values) and normalizing it.

[0761] Step 8:

[0762] The server stores the pre-processed data in the main database.

[0763] Step 9:

[0764] The server reads the pre-processed data from the main database and begins data analysis.

[0765] Step 10:

[0766] The server executes queries to analyze the data and calculates the following metrics:

[0767] Exit rate (number of exits on a specific page divided by total number of sessions)

[0768] Duration of visit (average time spent by users on each page)

[0769] Page transition patterns (analyzing the user's transition sequence between pages)

[0770] Feature usage rate (number of times a specific feature is used divided by the total number of accesses)

[0771] Step 11:

[0772] The server stores the calculation results in temporary storage in preparation for the next process.

[0773] Step 12:

[0774] The server applies a rule-based algorithm based on the analysis results to extract UI / UX issues.

[0775] Step 13:

[0776] The server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[0777] Step 14:

[0778] The server uses heat map analysis and user behavior data (click patterns, scrolling volume, etc.) to reveal details of UI / UX issues.

[0779] Step 15:

[0780] The server lists the extracted issues and stores them together with the associated evidence.

[0781] Step 16:

[0782] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[0783] Step 17:

[0784] The server creates a report detailing the generated improvement proposals and the reasons for them, and stores it in temporary storage.

[0785] Step 18:

[0786] The user logs into the web portal and opens the analysis results dashboard.

[0787] Step 19:

[0788] The device retrieves the latest analysis results and improvement suggestions from the server in response to a user request.

[0789] Step 20:

[0790] The server reads the saved report and sends it to the user's terminal.

[0791] Step 21:

[0792] The terminal displays the received report on a dashboard so that the user can check it.

[0793] Step 22:

[0794] Users can review the suggested improvements on the dashboard and download or print the report if desired.

[0795] Example 1

[0796] 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."

[0797] Optimizing the user experience (UI / UX) is extremely important for modern web services. However, the process of data analysis and UX improvement is complex and requires specialized skills. Furthermore, many web service professionals lack the time and resources to efficiently identify issues and propose appropriate improvement plans. This can lead to poor service performance and reduced user satisfaction. Therefore, there is a need for a system that can easily and efficiently analyze data and improve the user experience.

[0798] 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.

[0799] In this invention, the server includes means for uploading data input by a user and transmitting it to the server, means for preprocessing the data and saving it in temporary storage, means for saving the preprocessed data in a main database, means for performing data analysis based on the preprocessed data, means for calculating key indicators based on data from the database, means for algorithmically extracting UI / UX issues based on the analysis results, means for generating improvement plans for the extracted issues by referring to past success stories and best practices, and means for providing the generated improvement plans and analysis results to the user's device. This makes it possible for even web service professionals without specialized knowledge to perform advanced data analysis and quickly and effectively improve UI / UX.

[0800] "User" refers to an end user who uses the system to upload data and receive analysis results and improvement suggestions.

[0801] "Server" is a central system that processes data sent by users, analyzes it and makes suggestions for improvement.

[0802] A "terminal" is a device that allows a user to access the server to upload data and check analysis results.

[0803] "Data input" is the process by which a user inputs information such as log data and access data into the system.

[0804] "Preprocessing" refers to a series of operations performed by the server to prepare the data it receives into an analyzable format, and specifically includes verifying the data format, filling in missing values, and processing invalid values.

[0805] "Data analysis" is the process of calculating indicators such as bounce rate, dwell time, and feature usage rate based on preprocessed data, and extracting meaningful information.

[0806] "UI / UX issues" refer to problems or factors that may degrade the user experience in a web service.

[0807] "Improvement proposals" are specific proposals and strategies generated by the server to solve the extracted UI / UX issues.

[0808] "Temporary storage" is a storage area for temporarily storing received data and analysis results.

[0809] The "main database" is a central storage area for storing pre-processed data and important data that needs to be stored for a long period of time.

[0810] A "rule-based algorithm" is a computational method for analyzing data based on predefined rules and extracting UI / UX issues.

[0811] "Past success stories" refer to improvement measures and methods whose effectiveness has been confirmed based on past performance.

[0812] "Best practices" refer to methods or techniques that are widely accepted across an industry.

[0813] A "dashboard" is a graphical user interface that allows users to visually check analysis results and improvement proposals.

[0814] A "query" is a search command executed against a database to retrieve specific indicators or information.

[0815] A "prompt sentence" is an input sentence that instructs a generative AI model to perform a specific analysis or generate a suggestion.

[0816] MODE FOR CARRYING OUT THE INVENTION

[0817] This invention is a system that efficiently identifies issues in the company's services that web service workers are responsible for and proposes improvement plans. This system automates the process of having the server preprocess data entered by users, performing data analysis, identifying UI / UX issues, and proposing improvement plans.

[0818] Hardware and software used

[0819] server:

[0820] A server is a computer equipped with sufficient computing resources and storage to perform high-performance data processing.

[0821] Software includes database management systems (e.g., MySQL, PostgreSQL), libraries for data analysis (e.g., Python's pandas, SciPy), and scripts for applying rule-based algorithms.

[0822] Device:

[0823] Terminals are devices that users use to access the web portal to upload data and check analysis results, such as PCs, smartphones, and tablets.

[0824] User:

[0825] Users are end users who operate and want to improve web services.

[0826] Specific operating procedures

[0827] 1. Data Input:

[0828] Users prepare log data and access data related to their website in CSV or JSON format, including access logs and click data.

[0829] Users log in to a dedicated web portal and open the data upload page, which provides an interface for users to select data files and click the submit button.

[0830] The terminal reads the selected data file and transmits it to the server.

[0831] The server stores the received data file in temporary storage.

[0832] 2. Data Preprocessing:

[0833] The server loads the data file from temporary storage and performs file format and content validation, including checking the CSV format and parsing JSON.

[0834] The server detects missing or invalid values ​​and handles them appropriately, for example, by filling in the missing values ​​with the mean value and deleting or correcting invalid values.

[0835] The server performs data normalization, scaling numeric data and encoding categorical data.

[0836] The server stores the pre-processed data in the main database.

[0837] 3. Data Analysis:

[0838] The server loads the pre-processed data from the main database and begins analyzing it, using SQL queries and Python libraries to calculate metrics such as bounce rates, time spent, page navigation patterns, and feature usage.

[0839] The server stores the calculation results in temporary storage in preparation for the next process.

[0840] 4. UI / UX issue extraction:

[0841] Based on the analysis results, the server applies a rule-based algorithm to identify UI / UX issues. For example, if a particular page has a high bounce rate, it analyzes the user behavior data for that page.

[0842] The server examines click patterns, scrolling depth, and other factors to generate a list of issues. For example, specific problems such as "key information is at the bottom of the page, making it difficult for users to find" are extracted.

[0843] 5. Suggestions for improvement:

[0844] The server then generates improvement suggestions based on the list of issues, referencing past success stories and industry best practices, such as "place key information at the top of the page and make the CTA button more prominent."

[0845] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[0846] 6. Providing reports to users:

[0847] The user logs in to the web portal again and opens the analysis results dashboard.

[0848] The device requests the latest analysis results and improvement suggestions from the server.

[0849] The server reads the saved report and sends it to the terminal.

[0850] The terminal displays the received report on a dashboard so that the user can check it.

[0851] Users can review the proposed improvements on the dashboard and download the report if necessary.

[0852] Examples of concrete examples and prompts

[0853] Example 1: Identifying and improving pages with high exit rates:

[0854] Users upload website log data in CSV file format.

[0855] The server verifies the data format, performs preprocessing, and then analyzes the log data to identify pages with high bounce rates.

[0856] The server analyzes user behavior data for this page, extracts issues such as "the main information is at the bottom of the page, making it difficult for users to find," and proposes improvements.

[0857] Example 2: Improving dashboards with low usage:

[0858] Users upload dashboard usage logs in JSON file format.

[0859] The server preprocesses the files, stores them in a database, and then analyzes the usage logs to identify underused features.

[0860] The server extracts issues such as "This function is located in a location that is difficult for users to understand" and proposes improvements.

[0861] Example prompt sentence:

[0862] "Please analyze the contents of this CSV file and summarize the issues and specific suggestions for improving the UI / UX of the website."

[0863] This system allows users to quickly and efficiently identify and improve issues without having advanced data analysis skills, and is expected to significantly contribute to improving the performance of web services.

[0864] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0865] Step 1:

[0866] Preparing and uploading data

[0867] Users prepare log data and access data related to their company's services in CSV or JSON format, including access logs and click data.

[0868] Users log in to a dedicated web portal and open the data upload page.

[0869] The user selects a data file in the upload interface and clicks the submit button.

[0870] Input: Log data in CSV or JSON format

[0871] Output: Data file sent to the server

[0872] Step 2:

[0873] Receiving and temporarily storing data

[0874] The terminal reads the selected data file and transmits it to the server.

[0875] The server stores the contents of the received data file in temporary storage.

[0876] Input: Data file submitted by the user

[0877] Output: Data file saved in temporary storage

[0878] Step 3:

[0879] Data validation and preprocessing

[0880] The server reads the data file from temporary storage and validates the file format and content, specifically checking the CSV format and parsing JSON.

[0881] The server detects missing or invalid data values ​​based on the verification results and takes appropriate action.

[0882] Input: Data file for temporary storage

[0883] Output: Validated and processed preprocessed data

[0884] Step 4:

[0885] Data normalization

[0886] The server normalizes the preprocessed data, specifically scaling numeric data and encoding categorical data.

[0887] The server stores the normalized data in a main database.

[0888] Input: Preprocessed data

[0889] Output: Main database with normalized data

[0890] Step 5:

[0891] Calculating key indicators

[0892] The server reads the pre-processed data from the main database and executes the necessary queries.

[0893] The server calculates important metrics such as bounce rate, time spent, page transition patterns, and feature usage.

[0894] Input: Data in the main database

[0895] Output: Analysis results including calculated key indicators

[0896] Step 6:

[0897] Identifying UI / UX issues

[0898] Based on the calculated analysis results, the server applies a rule-based algorithm to extract UI / UX issues.

[0899] Specifically, the server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[0900] Input: Analysis results

[0901] Output: Issue list

[0902] Step 7:

[0903] Generate improvement proposals

[0904] Based on the list of issues, the server generates improvement proposals by referencing past success stories and industry best practices.

[0905] The server generates specific recommendations (e.g., "Place key information at the top of the page and make the CTA button prominent").

[0906] Input: Issue list, past success stories, best practices

[0907] Output: A report with concrete improvement suggestions

[0908] Step 8:

[0909] Providing reports

[0910] The user logs in to the web portal again and opens the analysis results dashboard.

[0911] The device requests the latest analysis results and improvement suggestions from the server.

[0912] The server reads the saved report and sends it to the terminal.

[0913] The terminal displays the received report on a dashboard so that the user can check it.

[0914] Input: Analysis results and improvement proposal request

[0915] Output: Report provided to the user

[0916] Through this series of processes, users can quickly and efficiently extract UI / UX issues and obtain appropriate improvement proposals, even without specialized knowledge.

[0917] (Application example 1)

[0918] 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."

[0919] In recent years, improving the user interface (UI) and user experience (UX) has become increasingly important in e-commerce (mail order) sites. However, identifying UI / UX issues and efficiently improving them requires advanced data analysis skills and a great deal of effort from site operators. Furthermore, they are required to not only provide analysis results but also propose specific improvement plans. Therefore, there is a need for a system that allows site operators to easily input data and receive analysis results and improvement proposals.

[0920] 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.

[0921] In this invention, the server includes means for inputting data, means for preprocessing data, means for performing data analysis based on the preprocessed data, means for extracting issues with the user interface and user experience from the analysis results, means for proposing improvement plans for the extracted issues, means for providing the improvement plans and analysis results to users, means for calculating multiple indicators, means for an online shopping site operator to upload data using a smartphone and receive the analysis results and improvement proposals, means for generating improvement plans based on past success stories and best practices, and means for saving and reading data using temporary storage and a main database. This enables operators to quickly and efficiently extract and improve issues using their smartphones, even without advanced data analysis skills.

[0922] 1. "Data input means" refers to the overall interface and process by which a user inputs data into the system.

[0923] 2. "Preprocessing measures" refers to measures to prepare data in an appropriate state before proceeding to the next step, such as data format verification, missing value imputation, invalid value processing, and data standardization.

[0924] 3. "Data analysis tools" refers to a set of processes and algorithms that calculate various indicators based on pre-processed data.

[0925] 4. "UI / UX issue extraction method" refers to the method for identifying issues and problems related to the user interface and user experience based on the analysis results.

[0926] 5. "Means for proposing improvements" refers to the means for generating specific improvement proposals based on the issues identified, with reference to past success stories and industry best practices.

[0927] 6. "Means for providing improvement proposals and analysis results" refers to the means for providing the generated improvement proposals and analysis results to the user.

[0928] 7. "Means for calculating indicators" refers to the means for calculating important indicators such as bounce rate, duration of visit, page transition patterns, and function usage rate.

[0929] 8. "Smartphone uploading means" refers to the means by which the operator of an online shopping site uploads data using a smartphone.

[0930] 9. "Means for referring to past success stories and best practices" refers to means for referring to past success stories and industry best practices when generating improvement proposals.

[0931] 10. "Temporary storage and main database means" refers to the storage means used temporarily to store and retrieve data and the main database for long-term data storage.

[0932] This invention relates to a data analysis and improvement proposal system that can be used by online shopping site operators. The system aims to enable operators to efficiently identify and improve UI / UX issues by automating a series of processes from data input to preprocessing, analysis, problem extraction, improvement proposal proposals, and result provision.

[0933] System Configuration

[0934] Data Input

[0935] Users use their smartphones to prepare log data and access data related to online shopping sites in CSV or JSON format, and then upload it to a cloud server using a dedicated application. The uploaded data is then stored in temporary storage.

[0936] Data Preprocessing

[0937] The server reads the data from the temporary storage, performs formal validation, and if the data contains missing or invalid values, it imputes or removes them appropriately and standardizes the data. The preprocessed data is then stored in the main database.

[0938] Data analysis

[0939] The server reads pre-processed data from the main database and calculates various metrics (e.g., exit rate, visit duration, page navigation patterns, feature usage rate) using multiple SQL queries and data processing algorithms.

[0940] Identifying UI / UX issues

[0941] Based on the data analysis results, the server identifies issues such as high bounce rates and low conversion rates for specific pages and functions, and uses rule-based algorithms to extract issues related to the user interface and user experience.

[0942] Improvement proposal

[0943] The server then generates specific improvement proposals for the identified issues, referencing past success stories and best practices, such as "place key information at the top of the page and make the CTA button more prominent."

[0944] Report provision

[0945] The server creates a report summarizing the generated improvement proposals and analysis results and provides it to the user, who can then check the report on their smartphone app and download it as needed.

[0946] Hardware and software used

[0947] The system consists of the following hardware and software:

[0948] Cloud Server: Responsible for storing and processing data.

[0949] Smartphone: Used by users to upload data and check results. Dedicated applications are installed.

[0950] Temporary storage and main database: Used for data storage.

[0951] Pandas and SQL: Used for data preprocessing and analysis.

[0952] Specific examples

[0953] The user prepares log data from an online shopping site in CSV format and uploads it to a cloud server via a smartphone app. The server stores the received data in temporary storage, performs formal validation, and processes missing values. The preprocessed data is then stored in the main database and indicators are calculated. Based on the calculation results, pages with high bounce rates are identified and issues on those pages are extracted. The server then proposes specific improvement plans, such as "moving key information to the top," and generates a report to provide to the user.

[0954] Prompt Sentence Examples

[0955] You can request specific analysis and improvement suggestions for your generative AI model using the following prompts:

[0956] Request Type: Analysis

[0957] Data format: CSV

[0958] Data Path: ecommerce_log.csv

[0959] Analysis type: Exit rate analysis, Conversion rate analysis

[0960] Proposal criteria: Past success stories, industry best practices

[0961] This prompt allows the system to take appropriate action based on the specified data format and analysis type.

[0962] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0963] Step 1:

[0964] A user uses a smartphone to prepare log data and access data related to an online shopping site in CSV or JSON format, and uploads it to a cloud server using a dedicated application. The input is a data file prepared by the user (e.g., ecommerce_log.csv), and the output is the uploaded data stored in temporary storage on the cloud server.

[0965] Step 2:

[0966] The server reads the uploaded data from temporary storage and verifies the data format. The input is the data file in temporary storage, and the output is the data file after format verification. Once verification is complete, it proceeds to the next process.

[0967] Step 3:

[0968] The server performs data preprocessing, such as missing value imputation, invalid value handling, and data standardization. The input is a data file that has been format-validated, and the output is a preprocessed data file. The preprocessed data is stored in the main database.

[0969] Step 4:

[0970] The server reads preprocessed data from the main database and analyzes and calculates various indicators (e.g., exit rate, duration of visit, page transition patterns, feature usage rate, etc.). The input is the preprocessed data, and the output is the calculated indicator results. The calculation results are saved in temporary storage.

[0971] Step 5:

[0972] The server extracts user interface and user experience related issues based on the analysis results. The input is the calculated metrics and the output is a list of extracted issues. Specific problems and issues are extracted using a rule-based algorithm.

[0973] Step 6:

[0974] The server generates specific improvement proposals for the extracted issues by referencing past success stories and industry best practices. The input is a list of issues, and the output is specific improvement proposals. For example, suggestions include "Place key information at the top of the page and make the CTA button more prominent."

[0975] Step 7:

[0976] The server creates a report that summarizes the generated improvement proposals and analysis results. The inputs are the improvement proposals and analysis results, and the output is a report. The report is saved in temporary storage and formatted so that it can be provided to the user.

[0977] Step 8:

[0978] Users check the reports using a smartphone app. The input is the report provided by the server, and the output is confirmation or download of the report contents. Users can check the details of the report generated in the smartphone app and obtain specific implementation procedures if necessary.

[0979] 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.

[0980] This invention is a system that enables web service professionals to efficiently identify issues in their company's services and propose improvement proposals. By combining it with an emotion engine that recognizes user emotions, it achieves more accurate issue identification and improvement proposal proposals. This system automates a series of processes: the server preprocesses data input by the user, performs data analysis, identifies UI / UX issues, and proposes improvement proposals for those issues. Furthermore, the emotion engine makes it possible to analyze and propose proposals that take into account user emotion data.

[0981] Program processing

[0982] Data Input

[0983] 1. The user prepares log data and access data related to their company's services in CSV or JSON format.

[0984] 2. The user logs in to the dedicated web portal and opens the data upload page.

[0985] 3. The user selects the prepared data file in the upload interface and clicks the Upload button.

[0986] 4. The terminal reads the selected data file and sends its contents to the server.

[0987] 5. The server stores the received data file in temporary storage.

[0988] Data Preprocessing

[0989] 1. The server reads the data file from temporary storage and verifies the data format and content.

[0990] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[0991] 3. The server normalizes the data to make it consistent.

[0992] 4. The server stores the preprocessed data in the main database.

[0993] Data analysis

[0994] 1. The server loads the preprocessed data from the main database and starts data analysis.

[0995] 2. The server executes queries to analyze the data and calculates the following metrics:

[0996] Abandonment rate

[0997] Stay time

[0998] Page Transition Pattern

[0999] Function usage rate

[1000] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[1001] Emotion data collection and analysis

[1002] 1. Users use dedicated tools and applications to collect emotional data during use.

[1003] 2. The device sends the emotion data to the server.

[1004] 3. The server analyzes the received emotion data and recognizes emotion patterns.

[1005] Identifying UI / UX issues

[1006] 1. The server applies a rule-based algorithm based on the analysis results and emotion data to extract UI / UX issues.

[1007] 2. The server identifies pages with high bounce rates and pages where users are likely to get lost, and analyzes the related factors.

[1008] 3. The server analyzes how specific UI elements affect emotions based on the user's emotional data.

[1009] 4. The server lists the extracted issues and stores them together with the associated evidence.

[1010] Proposal of improvement plan

[1011] 1. The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[1012] 2. The server compares the generated improvement proposals with the user's emotional data and makes suggestions that are appropriate for each individual user.

[1013] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[1014] Providing reports to users

[1015] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[1016] 2. The device requests the latest analysis results and improvement suggestions from the server.

[1017] 3. The server reads the saved report and sends it to the device.

[1018] 4. The device displays the received report on the dashboard so that the user can check it.

[1019] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[1020] Specific examples

[1021] Example 1: Identifying and improving pages with high bounce rates

[1022] 1. The user uploads the website log data in CSV format.

[1023] 2. The server validates the data format and performs preprocessing.

[1024] 3. The server analyzes the log data and identifies pages with high bounce rates.

[1025] 4. The server analyzes the user behavior and emotion data for this page to identify the cause of abandonment.

[1026] 5. The server extracts issues such as "key information is at the bottom of the page and difficult for users to find."

[1027] 6. The server will suggest improvements such as "move the main information to the top of the page and make the CTA button more prominent."

[1028] 7. Users can view suggested improvements on their dashboard and receive detailed guidelines for implementation.

[1029] Example 2: Improving a dashboard with low feature usage

[1030] 1. The user uploads dashboard usage logs in JSON format.

[1031] 2. The server preprocesses the data and stores it in a database.

[1032] 3. The server analyzes usage logs and sentiment data to identify features with low usage rates.

[1033] 4. The server analyzes user feedback and survey data to identify the causes of low usage.

[1034] 5. The server extracts issues such as, "This function is located in a location that is difficult for users to understand."

[1035] 6. The server suggests improvements such as "move this feature to the top menu and add a tooltip."

[1036] 7. The user checks the proposed changes on the dashboard and implements the improvements by referring to the implementation procedures.

[1037] As described above, this system enables even users without advanced data analysis skills to quickly and efficiently identify issues and obtain improvement proposals that take into account the emotions of individual users. This system is expected to make a significant contribution to improving the performance of web services and optimizing the user experience.

[1038] The processing flow will be explained below.

[1039] Step 1:

[1040] Users prepare log data and access data related to their services in CSV or JSON format.

[1041] Step 2:

[1042] Users log in to a dedicated web portal and open the data upload page.

[1043] Step 3:

[1044] The user selects the prepared data file in the upload interface and clicks the upload button.

[1045] Step 4:

[1046] The terminal reads the selected data file and transmits its contents to the server.

[1047] Step 5:

[1048] The server stores the received data file in temporary storage.

[1049] Step 6:

[1050] The server reads the data file from temporary storage, validates the data format and content, and corrects any invalid data format, missing values, or invalid values.

[1051] Step 7:

[1052] The server performs preprocessing of the data, specifically cleaning the data (removing missing or invalid values) and normalizing it.

[1053] Step 8:

[1054] The server stores the pre-processed data in the main database.

[1055] Step 9:

[1056] The server reads the pre-processed data from the main database and begins data analysis.

[1057] Step 10:

[1058] The server executes queries to analyze the data and calculates the following metrics:

[1059] Exit rate (number of exits on a specific page divided by total number of sessions)

[1060] Duration of visit (average time spent by users on each page)

[1061] Page transition patterns (analyzing the user's transition sequence between pages)

[1062] Feature usage rate (number of times a specific feature is used divided by the total number of accesses)

[1063] Step 11:

[1064] The server stores the calculation results in temporary storage in preparation for the next process.

[1065] Step 12:

[1066] Users use dedicated tools and applications to collect emotion data during use.

[1067] Step 13:

[1068] The terminal transmits the collected emotion data to the server.

[1069] Step 14:

[1070] The server analyzes the received emotion data and recognizes emotion patterns.

[1071] Step 15:

[1072] Based on the analysis results and emotional data, the server applies a rule-based algorithm to extract UI / UX issues.

[1073] Step 16:

[1074] The server identifies pages with high drop-off rates and pages where users tend to get lost, analyzes the associated factors, and takes sentiment data into account.

[1075] Step 17:

[1076] The server uses heat map analysis and user behavior data (click patterns, scrolling volume, etc.) to reveal details of UI / UX issues.

[1077] Step 18:

[1078] The server lists the extracted issues and stores them together with the associated evidence.

[1079] Step 19:

[1080] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[1081] Step 20:

[1082] The server compares the generated improvement proposals with the user's emotional data and makes suggestions that are appropriate for each individual user.

[1083] Step 21:

[1084] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[1085] Step 22:

[1086] The user logs in to the web portal again and opens the analysis results dashboard.

[1087] Step 23:

[1088] The device requests the latest analysis results and improvement suggestions from the server.

[1089] Step 24:

[1090] The server reads the saved report and sends it to the terminal.

[1091] Step 25:

[1092] The terminal displays the received report on a dashboard so that the user can check it.

[1093] Step 26:

[1094] Users can review the suggested improvements on the dashboard and download or print the report if desired.

[1095] Through this process, users can quickly and efficiently identify issues and obtain improvement proposals that take into account the emotions of individual users, even without advanced data analysis skills. This system is expected to make a significant contribution to improving the performance of web services and optimizing the user experience.

[1096] Example 2

[1097] 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."

[1098] With conventional web services, it was difficult to efficiently identify issues with the user interface and user experience and propose improvement proposals. Furthermore, the effectiveness of improvement proposals was limited because they did not take user emotions into consideration. This meant that service performance improvements and optimization of the user experience could not be fully achieved.

[1099] The identification process 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 inputting data, means for preprocessing data, means for performing data analysis based on the preprocessed data, means for extracting issues in the user interface and user experience, means for proposing improvement plans for the extracted issues, means for collecting and analyzing user emotion data, means for adjusting the issues and improvement plans based on the emotion data, means for providing the improvement plans and analysis results to the user, and means for generating a report to be provided to the user. This makes it possible to accurately extract issues and propose effective improvement plans that take user emotions into consideration.

[1100] "Data input" refers to a user providing log data and access data to the system.

[1101] "Data preprocessing" refers to the process of filling in missing values, correcting invalid values, and normalizing the data to make it consistent, in order to make the collected data easier to analyze.

[1102] "Data analysis" refers to the process of calculating metrics and identifying issues related to the user interface and user experience based on pre-processed data.

[1103] "Identifying issues in the user interface and user experience" refers to using data analysis results and user emotion data to identify problems in the user interface and user experience of web services.

[1104] "Proposing improvements" refers to presenting specific methods for correcting or improving the identified issues based on past success stories and best practices.

[1105] "Collection and analysis of emotional data" refers to the process of collecting emotional data from users while they are using the service and analyzing that data to understand the user's emotional state.

[1106] "Adjustment of issues and improvement proposals" refers to optimizing identified issues and proposed improvement proposals for individual users based on collected and analyzed emotional data.

[1107] "Report generation" refers to the process of creating a report detailing the analysis results and improvement proposals and providing it to the user.

[1108] This invention is a system that allows users of web services to efficiently identify issues with their own services and propose improvement plans. The system includes the following main components:

[1109] 1. Data input method

[1110] Users prepare log data and access data related to their services in CSV or JSON format.

[1111] Users log in to a dedicated web portal and upload data files from the data upload page.

[1112] The terminal reads the uploaded data file and transmits its contents to the server.

[1113] The server stores the received data file in temporary storage.

[1114] 2. Data preprocessing methods

[1115] The server reads the data file from the temporary storage and verifies the data format and content.

[1116] The server identifies missing, invalid, and outlier values ​​and takes appropriate action (e.g., imputing the mean value of missing values).

[1117] The server normalizes the data to ensure consistency.

[1118] The server stores the pre-processed data in the main database.

[1119] 3. Data Analysis Methods

[1120] The server reads the pre-processed data from the main database and runs queries to perform data analysis.

[1121] The server calculates the following metrics: exit rate, visit duration, page transition patterns, and feature usage rate.

[1122] The server stores the calculation results in temporary storage in preparation for the next process.

[1123] 4. Methods for collecting and analyzing emotion data

[1124] Users collect emotion data during use using dedicated tools and applications.

[1125] The terminal transmits the emotion data to the server.

[1126] The server analyzes the received emotion data and recognizes emotion patterns.

[1127] 5. Methods for extracting UI / UX issues

[1128] The server applies a rule-based algorithm to extract issues based on the analysis results and emotion data.

[1129] The server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[1130] The server analyzes how specific UI elements affect emotions.

[1131] The server lists the extracted issues and stores them together with the associated evidence.

[1132] 6. Means of proposing improvements

[1133] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[1134] The server compares the proposed improvement plan with the user's emotional data and makes suggestions that are appropriate for each individual user.

[1135] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[1136] 7. Report Generation Methods

[1137] The server has means for generating and providing reports to the user.

[1138] Specific examples

[1139] For example, when uploading a website's log data in CSV format, a user selects and uploads the file from the data upload page. This data is then sent to the server, where it is validated and pre-processed. Data analysis identifies pages with high drop-off rates and user sentiment data, and UI / UX issues are extracted. Improvement proposals are then proposed based on past success stories and industry best practices. Finally, the proposals are provided to the user in the form of a detailed report.

[1140] The specific hardware or software used

[1141] Temporary storage: Amazon S3, etc.

[1142] Main database: PostgreSQL, etc.

[1143] Data analysis libraries: Python Pandas, TensorFlow, etc.

[1144] Prompt Sentence Examples

[1145] "If a particular page has a high bounce rate, identify the cause and suggest appropriate improvements."

[1146] The above is an embodiment of the present invention, which contributes greatly to improving the performance of Web services and optimizing the user experience.

[1147] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1148] Step 1: Data Input

[1149] 1. The user prepares log data and access data related to their company's services in CSV or JSON format.

[1150] Input: User-prepared CSV or JSON file

[1151] What happens: A user accesses a web portal in their browser to select and upload a data file.

[1152] 2. The user logs in to the dedicated web portal and opens the data upload page.

[1153] Input: Portal login information

[1154] Specific behavior: The user enters their authentication information and clicks the login button.

[1155] 3. The user selects the prepared data file in the upload interface and clicks the Upload button.

[1156] Input: Selected data file

[1157] Specific behavior: The user clicks the "Choose File" button, selects a CSV file from local storage, and clicks the "Upload" button.

[1158] 4. The terminal reads the selected data file and sends its contents to the server.

[1159] Input: Selected data file

[1160] Output: Sending the data file to the server

[1161] Specific operation: The device sends a data file to the server using an HTTP POST request.

[1162] 5. The server stores the received data file in temporary storage.

[1163] Input: Received data file

[1164] Output: Data file saved in temporary storage

[1165] Specific operation: The server stores the received file in temporary storage such as an Amazon S3 bucket.

[1166] Step 2: Data Preprocessing

[1167] 1. The server reads the data file from temporary storage and verifies the data format and content.

[1168] Input: Data file saved in temporary storage

[1169] Output: Validated data file

[1170] Specific operation: The server checks the data format (such as the CSV header row) and validates the contents.

[1171] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[1172] Input: Validated data file

[1173] Output: Preprocessed data

[1174] Specific operation: Uses the Pandas library to perform operations such as filling in NaN (missing values) with the average value of the column.

[1175] 3. The server normalizes the data to make it consistent.

[1176] Input: Data file with missing, invalid, and outlier processed

[1177] Output: Normalized data file

[1178] Specific operation: Scales numerical data and normalizes it to the range 0 to 1.

[1179] 4. The server stores the preprocessed data in the main database.

[1180] Input: Normalized data file

[1181] Output: Preprocessed data stored in the main database

[1182] Specific operation: Insert the preprocessed data into a PostgreSQL database.

[1183] Step 3: Data analysis

[1184] 1. The server loads the preprocessed data from the main database and starts data analysis.

[1185] Input: Preprocessed data stored in the main database

[1186] Output: Analysis results

[1187] Specific behavior: Executes an SQL query to retrieve the required data from the database.

[1188] 2. The server executes queries to analyze the data and calculates the following metrics:

[1189] Abandonment rate

[1190] Stay time

[1191] Page Transition Pattern

[1192] Function usage rate

[1193] Input: Data retrieved from the database

[1194] Output: Calculation results for each indicator

[1195] Specific operation: Calculate each metric using SQL queries or Python scripts.

[1196] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[1197] Input: Calculated indicator data

[1198] Output: Calculation results saved in temporary storage

[1199] Specific operation: The calculation results are saved as a JSON format file on Amazon S3.

[1200] Step 4: Collect and analyze emotion data

[1201] 1. Users use dedicated tools and applications to collect emotional data during use.

[1202] Input: Data from emotion data collection tools

[1203] Output: Collected emotion data

[1204] What it does: Collects facial expression data from users using emotion recognition apps and browser extensions.

[1205] 2. The device sends the emotion data to the server.

[1206] Input: Collected emotion data

[1207] Output: Emotion data sent to the server

[1208] Specific operation: Emotion data is sent to the server in real time using a REST API.

[1209] 3. The server analyzes the received emotion data and recognizes emotion patterns.

[1210] Input: Emotion data sent to the server

[1211] Output: Parsed emotion patterns

[1212] What it does: Analyzes emotional patterns using deep learning models (e.g., TensorFlow or PyTorch).

[1213] Step 5: Identify UI / UX issues

[1214] 1. The server applies a rule-based algorithm to extract issues based on the analysis results and emotion data.

[1215] Input: Data analysis results and emotion data

[1216] Output: Extracted issues

[1217] Specific behavior: Applying rule-based algorithms to identify issues from specific indicator values ​​and sentiment patterns.

[1218] 2. The server identifies pages with high bounce rates and pages where users are likely to get lost, and analyzes the related factors.

[1219] Input: Extracted issues

[1220] Output: Identified high exit rate pages and pages where users are likely to get lost

[1221] Specific actions: Correlate and analyze user behavioral data and sentiment data to identify problematic pages.

[1222] 3. The server analyzes how specific UI elements affect emotions.

[1223] Input: User behavioral and emotional data

[1224] Output: UI elements that affect emotions

[1225] Specific behavior: Analyze how clicking a specific button or link affects a user's emotions.

[1226] 4. The server lists the extracted issues and stores them together with the associated evidence.

[1227] Input: Clarified issue

[1228] Output: A list of issues saved with evidence

[1229] Specific action: Compile a list of issues and related data into a single report.

[1230] Step 6: Propose improvements

[1231] 1. The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[1232] Input: Extracted issues

[1233] Output: Generated improvement suggestions

[1234] Specific operation: Query past success stories from a database and generate improvement suggestions based on them.

[1235] 2. The server compares the proposed improvement plan with the user's emotional data and makes suggestions that are appropriate for each individual user.

[1236] Input: Improvement proposals and user emotion data

[1237] Output: Adjusted improvement proposal

[1238] Specific action: Check whether the generated improvement proposals can elicit positive emotions from users.

[1239] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[1240] Input: Adjusted improvement proposal

[1241] Output: Improvement suggestions saved as a report

[1242] Specific operation: The proposal and its rationale are written in Markdown format and saved in temporary storage (e.g., Amazon S3).

[1243] Step 7: Provide the report to the user

[1244] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[1245] Input: Portal login information

[1246] Output: Access to the dashboard

[1247] Specific operations: After logging in to the web portal, click the "View analysis results" button.

[1248] 2. The device requests the latest analysis results and improvement suggestions from the server.

[1249] Input: Request from the dashboard page

[1250] Output: The data requested from the server

[1251] Specific operation: Send an Ajax request to get the latest data.

[1252] 3. The server reads the saved report and sends it to the device.

[1253] Input: Saved Report

[1254] Output: Report sent to terminal

[1255] Specific operation: Download the report from Amazon S3 etc. and send it to the device.

[1256] 4. The device displays the received report on the dashboard so that the user can check it.

[1257] Input: Report sent from the server

[1258] Output: The report displayed in a dashboard

[1259] Specific operation: Renders the retrieved report data in HTML format and displays it on a dashboard.

[1260] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[1261] Input: Report displayed on dashboard

[1262] Output: Downloaded report

[1263] Specific behavior: Click the "Download Report" button and save the report in PDF format to local storage.

[1264] (Application example 2)

[1265] 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."

[1266] The present invention aims to provide an effective system for improving the quality of customer experience in brick-and-mortar stores. In particular, the system aims to support store operators in increasing customer satisfaction by extracting issues in the customer experience based on customer behavioral and emotional data and automatically proposing appropriate improvement plans.

[1267] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1268] In this invention, the server includes means for inputting data, means for preprocessing the data, means for performing data analysis based on the preprocessed data, means for extracting issues in the user interface and user experience, means for proposing improvement plans for the extracted issues, means for collecting and analyzing user emotion data, and means for providing the improvement plans and analysis results to the user. This makes it possible to identify detailed customer experience issues based on customer behavioral data and emotion data, and to provide effective improvement plans.

[1269] "Means for inputting data" is a general term for various hardware and software that input data into the system from outside.

[1270] "Means for preprocessing data" refers to functions that include processes for verifying the format and content of input data, handling missing values ​​and invalid values, and normalizing data.

[1271] "Means for performing data analysis based on preprocessed data" refers to the function of using normalized data to perform various analyses, calculate indicators, and discover patterns.

[1272] "Means for identifying issues in user interfaces and user experiences" includes algorithms and procedures for identifying problems related to the use of systems and services based on the results of data analysis.

[1273] "Means for proposing improvement plans for extracted issues" refers to the function within the system that automatically generates and proposes specific solutions to issues.

[1274] "Means for collecting and analyzing user emotional data" includes tools and algorithms for measuring and recording a user's emotional state and analyzing emotional patterns.

[1275] "Means for providing improvement proposals and analysis results to users" refers to various interfaces that visually display the improvement proposals and analysis results generated by the system and provide them to users.

[1276] A "temporary storage device" is a memory or storage device for short-term storage of data files.

[1277] The system of the present invention collects and analyzes various data, automatically extracts issues, and proposes improvement plans in order to improve the customer experience in physical stores. This system is composed of a means for inputting data, a means for preprocessing the data, a means for performing data analysis based on the preprocessed data, a means for extracting issues in the user interface and user experience, a means for proposing improvement plans for the extracted issues, a means for collecting and analyzing user emotion data, and a means for providing the user with improvement plans and analysis results.

[1278] Hardware and software used

[1279] 1. Hardware

[1280] Smartphone

[1281] camera

[1282] server

[1283] 2. Software

[1284] Python

[1285] Pandas

[1286] Scikit-learn

[1287] EmotionEngine (virtual module)

[1288] UI_UX_Analyzer (virtual module)

[1289] What the program does

[1290] Data Input

[1291] Users upload customer behavior and feedback data collected in-store to the system using their smartphones, with the data provided in CSV or JSON format.

[1292] Data Preprocessing

[1293] The server first performs formal validation of the received data and processes invalid and missing values. Specifically, it reads the data as a data frame using Pandas, removes missing values, and normalizes and standardizes the numerical data using Scikit-learn.

[1294] Data analysis

[1295] Once the data preprocessing is complete, the server analyzes the data using UI_UX_Analyzer, which calculates important metrics such as customer behavior patterns, dropout rates, and dwell time.

[1296] Emotion data collection and analysis

[1297] Customer emotional data is collected in real time via smartphones and analyzed using EmotionEngine to recognize customer emotional patterns (e.g., satisfaction, dissatisfaction, excitement, etc.).

[1298] Identifying UI / UX issues and proposing improvements

[1299] Based on the results of data analysis and sentiment data, the server extracts issues in the user interface and user experience. For any issues discovered, it generates effective improvement proposals based on past success stories and industry standards.

[1300] Providing reports to users

[1301] Finally, the analysis results and improvement recommendations are provided to the user. This information is displayed in a visually easy-to-understand report format on a dashboard, where the user can view the details of the improvement recommendations and receive guidance on how to implement them.

[1302] Examples of concrete examples and prompts

[1303] Specific examples

[1304] For example, if a problem is identified where in-store navigation is difficult for customers to understand, the server will suggest moving important information to the top of the page. This suggestion is based on customer behavioral and emotional data, reducing customer frustration when trying to find information.

[1305] Prompt Sentence Examples

[1306] Analyze customer sentiment based on the feedback below.

[1307] Feedback: "The navigation in this store is very confusing. It took me a while to find the product I wanted."

[1308] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1309] Step 1: Data Input

[1310] Users upload customer behavior and feedback data collected in physical stores to the system using their smartphones, and this data is provided in CSV or JSON format.

[1311] Input: Customer behavior and feedback data in CSV or JSON format

[1312] Output: Raw data uploaded to the server

[1313] Step 2: Receiving and storing data

[1314] The terminal receives the uploaded data file and transmits the contents to the server, which stores the received data file in a temporary storage device.

[1315] Input: Data file sent to the server

[1316] Output: Raw data file saved to temporary storage

[1317] Step 3: Data Preprocessing

[1318] The server reads the data file from temporary storage, validates the data format, handles invalid and missing values, and performs standardization and normalization. It converts the data into a data frame using Pandas, removes missing values, and normalizes the numeric data using Scikit-learn.

[1319] Input: Raw data file read from temporary storage

[1320] Output: Preprocessed data

[1321] Step 4: Data analysis

[1322] The server uses UI_UX_Analyzer to perform detailed data analysis based on the pre-processed data, and calculates key indicators such as customer behavior patterns, dropout rates, and duration of stay.

[1323] Input: Preprocessed data

[1324] Output: Analysis results (customer behavior patterns, abandonment rate, duration of stay, etc.)

[1325] Step 5: Collect and analyze emotion data

[1326] The terminal collects customer emotional data in real time via the smartphone. The server uses EmotionEngine to analyze the emotional data and recognize the customer's emotional patterns. This analysis process utilizes, for example, feedback text and facial expressions provided when customers answer questionnaires on their smartphones.

[1327] Input: Emotion data collected in real time

[1328] Output: Parsed emotion patterns

[1329] Step 6: Identify UI / UX issues

[1330] The server applies rule-based algorithms based on data analysis and sentiment data to identify issues with the user interface and user experience. For example, it can identify areas where customers are experiencing inconvenience on specific pages or operations based on customer feedback and behavioral analysis data.

[1331] Input: Data analysis results and sentiment pattern analysis results

[1332] Output: A list of extracted UI / UX issues

[1333] Step 7: Propose improvements

[1334] The server generates improvement suggestions for the extracted issues based on past best practices and industry standards, including specific suggestions such as "move important information to the top of the page" or "change the location of new features."

[1335] Input: Extracted UI / UX issue list

[1336] Output: Suggested improvements

[1337] Step 8: Generate and deliver reports

[1338] The server generates a visually easy-to-understand report of the proposed improvements and analysis results and stores it in temporary storage. Users can log in to the web portal, view the report on the dashboard, and download the report if necessary.

[1339] Input: Proposed improvements and analysis results

[1340] Output: Generated report with improvement suggestions and analysis results

[1341] 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.

[1342] 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.

[1343] 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.

[1344] [Third embodiment]

[1345] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1346] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1347] 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).

[1348] 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.

[1349] 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.

[1350] 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).

[1351] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1352] 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.

[1353] 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.

[1354] 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.

[1355] 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.

[1356] 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."

[1357] This invention is a system that efficiently identifies issues in the company's services that web service workers are responsible for and proposes improvement plans. This system automates the process of having the server preprocess data entered by users, performing data analysis, identifying UI / UX issues, and proposing improvement plans.

[1358] Program processing

[1359] Data Input

[1360] 1. The user prepares log data and access data related to their company's service in CSV or JSON format.

[1361] 2. The user logs in to the dedicated web portal and opens the data upload page.

[1362] 3. The user selects the data file in the upload interface and clicks the submit button.

[1363] 4. The terminal reads the selected data file and sends it to the server.

[1364] 5. The server stores the received data file in temporary storage.

[1365] Data Preprocessing

[1366] 1. The server reads the data file from temporary storage and validates the file format and content.

[1367] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[1368] 3. The server normalizes the data to make it consistent.

[1369] 4. The server stores the preprocessed data in the main database.

[1370] Data analysis

[1371] 1. The server loads the preprocessed data from the main database and starts data analysis.

[1372] 2. The server executes queries to calculate key metrics such as bounce rate, time on site, page navigation patterns, and feature usage.

[1373] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[1374] Identifying UI / UX issues

[1375] 1. Based on the analysis results, the server applies a rule-based algorithm to extract UI / UX issues.

[1376] 2. The server identifies pages with high drop-off rates or pages where users tend to get lost, and analyzes related factors, such as scrolling and click patterns on specific pages.

[1377] 3. The server generates a list of issues and stores it with the evidence.

[1378] Proposal of improvement plan

[1379] 1. Based on the list of issues, the server generates improvement proposals by referencing past success stories and industry best practices.

[1380] 2. The server creates specific suggestions, such as "To reduce the bounce rate on this page, place the main information at the top and make the CTA button more prominent."

[1381] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[1382] Providing reports to users

[1383] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[1384] 2. The device requests the latest analysis results and improvement suggestions from the server.

[1385] 3. The server reads the saved report and sends it to the device.

[1386] 4. The device displays the received report on the dashboard so that the user can check it.

[1387] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[1388] Specific examples

[1389] Example 1: Identifying and improving pages with high bounce rates

[1390] 1. The user uploads website log data in CSV file format.

[1391] 2. The server validates the data format and performs preprocessing.

[1392] 3. The server analyzes the log data and identifies pages with high bounce rates.

[1393] 4. The server analyzes the user behavior data for this page and identifies the reason for abandonment.

[1394] 5. The server extracts issues such as "key information is at the bottom of the page and difficult for users to find."

[1395] 6. The server will suggest improvements such as "move the main information to the top of the page and make the CTA button more prominent."

[1396] 7. Users can view suggested improvements on their dashboard and receive detailed guidelines for implementation.

[1397] Example 2: Improving a dashboard with low feature usage

[1398] 1. The user uploads dashboard usage logs in JSON file format.

[1399] 2. The server pre-processes the file and stores it in a database.

[1400] 3. The server analyzes the usage log and identifies functions with low usage rates.

[1401] 4. The server analyzes user feedback and survey data to identify the causes of low usage.

[1402] 5. The server extracts issues such as, "This function is located in a location that is difficult for users to understand."

[1403] 6. The server suggests improvements such as "move this feature to the top menu and add a tooltip."

[1404] 7. The user checks the proposed changes on the dashboard and implements the improvements by referring to the implementation procedures.

[1405] This allows users to quickly and efficiently identify and improve issues without having advanced data analysis skills. This system is expected to greatly contribute to improving the performance of web services.

[1406] The processing flow will be explained below.

[1407] Step 1:

[1408] Users prepare log data and access data for their services and save them as CSV or JSON format files.

[1409] Step 2:

[1410] Users log in to a dedicated web portal and open the data upload page.

[1411] Step 3:

[1412] The user selects the prepared data file in the upload interface and clicks the upload button.

[1413] Step 4:

[1414] The terminal reads the selected data file and transmits its contents to the server.

[1415] Step 5:

[1416] The server stores the received data file in temporary storage.

[1417] Step 6:

[1418] The server reads the data file from temporary storage, validates the data format and content, and corrects any invalid data format, missing values, or invalid values.

[1419] Step 7:

[1420] The server performs preprocessing of the data, specifically cleaning the data (removing missing or invalid values) and normalizing it.

[1421] Step 8:

[1422] The server stores the pre-processed data in the main database.

[1423] Step 9:

[1424] The server reads the pre-processed data from the main database and begins data analysis.

[1425] Step 10:

[1426] The server executes queries to analyze the data and calculates the following metrics:

[1427] Exit rate (number of exits on a specific page divided by total number of sessions)

[1428] Duration of visit (average time spent by users on each page)

[1429] Page transition patterns (analyzing the user's transition sequence between pages)

[1430] Feature usage rate (number of times a specific feature is used divided by the total number of accesses)

[1431] Step 11:

[1432] The server stores the calculation results in temporary storage in preparation for the next process.

[1433] Step 12:

[1434] The server applies a rule-based algorithm based on the analysis results to extract UI / UX issues.

[1435] Step 13:

[1436] The server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[1437] Step 14:

[1438] The server uses heat map analysis and user behavior data (click patterns, scrolling volume, etc.) to reveal details of UI / UX issues.

[1439] Step 15:

[1440] The server lists the extracted issues and stores them together with the associated evidence.

[1441] Step 16:

[1442] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[1443] Step 17:

[1444] The server creates a report detailing the generated improvement proposals and the reasons for them, and stores it in temporary storage.

[1445] Step 18:

[1446] The user logs into the web portal and opens the analysis results dashboard.

[1447] Step 19:

[1448] The device retrieves the latest analysis results and improvement suggestions from the server in response to a user request.

[1449] Step 20:

[1450] The server reads the saved report and sends it to the user's terminal.

[1451] Step 21:

[1452] The terminal displays the received report on a dashboard so that the user can check it.

[1453] Step 22:

[1454] Users can review the suggested improvements on the dashboard and download or print the report if desired.

[1455] Example 1

[1456] 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."

[1457] Optimizing the user experience (UI / UX) is extremely important for modern web services. However, the process of data analysis and UX improvement is complex and requires specialized skills. Furthermore, many web service professionals lack the time and resources to efficiently identify issues and propose appropriate improvement plans. This can lead to poor service performance and reduced user satisfaction. Therefore, there is a need for a system that can easily and efficiently analyze data and improve the user experience.

[1458] 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.

[1459] In this invention, the server includes means for uploading data input by a user and transmitting it to the server, means for preprocessing the data and saving it in temporary storage, means for saving the preprocessed data in a main database, means for performing data analysis based on the preprocessed data, means for calculating key indicators based on data from the database, means for algorithmically extracting UI / UX issues based on the analysis results, means for generating improvement plans for the extracted issues by referring to past success stories and best practices, and means for providing the generated improvement plans and analysis results to the user's device. This makes it possible for even web service professionals without specialized knowledge to perform advanced data analysis and quickly and effectively improve UI / UX.

[1460] "User" refers to an end user who uses the system to upload data and receive analysis results and improvement suggestions.

[1461] "Server" is a central system that processes data sent by users, analyzes it and makes suggestions for improvement.

[1462] A "terminal" is a device that allows a user to access the server to upload data and check analysis results.

[1463] "Data input" is the process by which a user inputs information such as log data and access data into the system.

[1464] "Preprocessing" refers to a series of operations performed by the server to prepare the data it receives into an analyzable format, and specifically includes verifying the data format, filling in missing values, and processing invalid values.

[1465] "Data analysis" is the process of calculating indicators such as bounce rate, dwell time, and feature usage rate based on preprocessed data, and extracting meaningful information.

[1466] "UI / UX issues" refer to problems or factors that may degrade the user experience in a web service.

[1467] "Improvement proposals" are specific proposals and strategies generated by the server to solve the extracted UI / UX issues.

[1468] "Temporary storage" is a storage area for temporarily storing received data and analysis results.

[1469] The "main database" is a central storage area for storing pre-processed data and important data that needs to be stored for a long period of time.

[1470] A "rule-based algorithm" is a computational method for analyzing data based on predefined rules and extracting UI / UX issues.

[1471] "Past success stories" refer to improvement measures and methods whose effectiveness has been confirmed based on past performance.

[1472] "Best practices" refer to methods or techniques that are widely accepted across an industry.

[1473] A "dashboard" is a graphical user interface that allows users to visually check analysis results and improvement proposals.

[1474] A "query" is a search command executed against a database to retrieve specific indicators or information.

[1475] A "prompt sentence" is an input sentence that instructs a generative AI model to perform a specific analysis or generate a suggestion.

[1476] MODE FOR CARRYING OUT THE INVENTION

[1477] This invention is a system that efficiently identifies issues in the company's services that web service workers are responsible for and proposes improvement plans. This system automates the process of having the server preprocess data entered by users, performing data analysis, identifying UI / UX issues, and proposing improvement plans.

[1478] Hardware and software used

[1479] server:

[1480] A server is a computer equipped with sufficient computing resources and storage to perform high-performance data processing.

[1481] Software includes database management systems (e.g., MySQL, PostgreSQL), libraries for data analysis (e.g., Python's pandas, SciPy), and scripts for applying rule-based algorithms.

[1482] Device:

[1483] Terminals are devices that users use to access the web portal to upload data and check analysis results, such as PCs, smartphones, and tablets.

[1484] User:

[1485] Users are end users who operate and want to improve web services.

[1486] Specific operating procedures

[1487] 1. Data Input:

[1488] Users prepare log data and access data related to their website in CSV or JSON format, including access logs and click data.

[1489] Users log in to a dedicated web portal and open the data upload page, which provides an interface for users to select data files and click the submit button.

[1490] The terminal reads the selected data file and transmits it to the server.

[1491] The server stores the received data file in temporary storage.

[1492] 2. Data Preprocessing:

[1493] The server loads the data file from temporary storage and performs file format and content validation, including checking the CSV format and parsing JSON.

[1494] The server detects missing or invalid values ​​and handles them appropriately, for example, by filling in the missing values ​​with the mean value and deleting or correcting invalid values.

[1495] The server performs data normalization, scaling numeric data and encoding categorical data.

[1496] The server stores the pre-processed data in the main database.

[1497] 3. Data Analysis:

[1498] The server loads the pre-processed data from the main database and begins analyzing it, using SQL queries and Python libraries to calculate metrics such as bounce rates, time spent, page navigation patterns, and feature usage.

[1499] The server stores the calculation results in temporary storage in preparation for the next process.

[1500] 4. UI / UX issue extraction:

[1501] Based on the analysis results, the server applies a rule-based algorithm to identify UI / UX issues. For example, if a particular page has a high bounce rate, it analyzes the user behavior data for that page.

[1502] The server examines click patterns, scrolling depth, and other factors to generate a list of issues. For example, specific problems such as "key information is at the bottom of the page, making it difficult for users to find" are extracted.

[1503] 5. Suggestions for improvement:

[1504] The server then generates improvement suggestions based on the list of issues, referencing past success stories and industry best practices, such as "place key information at the top of the page and make the CTA button more prominent."

[1505] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[1506] 6. Providing reports to users:

[1507] The user logs in to the web portal again and opens the analysis results dashboard.

[1508] The device requests the latest analysis results and improvement suggestions from the server.

[1509] The server reads the saved report and sends it to the terminal.

[1510] The terminal displays the received report on a dashboard so that the user can check it.

[1511] Users can review the proposed improvements on the dashboard and download the report if necessary.

[1512] Examples of concrete examples and prompts

[1513] Example 1: Identifying and improving pages with high exit rates:

[1514] Users upload website log data in CSV file format.

[1515] The server verifies the data format, performs preprocessing, and then analyzes the log data to identify pages with high bounce rates.

[1516] The server analyzes user behavior data for this page, extracts issues such as "the main information is at the bottom of the page, making it difficult for users to find," and proposes improvements.

[1517] Example 2: Improving dashboards with low usage:

[1518] Users upload dashboard usage logs in JSON file format.

[1519] The server preprocesses the files, stores them in a database, and then analyzes the usage logs to identify underused features.

[1520] The server extracts issues such as "This function is located in a location that is difficult for users to understand" and proposes improvements.

[1521] Example prompt sentence:

[1522] "Please analyze the contents of this CSV file and summarize the issues and specific suggestions for improving the UI / UX of the website."

[1523] This system allows users to quickly and efficiently identify and improve issues without having advanced data analysis skills, and is expected to significantly contribute to improving the performance of web services.

[1524] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1525] Step 1:

[1526] Preparing and uploading data

[1527] Users prepare log data and access data related to their company's services in CSV or JSON format, including access logs and click data.

[1528] Users log in to a dedicated web portal and open the data upload page.

[1529] The user selects a data file in the upload interface and clicks the submit button.

[1530] Input: Log data in CSV or JSON format

[1531] Output: Data file sent to the server

[1532] Step 2:

[1533] Receiving and temporarily storing data

[1534] The terminal reads the selected data file and transmits it to the server.

[1535] The server stores the contents of the received data file in temporary storage.

[1536] Input: Data file submitted by the user

[1537] Output: Data file saved in temporary storage

[1538] Step 3:

[1539] Data validation and preprocessing

[1540] The server reads the data file from temporary storage and validates the file format and content, specifically checking the CSV format and parsing JSON.

[1541] The server detects missing or invalid data values ​​based on the verification results and takes appropriate action.

[1542] Input: Data file for temporary storage

[1543] Output: Validated and processed preprocessed data

[1544] Step 4:

[1545] Data normalization

[1546] The server normalizes the preprocessed data, specifically scaling numeric data and encoding categorical data.

[1547] The server stores the normalized data in a main database.

[1548] Input: Preprocessed data

[1549] Output: Main database with normalized data

[1550] Step 5:

[1551] Calculating key indicators

[1552] The server reads the pre-processed data from the main database and executes the necessary queries.

[1553] The server calculates important metrics such as bounce rate, time spent, page transition patterns, and feature usage.

[1554] Input: Data in the main database

[1555] Output: Analysis results including calculated key indicators

[1556] Step 6:

[1557] Identifying UI / UX issues

[1558] Based on the calculated analysis results, the server applies a rule-based algorithm to extract UI / UX issues.

[1559] Specifically, the server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[1560] Input: Analysis results

[1561] Output: Issue list

[1562] Step 7:

[1563] Generate improvement proposals

[1564] Based on the list of issues, the server generates improvement proposals by referencing past success stories and industry best practices.

[1565] The server generates specific recommendations (e.g., "Place key information at the top of the page and make the CTA button prominent").

[1566] Input: Issue list, past success stories, best practices

[1567] Output: A report with concrete improvement suggestions

[1568] Step 8:

[1569] Providing reports

[1570] The user logs in to the web portal again and opens the analysis results dashboard.

[1571] The device requests the latest analysis results and improvement suggestions from the server.

[1572] The server reads the saved report and sends it to the terminal.

[1573] The terminal displays the received report on a dashboard so that the user can check it.

[1574] Input: Analysis results and improvement proposal request

[1575] Output: Report provided to the user

[1576] Through this series of processes, users can quickly and efficiently extract UI / UX issues and obtain appropriate improvement proposals, even without specialized knowledge.

[1577] (Application example 1)

[1578] 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."

[1579] In recent years, improving the user interface (UI) and user experience (UX) has become increasingly important in e-commerce (mail order) sites. However, identifying UI / UX issues and efficiently improving them requires advanced data analysis skills and a great deal of effort from site operators. Furthermore, they are required to not only provide analysis results but also propose specific improvement plans. Therefore, there is a need for a system that allows site operators to easily input data and receive analysis results and improvement proposals.

[1580] 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.

[1581] In this invention, the server includes means for inputting data, means for preprocessing data, means for performing data analysis based on the preprocessed data, means for extracting issues with the user interface and user experience from the analysis results, means for proposing improvement plans for the extracted issues, means for providing the improvement plans and analysis results to users, means for calculating multiple indicators, means for an online shopping site operator to upload data using a smartphone and receive the analysis results and improvement proposals, means for generating improvement plans based on past success stories and best practices, and means for saving and reading data using temporary storage and a main database. This enables operators to quickly and efficiently extract and improve issues using their smartphones, even without advanced data analysis skills.

[1582] 1. "Data input means" refers to the overall interface and process by which a user inputs data into the system.

[1583] 2. "Preprocessing measures" refers to measures to prepare data in an appropriate state before proceeding to the next step, such as data format verification, missing value imputation, invalid value processing, and data standardization.

[1584] 3. "Data analysis tools" refers to a set of processes and algorithms that calculate various indicators based on pre-processed data.

[1585] 4. "UI / UX issue extraction method" refers to the method for identifying issues and problems related to the user interface and user experience based on the analysis results.

[1586] 5. "Means for proposing improvements" refers to the means for generating specific improvement proposals based on the issues identified, with reference to past success stories and industry best practices.

[1587] 6. "Means for providing improvement proposals and analysis results" refers to the means for providing the generated improvement proposals and analysis results to the user.

[1588] 7. "Means for calculating indicators" refers to the means for calculating important indicators such as bounce rate, duration of visit, page transition patterns, and function usage rate.

[1589] 8. "Smartphone uploading means" refers to the means by which the operator of an online shopping site uploads data using a smartphone.

[1590] 9. "Means for referring to past success stories and best practices" refers to means for referring to past success stories and industry best practices when generating improvement proposals.

[1591] 10. "Temporary storage and main database means" refers to the storage means used temporarily to store and retrieve data and the main database for long-term data storage.

[1592] This invention relates to a data analysis and improvement proposal system that can be used by online shopping site operators. The system aims to enable operators to efficiently identify and improve UI / UX issues by automating a series of processes from data input to preprocessing, analysis, problem extraction, improvement proposal proposals, and result provision.

[1593] System Configuration

[1594] Data Input

[1595] Users use their smartphones to prepare log data and access data related to online shopping sites in CSV or JSON format, and then upload it to a cloud server using a dedicated application. The uploaded data is then stored in temporary storage.

[1596] Data Preprocessing

[1597] The server reads the data from the temporary storage, performs formal validation, and if the data contains missing or invalid values, it imputes or removes them appropriately and standardizes the data. The preprocessed data is then stored in the main database.

[1598] Data analysis

[1599] The server reads pre-processed data from the main database and calculates various metrics (e.g., exit rate, visit duration, page navigation patterns, feature usage rate) using multiple SQL queries and data processing algorithms.

[1600] Identifying UI / UX issues

[1601] Based on the data analysis results, the server identifies issues such as high bounce rates and low conversion rates for specific pages and functions, and uses rule-based algorithms to extract issues related to the user interface and user experience.

[1602] Improvement proposal

[1603] The server then generates specific improvement proposals for the identified issues, referencing past success stories and best practices, such as "place key information at the top of the page and make the CTA button more prominent."

[1604] Report provision

[1605] The server creates a report summarizing the generated improvement proposals and analysis results and provides it to the user, who can then check the report on their smartphone app and download it as needed.

[1606] Hardware and software used

[1607] The system consists of the following hardware and software:

[1608] Cloud Server: Responsible for storing and processing data.

[1609] Smartphone: Used by users to upload data and check results. Dedicated applications are installed.

[1610] Temporary storage and main database: Used for data storage.

[1611] Pandas and SQL: Used for data preprocessing and analysis.

[1612] Specific examples

[1613] The user prepares log data from an online shopping site in CSV format and uploads it to a cloud server via a smartphone app. The server stores the received data in temporary storage, performs formal validation, and processes missing values. The preprocessed data is then stored in the main database and indicators are calculated. Based on the calculation results, pages with high bounce rates are identified and issues on those pages are extracted. The server then proposes specific improvement plans, such as "moving key information to the top," and generates a report to provide to the user.

[1614] Prompt Sentence Examples

[1615] You can request specific analysis and improvement suggestions for your generative AI model using the following prompts:

[1616] Request Type: Analysis

[1617] Data format: CSV

[1618] Data Path: ecommerce_log.csv

[1619] Analysis type: Exit rate analysis, Conversion rate analysis

[1620] Proposal criteria: Past success stories, industry best practices

[1621] This prompt allows the system to take appropriate action based on the specified data format and analysis type.

[1622] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1623] Step 1:

[1624] A user uses a smartphone to prepare log data and access data related to an online shopping site in CSV or JSON format, and uploads it to a cloud server using a dedicated application. The input is a data file prepared by the user (e.g., ecommerce_log.csv), and the output is the uploaded data stored in temporary storage on the cloud server.

[1625] Step 2:

[1626] The server reads the uploaded data from temporary storage and verifies the data format. The input is the data file in temporary storage, and the output is the data file after format verification. Once verification is complete, it proceeds to the next process.

[1627] Step 3:

[1628] The server performs data preprocessing, such as missing value imputation, invalid value handling, and data standardization. The input is a data file that has been format-validated, and the output is a preprocessed data file. The preprocessed data is stored in the main database.

[1629] Step 4:

[1630] The server reads preprocessed data from the main database and analyzes and calculates various indicators (e.g., exit rate, duration of visit, page transition patterns, feature usage rate, etc.). The input is the preprocessed data, and the output is the calculated indicator results. The calculation results are saved in temporary storage.

[1631] Step 5:

[1632] The server extracts user interface and user experience related issues based on the analysis results. The input is the calculated metrics and the output is a list of extracted issues. Specific problems and issues are extracted using a rule-based algorithm.

[1633] Step 6:

[1634] The server generates specific improvement proposals for the extracted issues by referencing past success stories and industry best practices. The input is a list of issues, and the output is specific improvement proposals. For example, suggestions include "Place key information at the top of the page and make the CTA button more prominent."

[1635] Step 7:

[1636] The server creates a report that summarizes the generated improvement proposals and analysis results. The inputs are the improvement proposals and analysis results, and the output is a report. The report is saved in temporary storage and formatted so that it can be provided to the user.

[1637] Step 8:

[1638] Users check the reports using a smartphone app. The input is the report provided by the server, and the output is confirmation or download of the report contents. Users can check the details of the report generated in the smartphone app and obtain specific implementation procedures if necessary.

[1639] 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.

[1640] This invention is a system that enables web service professionals to efficiently identify issues in their company's services and propose improvement proposals. By combining it with an emotion engine that recognizes user emotions, it achieves more accurate issue identification and improvement proposal proposals. This system automates a series of processes: the server preprocesses data input by the user, performs data analysis, identifies UI / UX issues, and proposes improvement proposals for those issues. Furthermore, the emotion engine makes it possible to analyze and propose proposals that take into account user emotion data.

[1641] Program processing

[1642] Data Input

[1643] 1. The user prepares log data and access data related to their company's services in CSV or JSON format.

[1644] 2. The user logs in to the dedicated web portal and opens the data upload page.

[1645] 3. The user selects the prepared data file in the upload interface and clicks the Upload button.

[1646] 4. The terminal reads the selected data file and sends its contents to the server.

[1647] 5. The server stores the received data file in temporary storage.

[1648] Data Preprocessing

[1649] 1. The server reads the data file from temporary storage and verifies the data format and content.

[1650] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[1651] 3. The server normalizes the data to make it consistent.

[1652] 4. The server stores the preprocessed data in the main database.

[1653] Data analysis

[1654] 1. The server loads the preprocessed data from the main database and starts data analysis.

[1655] 2. The server executes queries to analyze the data and calculates the following metrics:

[1656] Abandonment rate

[1657] Stay time

[1658] Page Transition Pattern

[1659] Function usage rate

[1660] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[1661] Emotion data collection and analysis

[1662] 1. Users use dedicated tools and applications to collect emotional data during use.

[1663] 2. The device sends the emotion data to the server.

[1664] 3. The server analyzes the received emotion data and recognizes emotion patterns.

[1665] Identifying UI / UX issues

[1666] 1. The server applies a rule-based algorithm based on the analysis results and emotion data to extract UI / UX issues.

[1667] 2. The server identifies pages with high bounce rates and pages where users are likely to get lost, and analyzes the related factors.

[1668] 3. The server analyzes how specific UI elements affect emotions based on the user's emotional data.

[1669] 4. The server lists the extracted issues and stores them together with the associated evidence.

[1670] Proposal of improvement plan

[1671] 1. The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[1672] 2. The server compares the generated improvement proposals with the user's emotional data and makes suggestions that are appropriate for each individual user.

[1673] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[1674] Providing reports to users

[1675] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[1676] 2. The device requests the latest analysis results and improvement suggestions from the server.

[1677] 3. The server reads the saved report and sends it to the device.

[1678] 4. The device displays the received report on the dashboard so that the user can check it.

[1679] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[1680] Specific examples

[1681] Example 1: Identifying and improving pages with high bounce rates

[1682] 1. The user uploads the website log data in CSV format.

[1683] 2. The server validates the data format and performs preprocessing.

[1684] 3. The server analyzes the log data and identifies pages with high bounce rates.

[1685] 4. The server analyzes the user behavior and emotion data for this page to identify the cause of abandonment.

[1686] 5. The server extracts issues such as "key information is at the bottom of the page and difficult for users to find."

[1687] 6. The server will suggest improvements such as "move the main information to the top of the page and make the CTA button more prominent."

[1688] 7. Users can view suggested improvements on their dashboard and receive detailed guidelines for implementation.

[1689] Example 2: Improving a dashboard with low feature usage

[1690] 1. The user uploads dashboard usage logs in JSON format.

[1691] 2. The server preprocesses the data and stores it in a database.

[1692] 3. The server analyzes usage logs and sentiment data to identify features with low usage rates.

[1693] 4. The server analyzes user feedback and survey data to identify the causes of low usage.

[1694] 5. The server extracts issues such as, "This function is located in a location that is difficult for users to understand."

[1695] 6. The server suggests improvements such as "move this feature to the top menu and add a tooltip."

[1696] 7. The user checks the proposed changes on the dashboard and implements the improvements by referring to the implementation procedures.

[1697] As described above, this system enables even users without advanced data analysis skills to quickly and efficiently identify issues and obtain improvement proposals that take into account the emotions of individual users. This system is expected to make a significant contribution to improving the performance of web services and optimizing the user experience.

[1698] The processing flow will be explained below.

[1699] Step 1:

[1700] Users prepare log data and access data related to their services in CSV or JSON format.

[1701] Step 2:

[1702] Users log in to a dedicated web portal and open the data upload page.

[1703] Step 3:

[1704] The user selects the prepared data file in the upload interface and clicks the upload button.

[1705] Step 4:

[1706] The terminal reads the selected data file and transmits its contents to the server.

[1707] Step 5:

[1708] The server stores the received data file in temporary storage.

[1709] Step 6:

[1710] The server reads the data file from temporary storage, validates the data format and content, and corrects any invalid data format, missing values, or invalid values.

[1711] Step 7:

[1712] The server performs preprocessing of the data, specifically cleaning the data (removing missing or invalid values) and normalizing it.

[1713] Step 8:

[1714] The server stores the pre-processed data in the main database.

[1715] Step 9:

[1716] The server reads the pre-processed data from the main database and begins data analysis.

[1717] Step 10:

[1718] The server executes queries to analyze the data and calculates the following metrics:

[1719] Exit rate (number of exits on a specific page divided by total number of sessions)

[1720] Duration of visit (average time spent by users on each page)

[1721] Page transition patterns (analyzing the user's transition sequence between pages)

[1722] Feature usage rate (number of times a specific feature is used divided by the total number of accesses)

[1723] Step 11:

[1724] The server stores the calculation results in temporary storage in preparation for the next process.

[1725] Step 12:

[1726] Users use dedicated tools and applications to collect emotion data during use.

[1727] Step 13:

[1728] The terminal transmits the collected emotion data to the server.

[1729] Step 14:

[1730] The server analyzes the received emotion data and recognizes emotion patterns.

[1731] Step 15:

[1732] Based on the analysis results and emotional data, the server applies a rule-based algorithm to extract UI / UX issues.

[1733] Step 16:

[1734] The server identifies pages with high drop-off rates and pages where users tend to get lost, analyzes the associated factors, and takes sentiment data into account.

[1735] Step 17:

[1736] The server uses heat map analysis and user behavior data (click patterns, scrolling volume, etc.) to reveal details of UI / UX issues.

[1737] Step 18:

[1738] The server lists the extracted issues and stores them together with the associated evidence.

[1739] Step 19:

[1740] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[1741] Step 20:

[1742] The server compares the generated improvement proposals with the user's emotional data and makes suggestions that are appropriate for each individual user.

[1743] Step 21:

[1744] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[1745] Step 22:

[1746] The user logs in to the web portal again and opens the analysis results dashboard.

[1747] Step 23:

[1748] The device requests the latest analysis results and improvement suggestions from the server.

[1749] Step 24:

[1750] The server reads the saved report and sends it to the terminal.

[1751] Step 25:

[1752] The terminal displays the received report on a dashboard so that the user can check it.

[1753] Step 26:

[1754] Users can review the suggested improvements on the dashboard and download or print the report if desired.

[1755] Through this process, users can quickly and efficiently identify issues and obtain improvement proposals that take into account the emotions of individual users, even without advanced data analysis skills. This system is expected to make a significant contribution to improving the performance of web services and optimizing the user experience.

[1756] Example 2

[1757] 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."

[1758] With conventional web services, it was difficult to efficiently identify issues with the user interface and user experience and propose improvement proposals. Furthermore, the effectiveness of improvement proposals was limited because they did not take user emotions into consideration. This meant that service performance improvements and optimization of the user experience could not be fully achieved.

[1759] The identification process 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 inputting data, means for preprocessing data, means for performing data analysis based on the preprocessed data, means for extracting issues in the user interface and user experience, means for proposing improvement plans for the extracted issues, means for collecting and analyzing user emotion data, means for adjusting the issues and improvement plans based on the emotion data, means for providing the improvement plans and analysis results to the user, and means for generating a report to be provided to the user. This makes it possible to accurately extract issues and propose effective improvement plans that take user emotions into consideration.

[1760] "Data input" refers to a user providing log data and access data to the system.

[1761] "Data preprocessing" refers to the process of filling in missing values, correcting invalid values, and normalizing the data to make it consistent, in order to make the collected data easier to analyze.

[1762] "Data analysis" refers to the process of calculating metrics and identifying issues related to the user interface and user experience based on pre-processed data.

[1763] "Identifying issues in the user interface and user experience" refers to using data analysis results and user emotion data to identify problems in the user interface and user experience of web services.

[1764] "Proposing improvements" refers to presenting specific methods for correcting or improving the identified issues based on past success stories and best practices.

[1765] "Collection and analysis of emotional data" refers to the process of collecting emotional data from users while they are using the service and analyzing that data to understand the user's emotional state.

[1766] "Adjustment of issues and improvement proposals" refers to optimizing identified issues and proposed improvement proposals for individual users based on collected and analyzed emotional data.

[1767] "Report generation" refers to the process of creating a report detailing the analysis results and improvement proposals and providing it to the user.

[1768] This invention is a system that allows users of web services to efficiently identify issues with their own services and propose improvement plans. The system includes the following main components:

[1769] 1. Data input method

[1770] Users prepare log data and access data related to their services in CSV or JSON format.

[1771] Users log in to a dedicated web portal and upload data files from the data upload page.

[1772] The terminal reads the uploaded data file and transmits its contents to the server.

[1773] The server stores the received data file in temporary storage.

[1774] 2. Data preprocessing methods

[1775] The server reads the data file from the temporary storage and verifies the data format and content.

[1776] The server identifies missing, invalid, and outlier values ​​and takes appropriate action (e.g., imputing the mean value of missing values).

[1777] The server normalizes the data to ensure consistency.

[1778] The server stores the pre-processed data in the main database.

[1779] 3. Data Analysis Methods

[1780] The server reads the pre-processed data from the main database and runs queries to perform data analysis.

[1781] The server calculates the following metrics: exit rate, visit duration, page transition patterns, and feature usage rate.

[1782] The server stores the calculation results in temporary storage in preparation for the next process.

[1783] 4. Methods for collecting and analyzing emotion data

[1784] Users collect emotion data during use using dedicated tools and applications.

[1785] The terminal transmits the emotion data to the server.

[1786] The server analyzes the received emotion data and recognizes emotion patterns.

[1787] 5. Methods for extracting UI / UX issues

[1788] The server applies a rule-based algorithm to extract issues based on the analysis results and emotion data.

[1789] The server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[1790] The server analyzes how specific UI elements affect emotions.

[1791] The server lists the extracted issues and stores them together with the associated evidence.

[1792] 6. Means of proposing improvements

[1793] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[1794] The server compares the proposed improvement plan with the user's emotional data and makes suggestions that are appropriate for each individual user.

[1795] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[1796] 7. Report Generation Methods

[1797] The server has means for generating and providing reports to the user.

[1798] Specific examples

[1799] For example, when uploading a website's log data in CSV format, a user selects and uploads the file from the data upload page. This data is then sent to the server, where it is validated and pre-processed. Data analysis identifies pages with high drop-off rates and user sentiment data, and UI / UX issues are extracted. Improvement proposals are then proposed based on past success stories and industry best practices. Finally, the proposals are provided to the user in the form of a detailed report.

[1800] The specific hardware or software used

[1801] Temporary storage: Amazon S3, etc.

[1802] Main database: PostgreSQL, etc.

[1803] Data analysis libraries: Python Pandas, TensorFlow, etc.

[1804] Prompt Sentence Examples

[1805] "If a particular page has a high bounce rate, identify the cause and suggest appropriate improvements."

[1806] The above is an embodiment of the present invention, which contributes greatly to improving the performance of Web services and optimizing the user experience.

[1807] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1808] Step 1: Data Input

[1809] 1. The user prepares log data and access data related to their company's services in CSV or JSON format.

[1810] Input: User-prepared CSV or JSON file

[1811] What happens: A user accesses a web portal in their browser to select and upload a data file.

[1812] 2. The user logs in to the dedicated web portal and opens the data upload page.

[1813] Input: Portal login information

[1814] Specific behavior: The user enters their authentication information and clicks the login button.

[1815] 3. The user selects the prepared data file in the upload interface and clicks the Upload button.

[1816] Input: Selected data file

[1817] Specific behavior: The user clicks the "Choose File" button, selects a CSV file from local storage, and clicks the "Upload" button.

[1818] 4. The terminal reads the selected data file and sends its contents to the server.

[1819] Input: Selected data file

[1820] Output: Sending the data file to the server

[1821] Specific operation: The device sends a data file to the server using an HTTP POST request.

[1822] 5. The server stores the received data file in temporary storage.

[1823] Input: Received data file

[1824] Output: Data file saved in temporary storage

[1825] Specific operation: The server stores the received file in temporary storage such as an Amazon S3 bucket.

[1826] Step 2: Data Preprocessing

[1827] 1. The server reads the data file from temporary storage and verifies the data format and content.

[1828] Input: Data file saved in temporary storage

[1829] Output: Validated data file

[1830] Specific operation: The server checks the data format (such as the CSV header row) and validates the contents.

[1831] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[1832] Input: Validated data file

[1833] Output: Preprocessed data

[1834] Specific operation: Uses the Pandas library to perform operations such as filling in NaN (missing values) with the average value of the column.

[1835] 3. The server normalizes the data to make it consistent.

[1836] Input: Data file with missing, invalid, and outlier processed

[1837] Output: Normalized data file

[1838] Specific operation: Scales numerical data and normalizes it to the range 0 to 1.

[1839] 4. The server stores the preprocessed data in the main database.

[1840] Input: Normalized data file

[1841] Output: Preprocessed data stored in the main database

[1842] Specific operation: Insert the preprocessed data into a PostgreSQL database.

[1843] Step 3: Data analysis

[1844] 1. The server loads the preprocessed data from the main database and starts data analysis.

[1845] Input: Preprocessed data stored in the main database

[1846] Output: Analysis results

[1847] Specific behavior: Executes an SQL query to retrieve the required data from the database.

[1848] 2. The server executes queries to analyze the data and calculates the following metrics:

[1849] Abandonment rate

[1850] Stay time

[1851] Page Transition Pattern

[1852] Function usage rate

[1853] Input: Data retrieved from the database

[1854] Output: Calculation results for each indicator

[1855] Specific operation: Calculate each metric using SQL queries or Python scripts.

[1856] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[1857] Input: Calculated indicator data

[1858] Output: Calculation results saved in temporary storage

[1859] Specific operation: The calculation results are saved as a JSON format file on Amazon S3.

[1860] Step 4: Collect and analyze emotion data

[1861] 1. Users use dedicated tools and applications to collect emotional data during use.

[1862] Input: Data from emotion data collection tools

[1863] Output: Collected emotion data

[1864] What it does: Collects facial expression data from users using emotion recognition apps and browser extensions.

[1865] 2. The device sends the emotion data to the server.

[1866] Input: Collected emotion data

[1867] Output: Emotion data sent to the server

[1868] Specific operation: Emotion data is sent to the server in real time using a REST API.

[1869] 3. The server analyzes the received emotion data and recognizes emotion patterns.

[1870] Input: Emotion data sent to the server

[1871] Output: Parsed emotion patterns

[1872] What it does: Analyzes emotional patterns using deep learning models (e.g., TensorFlow or PyTorch).

[1873] Step 5: Identify UI / UX issues

[1874] 1. The server applies a rule-based algorithm to extract issues based on the analysis results and emotion data.

[1875] Input: Data analysis results and emotion data

[1876] Output: Extracted issues

[1877] Specific behavior: Applying rule-based algorithms to identify issues from specific indicator values ​​and sentiment patterns.

[1878] 2. The server identifies pages with high bounce rates and pages where users are likely to get lost, and analyzes the related factors.

[1879] Input: Extracted issues

[1880] Output: Identified high exit rate pages and pages where users are likely to get lost

[1881] Specific actions: Correlate and analyze user behavioral data and sentiment data to identify problematic pages.

[1882] 3. The server analyzes how specific UI elements affect emotions.

[1883] Input: User behavioral and emotional data

[1884] Output: UI elements that affect emotions

[1885] Specific behavior: Analyze how clicking a specific button or link affects a user's emotions.

[1886] 4. The server lists the extracted issues and stores them together with the associated evidence.

[1887] Input: Clarified issue

[1888] Output: A list of issues saved with evidence

[1889] Specific action: Compile a list of issues and related data into a single report.

[1890] Step 6: Propose improvements

[1891] 1. The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[1892] Input: Extracted issues

[1893] Output: Generated improvement suggestions

[1894] Specific operation: Query past success stories from a database and generate improvement suggestions based on them.

[1895] 2. The server compares the proposed improvement plan with the user's emotional data and makes suggestions that are appropriate for each individual user.

[1896] Input: Improvement proposals and user emotion data

[1897] Output: Adjusted improvement proposal

[1898] Specific action: Check whether the generated improvement proposals can elicit positive emotions from users.

[1899] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[1900] Input: Adjusted improvement proposal

[1901] Output: Improvement suggestions saved as a report

[1902] Specific operation: The proposal and its rationale are written in Markdown format and saved in temporary storage (e.g., Amazon S3).

[1903] Step 7: Provide the report to the user

[1904] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[1905] Input: Portal login information

[1906] Output: Access to the dashboard

[1907] Specific operations: After logging in to the web portal, click the "View analysis results" button.

[1908] 2. The device requests the latest analysis results and improvement suggestions from the server.

[1909] Input: Request from the dashboard page

[1910] Output: The data requested from the server

[1911] Specific operation: Send an Ajax request to get the latest data.

[1912] 3. The server reads the saved report and sends it to the device.

[1913] Input: Saved Report

[1914] Output: Report sent to terminal

[1915] Specific operation: Download the report from Amazon S3 etc. and send it to the device.

[1916] 4. The device displays the received report on the dashboard so that the user can check it.

[1917] Input: Report sent from the server

[1918] Output: The report displayed in a dashboard

[1919] Specific operation: Renders the retrieved report data in HTML format and displays it on a dashboard.

[1920] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[1921] Input: Report displayed on dashboard

[1922] Output: Downloaded report

[1923] Specific behavior: Click the "Download Report" button and save the report in PDF format to local storage.

[1924] (Application example 2)

[1925] 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."

[1926] The present invention aims to provide an effective system for improving the quality of customer experience in brick-and-mortar stores. In particular, the system aims to support store operators in increasing customer satisfaction by extracting issues in the customer experience based on customer behavioral and emotional data and automatically proposing appropriate improvement plans.

[1927] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1928] In this invention, the server includes means for inputting data, means for preprocessing the data, means for performing data analysis based on the preprocessed data, means for extracting issues in the user interface and user experience, means for proposing improvement plans for the extracted issues, means for collecting and analyzing user emotion data, and means for providing the improvement plans and analysis results to the user. This makes it possible to identify detailed customer experience issues based on customer behavioral data and emotion data, and to provide effective improvement plans.

[1929] "Means for inputting data" is a general term for various hardware and software that input data into the system from outside.

[1930] "Means for preprocessing data" refers to functions that include processes for verifying the format and content of input data, handling missing values ​​and invalid values, and normalizing data.

[1931] "Means for performing data analysis based on preprocessed data" refers to the function of using normalized data to perform various analyses, calculate indicators, and discover patterns.

[1932] "Means for identifying issues in user interfaces and user experiences" includes algorithms and procedures for identifying problems related to the use of systems and services based on the results of data analysis.

[1933] "Means for proposing improvement plans for extracted issues" refers to the function within the system that automatically generates and proposes specific solutions to issues.

[1934] "Means for collecting and analyzing user emotional data" includes tools and algorithms for measuring and recording a user's emotional state and analyzing emotional patterns.

[1935] "Means for providing improvement proposals and analysis results to users" refers to various interfaces that visually display the improvement proposals and analysis results generated by the system and provide them to users.

[1936] A "temporary storage device" is a memory or storage device for short-term storage of data files.

[1937] The system of the present invention collects and analyzes various data, automatically extracts issues, and proposes improvement plans in order to improve the customer experience in physical stores. This system is composed of a means for inputting data, a means for preprocessing the data, a means for performing data analysis based on the preprocessed data, a means for extracting issues in the user interface and user experience, a means for proposing improvement plans for the extracted issues, a means for collecting and analyzing user emotion data, and a means for providing the user with improvement plans and analysis results.

[1938] Hardware and software used

[1939] 1. Hardware

[1940] Smartphone

[1941] camera

[1942] server

[1943] 2. Software

[1944] Python

[1945] Pandas

[1946] Scikit-learn

[1947] EmotionEngine (virtual module)

[1948] UI_UX_Analyzer (virtual module)

[1949] What the program does

[1950] Data Input

[1951] Users upload customer behavior and feedback data collected in-store to the system using their smartphones, with the data provided in CSV or JSON format.

[1952] Data Preprocessing

[1953] The server first performs formal validation of the received data and processes invalid and missing values. Specifically, it reads the data as a data frame using Pandas, removes missing values, and normalizes and standardizes the numerical data using Scikit-learn.

[1954] Data analysis

[1955] Once the data preprocessing is complete, the server analyzes the data using UI_UX_Analyzer, which calculates important metrics such as customer behavior patterns, dropout rates, and dwell time.

[1956] Emotion data collection and analysis

[1957] Customer emotional data is collected in real time via smartphones and analyzed using EmotionEngine to recognize customer emotional patterns (e.g., satisfaction, dissatisfaction, excitement, etc.).

[1958] Identifying UI / UX issues and proposing improvements

[1959] Based on the results of data analysis and sentiment data, the server extracts issues in the user interface and user experience. For any issues discovered, it generates effective improvement proposals based on past success stories and industry standards.

[1960] Providing reports to users

[1961] Finally, the analysis results and improvement recommendations are provided to the user. This information is displayed in a visually easy-to-understand report format on a dashboard, where the user can view the details of the improvement recommendations and receive guidance on how to implement them.

[1962] Examples of concrete examples and prompts

[1963] Specific examples

[1964] For example, if a problem is identified where in-store navigation is difficult for customers to understand, the server will suggest moving important information to the top of the page. This suggestion is based on customer behavioral and emotional data, reducing customer frustration when trying to find information.

[1965] Prompt Sentence Examples

[1966] Analyze customer sentiment based on the feedback below.

[1967] Feedback: "The navigation in this store is very confusing. It took me a while to find the product I wanted."

[1968] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1969] Step 1: Data Input

[1970] Users upload customer behavior and feedback data collected in physical stores to the system using their smartphones, and this data is provided in CSV or JSON format.

[1971] Input: Customer behavior and feedback data in CSV or JSON format

[1972] Output: Raw data uploaded to the server

[1973] Step 2: Receiving and storing data

[1974] The terminal receives the uploaded data file and transmits the contents to the server, which stores the received data file in a temporary storage device.

[1975] Input: Data file sent to the server

[1976] Output: Raw data file saved to temporary storage

[1977] Step 3: Data Preprocessing

[1978] The server reads the data file from temporary storage, validates the data format, handles invalid and missing values, and performs standardization and normalization. It converts the data into a data frame using Pandas, removes missing values, and normalizes the numeric data using Scikit-learn.

[1979] Input: Raw data file read from temporary storage

[1980] Output: Preprocessed data

[1981] Step 4: Data analysis

[1982] The server uses UI_UX_Analyzer to perform detailed data analysis based on the pre-processed data, and calculates key indicators such as customer behavior patterns, dropout rates, and duration of stay.

[1983] Input: Preprocessed data

[1984] Output: Analysis results (customer behavior patterns, abandonment rate, duration of stay, etc.)

[1985] Step 5: Collect and analyze emotion data

[1986] The terminal collects customer emotional data in real time via the smartphone. The server uses EmotionEngine to analyze the emotional data and recognize the customer's emotional patterns. This analysis process utilizes, for example, feedback text and facial expressions provided when customers answer questionnaires on their smartphones.

[1987] Input: Emotion data collected in real time

[1988] Output: Parsed emotion patterns

[1989] Step 6: Identify UI / UX issues

[1990] The server applies rule-based algorithms based on data analysis and sentiment data to identify issues with the user interface and user experience. For example, it can identify areas where customers are experiencing inconvenience on specific pages or operations based on customer feedback and behavioral analysis data.

[1991] Input: Data analysis results and sentiment pattern analysis results

[1992] Output: A list of extracted UI / UX issues

[1993] Step 7: Propose improvements

[1994] The server generates improvement suggestions for the extracted issues based on past best practices and industry standards, including specific suggestions such as "move important information to the top of the page" or "change the location of new features."

[1995] Input: Extracted UI / UX issue list

[1996] Output: Suggested improvements

[1997] Step 8: Generate and deliver reports

[1998] The server generates a visually easy-to-understand report of the proposed improvements and analysis results and stores it in temporary storage. Users can log in to the web portal, view the report on the dashboard, and download the report if necessary.

[1999] Input: Proposed improvements and analysis results

[2000] Output: Generated report with improvement suggestions and analysis results

[2001] 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.

[2002] 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.

[2003] 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.

[2004] [Fourth embodiment]

[2005] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2006] 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.

[2007] 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).

[2008] 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.

[2009] 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.

[2010] 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).

[2011] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[2012] 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.

[2013] 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.

[2014] 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.

[2015] 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.

[2016] 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.

[2017] 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."

[2018] This invention is a system that efficiently identifies issues in the company's services that web service workers are responsible for and proposes improvement plans. This system automates the process of having the server preprocess data entered by users, performing data analysis, identifying UI / UX issues, and proposing improvement plans.

[2019] Program processing

[2020] Data Input

[2021] 1. The user prepares log data and access data related to their company's service in CSV or JSON format.

[2022] 2. The user logs in to the dedicated web portal and opens the data upload page.

[2023] 3. The user selects the data file in the upload interface and clicks the submit button.

[2024] 4. The terminal reads the selected data file and sends it to the server.

[2025] 5. The server stores the received data file in temporary storage.

[2026] Data Preprocessing

[2027] 1. The server reads the data file from temporary storage and validates the file format and content.

[2028] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[2029] 3. The server normalizes the data to make it consistent.

[2030] 4. The server stores the preprocessed data in the main database.

[2031] Data analysis

[2032] 1. The server loads the preprocessed data from the main database and starts data analysis.

[2033] 2. The server executes queries to calculate key metrics such as bounce rate, time on site, page navigation patterns, and feature usage.

[2034] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[2035] Identifying UI / UX issues

[2036] 1. Based on the analysis results, the server applies a rule-based algorithm to extract UI / UX issues.

[2037] 2. The server identifies pages with high drop-off rates or pages where users tend to get lost, and analyzes related factors, such as scrolling and click patterns on specific pages.

[2038] 3. The server generates a list of issues and stores it with the evidence.

[2039] Proposal of improvement plan

[2040] 1. Based on the list of issues, the server generates improvement proposals by referencing past success stories and industry best practices.

[2041] 2. The server creates specific suggestions, such as "To reduce the bounce rate on this page, place the main information at the top and make the CTA button more prominent."

[2042] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[2043] Providing reports to users

[2044] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[2045] 2. The device requests the latest analysis results and improvement suggestions from the server.

[2046] 3. The server reads the saved report and sends it to the device.

[2047] 4. The device displays the received report on the dashboard so that the user can check it.

[2048] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[2049] Specific examples

[2050] Example 1: Identifying and improving pages with high bounce rates

[2051] 1. The user uploads website log data in CSV file format.

[2052] 2. The server validates the data format and performs preprocessing.

[2053] 3. The server analyzes the log data and identifies pages with high bounce rates.

[2054] 4. The server analyzes the user behavior data for this page and identifies the reason for abandonment.

[2055] 5. The server extracts issues such as "key information is at the bottom of the page and difficult for users to find."

[2056] 6. The server will suggest improvements such as "move the main information to the top of the page and make the CTA button more prominent."

[2057] 7. Users can view suggested improvements on their dashboard and receive detailed guidelines for implementation.

[2058] Example 2: Improving a dashboard with low feature usage

[2059] 1. The user uploads dashboard usage logs in JSON file format.

[2060] 2. The server pre-processes the file and stores it in a database.

[2061] 3. The server analyzes the usage log and identifies functions with low usage rates.

[2062] 4. The server analyzes user feedback and survey data to identify the causes of low usage.

[2063] 5. The server extracts issues such as, "This function is located in a location that is difficult for users to understand."

[2064] 6. The server suggests improvements such as "move this feature to the top menu and add a tooltip."

[2065] 7. The user checks the proposed changes on the dashboard and implements the improvements by referring to the implementation procedures.

[2066] This allows users to quickly and efficiently identify and improve issues without having advanced data analysis skills. This system is expected to greatly contribute to improving the performance of web services.

[2067] The processing flow will be explained below.

[2068] Step 1:

[2069] Users prepare log data and access data for their services and save them as CSV or JSON format files.

[2070] Step 2:

[2071] Users log in to a dedicated web portal and open the data upload page.

[2072] Step 3:

[2073] The user selects the prepared data file in the upload interface and clicks the upload button.

[2074] Step 4:

[2075] The terminal reads the selected data file and transmits its contents to the server.

[2076] Step 5:

[2077] The server stores the received data file in temporary storage.

[2078] Step 6:

[2079] The server reads the data file from temporary storage, validates the data format and content, and corrects any invalid data format, missing values, or invalid values.

[2080] Step 7:

[2081] The server performs preprocessing of the data, specifically cleaning the data (removing missing or invalid values) and normalizing it.

[2082] Step 8:

[2083] The server stores the pre-processed data in the main database.

[2084] Step 9:

[2085] The server reads the pre-processed data from the main database and begins data analysis.

[2086] Step 10:

[2087] The server executes queries to analyze the data and calculates the following metrics:

[2088] Exit rate (number of exits on a specific page divided by total number of sessions)

[2089] Duration of visit (average time spent by users on each page)

[2090] Page transition patterns (analyzing the user's transition sequence between pages)

[2091] Feature usage rate (number of times a specific feature is used divided by the total number of accesses)

[2092] Step 11:

[2093] The server stores the calculation results in temporary storage in preparation for the next process.

[2094] Step 12:

[2095] The server applies a rule-based algorithm based on the analysis results to extract UI / UX issues.

[2096] Step 13:

[2097] The server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[2098] Step 14:

[2099] The server uses heat map analysis and user behavior data (click patterns, scrolling volume, etc.) to reveal details of UI / UX issues.

[2100] Step 15:

[2101] The server lists the extracted issues and stores them together with the associated evidence.

[2102] Step 16:

[2103] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[2104] Step 17:

[2105] The server creates a report detailing the generated improvement proposals and the reasons for them, and stores it in temporary storage.

[2106] Step 18:

[2107] The user logs into the web portal and opens the analysis results dashboard.

[2108] Step 19:

[2109] The device retrieves the latest analysis results and improvement suggestions from the server in response to a user request.

[2110] Step 20:

[2111] The server reads the saved report and sends it to the user's terminal.

[2112] Step 21:

[2113] The terminal displays the received report on a dashboard so that the user can check it.

[2114] Step 22:

[2115] Users can review the suggested improvements on the dashboard and download or print the report if desired.

[2116] Example 1

[2117] 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."

[2118] Optimizing the user experience (UI / UX) is extremely important for modern web services. However, the process of data analysis and UX improvement is complex and requires specialized skills. Furthermore, many web service professionals lack the time and resources to efficiently identify issues and propose appropriate improvement plans. This can lead to poor service performance and reduced user satisfaction. Therefore, there is a need for a system that can easily and efficiently analyze data and improve the user experience.

[2119] 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.

[2120] In this invention, the server includes means for uploading data input by a user and transmitting it to the server, means for preprocessing the data and saving it in temporary storage, means for saving the preprocessed data in a main database, means for performing data analysis based on the preprocessed data, means for calculating key indicators based on data from the database, means for algorithmically extracting UI / UX issues based on the analysis results, means for generating improvement plans for the extracted issues by referring to past success stories and best practices, and means for providing the generated improvement plans and analysis results to the user's device. This makes it possible for even web service professionals without specialized knowledge to perform advanced data analysis and quickly and effectively improve UI / UX.

[2121] "User" refers to an end user who uses the system to upload data and receive analysis results and improvement suggestions.

[2122] "Server" is a central system that processes data sent by users, analyzes it and makes suggestions for improvement.

[2123] A "terminal" is a device that allows a user to access the server to upload data and check analysis results.

[2124] "Data input" is the process by which a user inputs information such as log data and access data into the system.

[2125] "Preprocessing" refers to a series of operations performed by the server to prepare the data it receives into an analyzable format, and specifically includes verifying the data format, filling in missing values, and processing invalid values.

[2126] "Data analysis" is the process of calculating indicators such as bounce rate, dwell time, and feature usage rate based on preprocessed data, and extracting meaningful information.

[2127] "UI / UX issues" refer to problems or factors that may degrade the user experience in a web service.

[2128] "Improvement proposals" are specific proposals and strategies generated by the server to solve the extracted UI / UX issues.

[2129] "Temporary storage" is a storage area for temporarily storing received data and analysis results.

[2130] The "main database" is a central storage area for storing pre-processed data and important data that needs to be stored for a long period of time.

[2131] A "rule-based algorithm" is a computational method for analyzing data based on predefined rules and extracting UI / UX issues.

[2132] "Past success stories" refer to improvement measures and methods whose effectiveness has been confirmed based on past performance.

[2133] "Best practices" refer to methods or techniques that are widely accepted across an industry.

[2134] A "dashboard" is a graphical user interface that allows users to visually check analysis results and improvement proposals.

[2135] A "query" is a search command executed against a database to retrieve specific indicators or information.

[2136] A "prompt sentence" is an input sentence that instructs a generative AI model to perform a specific analysis or generate a suggestion.

[2137] MODE FOR CARRYING OUT THE INVENTION

[2138] This invention is a system that efficiently identifies issues in the company's services that web service workers are responsible for and proposes improvement plans. This system automates the process of having the server preprocess data entered by users, performing data analysis, identifying UI / UX issues, and proposing improvement plans.

[2139] Hardware and software used

[2140] server:

[2141] A server is a computer equipped with sufficient computing resources and storage to perform high-performance data processing.

[2142] Software includes database management systems (e.g., MySQL, PostgreSQL), libraries for data analysis (e.g., Python's pandas, SciPy), and scripts for applying rule-based algorithms.

[2143] Device:

[2144] Terminals are devices that users use to access the web portal to upload data and check analysis results, such as PCs, smartphones, and tablets.

[2145] User:

[2146] Users are end users who operate and want to improve web services.

[2147] Specific operating procedures

[2148] 1. Data Input:

[2149] Users prepare log data and access data related to their website in CSV or JSON format, including access logs and click data.

[2150] Users log in to a dedicated web portal and open the data upload page, which provides an interface for users to select data files and click the submit button.

[2151] The terminal reads the selected data file and transmits it to the server.

[2152] The server stores the received data file in temporary storage.

[2153] 2. Data Preprocessing:

[2154] The server loads the data file from temporary storage and performs file format and content validation, including checking the CSV format and parsing JSON.

[2155] The server detects missing or invalid values ​​and handles them appropriately, for example, by filling in the missing values ​​with the mean value and deleting or correcting invalid values.

[2156] The server performs data normalization, scaling numeric data and encoding categorical data.

[2157] The server stores the pre-processed data in the main database.

[2158] 3. Data Analysis:

[2159] The server loads the pre-processed data from the main database and begins analyzing it, using SQL queries and Python libraries to calculate metrics such as bounce rates, time spent, page navigation patterns, and feature usage.

[2160] The server stores the calculation results in temporary storage in preparation for the next process.

[2161] 4. UI / UX issue extraction:

[2162] Based on the analysis results, the server applies a rule-based algorithm to identify UI / UX issues. For example, if a particular page has a high bounce rate, it analyzes the user behavior data for that page.

[2163] The server examines click patterns, scrolling depth, and other factors to generate a list of issues. For example, specific problems such as "key information is at the bottom of the page, making it difficult for users to find" are extracted.

[2164] 5. Suggestions for improvement:

[2165] The server then generates improvement suggestions based on the list of issues, referencing past success stories and industry best practices, such as "place key information at the top of the page and make the CTA button more prominent."

[2166] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[2167] 6. Providing reports to users:

[2168] The user logs in to the web portal again and opens the analysis results dashboard.

[2169] The device requests the latest analysis results and improvement suggestions from the server.

[2170] The server reads the saved report and sends it to the terminal.

[2171] The terminal displays the received report on a dashboard so that the user can check it.

[2172] Users can review the proposed improvements on the dashboard and download the report if necessary.

[2173] Examples of concrete examples and prompts

[2174] Example 1: Identifying and improving pages with high exit rates:

[2175] Users upload website log data in CSV file format.

[2176] The server verifies the data format, performs preprocessing, and then analyzes the log data to identify pages with high bounce rates.

[2177] The server analyzes user behavior data for this page, extracts issues such as "the main information is at the bottom of the page, making it difficult for users to find," and proposes improvements.

[2178] Example 2: Improving dashboards with low usage:

[2179] Users upload dashboard usage logs in JSON file format.

[2180] The server preprocesses the files, stores them in a database, and then analyzes the usage logs to identify underused features.

[2181] The server extracts issues such as "This function is located in a location that is difficult for users to understand" and proposes improvements.

[2182] Example prompt sentence:

[2183] "Please analyze the contents of this CSV file and summarize the issues and specific suggestions for improving the UI / UX of the website."

[2184] This system allows users to quickly and efficiently identify and improve issues without having advanced data analysis skills, and is expected to significantly contribute to improving the performance of web services.

[2185] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2186] Step 1:

[2187] Preparing and uploading data

[2188] Users prepare log data and access data related to their company's services in CSV or JSON format, including access logs and click data.

[2189] Users log in to a dedicated web portal and open the data upload page.

[2190] The user selects a data file in the upload interface and clicks the submit button.

[2191] Input: Log data in CSV or JSON format

[2192] Output: Data file sent to the server

[2193] Step 2:

[2194] Receiving and temporarily storing data

[2195] The terminal reads the selected data file and transmits it to the server.

[2196] The server stores the contents of the received data file in temporary storage.

[2197] Input: Data file submitted by the user

[2198] Output: Data file saved in temporary storage

[2199] Step 3:

[2200] Data validation and preprocessing

[2201] The server reads the data file from temporary storage and validates the file format and content, specifically checking the CSV format and parsing JSON.

[2202] The server detects missing or invalid data values ​​based on the verification results and takes appropriate action.

[2203] Input: Data file for temporary storage

[2204] Output: Validated and processed preprocessed data

[2205] Step 4:

[2206] Data normalization

[2207] The server normalizes the preprocessed data, specifically scaling numeric data and encoding categorical data.

[2208] The server stores the normalized data in a main database.

[2209] Input: Preprocessed data

[2210] Output: Main database with normalized data

[2211] Step 5:

[2212] Calculating key indicators

[2213] The server reads the pre-processed data from the main database and executes the necessary queries.

[2214] The server calculates important metrics such as bounce rate, time spent, page transition patterns, and feature usage.

[2215] Input: Data in the main database

[2216] Output: Analysis results including calculated key indicators

[2217] Step 6:

[2218] Identifying UI / UX issues

[2219] Based on the calculated analysis results, the server applies a rule-based algorithm to extract UI / UX issues.

[2220] Specifically, the server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[2221] Input: Analysis results

[2222] Output: Issue list

[2223] Step 7:

[2224] Generate improvement proposals

[2225] Based on the list of issues, the server generates improvement proposals by referencing past success stories and industry best practices.

[2226] The server generates specific recommendations (e.g., "Place key information at the top of the page and make the CTA button prominent").

[2227] Input: Issue list, past success stories, best practices

[2228] Output: A report with concrete improvement suggestions

[2229] Step 8:

[2230] Providing reports

[2231] The user logs in to the web portal again and opens the analysis results dashboard.

[2232] The device requests the latest analysis results and improvement suggestions from the server.

[2233] The server reads the saved report and sends it to the terminal.

[2234] The terminal displays the received report on a dashboard so that the user can check it.

[2235] Input: Analysis results and improvement proposal request

[2236] Output: Report provided to the user

[2237] Through this series of processes, users can quickly and efficiently extract UI / UX issues and obtain appropriate improvement proposals, even without specialized knowledge.

[2238] (Application example 1)

[2239] 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."

[2240] In recent years, improving the user interface (UI) and user experience (UX) has become increasingly important in e-commerce (mail order) sites. However, identifying UI / UX issues and efficiently improving them requires advanced data analysis skills and a great deal of effort from site operators. Furthermore, they are required to not only provide analysis results but also propose specific improvement plans. Therefore, there is a need for a system that allows site operators to easily input data and receive analysis results and improvement proposals.

[2241] 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.

[2242] In this invention, the server includes means for inputting data, means for preprocessing data, means for performing data analysis based on the preprocessed data, means for extracting issues with the user interface and user experience from the analysis results, means for proposing improvement plans for the extracted issues, means for providing the improvement plans and analysis results to users, means for calculating multiple indicators, means for an online shopping site operator to upload data using a smartphone and receive the analysis results and improvement proposals, means for generating improvement plans based on past success stories and best practices, and means for saving and reading data using temporary storage and a main database. This enables operators to quickly and efficiently extract and improve issues using their smartphones, even without advanced data analysis skills.

[2243] 1. "Data input means" refers to the overall interface and process by which a user inputs data into the system.

[2244] 2. "Preprocessing measures" refers to measures to prepare data in an appropriate state before proceeding to the next step, such as data format verification, missing value imputation, invalid value processing, and data standardization.

[2245] 3. "Data analysis tools" refers to a set of processes and algorithms that calculate various indicators based on pre-processed data.

[2246] 4. "UI / UX issue extraction method" refers to the method for identifying issues and problems related to the user interface and user experience based on the analysis results.

[2247] 5. "Means for proposing improvements" refers to the means for generating specific improvement proposals based on the issues identified, with reference to past success stories and industry best practices.

[2248] 6. "Means for providing improvement proposals and analysis results" refers to the means for providing the generated improvement proposals and analysis results to the user.

[2249] 7. "Means for calculating indicators" refers to the means for calculating important indicators such as bounce rate, duration of visit, page transition patterns, and function usage rate.

[2250] 8. "Smartphone uploading means" refers to the means by which the operator of an online shopping site uploads data using a smartphone.

[2251] 9. "Means for referring to past success stories and best practices" refers to means for referring to past success stories and industry best practices when generating improvement proposals.

[2252] 10. "Temporary storage and main database means" refers to the storage means used temporarily to store and retrieve data and the main database for long-term data storage.

[2253] This invention relates to a data analysis and improvement proposal system that can be used by online shopping site operators. The system aims to enable operators to efficiently identify and improve UI / UX issues by automating a series of processes from data input to preprocessing, analysis, problem extraction, improvement proposal proposals, and result provision.

[2254] System Configuration

[2255] Data Input

[2256] Users use their smartphones to prepare log data and access data related to online shopping sites in CSV or JSON format, and then upload it to a cloud server using a dedicated application. The uploaded data is then stored in temporary storage.

[2257] Data Preprocessing

[2258] The server reads the data from the temporary storage, performs formal validation, and if the data contains missing or invalid values, it imputes or removes them appropriately and standardizes the data. The preprocessed data is then stored in the main database.

[2259] Data analysis

[2260] The server reads pre-processed data from the main database and calculates various metrics (e.g., exit rate, visit duration, page navigation patterns, feature usage rate) using multiple SQL queries and data processing algorithms.

[2261] Identifying UI / UX issues

[2262] Based on the data analysis results, the server identifies issues such as high bounce rates and low conversion rates for specific pages and functions, and uses rule-based algorithms to extract issues related to the user interface and user experience.

[2263] Improvement proposal

[2264] The server then generates specific improvement proposals for the identified issues, referencing past success stories and best practices, such as "place key information at the top of the page and make the CTA button more prominent."

[2265] Report provision

[2266] The server creates a report summarizing the generated improvement proposals and analysis results and provides it to the user, who can then check the report on their smartphone app and download it as needed.

[2267] Hardware and software used

[2268] The system consists of the following hardware and software:

[2269] Cloud Server: Responsible for storing and processing data.

[2270] Smartphone: Used by users to upload data and check results. Dedicated applications are installed.

[2271] Temporary storage and main database: Used for data storage.

[2272] Pandas and SQL: Used for data preprocessing and analysis.

[2273] Specific examples

[2274] The user prepares log data from an online shopping site in CSV format and uploads it to a cloud server via a smartphone app. The server stores the received data in temporary storage, performs formal validation, and processes missing values. The preprocessed data is then stored in the main database and indicators are calculated. Based on the calculation results, pages with high bounce rates are identified and issues on those pages are extracted. The server then proposes specific improvement plans, such as "moving key information to the top," and generates a report to provide to the user.

[2275] Prompt Sentence Examples

[2276] You can request specific analysis and improvement suggestions for your generative AI model using the following prompts:

[2277] Request Type: Analysis

[2278] Data format: CSV

[2279] Data Path: ecommerce_log.csv

[2280] Analysis type: Exit rate analysis, Conversion rate analysis

[2281] Proposal criteria: Past success stories, industry best practices

[2282] This prompt allows the system to take appropriate action based on the specified data format and analysis type.

[2283] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2284] Step 1:

[2285] A user uses a smartphone to prepare log data and access data related to an online shopping site in CSV or JSON format, and uploads it to a cloud server using a dedicated application. The input is a data file prepared by the user (e.g., ecommerce_log.csv), and the output is the uploaded data stored in temporary storage on the cloud server.

[2286] Step 2:

[2287] The server reads the uploaded data from temporary storage and verifies the data format. The input is the data file in temporary storage, and the output is the data file after format verification. Once verification is complete, it proceeds to the next process.

[2288] Step 3:

[2289] The server performs data preprocessing, such as missing value imputation, invalid value handling, and data standardization. The input is a data file that has been format-validated, and the output is a preprocessed data file. The preprocessed data is stored in the main database.

[2290] Step 4:

[2291] The server reads preprocessed data from the main database and analyzes and calculates various indicators (e.g., exit rate, duration of visit, page transition patterns, feature usage rate, etc.). The input is the preprocessed data, and the output is the calculated indicator results. The calculation results are saved in temporary storage.

[2292] Step 5:

[2293] The server extracts user interface and user experience related issues based on the analysis results. The input is the calculated metrics and the output is a list of extracted issues. Specific problems and issues are extracted using a rule-based algorithm.

[2294] Step 6:

[2295] The server generates specific improvement proposals for the extracted issues by referencing past success stories and industry best practices. The input is a list of issues, and the output is specific improvement proposals. For example, suggestions include "Place key information at the top of the page and make the CTA button more prominent."

[2296] Step 7:

[2297] The server creates a report that summarizes the generated improvement proposals and analysis results. The inputs are the improvement proposals and analysis results, and the output is a report. The report is saved in temporary storage and formatted so that it can be provided to the user.

[2298] Step 8:

[2299] Users check the reports using a smartphone app. The input is the report provided by the server, and the output is confirmation or download of the report contents. Users can check the details of the report generated in the smartphone app and obtain specific implementation procedures if necessary.

[2300] 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.

[2301] This invention is a system that enables web service professionals to efficiently identify issues in their company's services and propose improvement proposals. By combining it with an emotion engine that recognizes user emotions, it achieves more accurate issue identification and improvement proposal proposals. This system automates a series of processes: the server preprocesses data input by the user, performs data analysis, identifies UI / UX issues, and proposes improvement proposals for those issues. Furthermore, the emotion engine makes it possible to analyze and propose proposals that take into account user emotion data.

[2302] Program processing

[2303] Data Input

[2304] 1. The user prepares log data and access data related to their company's services in CSV or JSON format.

[2305] 2. The user logs in to the dedicated web portal and opens the data upload page.

[2306] 3. The user selects the prepared data file in the upload interface and clicks the Upload button.

[2307] 4. The terminal reads the selected data file and sends its contents to the server.

[2308] 5. The server stores the received data file in temporary storage.

[2309] Data Preprocessing

[2310] 1. The server reads the data file from temporary storage and verifies the data format and content.

[2311] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[2312] 3. The server normalizes the data to make it consistent.

[2313] 4. The server stores the preprocessed data in the main database.

[2314] Data analysis

[2315] 1. The server loads the preprocessed data from the main database and starts data analysis.

[2316] 2. The server executes queries to analyze the data and calculates the following metrics:

[2317] Abandonment rate

[2318] Stay time

[2319] Page Transition Pattern

[2320] Function usage rate

[2321] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[2322] Emotion data collection and analysis

[2323] 1. Users use dedicated tools and applications to collect emotional data during use.

[2324] 2. The device sends the emotion data to the server.

[2325] 3. The server analyzes the received emotion data and recognizes emotion patterns.

[2326] Identifying UI / UX issues

[2327] 1. The server applies a rule-based algorithm based on the analysis results and emotion data to extract UI / UX issues.

[2328] 2. The server identifies pages with high bounce rates and pages where users are likely to get lost, and analyzes the related factors.

[2329] 3. The server analyzes how specific UI elements affect emotions based on the user's emotional data.

[2330] 4. The server lists the extracted issues and stores them together with the associated evidence.

[2331] Proposal of improvement plan

[2332] 1. The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[2333] 2. The server compares the generated improvement proposals with the user's emotional data and makes suggestions that are appropriate for each individual user.

[2334] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[2335] Providing reports to users

[2336] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[2337] 2. The device requests the latest analysis results and improvement suggestions from the server.

[2338] 3. The server reads the saved report and sends it to the device.

[2339] 4. The device displays the received report on the dashboard so that the user can check it.

[2340] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[2341] Specific examples

[2342] Example 1: Identifying and improving pages with high bounce rates

[2343] 1. The user uploads the website log data in CSV format.

[2344] 2. The server validates the data format and performs preprocessing.

[2345] 3. The server analyzes the log data and identifies pages with high bounce rates.

[2346] 4. The server analyzes the user behavior and emotion data for this page to identify the cause of abandonment.

[2347] 5. The server extracts issues such as "key information is at the bottom of the page and difficult for users to find."

[2348] 6. The server will suggest improvements such as "move the main information to the top of the page and make the CTA button more prominent."

[2349] 7. Users can view suggested improvements on their dashboard and receive detailed guidelines for implementation.

[2350] Example 2: Improving a dashboard with low feature usage

[2351] 1. The user uploads dashboard usage logs in JSON format.

[2352] 2. The server preprocesses the data and stores it in a database.

[2353] 3. The server analyzes usage logs and sentiment data to identify features with low usage rates.

[2354] 4. The server analyzes user feedback and survey data to identify the causes of low usage.

[2355] 5. The server extracts issues such as, "This function is located in a location that is difficult for users to understand."

[2356] 6. The server suggests improvements such as "move this feature to the top menu and add a tooltip."

[2357] 7. The user checks the proposed changes on the dashboard and implements the improvements by referring to the implementation procedures.

[2358] As described above, this system enables even users without advanced data analysis skills to quickly and efficiently identify issues and obtain improvement proposals that take into account the emotions of individual users. This system is expected to make a significant contribution to improving the performance of web services and optimizing the user experience.

[2359] The processing flow will be explained below.

[2360] Step 1:

[2361] Users prepare log data and access data related to their services in CSV or JSON format.

[2362] Step 2:

[2363] Users log in to a dedicated web portal and open the data upload page.

[2364] Step 3:

[2365] The user selects the prepared data file in the upload interface and clicks the upload button.

[2366] Step 4:

[2367] The terminal reads the selected data file and transmits its contents to the server.

[2368] Step 5:

[2369] The server stores the received data file in temporary storage.

[2370] Step 6:

[2371] The server reads the data file from temporary storage, validates the data format and content, and corrects any invalid data format, missing values, or invalid values.

[2372] Step 7:

[2373] The server performs preprocessing of the data, specifically cleaning the data (removing missing or invalid values) and normalizing it.

[2374] Step 8:

[2375] The server stores the pre-processed data in the main database.

[2376] Step 9:

[2377] The server reads the pre-processed data from the main database and begins data analysis.

[2378] Step 10:

[2379] The server executes queries to analyze the data and calculates the following metrics:

[2380] Exit rate (number of exits on a specific page divided by total number of sessions)

[2381] Duration of visit (average time spent by users on each page)

[2382] Page transition patterns (analyzing the user's transition sequence between pages)

[2383] Feature usage rate (number of times a specific feature is used divided by the total number of accesses)

[2384] Step 11:

[2385] The server stores the calculation results in temporary storage in preparation for the next process.

[2386] Step 12:

[2387] Users use dedicated tools and applications to collect emotion data during use.

[2388] Step 13:

[2389] The terminal transmits the collected emotion data to the server.

[2390] Step 14:

[2391] The server analyzes the received emotion data and recognizes emotion patterns.

[2392] Step 15:

[2393] Based on the analysis results and emotional data, the server applies a rule-based algorithm to extract UI / UX issues.

[2394] Step 16:

[2395] The server identifies pages with high drop-off rates and pages where users tend to get lost, analyzes the associated factors, and takes sentiment data into account.

[2396] Step 17:

[2397] The server uses heat map analysis and user behavior data (click patterns, scrolling volume, etc.) to reveal details of UI / UX issues.

[2398] Step 18:

[2399] The server lists the extracted issues and stores them together with the associated evidence.

[2400] Step 19:

[2401] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[2402] Step 20:

[2403] The server compares the generated improvement proposals with the user's emotional data and makes suggestions that are appropriate for each individual user.

[2404] Step 21:

[2405] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[2406] Step 22:

[2407] The user logs in to the web portal again and opens the analysis results dashboard.

[2408] Step 23:

[2409] The device requests the latest analysis results and improvement suggestions from the server.

[2410] Step 24:

[2411] The server reads the saved report and sends it to the terminal.

[2412] Step 25:

[2413] The terminal displays the received report on a dashboard so that the user can check it.

[2414] Step 26:

[2415] Users can review the suggested improvements on the dashboard and download or print the report if desired.

[2416] Through this process, users can quickly and efficiently identify issues and obtain improvement proposals that take into account the emotions of individual users, even without advanced data analysis skills. This system is expected to make a significant contribution to improving the performance of web services and optimizing the user experience.

[2417] Example 2

[2418] 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."

[2419] With conventional web services, it was difficult to efficiently identify issues with the user interface and user experience and propose improvement proposals. Furthermore, the effectiveness of improvement proposals was limited because they did not take user emotions into consideration. This meant that service performance improvements and optimization of the user experience could not be fully achieved.

[2420] The identification process 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 inputting data, means for preprocessing data, means for performing data analysis based on the preprocessed data, means for extracting issues in the user interface and user experience, means for proposing improvement plans for the extracted issues, means for collecting and analyzing user emotion data, means for adjusting the issues and improvement plans based on the emotion data, means for providing the improvement plans and analysis results to the user, and means for generating a report to be provided to the user. This makes it possible to accurately extract issues and propose effective improvement plans that take user emotions into consideration.

[2421] "Data input" refers to a user providing log data and access data to the system.

[2422] "Data preprocessing" refers to the process of filling in missing values, correcting invalid values, and normalizing the data to make it consistent, in order to make the collected data easier to analyze.

[2423] "Data analysis" refers to the process of calculating metrics and identifying issues related to the user interface and user experience based on pre-processed data.

[2424] "Identifying issues in the user interface and user experience" refers to using data analysis results and user emotion data to identify problems in the user interface and user experience of web services.

[2425] "Proposing improvements" refers to presenting specific methods for correcting or improving the identified issues based on past success stories and best practices.

[2426] "Collection and analysis of emotional data" refers to the process of collecting emotional data from users while they are using the service and analyzing that data to understand the user's emotional state.

[2427] "Adjustment of issues and improvement proposals" refers to optimizing identified issues and proposed improvement proposals for individual users based on collected and analyzed emotional data.

[2428] "Report generation" refers to the process of creating a report detailing the analysis results and improvement proposals and providing it to the user.

[2429] This invention is a system that allows users of web services to efficiently identify issues with their own services and propose improvement plans. The system includes the following main components:

[2430] 1. Data input method

[2431] Users prepare log data and access data related to their services in CSV or JSON format.

[2432] Users log in to a dedicated web portal and upload data files from the data upload page.

[2433] The terminal reads the uploaded data file and transmits its contents to the server.

[2434] The server stores the received data file in temporary storage.

[2435] 2. Data preprocessing methods

[2436] The server reads the data file from the temporary storage and verifies the data format and content.

[2437] The server identifies missing, invalid, and outlier values ​​and takes appropriate action (e.g., imputing the mean value of missing values).

[2438] The server normalizes the data to ensure consistency.

[2439] The server stores the pre-processed data in the main database.

[2440] 3. Data Analysis Methods

[2441] The server reads the pre-processed data from the main database and runs queries to perform data analysis.

[2442] The server calculates the following metrics: exit rate, visit duration, page transition patterns, and feature usage rate.

[2443] The server stores the calculation results in temporary storage in preparation for the next process.

[2444] 4. Methods for collecting and analyzing emotion data

[2445] Users collect emotion data during use using dedicated tools and applications.

[2446] The terminal transmits the emotion data to the server.

[2447] The server analyzes the received emotion data and recognizes emotion patterns.

[2448] 5. Methods for extracting UI / UX issues

[2449] The server applies a rule-based algorithm to extract issues based on the analysis results and emotion data.

[2450] The server identifies pages with high dropout rates and pages where users tend to get lost, and analyzes related factors.

[2451] The server analyzes how specific UI elements affect emotions.

[2452] The server lists the extracted issues and stores them together with the associated evidence.

[2453] 6. Means of proposing improvements

[2454] The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[2455] The server compares the proposed improvement plan with the user's emotional data and makes suggestions that are appropriate for each individual user.

[2456] The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[2457] 7. Report Generation Methods

[2458] The server has means for generating and providing reports to the user.

[2459] Specific examples

[2460] For example, when uploading a website's log data in CSV format, a user selects and uploads the file from the data upload page. This data is then sent to the server, where it is validated and pre-processed. Data analysis identifies pages with high drop-off rates and user sentiment data, and UI / UX issues are extracted. Improvement proposals are then proposed based on past success stories and industry best practices. Finally, the proposals are provided to the user in the form of a detailed report.

[2461] The specific hardware or software used

[2462] Temporary storage: Amazon S3, etc.

[2463] Main database: PostgreSQL, etc.

[2464] Data analysis libraries: Python Pandas, TensorFlow, etc.

[2465] Prompt Sentence Examples

[2466] "If a particular page has a high bounce rate, identify the cause and suggest appropriate improvements."

[2467] The above is an embodiment of the present invention, which contributes greatly to improving the performance of Web services and optimizing the user experience.

[2468] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2469] Step 1: Data Input

[2470] 1. The user prepares log data and access data related to their company's services in CSV or JSON format.

[2471] Input: User-prepared CSV or JSON file

[2472] What happens: A user accesses a web portal in their browser to select and upload a data file.

[2473] 2. The user logs in to the dedicated web portal and opens the data upload page.

[2474] Input: Portal login information

[2475] Specific behavior: The user enters their authentication information and clicks the login button.

[2476] 3. The user selects the prepared data file in the upload interface and clicks the Upload button.

[2477] Input: Selected data file

[2478] Specific behavior: The user clicks the "Choose File" button, selects a CSV file from local storage, and clicks the "Upload" button.

[2479] 4. The terminal reads the selected data file and sends its contents to the server.

[2480] Input: Selected data file

[2481] Output: Sending the data file to the server

[2482] Specific operation: The device sends a data file to the server using an HTTP POST request.

[2483] 5. The server stores the received data file in temporary storage.

[2484] Input: Received data file

[2485] Output: Data file saved in temporary storage

[2486] Specific operation: The server stores the received file in temporary storage such as an Amazon S3 bucket.

[2487] Step 2: Data Preprocessing

[2488] 1. The server reads the data file from temporary storage and verifies the data format and content.

[2489] Input: Data file saved in temporary storage

[2490] Output: Validated data file

[2491] Specific operation: The server checks the data format (such as the CSV header row) and validates the contents.

[2492] 2. The server detects missing, invalid, and outlier values ​​and handles them appropriately, for example by filling in the missing values ​​with the average value.

[2493] Input: Validated data file

[2494] Output: Preprocessed data

[2495] Specific operation: Uses the Pandas library to perform operations such as filling in NaN (missing values) with the average value of the column.

[2496] 3. The server normalizes the data to make it consistent.

[2497] Input: Data file with missing, invalid, and outlier processed

[2498] Output: Normalized data file

[2499] Specific operation: Scales numerical data and normalizes it to the range 0 to 1.

[2500] 4. The server stores the preprocessed data in the main database.

[2501] Input: Normalized data file

[2502] Output: Preprocessed data stored in the main database

[2503] Specific operation: Insert the preprocessed data into a PostgreSQL database.

[2504] Step 3: Data analysis

[2505] 1. The server loads the preprocessed data from the main database and starts data analysis.

[2506] Input: Preprocessed data stored in the main database

[2507] Output: Analysis results

[2508] Specific behavior: Executes an SQL query to retrieve the required data from the database.

[2509] 2. The server executes queries to analyze the data and calculates the following metrics:

[2510] Abandonment rate

[2511] Stay time

[2512] Page Transition Pattern

[2513] Function usage rate

[2514] Input: Data retrieved from the database

[2515] Output: Calculation results for each indicator

[2516] Specific operation: Calculate each metric using SQL queries or Python scripts.

[2517] 3. The server stores the calculation results in temporary storage in preparation for the next process.

[2518] Input: Calculated indicator data

[2519] Output: Calculation results saved in temporary storage

[2520] Specific operation: The calculation results are saved as a JSON format file on Amazon S3.

[2521] Step 4: Collect and analyze emotion data

[2522] 1. Users use dedicated tools and applications to collect emotional data during use.

[2523] Input: Data from emotion data collection tools

[2524] Output: Collected emotion data

[2525] What it does: Collects facial expression data from users using emotion recognition apps and browser extensions.

[2526] 2. The device sends the emotion data to the server.

[2527] Input: Collected emotion data

[2528] Output: Emotion data sent to the server

[2529] Specific operation: Emotion data is sent to the server in real time using a REST API.

[2530] 3. The server analyzes the received emotion data and recognizes emotion patterns.

[2531] Input: Emotion data sent to the server

[2532] Output: Parsed emotion patterns

[2533] What it does: Analyzes emotional patterns using deep learning models (e.g., TensorFlow or PyTorch).

[2534] Step 5: Identify UI / UX issues

[2535] 1. The server applies a rule-based algorithm to extract issues based on the analysis results and emotion data.

[2536] Input: Data analysis results and emotion data

[2537] Output: Extracted issues

[2538] Specific behavior: Applying rule-based algorithms to identify issues from specific indicator values ​​and sentiment patterns.

[2539] 2. The server identifies pages with high bounce rates and pages where users are likely to get lost, and analyzes the related factors.

[2540] Input: Extracted issues

[2541] Output: Identified high exit rate pages and pages where users are likely to get lost

[2542] Specific actions: Correlate and analyze user behavioral data and sentiment data to identify problematic pages.

[2543] 3. The server analyzes how specific UI elements affect emotions.

[2544] Input: User behavioral and emotional data

[2545] Output: UI elements that affect emotions

[2546] Specific behavior: Analyze how clicking a specific button or link affects a user's emotions.

[2547] 4. The server lists the extracted issues and stores them together with the associated evidence.

[2548] Input: Clarified issue

[2549] Output: A list of issues saved with evidence

[2550] Specific action: Compile a list of issues and related data into a single report.

[2551] Step 6: Propose improvements

[2552] 1. The server generates improvement proposals for the listed issues based on past success stories and industry best practices.

[2553] Input: Extracted issues

[2554] Output: Generated improvement suggestions

[2555] Specific operation: Query past success stories from a database and generate improvement suggestions based on them.

[2556] 2. The server compares the proposed improvement plan with the user's emotional data and makes suggestions that are appropriate for each individual user.

[2557] Input: Improvement proposals and user emotion data

[2558] Output: Adjusted improvement proposal

[2559] Specific action: Check whether the generated improvement proposals can elicit positive emotions from users.

[2560] 3. The server creates a report detailing the recommendations and the reasons for them and stores it in temporary storage.

[2561] Input: Adjusted improvement proposal

[2562] Output: Improvement suggestions saved as a report

[2563] Specific operation: The proposal and its rationale are written in Markdown format and saved in temporary storage (e.g., Amazon S3).

[2564] Step 7: Provide the report to the user

[2565] 1. The user logs in to the web portal again and opens the analysis results dashboard.

[2566] Input: Portal login information

[2567] Output: Access to the dashboard

[2568] Specific operations: After logging in to the web portal, click the "View analysis results" button.

[2569] 2. The device requests the latest analysis results and improvement suggestions from the server.

[2570] Input: Request from the dashboard page

[2571] Output: The data requested from the server

[2572] Specific operation: Send an Ajax request to get the latest data.

[2573] 3. The server reads the saved report and sends it to the device.

[2574] Input: Saved Report

[2575] Output: Report sent to terminal

[2576] Specific operation: Download the report from Amazon S3 etc. and send it to the device.

[2577] 4. The device displays the received report on the dashboard so that the user can check it.

[2578] Input: Report sent from the server

[2579] Output: The report displayed in a dashboard

[2580] Specific operation: Renders the retrieved report data in HTML format and displays it on a dashboard.

[2581] 5. Users can review the proposed improvements on their dashboard and download the report if needed.

[2582] Input: Report displayed on dashboard

[2583] Output: Downloaded report

[2584] Specific behavior: Click the "Download Report" button and save the report in PDF format to local storage.

[2585] (Application example 2)

[2586] 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."

[2587] The present invention aims to provide an effective system for improving the quality of customer experience in brick-and-mortar stores. In particular, the system aims to support store operators in increasing customer satisfact...

Claims

1. A means of inputting data; a means for preprocessing the data; a means for performing data analysis based on the preprocessed data; A method to extract UI / UX issues from the analysis results, A means of proposing improvement plans for the extracted issues; A system that includes a means for providing improvement suggestions and analysis results to the user.

2. The system of claim 1 further comprising means for receiving and storing in temporary storage data files uploaded by users.

3. 2. The system of claim 1, further comprising preprocessing means for validating data formats, handling missing and invalid values, and normalizing data.

4. The system according to claim 1 , further comprising a data analysis means for calculating an exit rate, a duration of stay, a page transition pattern, and a function usage rate.

5. The system of claim 1 , further comprising means for applying a rule-based algorithm to extract UI / UX issues.

6. The system according to claim 1 , further comprising means for generating improvement proposals for the issues based on past success stories and industry best practices.

7. The system of claim 1 , further comprising means for displaying the analysis results and improvement suggestions in a dashboard accessed by a user.

Images