system

Abstract

We provide the system. [Solution] An input means for the user to input a failure event, A processing means that receives details of a failure event and performs preprocessing, A search method for searching a database for past cases and countermeasures related to failure events, A means of displaying search results to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern information systems, the obstacle events encountered by users are diverse. Each time, it takes time and effort to find an appropriate solution method, resulting in a problem of reduced productivity. Conventional methods lack means to quickly and accurately search for past cases and corresponding methods and appropriately present them to users. Therefore, there is a demand for providing an efficient system for users to quickly solve obstacle events.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides the following means: a system including an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, and a display means for presenting the search results to the user. The preprocessing means includes tokenization, stop word removal, and stemming. The search means can quickly provide appropriate past cases and countermeasures for the failure event entered by the user by using the TF-IDF method or cosine similarity.

[0006] A "user" refers to a person or other entity that operates the system and enters error events.

[0007] A "failure event" refers to a problem or malfunction that occurs in a system or device.

[0008] "Input means" refers to interfaces or devices that users use to communicate fault events to the system.

[0009] "Processing means" refers to a component that receives information entered by the user and performs the necessary pre-processing.

[0010] "Preprocessing" refers to the process of organizing and transforming data to make searching more efficient.

[0011] "Tokenization" refers to the process of dividing text data into individual words.

[0012] A "stop word" refers to a word that appears frequently but has little meaning in context (e.g., "ga", "no").

[0013] "Deletion" refers to the act of removing unnecessary elements from the target data.

[0014] "Stemming" refers to the process of extracting the root (base form) of a word.

[0015] "Search means" refers to a component that retrieves past cases and countermeasures related to the input fault event from a database.

[0016] "Database" refers to an aggregate of information in which past fault events and their countermeasure methods are accumulated.

[0017] "Display means" refers to an interface or device for visually presenting search results to the user.

[0018] "TF-IDF method" is a statistical method for measuring the importance of words and is used in a search engine for text data.

[0019] "Cosine similarity" refers to a method of measuring the similarity using the cosine value between two vectors in a vector space.

Brief Explanation of Drawings

[0020] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment.​​​​​​​​​​​​​​​​​​​​It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0021] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0022] First, the language used in the following description will be explained.

[0023] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0033] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0041] This invention relates to a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. This system provides an interface for user input of failure events and includes multiple functions for processing them.

[0042] User error event input

[0043] Users access the system via a web browser or dedicated application and enter details of the problem into a text box. This text box is intuitive for users and allows for detailed descriptions of the problem.

[0044] Transmission and preprocessing of failure events

[0045] The terminal sends the user-entered text of the incident as a JSON request to the server. The server parses the received text and performs preprocessing such as tokenization, stop word removal, and stemming. This ensures that the text data is properly organized, allowing for efficient subsequent search processing.

[0046] Database search and selection of appropriate case studies

[0047] The server searches a database containing records of past failures and their solutions based on pre-processed text. Algorithms such as TF-IDF and cosine similarity are used for the search. This allows the most similar past cases and their solutions to be identified.

[0048] Presenting results to the user

[0049] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own.

[0050] Specific example

[0051] For example, suppose a user enters a problem report stating that "the internet connection frequently drops." The terminal sends this information to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this information is presented to the user. As a result, the user can update the router firmware based on the presented information and resolve the problem.

[0052] In this way, troubleshooting becomes more efficient by quickly analyzing the problems users encounter and providing appropriate solutions.

[0053] The following describes the processing flow.

[0054] Step 1:

[0055] The user opens the system interface and enters details of the problem into the text box. For example, they might enter, "The internet connection frequently drops."

[0056] Step 2:

[0057] The device retrieves the text entered by the user and converts it into JSON-formatted request data. The format will be as follows:

[0058] json

[0059] {

[0060] "event_description": "Internet connection frequently drops"

[0061] }

[0062] Step 3:

[0063] The device sends request data in JSON format to the server.

[0064] Step 4:

[0065] The server receives the request data and extracts a description of the failure from the JSON data.

[0066] Step 5:

[0067] The server performs preprocessing on the description of the failure event. The following processes are carried out:

[0068] Tokenization: Dividing text into individual words. Examples: "Internet," "connection," "frequent," "disconnect."

[0069] Stop word removal: Remove words with little meaning. For example, "ga" is removed.

[0070] Stemming: Extracting the base form of a word. "Connection" becomes "connection," and "break" becomes "break."

[0071] Step 6:

[0072] The server searches a database containing records of past failure events and their solutions based on pre-processed text. For example, it might use the TF-IDF method to calculate severity and compare it to past cases using cosine similarity.

[0073] Step 7:

[0074] The server identifies the most similar past case and its corresponding solution from the search results, and creates the result as response data in JSON format.

[0075] json

[0076] {

[0077] "past_event": "The internet connection frequently drops due to insufficient router firmware updates",

[0078] "solution": "Update the router's firmware to the latest version"

[0079] }

[0080] Step 8:

[0081] The server sends response data to the terminal.

[0082] Step 9:

[0083] The terminal receives response data from the server, analyzes it, and displays it on the screen in a format that is easy for the user to understand. For example, it might display: "In past cases, there have been problems with frequent internet connection drops due to insufficient router firmware updates. As a solution, it is recommended to update the router firmware to the latest version."

[0084] This allows users to quickly resolve problems in their environment based on the information provided.

[0085] (Example 1)

[0086] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] It is necessary for users to quickly analyze incidents and be presented with appropriate information on past cases and solutions. However, current systems lack the ability to effectively process incident data entered by users and provide appropriate search results. In particular, accuracy and efficiency are required in data preprocessing and searching for similar cases, but solutions that meet these requirements are limited.

[0088] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0089] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, and a display means for presenting the search results to the user. This makes it possible to effectively process the failure event data entered by the user and to quickly and accurately present past cases and countermeasures.

[0090] "Input means" refers to a means by which a user enters details of a problem, and is used via a web browser or a dedicated application.

[0091] The "processing means" refers to a means for receiving details of a failure event entered by the user and performing preprocessing. Preprocessing includes tokenization, stop word removal, and stemming.

[0092] The "search means" is a method for searching a database for past events and their corresponding methods using text data preprocessed by the processing means. The TF-IDF method and cosine similarity are used for the search.

[0093] The "display means" refers to the means of presenting the results obtained from the search means to the user. It is responsible for receiving the search results in JSON format and displaying them on the user's device.

[0094] "Tokenization" is a preprocessing technique that divides text data into words and phrases.

[0095] "Stop word removal" is a preprocessing technique that removes words that are too common and unnecessary for search results in order to improve search accuracy.

[0096] Stemming is a preprocessing technique that converts words into their base form.

[0097] The "TF-IDF method" is a statistical technique used to assess the importance of text data, taking into account the frequency of terms and their inverse document frequency.

[0098] "Cosine similarity" is a method for calculating the similarity between two vectors, and is mainly used in text mining.

[0099] A "database" is an information system used to systematically store information about past incidents and how they were dealt with.

[0100] JSON format is a lightweight data exchange format for storing and transferring data.

[0101] This invention relates to a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. This system provides an interface for user input of failure events and includes multiple functions for processing them. The following describes a specific implementation of this system.

[0102] Hardware and software to be used

[0103] Hardware: Servers (high-performance computers), terminals (PCs, smartphones)

[0104] software:

[0105] Web browser (e.g., Chrome, Firefox)

[0106] Dedicated application

[0107] Natural language processing libraries (e.g., spaCy, NLTK)

[0108] Database Management System (DBMS)

[0109] Software for handling JSON format (e.g., Python's json library)

[0110] User input of failure events

[0111] Users access the system via its web interface or a dedicated application and enter details of the problem into an intuitively usable text box. For example, consider a scenario where a user enters the problem "frequent internet connection drops."

[0112] Transmission and preprocessing of failure events

[0113] The terminal sends the user-entered text of the problem as a JSON request to the server. The server parses the received text using a natural language processing library (e.g., spaCy).

[0114] As a specific example of preprocessing, the following steps are performed:

[0115] Tokenization: Dividing text into words or phrases. Example: "My internet connection frequently drops" → "Internet," "Connection," "Drops"

[0116] Stop word removal: Remove overly common words to improve search accuracy. Example: "ga", "ni" → remove

[0117] Stemming: Converting a word to its base form. Example: "kireru" → "kire"

[0118] Database search and presentation of results

[0119] The server uses the TF-IDF method and cosine similarity to search the database for past failure events and their solutions based on pre-processed text data. This identifies the most similar past case and its solution.

[0120] For example, if there was a past instance where "internet connection frequently dropped due to insufficient router firmware updates," the solution identified would be "update the router firmware to the latest version."

[0121] Displaying Results

[0122] The server returns the search results to the terminal in JSON format. The terminal displays the received information on the user's screen, showing details of past cases and specific solutions. The user can then use this information to solve the problem on their own.

[0123] Specific examples and prompt statements

[0124] Specific example: A user inputs a problem description such as "the internet connection frequently drops," and the terminal sends this information to the server. The server performs preprocessing and a database search, identifying a past case where the cause was "insufficient router firmware updates" and a solution of "update the router firmware to the latest version." This information is returned to the terminal, and specific countermeasures are displayed on the user's screen.

[0125] Example of a prompt:

[0126] Please explain how the server searches for past cases and provides solutions when a user enters "My internet connection frequently drops."

[0127] By using this system, users can obtain solutions to problems quickly and efficiently.

[0128] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0129] Step 1: User input of the failure event

[0130] The user accesses the system's web browser or dedicated application and enters details of the problem into a text box. For example, the user might write "Internet connection frequently drops." This text data is then recorded on the terminal as output.

[0131] Step 2: Sending the Incident Report

[0132] The terminal converts the user-entered error text into JSON format and sends it to the server. Specifically, it serializes the entered text data as a JSON object and sends it to the server via an HTTPS request. The input is the user's text, and the output is the JSON data sent to the server.

[0133] Step 3: Text Preprocessing

[0134] The server parses the JSON-formatted error message text received from the terminal. It receives JSON data as input and performs the following specific text preprocessing:

[0135] Tokenization: Dividing text into words or phrases. Example: "My internet connection frequently drops" → "Internet," "Connection," "Drops"

[0136] Stop word removal: Remove overly common words to improve search accuracy. Example: "ga", "ni" → remove

[0137] Stemming: Converting a word to its base form. Example: "kireru" → "kire"

[0138] The output is pre-processed text data.

[0139] Step 4: Search the database

[0140] The server searches a database containing records of past failure events and their solutions, based on pre-processed text data. The input is pre-processed text data, and the search uses methods such as TF-IDF or cosine similarity. As a specific example, a search is performed using the keyword "Internet connection lost." The output is search results data containing the most similar past cases and their solutions.

[0141] Step 5: Submit search results

[0142] The server returns the identified past cases and their corresponding solutions to the terminal in JSON format. The input is search result data, and the output is response data in JSON format. Specifically, the search results are serialized as a JSON object and sent to the terminal as an HTTP response.

[0143] Step 6: Displaying the results

[0144] The terminal parses the search results received from the server in JSON format and displays them on the user's screen. Specifically, it parses the received JSON data and displays past cases and solutions on the interface in list or detailed view formats. The input is JSON data received from the server, and the output is in a format that the user can view on the screen.

[0145] By following these steps, users can quickly and accurately find solutions to their problems.

[0146] (Application Example 1)

[0147] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0148] In modern security systems, finding quick and appropriate countermeasures for the various security breaches users encounter is extremely difficult. This problem stems particularly from the insufficient utilization of past cases and knowledge. As a result, users spend a great deal of time and effort finding appropriate countermeasures. There is a need to solve these challenges and enable users to respond quickly to security breaches.

[0149] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0150] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, a display means for presenting the search results to the user, a similarity calculation means for calculating the similarity between the input failure event and past cases, and a recommendation presentation means for presenting recommended countermeasures based on the most similar past cases. This enables the user to obtain quick and appropriate countermeasures for the input failure event.

[0151] Definition of Terms

[0152] "User input means for entering failure events" refers to an interface provided for users to input details of failure events they encounter. This interface is used for communication between the user and the system via devices such as smartphones, computers, and tablets.

[0153] "Processing means for receiving details of a failure event and performing preprocessing" refers to a function that receives information about a failure event entered by the user, analyzes it, and performs preprocessing such as tokenization, stop word removal, and stemming.

[0154] The "search method for searching a database for past cases and countermeasures related to failure events" refers to a function that searches a database containing records of past cases and their countermeasures, based on pre-processed information about failure events. Algorithms such as the TF-IDF method and cosine similarity are used for this search.

[0155] "A means of displaying search results to the user" refers to an interface that presents the results obtained through a search in an easy-to-understand manner to the user. This interface is displayed on the device's screen.

[0156] The "similarity calculation means for calculating the similarity between an input failure event and past cases" refers to a function for calculating the similarity between a failure event entered by a user and past cases in the database. This calculation uses cosine similarity or other similarity calculation algorithms.

[0157] The "recommendation suggestion method that presents recommended countermeasures based on the most similar past cases" refers to a function that presents the user with the most similar past cases and their solutions based on a calculated similarity score. This allows the user to quickly obtain appropriate countermeasures.

[0158] Modes for carrying out the invention

[0159] This invention is a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. The specific implementation of this system is described below.

[0160] System Overview

[0161] This system allows users to input incidents using smartphones or other devices, processes the information, and quickly presents relevant past cases and solutions. The main components of the system include input means, processing means, search means, display means, similarity calculation means, and recommendation suggestion means.

[0162] Hardware and software to be used

[0163] Hardware: Smartphones, computers, tablets

[0164] Software: Python, scikit-learn, web browser

[0165] Program Processing Overview

[0166] 1. The user enters the error message.

[0167] Users access a dedicated application or web interface via their smartphone or computer and enter details of the problem into a text box. This input method is designed to be intuitive for users.

[0168] 2. Receiving and pre-processing of failure events

[0169] The terminal sends the user-entered error information to the server in JSON format. The server preprocesses the received text by performing tokenization, stop word removal, stemming, etc., to properly organize the text data.

[0170] 3. Database search and similarity calculation

[0171] The server uses pre-processed text data to search a database containing records of past failure events and how they were handled. Algorithms such as the TF-IDF method and cosine similarity are used in the search to calculate the similarity between the input failure event and past cases.

[0172] 4. Presentation of search results and recommendations

[0173] The server identifies the most similar past cases from the search results and generates recommended countermeasures based on them. The terminal displays the results to the user, including the relevant past cases and how they were handled.

[0174] Specific example

[0175] For example, if a user enters a problem report stating "Unauthorized access detected, warning displayed," the terminal sends this information to the server. The server performs preprocessing and a database search, and if a record of "unauthorized access detected" is found in the database, a solution such as "immediately change your password and check your login history" is suggested. In this way, the user can quickly obtain appropriate countermeasures.

[0176] Example of a prompt

[0177] "If unauthorized access is detected and a warning is displayed, what countermeasures are effective?"

[0178] This invention enables users to quickly find appropriate countermeasures and deal with failure events.

[0179] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0180] Program processing flow

[0181] Step 1: The user enters the fault report.

[0182] Users enter details of the incident into text boxes using smartphone or computer applications or web interfaces. The entered information is converted to JSON format for use in subsequent processing.

[0183] Input: Details of the incident (text)

[0184] Output: Input data in JSON format

[0185] Action: The user enters "Unauthorized access has been detected and a warning has been displayed."

[0186] Step 2: Receiving and pre-processing of the failure event

[0187] The terminal sends the input error event to the server in JSON format. The server preprocesses the received text by performing tokenization, stop word removal, stemming, etc., to properly organize the text data.

[0188] Input: Failure event data in JSON format

[0189] Output: Preprocessed text data

[0190] Operation: The server splits the received text into words such as "malicious," "access," "detect," "warning," and "display," removes unnecessary words, and converts them into core words.

[0191] Step 3: Database search and similarity calculation

[0192] The server uses pre-processed text data to search a database containing records of past failure events and their resolution methods. Algorithms such as the TF-IDF method and cosine similarity are used for the search. The server calculates the similarity between the input failure event and past cases.

[0193] Input: Preprocessed text data

[0194] Output: List of similar past cases and countermeasures

[0195] Operation: The server searches a database of past cases, extracts relevant cases based on the keyword "unauthorized access," and performs a similarity calculation.

[0196] Step 4: Presentation of search results and recommendations

[0197] The server identifies the most similar past cases from the search results and generates recommended countermeasures based on them. The terminal then displays these results to the user.

[0198] Input: List of similar past cases and countermeasures

[0199] Output: Recommended countermeasures and their display

[0200] Action: The server generates a recommendation to "change your password immediately and check your login history" and sends it to the terminal. The terminal displays this to the user.

[0201] In this way, users can quickly obtain appropriate countermeasures.

[0202] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0203] This invention provides a system that quickly analyzes user-inputted failure events and appropriately presents past cases and response methods, further incorporating an emotion engine that recognizes the user's emotions. This system includes an interface for the user to input failure events and multiple functions for processing them.

[0204] User error event input and emotion recognition

[0205] Users access the system via a web browser or dedicated application and enter details of the problem into a text box. This text box is intuitive to use and allows users to describe the problem in detail. Furthermore, an emotion engine operates to recognize emotions from the text data entered by the user.

[0206] Transmission and preprocessing of failure events

[0207] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server. The data sent is in the following format:

[0208] json

[0209] {

[0210] "event_description": "Internet connection frequently drops",

[0211] "user_emotion": "frustration"

[0212] }

[0213] Analysis of disturbance events and emotional processing

[0214] The server receives the request data and extracts a description of the incident and the user's sentiment from the JSON data. Then, it performs preprocessing on the incident description (tokenization, stop word removal, stemming). This preprocessing organizes the text data, enabling more efficient search operations.

[0215] Database search and emotionally conscious adjustments

[0216] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. Furthermore, the search results and suggested solutions are adjusted based on sentiment data recognized by the sentiment engine. For example, if a user indicates "frustration," the server prioritizes presenting solutions and procedures that can resolve the issue more quickly.

[0217] Presenting results to the user

[0218] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own. Advice and warnings tailored to the user's feelings are also displayed.

[0219] Specific example

[0220] For example, suppose a user enters a problem report such as "My internet connection keeps dropping," and the emotion engine detects "frustration." The terminal sends this to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this will be presented to the user. Furthermore, emotion-based advice such as "If you need a quick solution, we recommend contacting manufacturer support" will also be displayed.

[0221] In this way, by quickly analyzing the problems users encounter and providing appropriate solutions, as well as offering information that takes users' feelings into consideration, troubleshooting can be carried out more efficiently, and an improvement in user satisfaction can be expected.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The user opens the system interface and enters details of the problem into the text box. For example, they might enter, "The internet connection frequently drops."

[0225] Step 2:

[0226] The device retrieves text entered by the user and uses an emotion engine to recognize the emotion from the text. In this case, the emotion engine detects "frustration."

[0227] Step 3:

[0228] The terminal converts the entered text and recognized emotions into JSON-formatted request data. The format will be as follows:

[0229] json

[0230] {

[0231] "event_description": "Internet connection frequently drops",

[0232] "user_emotion": "frustration"

[0233] }

[0234] Step 4:

[0235] The device sends request data in JSON format to the server.

[0236] Step 5:

[0237] The server receives the request data and extracts "event_description" (description of the incident) and "user_emotion" (user's emotion) from the JSON data.

[0238] Step 6:

[0239] The server performs preprocessing on "event_description". The following processes are carried out:

[0240] Tokenization: Dividing text into individual words. Examples: "Internet," "connection," "frequent," "disconnect."

[0241] Stop word removal: Remove words with little meaning. For example, "ga" is removed.

[0242] Stemming: Extracting the base form of a word. "Connection" becomes "connection," and "break" becomes "break."

[0243] Step 7:

[0244] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses the TF-IDF method and cosine similarity.

[0245] Step 8:

[0246] The server identifies the most similar past cases and their corresponding solutions from the search results, and creates a response data in JSON format. Furthermore, based on the emotions recognized by the emotion engine, it adds advice for quick action if the user is irritated.

[0247] json

[0248] {

[0249] "past_event": "The internet connection frequently drops due to insufficient router firmware updates",

[0250] "solution": "Update the router's firmware to the latest version",

[0251] "emotion_based_advice": "If you need a quick solution, we recommend contacting manufacturer support."

[0252] }

[0253] Step 9:

[0254] The server sends response data to the terminal.

[0255] Step 10:

[0256] The terminal receives response data from the server, analyzes it, and displays it on the screen in a format that is easy for the user to understand. For example, it might display: "In past cases, there have been problems with frequent internet connection drops due to insufficient router firmware updates. As a solution, it is recommended to update the router firmware to the latest version. If a quick solution is needed, it is recommended to contact manufacturer support."

[0257] This allows users to quickly resolve problems in their environment based on the information presented and emotionally-driven advice.

[0258] (Example 2)

[0259] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0260] Conventional failure event analysis systems not only analyze the details of failure events entered by users, but also fail to adequately provide solutions that take into account the user's feelings. As a result, this can increase user dissatisfaction. Therefore, a system is needed that not only analyzes the failure events entered by users but also provides information that responds to the user's feelings, thereby improving user satisfaction.

[0261] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0262] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving the details and emotions of the input failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event and adjusting the search results based on emotions, and a display means for presenting the adjusted search results to the user. This enables the user to analyze the failure event and provide information that takes emotions into consideration.

[0263] "Input means" refers to an interface for users to input details of a failure event into the system, and includes web browsers and dedicated applications.

[0264] The "processing means" is a component that receives the details of the input failure event and the user's sentiment data, and has the function of organizing and analyzing the text data, performing tokenization, stop word removal, and stemming.

[0265] The "search method" involves searching a database based on processed text data to identify past failure cases and their solutions, and adjusting the search results based on the user's sentiment. It utilizes methods such as TF-IDF and cosine similarity.

[0266] "Display means" refers to an interface for presenting search results and adjusted responses to the user, and includes web screens and application displays.

[0267] "Emotions" refer to the psychological state expressed by the user in relation to the incidents they have entered, and are part of the data that the system analyzes and considers.

[0268] "Preprocessing" refers to a series of processes to organize input data into an analyzable format, specifically including tokenization, stop word removal, and stemming.

[0269] A "database" is a place where information is collected, recording past incidents and countermeasures for failures, and is accessed through search methods.

[0270] "Tokenization" is the process of dividing text data into words and phrases, and it is performed in the initial stages of text analysis.

[0271] "Stop word removal" is the process of removing words that are considered to be of low importance during searching or analysis (for example, "no" or "toita").

[0272] Stemming is the process of extracting the root of a word, and it is performed to combine words with different forms into a single word.

[0273] The "TF-IDF method" is a numerical method for calculating the importance of words within a document and evaluating their relevance.

[0274] "Cosine similarity" is a method for calculating the similarity between documents based on a vector space, and is used to improve the accuracy of search results.

[0275] This invention provides a system that quickly analyzes user-inputted failure events, appropriately presents past cases and solutions, and further incorporates an emotion engine that recognizes the user's emotions. This system is implemented using the following hardware and software.

[0276] Hardware and software used

[0277] The system includes terminals (such as PCs and smartphones) for user access and servers for processing.

[0278] Input Interface: Users access the system via a web browser or dedicated application and input details of the failure.

[0279] Emotional Engine: The Emotion Recognition API (EmotionAPI) is used to recognize emotions from the text data input by the user.

[0280] Preprocessing Module: The server uses the natural language processing library (nltk) to perform tokenization, stop word removal, and stemming on the received text data.

[0281] Database: A relational database (MySQL (registered trademark)) is used to store the response and data of the accumulated failure events.

[0282] Search Algorithm: When evaluating the relevance of text data and performing searches, the TF-IDF method or cosine similarity is used.

[0283] Display Interface: The front-end framework (React.js) is used to present the search results and corresponding methods to the user.

[0284] Specific Operations of the System

[0285] 1. User Input of Failure Events and Emotion Recognition

[0286] The user accesses the system using a web browser or dedicated application and enters the details of the failure event in a text box.

[0287] The emotional engine recognizes emotions from the text data input by the user and generates emotion data (e.g., "frustration").

[0288] 2. Transmission and Preprocessing of Failure Events

[0289] The terminal converts the text input by the user and the emotion data recognized by the emotional engine into JSON-formatted request data and sends it to the server.

[0290] The server uses "Express.js" to parse the JSON data and extract descriptions of the failure events and sentiment data.

[0291] The server uses the Natural Language Processing Library (NLTK) to perform tokenization, stop word removal, and stemming of text data.

[0292] 3. Database search and adjustment based on sentiment.

[0293] The server searches the MySQL database based on the pre-processed text data.

[0294] The TF-IDF method and cosine similarity are used for the search.

[0295] The server also adjusts search results based on sentiment data, prioritizing responses that correspond to the emotions expressed by the user.

[0296] 4. Presenting results to the user

[0297] The server sends response data to the terminal, including relevant past cases, how they were handled, and emotionally sensitive advice.

[0298] The device uses "React.js" to display this information on the user's screen.

[0299] Specific examples and prompt statements

[0300] For example, assume that a user inputs a trouble event of "frequent disconnection of the Internet connection" and the emotion engine detects "frustration". The terminal sends this to the server, and the server analyzes the JSON data. If there is a case in the database where "a similar trouble occurred due to insufficient firmware update of the router in the past" and the corresponding method "update the firmware of the router to the latest version" is recorded, this will be presented to the user. Furthermore, emotion-based advice such as "If a quick solution is needed, it is recommended to contact the manufacturer support" will also be displayed.

[0301] The flow of the specific process in Example 2 will be described using FIG. 13.

[0302] Step 1:

[0303] The user inputs a trouble event.

[0304] Specific operation

[0305] The user accesses the system using a web browser or a dedicated application and enters the details of the trouble event in a text box. For example, enter "frequent disconnection of the Internet connection". This input text becomes the input data for the next process.

[0306] Input and output

[0307] Input: Details of the trouble event (manually input by the user)

[0308] Output: Text data (description of the trouble event)

[0309] Step 2:

[0310] Recognition of emotion

[0311] Specific operation

[0312] The server receives the text data entered by the user and sends it to the Emotion API. The Emotion API extracts emotions such as "frustration" from the text data. This emotion data is then passed on to the next process.

[0313] Input and Output

[0314] Input: Detailed text of the failure event

[0315] Output: Sentiment data (e.g., "frustration")

[0316] Step 3:

[0317] Sending a failure event

[0318] Specific actions

[0319] The device converts the text data entered by the user and the emotion data returned by the emotion recognition API into JSON-formatted request data. Specifically, it generates JSON data like the following:

[0320] json

[0321] {

[0322] "event_description": "Internet connection frequently drops",

[0323] "user_emotion": "frustration"

[0324] }

[0325] Send this JSON data to the server.

[0326] Input and Output

[0327] Input: Detailed text and sentiment data of the incident.

[0328] Output: JSON data

[0329] Step 4:

[0330] JSON data parsing and preprocessing

[0331] Specific actions

[0332] The server parses the received JSON data and extracts the error description text and user sentiment data. This process uses "Express.js". Next, the error description text undergoes tokenization, stop word removal, and stemming. The "nltk" library is used to organize the text data into a parseable format.

[0333] Input and Output

[0334] Input: JSON data

[0335] Output: Preprocessed text data

[0336] Step 5:

[0337] Database Search

[0338] Specific actions

[0339] The server searches the MySQL database based on pre-processed text data. The search uses methods such as TF-IDF and cosine similarity to identify past cases related to the failure event and their corresponding solutions. If necessary, the search results are refined to take user sentiment data into consideration.

[0340] Input and Output

[0341] Input: Preprocessed text data and sentiment data

[0342] Output: Search results (past cases and countermeasures)

[0343] Step 6:

[0344] Displaying search results

[0345] Specific actions

[0346] The server sends search results to the device, which then displays them on the user's screen. Specifically, the search results, which include suggested actions and advice tailored to the user's emotions, are displayed using a front-end framework (React.js). For example, a past case "The problem was caused by insufficient router firmware updates" and the suggested solution "Update the router firmware to the latest version" might be displayed.

[0347] Input and Output

[0348] Input: Search Results

[0349] Output: Display of results to the user

[0350] (Application Example 2)

[0351] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0352] In recent years, with the proliferation of food delivery services, users are increasingly encountering various problems related to delivery. For example, there are cases of delayed orders, cold food, and misdeliveries. While there is a need to respond quickly and appropriately to these problems, conventional systems have struggled to provide solutions that take user feelings into consideration. Furthermore, there is a lack of systems that can effectively analyze the details of problems entered by users and suggest appropriate solutions based on past cases. This leads to increased user stress and dissatisfaction with the service.

[0353] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, a display means for presenting the search results to the user, an emotion recognition means for recognizing emotions, and an adjustment means for adjusting the presentation method of search results and countermeasures based on emotion data. This enables rapid analysis of delivery-related troubles entered by the user, the presentation of appropriate solutions based on past cases, and the provision of information that takes the user's emotions into consideration.

[0354] A "user" is the entity that accesses the system and inputs error reports.

[0355] A "failure event" refers to a problem or trouble that occurs while using a system or service.

[0356] An "input mechanism" is a function that provides an interface for users to input fault events into the system.

[0357] The "processing means" refers to a function that receives details of a failure event entered by the user and performs preprocessing on the data.

[0358] "Search method" refers to a function that searches a database for past cases and countermeasures related to failure events, based on pre-processed data.

[0359] "Display means" refers to functions for presenting search results to the user.

[0360] "Emotion recognition means" refers to a function that recognizes emotions from text data entered by the user.

[0361] "Adjustment mechanism" refers to a function that adjusts the way search results and response methods are presented based on sentiment data.

[0362] "Past incidents" refer to data that records past incidents and how they were handled.

[0363] "Response method" refers to the procedures and methods for dealing with a failure or malfunction.

[0364] This invention is a system that quickly analyzes user-inputted problems and appropriately presents past cases and solutions, further incorporating an emotion engine that recognizes the user's emotions. This invention is particularly applicable to troubleshooting in food delivery services.

[0365] User error event input and emotion recognition

[0366] Users access the system via a smartphone application and enter details of delivery problems into a text box. This text box is intuitive for users to use and allows for detailed descriptions of problems. Furthermore, an emotion engine operates to recognize emotions from the text data entered by the user.

[0367] Transmission and preprocessing of failure events

[0368] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server. For example, the following data is sent:

[0369] json

[0370] {

[0371] "event_description": "The delivery was late, and the order got cold."

[0372] "user_emotion": "frustration"

[0373] }

[0374] Analysis of disturbance events and emotional processing

[0375] The server receives the request data and extracts a description of the incident and the user's sentiment from the JSON data. Then, it performs preprocessing on the incident description (tokenization, stop word removal, stemming). This preprocessing organizes the text data, enabling more efficient search operations.

[0376] Database search and emotionally conscious adjustments

[0377] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. Furthermore, the search results and suggested solutions are adjusted based on sentiment data recognized by the sentiment engine. For example, if a user indicates "frustration," the server prioritizes presenting solutions and procedures that can resolve the issue more quickly.

[0378] Presenting results to the user

[0379] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own. Advice and warnings tailored to the user's feelings are also displayed.

[0380] Specific example

[0381] For example, suppose a user enters a problem report stating, "The delivery was late and the order got cold," and the emotion engine detects "frustration." The terminal sends this to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past, where a re-cooking request was made and the order was delivered directly, and the suggested solution is "request re-cooking," this is presented to the user. Furthermore, emotion-based advice such as "We recommend issuing an apology coupon" is also displayed. Examples of prompt messages include:

[0382] A user posted the following problem: "The delivery was late and my order got cold 😡"

[0383] Based on this information, search for past cases and solutions, and present solutions and emotion-based advice in the following output format.

[0384] Problem: {Question content}

[0385] Solution:

[0386] 1. {Solution 1}

[0387] 2. {Solution 2}

[0388] Advice: {Emotion-based advice}

[0389] This makes it possible to quickly analyze delivery-related problems that users encounter, provide appropriate solutions, and offer information that is sensitive to the user's feelings.

[0390] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0391] Step 1:

[0392] The user enters details of a delivery issue into a text box in the smartphone application. This input includes problems such as delivery delays, misdeliveries, or cold food. When the user enters the problem into the text box and clicks the submit button, the input data is sent to the device. The input data is a text-based description of the problem.

[0393] Step 2:

[0394] The device receives text data entered by the user and uses an emotion engine to recognize the user's emotions. This process estimates emotions such as "frustration" from emojis like "😡" and the content of the text. The recognition results are prepared in JSON format along with the emotion data. The input is the user's text data, and the output is JSON data including emotions.

[0395] Step 3:

[0396] The terminal sends the prepared JSON data to the server. The data sent will be in the following format:

[0397] json

[0398] {

[0399] "event_description": "The delivery was late, and the order got cold."

[0400] "user_emotion": "frustration"

[0401] }

[0402] The input is JSON data containing emotions, and the output is the status indicating whether the transmission to the server was successful.

[0403] Step 4:

[0404] The server extracts a description of the incident and user sentiment data from the received JSON data. The extracted data is used in the next analysis step. The input is the received JSON data, and the output is a text-formatted problem description and sentiment data.

[0405] Step 5:

[0406] The server preprocesses the description of the failure event. This preprocessing includes tokenization (separating the text into individual words), stop word removal (removing frequently occurring, meaningless words), and stemming (converting words back to their base forms). The input is the problem description text, and the output is the preprocessed text data.

[0407] Step 6:

[0408] The server searches a database containing records of past failure events and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. The input is pre-processed text data, and the output is a list of similar past cases and their solutions.

[0409] Step 7:

[0410] The server adjusts the way search results and suggested solutions are presented based on sentiment data. For example, if a user indicates "frustration," it prioritizes providing quick solutions. This adjustment uses generative AI models and prompts. The input is a list of similar past cases and solutions, along with sentiment data, and the output is a list of adjusted solutions.

[0411] Step 8:

[0412] The server sends response data to the terminal, including tailored solutions. This data includes specific steps and sentiment-based advice. The input is a list of tailored solutions, and the output is the status of the transmission to the terminal.

[0413] Step 9:

[0414] The terminal displays response data received from the server on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve problems independently. Advice and warnings tailored to the user's emotional state are also displayed. Input is the response data, and output is the display to the user.

[0415] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0416] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0417] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0418] [Second Embodiment]

[0419] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0420] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0421] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0422] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0423] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0424] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0425] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0426] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0427] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0428] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0429] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0430] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0431] This invention relates to a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. This system provides an interface for user input of failure events and includes multiple functions for processing them.

[0432] User error event input

[0433] Users access the system via a web browser or dedicated application and enter details of the problem into a text box. This text box is intuitive for users and allows for detailed descriptions of the problem.

[0434] Transmission and preprocessing of failure events

[0435] The terminal sends the user-entered text of the incident as a JSON request to the server. The server parses the received text and performs preprocessing such as tokenization, stop word removal, and stemming. This ensures that the text data is properly organized, allowing for efficient subsequent search processing.

[0436] Database search and selection of appropriate case studies

[0437] The server searches a database containing records of past failures and their solutions based on pre-processed text. Algorithms such as TF-IDF and cosine similarity are used for the search. This allows the most similar past cases and their solutions to be identified.

[0438] Presenting results to the user

[0439] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own.

[0440] Specific example

[0441] For example, suppose a user enters a problem report stating that "the internet connection frequently drops." The terminal sends this information to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this information is presented to the user. As a result, the user can update the router firmware based on the presented information and resolve the problem.

[0442] In this way, troubleshooting becomes more efficient by quickly analyzing the problems users encounter and providing appropriate solutions.

[0443] The following describes the processing flow.

[0444] Step 1:

[0445] The user opens the system interface and enters details of the problem into the text box. For example, they might enter, "The internet connection frequently drops."

[0446] Step 2:

[0447] The device retrieves the text entered by the user and converts it into JSON-formatted request data. The format will be as follows:

[0448] json

[0449] {

[0450] "event_description": "Internet connection frequently drops"

[0451] }

[0452] Step 3:

[0453] The device sends request data in JSON format to the server.

[0454] Step 4:

[0455] The server receives the request data and extracts a description of the failure from the JSON data.

[0456] Step 5:

[0457] The server performs preprocessing on the description of the failure event. The following processes are carried out:

[0458] Tokenization: Dividing text into individual words. Examples: "Internet," "connection," "frequent," "disconnect."

[0459] Stop word removal: Remove words with little meaning. For example, "ga" is removed.

[0460] Stemming: Extracting the base form of a word. "Connection" becomes "connection," and "break" becomes "break."

[0461] Step 6:

[0462] The server searches a database containing records of past failure events and their solutions based on pre-processed text. For example, it might use the TF-IDF method to calculate severity and compare it to past cases using cosine similarity.

[0463] Step 7:

[0464] The server identifies the most similar past case and its corresponding solution from the search results, and creates the result as response data in JSON format.

[0465] json

[0466] {

[0467] "past_event": "The internet connection frequently drops due to insufficient router firmware updates",

[0468] "solution": "Update the router's firmware to the latest version"

[0469] }

[0470] Step 8:

[0471] The server sends response data to the terminal.

[0472] Step 9:

[0473] The terminal receives response data from the server, analyzes it, and displays it on the screen in a format that is easy for the user to understand. For example, it might display: "In past cases, there have been problems with frequent internet connection drops due to insufficient router firmware updates. As a solution, it is recommended to update the router firmware to the latest version."

[0474] This allows users to quickly resolve problems in their environment based on the information provided.

[0475] (Example 1)

[0476] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0477] It is necessary for users to quickly analyze incidents and be presented with appropriate information on past cases and solutions. However, current systems lack the ability to effectively process incident data entered by users and provide appropriate search results. In particular, accuracy and efficiency are required in data preprocessing and searching for similar cases, but solutions that meet these requirements are limited.

[0478] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0479] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, and a display means for presenting the search results to the user. This makes it possible to effectively process the failure event data entered by the user and to quickly and accurately present past cases and countermeasures.

[0480] "Input means" refers to a means by which a user enters details of a problem, and is used via a web browser or a dedicated application.

[0481] The "processing means" refers to a means for receiving details of a failure event entered by the user and performing preprocessing. Preprocessing includes tokenization, stop word removal, and stemming.

[0482] The "search means" is a method for searching a database for past events and their corresponding methods using text data preprocessed by the processing means. The TF-IDF method and cosine similarity are used for the search.

[0483] The "display means" refers to the means of presenting the results obtained from the search means to the user. It is responsible for receiving the search results in JSON format and displaying them on the user's device.

[0484] "Tokenization" is a preprocessing technique that divides text data into words and phrases.

[0485] "Stop word removal" is a preprocessing technique that removes words that are too common and unnecessary for search results in order to improve search accuracy.

[0486] Stemming is a preprocessing technique that converts words into their base form.

[0487] The "TF-IDF method" is a statistical technique used to assess the importance of text data, taking into account the frequency of terms and their inverse document frequency.

[0488] "Cosine similarity" is a method for calculating the similarity between two vectors, and is mainly used in text mining.

[0489] A "database" is an information system used to systematically store information about past incidents and how they were dealt with.

[0490] JSON format is a lightweight data exchange format for storing and transferring data.

[0491] This invention relates to a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. This system provides an interface for user input of failure events and includes multiple functions for processing them. The following describes a specific implementation of this system.

[0492] Hardware and software to be used

[0493] Hardware: Servers (high-performance computers), terminals (PCs, smartphones)

[0494] software:

[0495] Web browser (e.g., Chrome, Firefox)

[0496] Dedicated application

[0497] Natural language processing libraries (e.g., spaCy, NLTK)

[0498] Database Management System (DBMS)

[0499] Software for handling JSON format (e.g., Python's json library)

[0500] User input of failure events

[0501] Users access the system via its web interface or a dedicated application and enter details of the problem into an intuitively usable text box. For example, consider a scenario where a user enters the problem "frequent internet connection drops."

[0502] Transmission and preprocessing of failure events

[0503] The terminal sends the user-entered text of the problem as a JSON request to the server. The server parses the received text using a natural language processing library (e.g., spaCy).

[0504] As a specific example of preprocessing, the following steps are performed:

[0505] Tokenization: Dividing text into words or phrases. Example: "My internet connection frequently drops" → "Internet," "Connection," "Drops"

[0506] Stop word removal: Remove overly common words to improve search accuracy. Example: "ga", "ni" → remove

[0507] Stemming: Converting a word to its base form. Example: "kireru" → "kire"

[0508] Database search and presentation of results

[0509] The server uses the TF-IDF method and cosine similarity to search the database for past failure events and their solutions based on pre-processed text data. This identifies the most similar past case and its solution.

[0510] For example, if there was a past instance where "internet connection frequently dropped due to insufficient router firmware updates," the solution identified would be "update the router firmware to the latest version."

[0511] Displaying Results

[0512] The server returns the search results to the terminal in JSON format. The terminal displays the received information on the user's screen, showing details of past cases and specific solutions. The user can then use this information to solve the problem on their own.

[0513] Specific examples and prompt statements

[0514] Specific example: A user inputs a problem description such as "the internet connection frequently drops," and the terminal sends this information to the server. The server performs preprocessing and a database search, identifying a past case where the cause was "insufficient router firmware updates" and a solution of "update the router firmware to the latest version." This information is returned to the terminal, and specific countermeasures are displayed on the user's screen.

[0515] Example of a prompt:

[0516] Please explain how the server searches for past cases and provides solutions when a user enters "My internet connection frequently drops."

[0517] By using this system, users can obtain solutions to problems quickly and efficiently.

[0518] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0519] Step 1: User input of the failure event

[0520] The user accesses the system's web browser or dedicated application and enters details of the problem into a text box. For example, the user might write "Internet connection frequently drops." This text data is then recorded on the terminal as output.

[0521] Step 2: Sending the Incident Report

[0522] The terminal converts the user-entered error text into JSON format and sends it to the server. Specifically, it serializes the entered text data as a JSON object and sends it to the server via an HTTPS request. The input is the user's text, and the output is the JSON data sent to the server.

[0523] Step 3: Text Preprocessing

[0524] The server parses the JSON-formatted error message text received from the terminal. It receives JSON data as input and performs the following specific text preprocessing:

[0525] Tokenization: Dividing text into words or phrases. Example: "My internet connection frequently drops" → "Internet," "Connection," "Drops"

[0526] Stop word removal: Remove overly common words to improve search accuracy. Example: "ga", "ni" → remove

[0527] Stemming: Converting a word to its base form. Example: "kireru" → "kire"

[0528] The output is pre-processed text data.

[0529] Step 4: Search the database

[0530] The server searches a database containing records of past failure events and their solutions, based on pre-processed text data. The input is pre-processed text data, and the search uses methods such as TF-IDF or cosine similarity. As a specific example, a search is performed using the keyword "Internet connection lost." The output is search results data containing the most similar past cases and their solutions.

[0531] Step 5: Submit search results

[0532] The server returns the identified past cases and their corresponding solutions to the terminal in JSON format. The input is search result data, and the output is response data in JSON format. Specifically, the search results are serialized as a JSON object and sent to the terminal as an HTTP response.

[0533] Step 6: Displaying the results

[0534] The terminal parses the search results received from the server in JSON format and displays them on the user's screen. Specifically, it parses the received JSON data and displays past cases and solutions on the interface in list or detailed view formats. The input is JSON data received from the server, and the output is in a format that the user can view on the screen.

[0535] By following these steps, users can quickly and accurately find solutions to their problems.

[0536] (Application Example 1)

[0537] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0538] In modern security systems, finding quick and appropriate countermeasures for the various security breaches users encounter is extremely difficult. This problem stems particularly from the insufficient utilization of past cases and knowledge. As a result, users spend a great deal of time and effort finding appropriate countermeasures. There is a need to solve these challenges and enable users to respond quickly to security breaches.

[0539] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0540] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, a display means for presenting the search results to the user, a similarity calculation means for calculating the similarity between the input failure event and past cases, and a recommendation presentation means for presenting recommended countermeasures based on the most similar past cases. This enables the user to obtain quick and appropriate countermeasures for the input failure event.

[0541] Definition of Terms

[0542] "User input means for entering failure events" refers to an interface provided for users to input details of failure events they encounter. This interface is used for communication between the user and the system via devices such as smartphones, computers, and tablets.

[0543] "Processing means for receiving details of a failure event and performing preprocessing" refers to a function that receives information about a failure event entered by the user, analyzes it, and performs preprocessing such as tokenization, stop word removal, and stemming.

[0544] The "search method for searching a database for past cases and countermeasures related to failure events" refers to a function that searches a database containing records of past cases and their countermeasures, based on pre-processed information about failure events. Algorithms such as the TF-IDF method and cosine similarity are used for this search.

[0545] "A means of displaying search results to the user" refers to an interface that presents the results obtained through a search in an easy-to-understand manner to the user. This interface is displayed on the device's screen.

[0546] The "similarity calculation means for calculating the similarity between an input failure event and past cases" refers to a function for calculating the similarity between a failure event entered by a user and past cases in the database. This calculation uses cosine similarity or other similarity calculation algorithms.

[0547] The "recommendation suggestion method that presents recommended countermeasures based on the most similar past cases" refers to a function that presents the user with the most similar past cases and their solutions based on a calculated similarity score. This allows the user to quickly obtain appropriate countermeasures.

[0548] Modes for carrying out the invention

[0549] This invention is a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. The specific implementation of this system is described below.

[0550] System Overview

[0551] This system allows users to input incidents using smartphones or other devices, processes the information, and quickly presents relevant past cases and solutions. The main components of the system include input means, processing means, search means, display means, similarity calculation means, and recommendation suggestion means.

[0552] Hardware and software to be used

[0553] Hardware: Smartphones, computers, tablets

[0554] Software: Python, scikit-learn, web browser

[0555] Program Processing Overview

[0556] 1. The user enters the error message.

[0557] Users access a dedicated application or web interface via their smartphone or computer and enter details of the problem into a text box. This input method is designed to be intuitive for users.

[0558] 2. Receiving and pre-processing of failure events

[0559] The terminal sends the user-entered error information to the server in JSON format. The server preprocesses the received text by performing tokenization, stop word removal, stemming, etc., to properly organize the text data.

[0560] 3. Database search and similarity calculation

[0561] The server uses pre-processed text data to search a database containing records of past failure events and how they were handled. Algorithms such as the TF-IDF method and cosine similarity are used in the search to calculate the similarity between the input failure event and past cases.

[0562] 4. Presentation of search results and recommendations

[0563] The server identifies the most similar past cases from the search results and generates recommended countermeasures based on them. The terminal displays the results to the user, including the relevant past cases and how they were handled.

[0564] Specific example

[0565] For example, if a user enters a problem report stating "Unauthorized access detected, warning displayed," the terminal sends this information to the server. The server performs preprocessing and a database search, and if a record of "unauthorized access detected" is found in the database, a solution such as "immediately change your password and check your login history" is suggested. In this way, the user can quickly obtain appropriate countermeasures.

[0566] Example of a prompt

[0567] "If unauthorized access is detected and a warning is displayed, what countermeasures are effective?"

[0568] This invention enables users to quickly find appropriate countermeasures and deal with failure events.

[0569] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0570] Program processing flow

[0571] Step 1: The user enters the fault report.

[0572] Users enter details of the incident into text boxes using smartphone or computer applications or web interfaces. The entered information is converted to JSON format for use in subsequent processing.

[0573] Input: Details of the incident (text)

[0574] Output: Input data in JSON format

[0575] Action: The user enters "Unauthorized access has been detected and a warning has been displayed."

[0576] Step 2: Receiving and pre-processing of the failure event

[0577] The terminal sends the input error event to the server in JSON format. The server preprocesses the received text by performing tokenization, stop word removal, stemming, etc., to properly organize the text data.

[0578] Input: Failure event data in JSON format

[0579] Output: Preprocessed text data

[0580] Operation: The server splits the received text into words such as "malicious," "access," "detect," "warning," and "display," removes unnecessary words, and converts them into core words.

[0581] Step 3: Database search and similarity calculation

[0582] The server uses pre-processed text data to search a database containing records of past failure events and their resolution methods. Algorithms such as the TF-IDF method and cosine similarity are used for the search. The server calculates the similarity between the input failure event and past cases.

[0583] Input: Preprocessed text data

[0584] Output: List of similar past cases and countermeasures

[0585] Operation: The server searches a database of past cases, extracts relevant cases based on the keyword "unauthorized access," and performs a similarity calculation.

[0586] Step 4: Presentation of search results and recommendations

[0587] The server identifies the most similar past cases from the search results and generates recommended countermeasures based on them. The terminal then displays these results to the user.

[0588] Input: List of similar past cases and countermeasures

[0589] Output: Recommended countermeasures and their display

[0590] Action: The server generates a recommendation to "change your password immediately and check your login history" and sends it to the terminal. The terminal displays this to the user.

[0591] In this way, users can quickly obtain appropriate countermeasures.

[0592] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0593] This invention provides a system that quickly analyzes user-inputted failure events and appropriately presents past cases and response methods, further incorporating an emotion engine that recognizes the user's emotions. This system includes an interface for the user to input failure events and multiple functions for processing them.

[0594] User error event input and emotion recognition

[0595] Users access the system via a web browser or dedicated application and enter details of the problem into a text box. This text box is intuitive to use and allows users to describe the problem in detail. Furthermore, an emotion engine operates to recognize emotions from the text data entered by the user.

[0596] Transmission and preprocessing of failure events

[0597] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server. The data sent is in the following format:

[0598] json

[0599] {

[0600] "event_description": "Internet connection frequently drops",

[0601] "user_emotion": "frustration"

[0602] }

[0603] Analysis of disturbance events and emotional processing

[0604] The server receives the request data and extracts a description of the incident and the user's sentiment from the JSON data. Then, it performs preprocessing on the incident description (tokenization, stop word removal, stemming). This preprocessing organizes the text data, enabling more efficient search operations.

[0605] Database search and emotionally conscious adjustments

[0606] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. Furthermore, the search results and suggested solutions are adjusted based on sentiment data recognized by the sentiment engine. For example, if a user indicates "frustration," the server prioritizes presenting solutions and procedures that can resolve the issue more quickly.

[0607] Presenting results to the user

[0608] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own. Advice and warnings tailored to the user's feelings are also displayed.

[0609] Specific example

[0610] For example, suppose a user enters a problem report such as "My internet connection keeps dropping," and the emotion engine detects "frustration." The terminal sends this to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this will be presented to the user. Furthermore, emotion-based advice such as "If you need a quick solution, we recommend contacting manufacturer support" will also be displayed.

[0611] In this way, by quickly analyzing the problems users encounter and providing appropriate solutions, as well as offering information that takes users' feelings into consideration, troubleshooting can be carried out more efficiently, and an improvement in user satisfaction can be expected.

[0612] The following describes the processing flow.

[0613] Step 1:

[0614] The user opens the system interface and enters details of the problem into the text box. For example, they might enter, "The internet connection frequently drops."

[0615] Step 2:

[0616] The device retrieves text entered by the user and uses an emotion engine to recognize the emotion from the text. In this case, the emotion engine detects "frustration."

[0617] Step 3:

[0618] The terminal converts the entered text and recognized emotions into JSON-formatted request data. The format will be as follows:

[0619] json

[0620] {

[0621] "event_description": "Internet connection frequently drops",

[0622] "user_emotion": "frustration"

[0623] }

[0624] Step 4:

[0625] The device sends request data in JSON format to the server.

[0626] Step 5:

[0627] The server receives the request data and extracts "event_description" (description of the incident) and "user_emotion" (user's emotion) from the JSON data.

[0628] Step 6:

[0629] The server performs preprocessing on "event_description". The following processes are carried out:

[0630] Tokenization: Dividing text into individual words. Examples: "Internet," "connection," "frequent," "disconnect."

[0631] Stop word removal: Remove words with little meaning. For example, "ga" is removed.

[0632] Stemming: Extracting the base form of a word. "Connection" becomes "connection," and "break" becomes "break."

[0633] Step 7:

[0634] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses the TF-IDF method and cosine similarity.

[0635] Step 8:

[0636] The server identifies the most similar past cases and their corresponding solutions from the search results, and creates a response data in JSON format. Furthermore, based on the emotions recognized by the emotion engine, it adds advice for quick action if the user is irritated.

[0637] json

[0638] {

[0639] "past_event": "The internet connection frequently drops due to insufficient router firmware updates",

[0640] "solution": "Update the router's firmware to the latest version",

[0641] "emotion_based_advice": "If you need a quick solution, we recommend contacting manufacturer support."

[0642] }

[0643] Step 9:

[0644] The server sends response data to the terminal.

[0645] Step 10:

[0646] The terminal receives response data from the server, analyzes it, and displays it on the screen in a format that is easy for the user to understand. For example, it might display: "In past cases, there have been problems with frequent internet connection drops due to insufficient router firmware updates. As a solution, it is recommended to update the router firmware to the latest version. If a quick solution is needed, it is recommended to contact manufacturer support."

[0647] This allows users to quickly resolve problems in their environment based on the information presented and emotionally-driven advice.

[0648] (Example 2)

[0649] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0650] Conventional failure event analysis systems not only analyze the details of failure events entered by users, but also fail to adequately provide solutions that take into account the user's feelings. As a result, this can increase user dissatisfaction. Therefore, a system is needed that not only analyzes the failure events entered by users but also provides information that responds to the user's feelings, thereby improving user satisfaction.

[0651] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0652] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving the details and emotions of the input failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event and adjusting the search results based on emotions, and a display means for presenting the adjusted search results to the user. This enables the user to analyze the failure event and provide information that takes emotions into consideration.

[0653] "Input means" refers to an interface for users to input details of a failure event into the system, and includes web browsers and dedicated applications.

[0654] The "processing means" is a component that receives the details of the input failure event and the user's sentiment data, and has the function of organizing and analyzing the text data, performing tokenization, stop word removal, and stemming.

[0655] The "search method" involves searching a database based on processed text data to identify past failure cases and their solutions, and adjusting the search results based on the user's sentiment. It utilizes methods such as TF-IDF and cosine similarity.

[0656] "Display means" refers to an interface for presenting search results and adjusted responses to the user, and includes web screens and application displays.

[0657] "Emotions" refer to the psychological state expressed by the user in relation to the incidents they have entered, and are part of the data that the system analyzes and considers.

[0658] "Preprocessing" refers to a series of processes to organize input data into an analyzable format, specifically including tokenization, stop word removal, and stemming.

[0659] A "database" is a place where information is collected, recording past incidents and countermeasures for failures, and is accessed through search methods.

[0660] "Tokenization" is the process of dividing text data into words and phrases, and it is performed in the initial stages of text analysis.

[0661] "Stop word removal" is the process of removing words that are considered to be of low importance during searching or analysis (for example, "no" or "toita").

[0662] Stemming is the process of extracting the root of a word, and it is performed to combine words with different forms into a single word.

[0663] The "TF-IDF method" is a numerical method for calculating the importance of words within a document and evaluating their relevance.

[0664] "Cosine similarity" is a method for calculating the similarity between documents based on a vector space, and is used to improve the accuracy of search results.

[0665] This invention provides a system that quickly analyzes user-inputted failure events, appropriately presents past cases and solutions, and further incorporates an emotion engine that recognizes the user's emotions. This system is implemented using the following hardware and software.

[0666] Hardware and software used

[0667] The system includes terminals (such as PCs and smartphones) for user access and servers for processing.

[0668] Input Interface: Users access the system via a web browser or dedicated application and input details of the failure.

[0669] Emotion Engine: Uses the Emotion Recognition API (EmotionAPI) to recognize emotions from text data entered by the user.

[0670] Preprocessing module: The server uses the Natural Language Processing Library (NLTK) to perform tokenization, stop word removal, and stemming on the received text data.

[0671] Database: A relational database (MySQL) is used to store response and accumulated failure event data.

[0672] Search algorithm: When evaluating the relevance of text data and performing searches, methods such as TF-IDF and cosine similarity are used.

[0673] Display Interface: A front-end framework (React.js) is used to present search results and solutions to the user.

[0674] Specific operation of the system

[0675] 1. User error event input and emotion recognition

[0676] Users access the system using a web browser or a dedicated application and enter details of the problem into a text box.

[0677] The emotion engine recognizes emotions from text data entered by the user and generates emotion data (for example, "frustration").

[0678] 2. Transmission of failure events and preprocessing

[0679] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server.

[0680] The server uses "Express.js" to parse the JSON data and extract descriptions of the failure events and sentiment data.

[0681] The server uses the Natural Language Processing Library (NLTK) to perform tokenization, stop word removal, and stemming of text data.

[0682] 3. Database search and adjustment based on sentiment.

[0683] The server searches the MySQL database based on the pre-processed text data.

[0684] The TF-IDF method and cosine similarity are used for the search.

[0685] The server also adjusts search results based on sentiment data, prioritizing responses that correspond to the emotions expressed by the user.

[0686] 4. Presenting results to the user

[0687] The server sends response data to the terminal, including relevant past cases, how they were handled, and emotionally sensitive advice.

[0688] The device uses "React.js" to display this information on the user's screen.

[0689] Specific examples and prompt statements

[0690] For example, suppose a user enters a problem report such as "My internet connection frequently drops," and the emotion engine detects "frustration." The terminal sends this to the server, which parses the JSON data. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this will be presented to the user. Furthermore, emotion-based advice such as "If you need a quick solution, we recommend contacting manufacturer support" will also be displayed.

[0691] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0692] Step 1:

[0693] Users enter error messages.

[0694] Specific actions

[0695] Users access the system using a web browser or a dedicated application and enter details of the problem into a text box. For example, they might enter "Internet connection frequently drops." This entered text becomes the input data for the next process.

[0696] Input and Output

[0697] Input: Details of the incident (manually entered by the user)

[0698] Output: Text data (description of the failure event)

[0699] Step 2:

[0700] Recognition of emotions

[0701] Specific actions

[0702] The server receives the text data entered by the user and sends it to the Emotion API. The Emotion API extracts emotions such as "frustration" from the text data. This emotion data is then passed on to the next process.

[0703] Input and Output

[0704] Input: Detailed text of the failure event

[0705] Output: Sentiment data (e.g., "frustration")

[0706] Step 3:

[0707] Sending a failure event

[0708] Specific actions

[0709] The device converts the text data entered by the user and the emotion data returned by the emotion recognition API into JSON-formatted request data. Specifically, it generates JSON data like the following:

[0710] json

[0711] {

[0712] "event_description": "Internet connection frequently drops",

[0713] "user_emotion": "frustration"

[0714] }

[0715] Send this JSON data to the server.

[0716] Input and Output

[0717] Input: Detailed text and sentiment data of the incident.

[0718] Output: JSON data

[0719] Step 4:

[0720] JSON data parsing and preprocessing

[0721] Specific actions

[0722] The server parses the received JSON data and extracts the error description text and user sentiment data. This process uses "Express.js". Next, the error description text undergoes tokenization, stop word removal, and stemming. The "nltk" library is used to organize the text data into a parseable format.

[0723] Input and Output

[0724] Input: JSON data

[0725] Output: Preprocessed text data

[0726] Step 5:

[0727] Database Search

[0728] Specific actions

[0729] The server searches the MySQL database based on pre-processed text data. The search uses methods such as TF-IDF and cosine similarity to identify past cases related to the failure event and their corresponding solutions. If necessary, the search results are refined to take user sentiment data into consideration.

[0730] Input and Output

[0731] Input: Preprocessed text data and sentiment data

[0732] Output: Search results (past cases and countermeasures)

[0733] Step 6:

[0734] Displaying search results

[0735] Specific actions

[0736] The server sends search results to the device, which then displays them on the user's screen. Specifically, the search results, which include suggested actions and advice tailored to the user's emotions, are displayed using a front-end framework (React.js). For example, a past case "The problem was caused by insufficient router firmware updates" and the suggested solution "Update the router firmware to the latest version" might be displayed.

[0737] Input and Output

[0738] Input: Search Results

[0739] Output: Display of results to the user

[0740] (Application Example 2)

[0741] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0742] In recent years, with the proliferation of food delivery services, users are increasingly encountering various problems related to delivery. For example, there are cases of delayed orders, cold food, and misdeliveries. While there is a need to respond quickly and appropriately to these problems, conventional systems have struggled to provide solutions that take user feelings into consideration. Furthermore, there is a lack of systems that can effectively analyze the details of problems entered by users and suggest appropriate solutions based on past cases. This leads to increased user stress and dissatisfaction with the service.

[0743] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, a display means for presenting the search results to the user, an emotion recognition means for recognizing emotions, and an adjustment means for adjusting the presentation method of search results and countermeasures based on emotion data. This enables rapid analysis of delivery-related troubles entered by the user, the presentation of appropriate solutions based on past cases, and the provision of information that takes the user's emotions into consideration.

[0744] A "user" is the entity that accesses the system and inputs error reports.

[0745] A "failure event" refers to a problem or trouble that occurs while using a system or service.

[0746] An "input mechanism" is a function that provides an interface for users to input fault events into the system.

[0747] The "processing means" refers to a function that receives details of a failure event entered by the user and performs preprocessing on the data.

[0748] "Search method" refers to a function that searches a database for past cases and countermeasures related to failure events, based on pre-processed data.

[0749] "Display means" refers to functions for presenting search results to the user.

[0750] "Emotion recognition means" refers to a function that recognizes emotions from text data entered by the user.

[0751] "Adjustment mechanism" refers to a function that adjusts the way search results and response methods are presented based on sentiment data.

[0752] "Past incidents" refer to data that records past incidents and how they were handled.

[0753] "Response method" refers to the procedures and methods for dealing with a failure or malfunction.

[0754] This invention is a system that quickly analyzes user-inputted problems and appropriately presents past cases and solutions, further incorporating an emotion engine that recognizes the user's emotions. This invention is particularly applicable to troubleshooting in food delivery services.

[0755] User error event input and emotion recognition

[0756] Users access the system via a smartphone application and enter details of delivery problems into a text box. This text box is intuitive for users to use and allows for detailed descriptions of problems. Furthermore, an emotion engine operates to recognize emotions from the text data entered by the user.

[0757] Transmission and preprocessing of failure events

[0758] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server. For example, the following data is sent:

[0759] json

[0760] {

[0761] "event_description": "The delivery was late, and the order got cold."

[0762] "user_emotion": "frustration"

[0763] }

[0764] Analysis of disturbance events and emotional processing

[0765] The server receives the request data and extracts a description of the incident and the user's sentiment from the JSON data. Then, it performs preprocessing on the incident description (tokenization, stop word removal, stemming). This preprocessing organizes the text data, enabling more efficient search operations.

[0766] Database search and emotionally conscious adjustments

[0767] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. Furthermore, the search results and suggested solutions are adjusted based on sentiment data recognized by the sentiment engine. For example, if a user indicates "frustration," the server prioritizes presenting solutions and procedures that can resolve the issue more quickly.

[0768] Presenting results to the user

[0769] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own. Advice and warnings tailored to the user's feelings are also displayed.

[0770] Specific example

[0771] For example, suppose a user enters a problem report stating, "The delivery was late and the order got cold," and the emotion engine detects "frustration." The terminal sends this to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past, where a re-cooking request was made and the order was delivered directly, and the suggested solution is "request re-cooking," this is presented to the user. Furthermore, emotion-based advice such as "We recommend issuing an apology coupon" is also displayed. Examples of prompt messages include:

[0772] A user posted the following problem: "The delivery was late and my order got cold 😡"

[0773] Based on this information, search for past cases and solutions, and present solutions and emotion-based advice in the following output format.

[0774] Problem: {Question content}

[0775] Solution:

[0776] 1. {Solution 1}

[0777] 2. {Solution 2}

[0778] Advice: {Emotion-based advice}

[0779] This makes it possible to quickly analyze delivery-related problems that users encounter, provide appropriate solutions, and offer information that is sensitive to the user's feelings.

[0780] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0781] Step 1:

[0782] The user enters details of a delivery issue into a text box in the smartphone application. This input includes problems such as delivery delays, misdeliveries, or cold food. When the user enters the problem into the text box and clicks the submit button, the input data is sent to the device. The input data is a text-based description of the problem.

[0783] Step 2:

[0784] The device receives text data entered by the user and uses an emotion engine to recognize the user's emotions. This process estimates emotions such as "frustration" from emojis like "😡" and the content of the text. The recognition results are prepared in JSON format along with the emotion data. The input is the user's text data, and the output is JSON data including emotions.

[0785] Step 3:

[0786] The terminal sends the prepared JSON data to the server. The data sent will be in the following format:

[0787] json

[0788] {

[0789] "event_description": "The delivery was late, and the order got cold."

[0790] "user_emotion": "frustration"

[0791] }

[0792] The input is JSON data containing emotions, and the output is the status indicating whether the transmission to the server was successful.

[0793] Step 4:

[0794] The server extracts a description of the incident and user sentiment data from the received JSON data. The extracted data is used in the next analysis step. The input is the received JSON data, and the output is a text-formatted problem description and sentiment data.

[0795] Step 5:

[0796] The server preprocesses the description of the failure event. This preprocessing includes tokenization (separating the text into individual words), stop word removal (removing frequently occurring, meaningless words), and stemming (converting words back to their base forms). The input is the problem description text, and the output is the preprocessed text data.

[0797] Step 6:

[0798] The server searches a database containing records of past failure events and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. The input is pre-processed text data, and the output is a list of similar past cases and their solutions.

[0799] Step 7:

[0800] The server adjusts the way search results and suggested solutions are presented based on sentiment data. For example, if a user indicates "frustration," it prioritizes providing quick solutions. This adjustment uses generative AI models and prompts. The input is a list of similar past cases and solutions, along with sentiment data, and the output is a list of adjusted solutions.

[0801] Step 8:

[0802] The server sends response data to the terminal, including tailored solutions. This data includes specific steps and sentiment-based advice. The input is a list of tailored solutions, and the output is the status of the transmission to the terminal.

[0803] Step 9:

[0804] The terminal displays response data received from the server on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve problems independently. Advice and warnings tailored to the user's emotional state are also displayed. Input is the response data, and output is the display to the user.

[0805] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0806] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0807] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0808] [Third Embodiment]

[0809] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0810] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0811] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0812] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0813] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0814] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0815] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0816] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0817] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0818] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0819] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0820] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0821] This invention relates to a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. This system provides an interface for user input of failure events and includes multiple functions for processing them.

[0822] User error event input

[0823] Users access the system via a web browser or dedicated application and enter details of the problem into a text box. This text box is intuitive for users and allows for detailed descriptions of the problem.

[0824] Transmission and preprocessing of failure events

[0825] The terminal sends the user-entered text of the incident as a JSON request to the server. The server parses the received text and performs preprocessing such as tokenization, stop word removal, and stemming. This ensures that the text data is properly organized, allowing for efficient subsequent search processing.

[0826] Database search and selection of appropriate case studies

[0827] The server searches a database containing records of past failures and their solutions based on pre-processed text. Algorithms such as TF-IDF and cosine similarity are used for the search. This allows the most similar past cases and their solutions to be identified.

[0828] Presenting results to the user

[0829] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own.

[0830] Specific example

[0831] For example, suppose a user enters a problem report stating that "the internet connection frequently drops." The terminal sends this information to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this information is presented to the user. As a result, the user can update the router firmware based on the presented information and resolve the problem.

[0832] In this way, troubleshooting becomes more efficient by quickly analyzing the problems users encounter and providing appropriate solutions.

[0833] The following describes the processing flow.

[0834] Step 1:

[0835] The user opens the system interface and enters details of the problem into the text box. For example, they might enter, "The internet connection frequently drops."

[0836] Step 2:

[0837] The device retrieves the text entered by the user and converts it into JSON-formatted request data. The format will be as follows:

[0838] json

[0839] {

[0840] "event_description": "Internet connection frequently drops"

[0841] }

[0842] Step 3:

[0843] The device sends request data in JSON format to the server.

[0844] Step 4:

[0845] The server receives the request data and extracts a description of the failure from the JSON data.

[0846] Step 5:

[0847] The server performs preprocessing on the description of the failure event. The following processes are carried out:

[0848] Tokenization: Dividing text into individual words. Examples: "Internet," "connection," "frequent," "disconnect."

[0849] Stop word removal: Remove words with little meaning. For example, "ga" is removed.

[0850] Stemming: Extracting the base form of a word. "Connection" becomes "connection," and "break" becomes "break."

[0851] Step 6:

[0852] The server searches a database containing records of past failure events and their solutions based on pre-processed text. For example, it might use the TF-IDF method to calculate severity and compare it to past cases using cosine similarity.

[0853] Step 7:

[0854] The server identifies the most similar past case and its corresponding solution from the search results, and creates the result as response data in JSON format.

[0855] json

[0856] {

[0857] "past_event": "The internet connection frequently drops due to insufficient router firmware updates",

[0858] "solution": "Update the router's firmware to the latest version"

[0859] }

[0860] Step 8:

[0861] The server sends response data to the terminal.

[0862] Step 9:

[0863] The terminal receives response data from the server, analyzes it, and displays it on the screen in a format that is easy for the user to understand. For example, it might display: "In past cases, there have been problems with frequent internet connection drops due to insufficient router firmware updates. As a solution, it is recommended to update the router firmware to the latest version."

[0864] This allows users to quickly resolve problems in their environment based on the information provided.

[0865] (Example 1)

[0866] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0867] It is necessary for users to quickly analyze incidents and be presented with appropriate information on past cases and solutions. However, current systems lack the ability to effectively process incident data entered by users and provide appropriate search results. In particular, accuracy and efficiency are required in data preprocessing and searching for similar cases, but solutions that meet these requirements are limited.

[0868] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0869] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, and a display means for presenting the search results to the user. This makes it possible to effectively process the failure event data entered by the user and to quickly and accurately present past cases and countermeasures.

[0870] "Input means" refers to a means by which a user enters details of a problem, and is used via a web browser or a dedicated application.

[0871] The "processing means" refers to a means for receiving details of a failure event entered by the user and performing preprocessing. Preprocessing includes tokenization, stop word removal, and stemming.

[0872] The "search means" is a method for searching a database for past events and their corresponding methods using text data preprocessed by the processing means. The TF-IDF method and cosine similarity are used for the search.

[0873] The "display means" refers to the means of presenting the results obtained from the search means to the user. It is responsible for receiving the search results in JSON format and displaying them on the user's device.

[0874] "Tokenization" is a preprocessing technique that divides text data into words and phrases.

[0875] "Stop word removal" is a preprocessing technique that removes words that are too common and unnecessary for search results in order to improve search accuracy.

[0876] Stemming is a preprocessing technique that converts words into their base form.

[0877] The "TF-IDF method" is a statistical technique used to assess the importance of text data, taking into account the frequency of terms and their inverse document frequency.

[0878] "Cosine similarity" is a method for calculating the similarity between two vectors, and is mainly used in text mining.

[0879] A "database" is an information system used to systematically store information about past incidents and how they were dealt with.

[0880] JSON format is a lightweight data exchange format for storing and transferring data.

[0881] This invention relates to a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. This system provides an interface for user input of failure events and includes multiple functions for processing them. The following describes a specific implementation of this system.

[0882] Hardware and software to be used

[0883] Hardware: Servers (high-performance computers), terminals (PCs, smartphones)

[0884] software:

[0885] Web browser (e.g., Chrome, Firefox)

[0886] Dedicated application

[0887] Natural language processing libraries (e.g., spaCy, NLTK)

[0888] Database Management System (DBMS)

[0889] Software for handling JSON format (e.g., Python's json library)

[0890] User input of failure events

[0891] Users access the system via its web interface or a dedicated application and enter details of the problem into an intuitively usable text box. For example, consider a scenario where a user enters the problem "frequent internet connection drops."

[0892] Transmission and preprocessing of failure events

[0893] The terminal sends the user-entered text of the problem as a JSON request to the server. The server parses the received text using a natural language processing library (e.g., spaCy).

[0894] As a specific example of preprocessing, the following steps are performed:

[0895] Tokenization: Dividing text into words or phrases. Example: "My internet connection frequently drops" → "Internet," "Connection," "Drops"

[0896] Stop word removal: Remove overly common words to improve search accuracy. Example: "ga", "ni" → remove

[0897] Stemming: Converting a word to its base form. Example: "kireru" → "kire"

[0898] Database search and presentation of results

[0899] The server uses the TF-IDF method and cosine similarity to search the database for past failure events and their solutions based on pre-processed text data. This identifies the most similar past case and its solution.

[0900] For example, if there was a past instance where "internet connection frequently dropped due to insufficient router firmware updates," the solution identified would be "update the router firmware to the latest version."

[0901] Displaying Results

[0902] The server returns the search results to the terminal in JSON format. The terminal displays the received information on the user's screen, showing details of past cases and specific solutions. The user can then use this information to solve the problem on their own.

[0903] Specific examples and prompt statements

[0904] Specific example: A user inputs a problem description such as "the internet connection frequently drops," and the terminal sends this information to the server. The server performs preprocessing and a database search, identifying a past case where the cause was "insufficient router firmware updates" and a solution of "update the router firmware to the latest version." This information is returned to the terminal, and specific countermeasures are displayed on the user's screen.

[0905] Example of a prompt:

[0906] Please explain how the server searches for past cases and provides solutions when a user enters "My internet connection frequently drops."

[0907] By using this system, users can obtain solutions to problems quickly and efficiently.

[0908] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0909] Step 1: User input of the failure event

[0910] The user accesses the system's web browser or dedicated application and enters details of the problem into a text box. For example, the user might write "Internet connection frequently drops." This text data is then recorded on the terminal as output.

[0911] Step 2: Sending the Incident Report

[0912] The terminal converts the user-entered error text into JSON format and sends it to the server. Specifically, it serializes the entered text data as a JSON object and sends it to the server via an HTTPS request. The input is the user's text, and the output is the JSON data sent to the server.

[0913] Step 3: Text Preprocessing

[0914] The server parses the JSON-formatted error message text received from the terminal. It receives JSON data as input and performs the following specific text preprocessing:

[0915] Tokenization: Dividing text into words or phrases. Example: "My internet connection frequently drops" → "Internet," "Connection," "Drops"

[0916] Stop word removal: Remove overly common words to improve search accuracy. Example: "ga", "ni" → remove

[0917] Stemming: Converting a word to its base form. Example: "kireru" → "kire"

[0918] The output is pre-processed text data.

[0919] Step 4: Search the database

[0920] The server searches a database containing records of past failure events and their solutions, based on pre-processed text data. The input is pre-processed text data, and the search uses methods such as TF-IDF or cosine similarity. As a specific example, a search is performed using the keyword "Internet connection lost." The output is search results data containing the most similar past cases and their solutions.

[0921] Step 5: Submit search results

[0922] The server returns the identified past cases and their corresponding solutions to the terminal in JSON format. The input is search result data, and the output is response data in JSON format. Specifically, the search results are serialized as a JSON object and sent to the terminal as an HTTP response.

[0923] Step 6: Displaying the results

[0924] The terminal parses the search results received from the server in JSON format and displays them on the user's screen. Specifically, it parses the received JSON data and displays past cases and solutions on the interface in list or detailed view formats. The input is JSON data received from the server, and the output is in a format that the user can view on the screen.

[0925] By following these steps, users can quickly and accurately find solutions to their problems.

[0926] (Application Example 1)

[0927] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0928] In modern security systems, finding quick and appropriate countermeasures for the various security breaches users encounter is extremely difficult. This problem stems particularly from the insufficient utilization of past cases and knowledge. As a result, users spend a great deal of time and effort finding appropriate countermeasures. There is a need to solve these challenges and enable users to respond quickly to security breaches.

[0929] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0930] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, a display means for presenting the search results to the user, a similarity calculation means for calculating the similarity between the input failure event and past cases, and a recommendation presentation means for presenting recommended countermeasures based on the most similar past cases. This enables the user to obtain quick and appropriate countermeasures for the input failure event.

[0931] Definition of Terms

[0932] "User input means for entering failure events" refers to an interface provided for users to input details of failure events they encounter. This interface is used for communication between the user and the system via devices such as smartphones, computers, and tablets.

[0933] "Processing means for receiving details of a failure event and performing preprocessing" refers to a function that receives information about a failure event entered by the user, analyzes it, and performs preprocessing such as tokenization, stop word removal, and stemming.

[0934] The "search method for searching a database for past cases and countermeasures related to failure events" refers to a function that searches a database containing records of past cases and their countermeasures, based on pre-processed information about failure events. Algorithms such as the TF-IDF method and cosine similarity are used for this search.

[0935] "A means of displaying search results to the user" refers to an interface that presents the results obtained through a search in an easy-to-understand manner to the user. This interface is displayed on the device's screen.

[0936] The "similarity calculation means for calculating the similarity between an input failure event and past cases" refers to a function for calculating the similarity between a failure event entered by a user and past cases in the database. This calculation uses cosine similarity or other similarity calculation algorithms.

[0937] The "recommendation suggestion method that presents recommended countermeasures based on the most similar past cases" refers to a function that presents the user with the most similar past cases and their solutions based on a calculated similarity score. This allows the user to quickly obtain appropriate countermeasures.

[0938] Modes for carrying out the invention

[0939] This invention is a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. The specific implementation of this system is described below.

[0940] System Overview

[0941] This system allows users to input incidents using smartphones or other devices, processes the information, and quickly presents relevant past cases and solutions. The main components of the system include input means, processing means, search means, display means, similarity calculation means, and recommendation suggestion means.

[0942] Hardware and software to be used

[0943] Hardware: Smartphones, computers, tablets

[0944] Software: Python, scikit-learn, web browser

[0945] Program Processing Overview

[0946] 1. The user enters the error message.

[0947] Users access a dedicated application or web interface via their smartphone or computer and enter details of the problem into a text box. This input method is designed to be intuitive for users.

[0948] 2. Receiving and pre-processing of failure events

[0949] The terminal sends the user-entered error information to the server in JSON format. The server preprocesses the received text by performing tokenization, stop word removal, stemming, etc., to properly organize the text data.

[0950] 3. Database search and similarity calculation

[0951] The server uses pre-processed text data to search a database containing records of past failure events and how they were handled. Algorithms such as the TF-IDF method and cosine similarity are used in the search to calculate the similarity between the input failure event and past cases.

[0952] 4. Presentation of search results and recommendations

[0953] The server identifies the most similar past cases from the search results and generates recommended countermeasures based on them. The terminal displays the results to the user, including the relevant past cases and how they were handled.

[0954] Specific example

[0955] For example, if a user enters a problem report stating "Unauthorized access detected, warning displayed," the terminal sends this information to the server. The server performs preprocessing and a database search, and if a record of "unauthorized access detected" is found in the database, a solution such as "immediately change your password and check your login history" is suggested. In this way, the user can quickly obtain appropriate countermeasures.

[0956] Example of a prompt

[0957] "If unauthorized access is detected and a warning is displayed, what countermeasures are effective?"

[0958] This invention enables users to quickly find appropriate countermeasures and deal with failure events.

[0959] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0960] Program processing flow

[0961] Step 1: The user enters the fault report.

[0962] Users enter details of the incident into text boxes using smartphone or computer applications or web interfaces. The entered information is converted to JSON format for use in subsequent processing.

[0963] Input: Details of the incident (text)

[0964] Output: Input data in JSON format

[0965] Action: The user enters "Unauthorized access has been detected and a warning has been displayed."

[0966] Step 2: Receiving and pre-processing of the failure event

[0967] The terminal sends the input error event to the server in JSON format. The server preprocesses the received text by performing tokenization, stop word removal, stemming, etc., to properly organize the text data.

[0968] Input: Failure event data in JSON format

[0969] Output: Preprocessed text data

[0970] Operation: The server splits the received text into words such as "malicious," "access," "detect," "warning," and "display," removes unnecessary words, and converts them into core words.

[0971] Step 3: Database search and similarity calculation

[0972] The server uses pre-processed text data to search a database containing records of past failure events and their resolution methods. Algorithms such as the TF-IDF method and cosine similarity are used for the search. The server calculates the similarity between the input failure event and past cases.

[0973] Input: Preprocessed text data

[0974] Output: List of similar past cases and countermeasures

[0975] Operation: The server searches a database of past cases, extracts relevant cases based on the keyword "unauthorized access," and performs a similarity calculation.

[0976] Step 4: Presentation of search results and recommendations

[0977] The server identifies the most similar past cases from the search results and generates recommended countermeasures based on them. The terminal then displays these results to the user.

[0978] Input: List of similar past cases and countermeasures

[0979] Output: Recommended countermeasures and their display

[0980] Action: The server generates a recommendation to "change your password immediately and check your login history" and sends it to the terminal. The terminal displays this to the user.

[0981] In this way, users can quickly obtain appropriate countermeasures.

[0982] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0983] This invention provides a system that quickly analyzes user-inputted failure events and appropriately presents past cases and response methods, further incorporating an emotion engine that recognizes the user's emotions. This system includes an interface for the user to input failure events and multiple functions for processing them.

[0984] User error event input and emotion recognition

[0985] Users access the system via a web browser or dedicated application and enter details of the problem into a text box. This text box is intuitive to use and allows users to describe the problem in detail. Furthermore, an emotion engine operates to recognize emotions from the text data entered by the user.

[0986] Transmission and preprocessing of failure events

[0987] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server. The data sent is in the following format:

[0988] json

[0989] {

[0990] "event_description": "Internet connection frequently drops",

[0991] "user_emotion": "frustration"

[0992] }

[0993] Analysis of disturbance events and emotional processing

[0994] The server receives the request data and extracts a description of the incident and the user's sentiment from the JSON data. Then, it performs preprocessing on the incident description (tokenization, stop word removal, stemming). This preprocessing organizes the text data, enabling more efficient search operations.

[0995] Database search and emotionally conscious adjustments

[0996] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. Furthermore, the search results and suggested solutions are adjusted based on sentiment data recognized by the sentiment engine. For example, if a user indicates "frustration," the server prioritizes presenting solutions and procedures that can resolve the issue more quickly.

[0997] Presenting results to the user

[0998] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own. Advice and warnings tailored to the user's feelings are also displayed.

[0999] Specific example

[1000] For example, suppose a user enters a problem report such as "My internet connection keeps dropping," and the emotion engine detects "frustration." The terminal sends this to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this will be presented to the user. Furthermore, emotion-based advice such as "If you need a quick solution, we recommend contacting manufacturer support" will also be displayed.

[1001] In this way, by quickly analyzing the problems users encounter and providing appropriate solutions, as well as offering information that takes users' feelings into consideration, troubleshooting can be carried out more efficiently, and an improvement in user satisfaction can be expected.

[1002] The following describes the processing flow.

[1003] Step 1:

[1004] The user opens the system interface and enters details of the problem into the text box. For example, they might enter, "The internet connection frequently drops."

[1005] Step 2:

[1006] The device retrieves text entered by the user and uses an emotion engine to recognize the emotion from the text. In this case, the emotion engine detects "frustration."

[1007] Step 3:

[1008] The terminal converts the entered text and recognized emotions into JSON-formatted request data. The format will be as follows:

[1009] json

[1010] {

[1011] "event_description": "Internet connection frequently drops",

[1012] "user_emotion": "frustration"

[1013] }

[1014] Step 4:

[1015] The device sends request data in JSON format to the server.

[1016] Step 5:

[1017] The server receives the request data and extracts "event_description" (description of the incident) and "user_emotion" (user's emotion) from the JSON data.

[1018] Step 6:

[1019] The server performs preprocessing on "event_description". The following processes are carried out:

[1020] Tokenization: Dividing text into individual words. Examples: "Internet," "connection," "frequent," "disconnect."

[1021] Stop word removal: Remove words with little meaning. For example, "ga" is removed.

[1022] Stemming: Extracting the base form of a word. "Connection" becomes "connection," and "break" becomes "break."

[1023] Step 7:

[1024] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses the TF-IDF method and cosine similarity.

[1025] Step 8:

[1026] The server identifies the most similar past cases and their corresponding solutions from the search results, and creates a response data in JSON format. Furthermore, based on the emotions recognized by the emotion engine, it adds advice for quick action if the user is irritated.

[1027] json

[1028] {

[1029] "past_event": "The internet connection frequently drops due to insufficient router firmware updates",

[1030] "solution": "Update the router's firmware to the latest version",

[1031] "emotion_based_advice": "If you need a quick solution, we recommend contacting manufacturer support."

[1032] }

[1033] Step 9:

[1034] The server sends response data to the terminal.

[1035] Step 10:

[1036] The terminal receives response data from the server, analyzes it, and displays it on the screen in a format that is easy for the user to understand. For example, it might display: "In past cases, there have been problems with frequent internet connection drops due to insufficient router firmware updates. As a solution, it is recommended to update the router firmware to the latest version. If a quick solution is needed, it is recommended to contact manufacturer support."

[1037] This allows users to quickly resolve problems in their environment based on the information presented and emotionally-driven advice.

[1038] (Example 2)

[1039] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1040] Conventional failure event analysis systems not only analyze the details of failure events entered by users, but also fail to adequately provide solutions that take into account the user's feelings. As a result, this can increase user dissatisfaction. Therefore, a system is needed that not only analyzes the failure events entered by users but also provides information that responds to the user's feelings, thereby improving user satisfaction.

[1041] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1042] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving the details and emotions of the input failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event and adjusting the search results based on emotions, and a display means for presenting the adjusted search results to the user. This enables the user to analyze the failure event and provide information that takes emotions into consideration.

[1043] "Input means" refers to an interface for users to input details of a failure event into the system, and includes web browsers and dedicated applications.

[1044] The "processing means" is a component that receives the details of the input failure event and the user's sentiment data, and has the function of organizing and analyzing the text data, performing tokenization, stop word removal, and stemming.

[1045] The "search method" involves searching a database based on processed text data to identify past failure cases and their solutions, and adjusting the search results based on the user's sentiment. It utilizes methods such as TF-IDF and cosine similarity.

[1046] "Display means" refers to an interface for presenting search results and adjusted responses to the user, and includes web screens and application displays.

[1047] "Emotions" refer to the psychological state expressed by the user in relation to the incidents they have entered, and are part of the data that the system analyzes and considers.

[1048] "Preprocessing" refers to a series of processes to organize input data into an analyzable format, specifically including tokenization, stop word removal, and stemming.

[1049] A "database" is a place where information is collected, recording past incidents and countermeasures for failures, and is accessed through search methods.

[1050] "Tokenization" is the process of dividing text data into words and phrases, and it is performed in the initial stages of text analysis.

[1051] "Stop word removal" is the process of removing words that are considered to be of low importance during searching or analysis (for example, "no" or "toita").

[1052] Stemming is the process of extracting the root of a word, and it is performed to combine words with different forms into a single word.

[1053] The "TF-IDF method" is a numerical method for calculating the importance of words within a document and evaluating their relevance.

[1054] "Cosine similarity" is a method for calculating the similarity between documents based on a vector space, and is used to improve the accuracy of search results.

[1055] This invention provides a system that quickly analyzes user-inputted failure events, appropriately presents past cases and solutions, and further incorporates an emotion engine that recognizes the user's emotions. This system is implemented using the following hardware and software.

[1056] Hardware and software used

[1057] The system includes terminals (such as PCs and smartphones) for user access and servers for processing.

[1058] Input Interface: Users access the system via a web browser or dedicated application and input details of the failure.

[1059] Emotion Engine: Uses the Emotion Recognition API (EmotionAPI) to recognize emotions from text data entered by the user.

[1060] Preprocessing module: The server uses the Natural Language Processing Library (NLTK) to perform tokenization, stop word removal, and stemming on the received text data.

[1061] Database: A relational database (MySQL) is used to store response and accumulated failure event data.

[1062] Search algorithm: When evaluating the relevance of text data and performing searches, methods such as TF-IDF and cosine similarity are used.

[1063] Display Interface: A front-end framework (React.js) is used to present search results and solutions to the user.

[1064] Specific operation of the system

[1065] 1. User error event input and emotion recognition

[1066] Users access the system using a web browser or a dedicated application and enter details of the problem into a text box.

[1067] The emotion engine recognizes emotions from text data entered by the user and generates emotion data (for example, "frustration").

[1068] 2. Transmission of failure events and preprocessing

[1069] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server.

[1070] The server uses "Express.js" to parse the JSON data and extract descriptions of the failure events and sentiment data.

[1071] The server uses the Natural Language Processing Library (NLTK) to perform tokenization, stop word removal, and stemming of text data.

[1072] 3. Database search and adjustment based on sentiment.

[1073] The server searches the MySQL database based on the pre-processed text data.

[1074] The TF-IDF method and cosine similarity are used for the search.

[1075] The server also adjusts search results based on sentiment data, prioritizing responses that correspond to the emotions expressed by the user.

[1076] 4. Presenting results to the user

[1077] The server sends response data to the terminal, including relevant past cases, how they were handled, and emotionally sensitive advice.

[1078] The device uses "React.js" to display this information on the user's screen.

[1079] Specific examples and prompt statements

[1080] For example, suppose a user enters a problem report such as "My internet connection frequently drops," and the emotion engine detects "frustration." The terminal sends this to the server, which parses the JSON data. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this will be presented to the user. Furthermore, emotion-based advice such as "If you need a quick solution, we recommend contacting manufacturer support" will also be displayed.

[1081] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1082] Step 1:

[1083] Users enter error messages.

[1084] Specific actions

[1085] Users access the system using a web browser or a dedicated application and enter details of the problem into a text box. For example, they might enter "Internet connection frequently drops." This entered text becomes the input data for the next process.

[1086] Input and Output

[1087] Input: Details of the incident (manually entered by the user)

[1088] Output: Text data (description of the failure event)

[1089] Step 2:

[1090] Recognition of emotions

[1091] Specific actions

[1092] The server receives the text data entered by the user and sends it to the Emotion API. The Emotion API extracts emotions such as "frustration" from the text data. This emotion data is then passed on to the next process.

[1093] Input and Output

[1094] Input: Detailed text of the failure event

[1095] Output: Sentiment data (e.g., "frustration")

[1096] Step 3:

[1097] Sending a failure event

[1098] Specific actions

[1099] The device converts the text data entered by the user and the emotion data returned by the emotion recognition API into JSON-formatted request data. Specifically, it generates JSON data like the following:

[1100] json

[1101] {

[1102] "event_description": "Internet connection frequently drops",

[1103] "user_emotion": "frustration"

[1104] }

[1105] Send this JSON data to the server.

[1106] Input and Output

[1107] Input: Detailed text and sentiment data of the incident.

[1108] Output: JSON data

[1109] Step 4:

[1110] JSON data parsing and preprocessing

[1111] Specific actions

[1112] The server parses the received JSON data and extracts the error description text and user sentiment data. This process uses "Express.js". Next, the error description text undergoes tokenization, stop word removal, and stemming. The "nltk" library is used to organize the text data into a parseable format.

[1113] Input and Output

[1114] Input: JSON data

[1115] Output: Preprocessed text data

[1116] Step 5:

[1117] Database Search

[1118] Specific actions

[1119] The server searches the MySQL database based on pre-processed text data. The search uses methods such as TF-IDF and cosine similarity to identify past cases related to the failure event and their corresponding solutions. If necessary, the search results are refined to take user sentiment data into consideration.

[1120] Input and Output

[1121] Input: Preprocessed text data and sentiment data

[1122] Output: Search results (past cases and countermeasures)

[1123] Step 6:

[1124] Displaying search results

[1125] Specific actions

[1126] The server sends search results to the device, which then displays them on the user's screen. Specifically, the search results, which include suggested actions and advice tailored to the user's emotions, are displayed using a front-end framework (React.js). For example, a past case "The problem was caused by insufficient router firmware updates" and the suggested solution "Update the router firmware to the latest version" might be displayed.

[1127] Input and Output

[1128] Input: Search Results

[1129] Output: Display of results to the user

[1130] (Application Example 2)

[1131] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1132] In recent years, with the proliferation of food delivery services, users are increasingly encountering various problems related to delivery. For example, there are cases of delayed orders, cold food, and misdeliveries. While there is a need to respond quickly and appropriately to these problems, conventional systems have struggled to provide solutions that take user feelings into consideration. Furthermore, there is a lack of systems that can effectively analyze the details of problems entered by users and suggest appropriate solutions based on past cases. This leads to increased user stress and dissatisfaction with the service.

[1133] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, a display means for presenting the search results to the user, an emotion recognition means for recognizing emotions, and an adjustment means for adjusting the presentation method of search results and countermeasures based on emotion data. This enables rapid analysis of delivery-related troubles entered by the user, the presentation of appropriate solutions based on past cases, and the provision of information that takes the user's emotions into consideration.

[1134] A "user" is the entity that accesses the system and inputs error reports.

[1135] A "failure event" refers to a problem or trouble that occurs while using a system or service.

[1136] An "input mechanism" is a function that provides an interface for users to input fault events into the system.

[1137] The "processing means" refers to a function that receives details of a failure event entered by the user and performs preprocessing on the data.

[1138] "Search method" refers to a function that searches a database for past cases and countermeasures related to failure events, based on pre-processed data.

[1139] "Display means" refers to functions for presenting search results to the user.

[1140] "Emotion recognition means" refers to a function that recognizes emotions from text data entered by the user.

[1141] "Adjustment mechanism" refers to a function that adjusts the way search results and response methods are presented based on sentiment data.

[1142] "Past incidents" refer to data that records past incidents and how they were handled.

[1143] "Response method" refers to the procedures and methods for dealing with a failure or malfunction.

[1144] This invention is a system that quickly analyzes user-inputted problems and appropriately presents past cases and solutions, further incorporating an emotion engine that recognizes the user's emotions. This invention is particularly applicable to troubleshooting in food delivery services.

[1145] User error event input and emotion recognition

[1146] Users access the system via a smartphone application and enter details of delivery problems into a text box. This text box is intuitive for users to use and allows for detailed descriptions of problems. Furthermore, an emotion engine operates to recognize emotions from the text data entered by the user.

[1147] Transmission and preprocessing of failure events

[1148] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server. For example, the following data is sent:

[1149] json

[1150] {

[1151] "event_description": "The delivery was late, and the order got cold."

[1152] "user_emotion": "frustration"

[1153] }

[1154] Analysis of disturbance events and emotional processing

[1155] The server receives the request data and extracts a description of the incident and the user's sentiment from the JSON data. Then, it performs preprocessing on the incident description (tokenization, stop word removal, stemming). This preprocessing organizes the text data, enabling more efficient search operations.

[1156] Database search and emotionally conscious adjustments

[1157] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. Furthermore, the search results and suggested solutions are adjusted based on sentiment data recognized by the sentiment engine. For example, if a user indicates "frustration," the server prioritizes presenting solutions and procedures that can resolve the issue more quickly.

[1158] Presenting results to the user

[1159] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own. Advice and warnings tailored to the user's feelings are also displayed.

[1160] Specific example

[1161] For example, suppose a user enters a problem report stating, "The delivery was late and the order got cold," and the emotion engine detects "frustration." The terminal sends this to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past, where a re-cooking request was made and the order was delivered directly, and the suggested solution is "request re-cooking," this is presented to the user. Furthermore, emotion-based advice such as "We recommend issuing an apology coupon" is also displayed. Examples of prompt messages include:

[1162] A user posted the following problem: "The delivery was late and my order got cold 😡"

[1163] Based on this information, search for past cases and solutions, and present solutions and emotion-based advice in the following output format.

[1164] Problem: {Question content}

[1165] Solution:

[1166] 1. {Solution 1}

[1167] 2. {Solution 2}

[1168] Advice: {Emotion-based advice}

[1169] This makes it possible to quickly analyze delivery-related problems that users encounter, provide appropriate solutions, and offer information that is sensitive to the user's feelings.

[1170] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1171] Step 1:

[1172] The user enters details of a delivery issue into a text box in the smartphone application. This input includes problems such as delivery delays, misdeliveries, or cold food. When the user enters the problem into the text box and clicks the submit button, the input data is sent to the device. The input data is a text-based description of the problem.

[1173] Step 2:

[1174] The device receives text data entered by the user and uses an emotion engine to recognize the user's emotions. This process estimates emotions such as "frustration" from emojis like "😡" and the content of the text. The recognition results are prepared in JSON format along with the emotion data. The input is the user's text data, and the output is JSON data including emotions.

[1175] Step 3:

[1176] The terminal sends the prepared JSON data to the server. The data sent will be in the following format:

[1177] json

[1178] {

[1179] "event_description": "The delivery was late, and the order got cold."

[1180] "user_emotion": "frustration"

[1181] }

[1182] The input is JSON data containing emotions, and the output is the status indicating whether the transmission to the server was successful.

[1183] Step 4:

[1184] The server extracts a description of the incident and user sentiment data from the received JSON data. The extracted data is used in the next analysis step. The input is the received JSON data, and the output is a text-formatted problem description and sentiment data.

[1185] Step 5:

[1186] The server preprocesses the description of the failure event. This preprocessing includes tokenization (separating the text into individual words), stop word removal (removing frequently occurring, meaningless words), and stemming (converting words back to their base forms). The input is the problem description text, and the output is the preprocessed text data.

[1187] Step 6:

[1188] The server searches a database containing records of past failure events and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. The input is pre-processed text data, and the output is a list of similar past cases and their solutions.

[1189] Step 7:

[1190] The server adjusts the way search results and suggested solutions are presented based on sentiment data. For example, if a user indicates "frustration," it prioritizes providing quick solutions. This adjustment uses generative AI models and prompts. The input is a list of similar past cases and solutions, along with sentiment data, and the output is a list of adjusted solutions.

[1191] Step 8:

[1192] The server sends response data to the terminal, including tailored solutions. This data includes specific steps and sentiment-based advice. The input is a list of tailored solutions, and the output is the status of the transmission to the terminal.

[1193] Step 9:

[1194] The terminal displays response data received from the server on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve problems independently. Advice and warnings tailored to the user's emotional state are also displayed. Input is the response data, and output is the display to the user.

[1195] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1196] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1197] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1198] [Fourth Embodiment]

[1199] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1200] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1201] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1202] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1203] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1204] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1205] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1206] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1207] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1208] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1209] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1210] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1211] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1212] This invention relates to a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. This system provides an interface for user input of failure events and includes multiple functions for processing them.

[1213] User error event input

[1214] Users access the system via a web browser or dedicated application and enter details of the problem into a text box. This text box is intuitive for users and allows for detailed descriptions of the problem.

[1215] Transmission and preprocessing of failure events

[1216] The terminal sends the user-entered text of the incident as a JSON request to the server. The server parses the received text and performs preprocessing such as tokenization, stop word removal, and stemming. This ensures that the text data is properly organized, allowing for efficient subsequent search processing.

[1217] Database search and selection of appropriate case studies

[1218] The server searches a database containing records of past failures and their solutions based on pre-processed text. Algorithms such as TF-IDF and cosine similarity are used for the search. This allows the most similar past cases and their solutions to be identified.

[1219] Presenting results to the user

[1220] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own.

[1221] Specific example

[1222] For example, suppose a user enters a problem report stating that "the internet connection frequently drops." The terminal sends this information to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this information is presented to the user. As a result, the user can update the router firmware based on the presented information and resolve the problem.

[1223] In this way, troubleshooting becomes more efficient by quickly analyzing the problems users encounter and providing appropriate solutions.

[1224] The following describes the processing flow.

[1225] Step 1:

[1226] The user opens the system interface and enters details of the problem into the text box. For example, they might enter, "The internet connection frequently drops."

[1227] Step 2:

[1228] The device retrieves the text entered by the user and converts it into JSON-formatted request data. The format will be as follows:

[1229] json

[1230] {

[1231] "event_description": "Internet connection frequently drops"

[1232] }

[1233] Step 3:

[1234] The device sends request data in JSON format to the server.

[1235] Step 4:

[1236] The server receives the request data and extracts a description of the failure from the JSON data.

[1237] Step 5:

[1238] The server performs preprocessing on the description of the failure event. The following processes are carried out:

[1239] Tokenization: Dividing text into individual words. Examples: "Internet," "connection," "frequent," "disconnect."

[1240] Stop word removal: Remove words with little meaning. For example, "ga" is removed.

[1241] Stemming: Extracting the base form of a word. "Connection" becomes "connection," and "break" becomes "break."

[1242] Step 6:

[1243] The server searches a database containing records of past failure events and their solutions based on pre-processed text. For example, it might use the TF-IDF method to calculate severity and compare it to past cases using cosine similarity.

[1244] Step 7:

[1245] The server identifies the most similar past case and its corresponding solution from the search results, and creates the result as response data in JSON format.

[1246] json

[1247] {

[1248] "past_event": "The internet connection frequently drops due to insufficient router firmware updates",

[1249] "solution": "Update the router's firmware to the latest version"

[1250] }

[1251] Step 8:

[1252] The server sends response data to the terminal.

[1253] Step 9:

[1254] The terminal receives response data from the server, analyzes it, and displays it on the screen in a format that is easy for the user to understand. For example, it might display: "In past cases, there have been problems with frequent internet connection drops due to insufficient router firmware updates. As a solution, it is recommended to update the router firmware to the latest version."

[1255] This allows users to quickly resolve problems in their environment based on the information provided.

[1256] (Example 1)

[1257] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1258] It is necessary for users to quickly analyze incidents and be presented with appropriate information on past cases and solutions. However, current systems lack the ability to effectively process incident data entered by users and provide appropriate search results. In particular, accuracy and efficiency are required in data preprocessing and searching for similar cases, but solutions that meet these requirements are limited.

[1259] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1260] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, and a display means for presenting the search results to the user. This makes it possible to effectively process the failure event data entered by the user and to quickly and accurately present past cases and countermeasures.

[1261] "Input means" refers to a means by which a user enters details of a problem, and is used via a web browser or a dedicated application.

[1262] The "processing means" refers to a means for receiving details of a failure event entered by the user and performing preprocessing. Preprocessing includes tokenization, stop word removal, and stemming.

[1263] The "search means" is a method for searching a database for past events and their corresponding methods using text data preprocessed by the processing means. The TF-IDF method and cosine similarity are used for the search.

[1264] The "display means" refers to the means of presenting the results obtained from the search means to the user. It is responsible for receiving the search results in JSON format and displaying them on the user's device.

[1265] "Tokenization" is a preprocessing technique that divides text data into words and phrases.

[1266] "Stop word removal" is a preprocessing technique that removes words that are too common and unnecessary for search results in order to improve search accuracy.

[1267] Stemming is a preprocessing technique that converts words into their base form.

[1268] The "TF-IDF method" is a statistical technique used to assess the importance of text data, taking into account the frequency of terms and their inverse document frequency.

[1269] "Cosine similarity" is a method for calculating the similarity between two vectors, and is mainly used in text mining.

[1270] A "database" is an information system used to systematically store information about past incidents and how they were dealt with.

[1271] JSON format is a lightweight data exchange format for storing and transferring data.

[1272] This invention relates to a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. This system provides an interface for user input of failure events and includes multiple functions for processing them. The following describes a specific implementation of this system.

[1273] Hardware and software to be used

[1274] Hardware: Servers (high-performance computers), terminals (PCs, smartphones)

[1275] software:

[1276] Web browser (e.g., Chrome, Firefox)

[1277] Dedicated application

[1278] Natural language processing libraries (e.g., spaCy, NLTK)

[1279] Database Management System (DBMS)

[1280] Software for handling JSON format (e.g., Python's json library)

[1281] User input of failure events

[1282] Users access the system via its web interface or a dedicated application and enter details of the problem into an intuitively usable text box. For example, consider a scenario where a user enters the problem "frequent internet connection drops."

[1283] Transmission and preprocessing of failure events

[1284] The terminal sends the user-entered text of the problem as a JSON request to the server. The server parses the received text using a natural language processing library (e.g., spaCy).

[1285] As a specific example of preprocessing, the following steps are performed:

[1286] Tokenization: Dividing text into words or phrases. Example: "My internet connection frequently drops" → "Internet," "Connection," "Drops"

[1287] Stop word removal: Remove overly common words to improve search accuracy. Example: "ga", "ni" → remove

[1288] Stemming: Converting a word to its base form. Example: "kireru" → "kire"

[1289] Database search and presentation of results

[1290] The server uses the TF-IDF method and cosine similarity to search the database for past failure events and their solutions based on pre-processed text data. This identifies the most similar past case and its solution.

[1291] For example, if there was a past instance where "internet connection frequently dropped due to insufficient router firmware updates," the solution identified would be "update the router firmware to the latest version."

[1292] Displaying Results

[1293] The server returns the search results to the terminal in JSON format. The terminal displays the received information on the user's screen, showing details of past cases and specific solutions. The user can then use this information to solve the problem on their own.

[1294] Specific examples and prompt statements

[1295] Specific example: A user inputs a problem description such as "the internet connection frequently drops," and the terminal sends this information to the server. The server performs preprocessing and a database search, identifying a past case where the cause was "insufficient router firmware updates" and a solution of "update the router firmware to the latest version." This information is returned to the terminal, and specific countermeasures are displayed on the user's screen.

[1296] Example of a prompt:

[1297] Please explain how the server searches for past cases and provides solutions when a user enters "My internet connection frequently drops."

[1298] By using this system, users can obtain solutions to problems quickly and efficiently.

[1299] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1300] Step 1: User input of the failure event

[1301] The user accesses the system's web browser or dedicated application and enters details of the problem into a text box. For example, the user might write "Internet connection frequently drops." This text data is then recorded on the terminal as output.

[1302] Step 2: Sending the Incident Report

[1303] The terminal converts the user-entered error text into JSON format and sends it to the server. Specifically, it serializes the entered text data as a JSON object and sends it to the server via an HTTPS request. The input is the user's text, and the output is the JSON data sent to the server.

[1304] Step 3: Text Preprocessing

[1305] The server parses the JSON-formatted error message text received from the terminal. It receives JSON data as input and performs the following specific text preprocessing:

[1306] Tokenization: Dividing text into words or phrases. Example: "My internet connection frequently drops" → "Internet," "Connection," "Drops"

[1307] Stop word removal: Remove overly common words to improve search accuracy. Example: "ga", "ni" → remove

[1308] Stemming: Converting a word to its base form. Example: "kireru" → "kire"

[1309] The output is pre-processed text data.

[1310] Step 4: Search the database

[1311] The server searches a database containing records of past failure events and their solutions, based on pre-processed text data. The input is pre-processed text data, and the search uses methods such as TF-IDF or cosine similarity. As a specific example, a search is performed using the keyword "Internet connection lost." The output is search results data containing the most similar past cases and their solutions.

[1312] Step 5: Submit search results

[1313] The server returns the identified past cases and their corresponding solutions to the terminal in JSON format. The input is search result data, and the output is response data in JSON format. Specifically, the search results are serialized as a JSON object and sent to the terminal as an HTTP response.

[1314] Step 6: Displaying the results

[1315] The terminal parses the search results received from the server in JSON format and displays them on the user's screen. Specifically, it parses the received JSON data and displays past cases and solutions on the interface in list or detailed view formats. The input is JSON data received from the server, and the output is in a format that the user can view on the screen.

[1316] By following these steps, users can quickly and accurately find solutions to their problems.

[1317] (Application Example 1)

[1318] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1319] In modern security systems, finding quick and appropriate countermeasures for the various security breaches users encounter is extremely difficult. This problem stems particularly from the insufficient utilization of past cases and knowledge. As a result, users spend a great deal of time and effort finding appropriate countermeasures. There is a need to solve these challenges and enable users to respond quickly to security breaches.

[1320] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1321] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, a display means for presenting the search results to the user, a similarity calculation means for calculating the similarity between the input failure event and past cases, and a recommendation presentation means for presenting recommended countermeasures based on the most similar past cases. This enables the user to obtain quick and appropriate countermeasures for the input failure event.

[1322] Definition of Terms

[1323] "User input means for entering failure events" refers to an interface provided for users to input details of failure events they encounter. This interface is used for communication between the user and the system via devices such as smartphones, computers, and tablets.

[1324] "Processing means for receiving details of a failure event and performing preprocessing" refers to a function that receives information about a failure event entered by the user, analyzes it, and performs preprocessing such as tokenization, stop word removal, and stemming.

[1325] The "search method for searching a database for past cases and countermeasures related to failure events" refers to a function that searches a database containing records of past cases and their countermeasures, based on pre-processed information about failure events. Algorithms such as the TF-IDF method and cosine similarity are used for this search.

[1326] "A means of displaying search results to the user" refers to an interface that presents the results obtained through a search in an easy-to-understand manner to the user. This interface is displayed on the device's screen.

[1327] The "similarity calculation means for calculating the similarity between an input failure event and past cases" refers to a function for calculating the similarity between a failure event entered by a user and past cases in the database. This calculation uses cosine similarity or other similarity calculation algorithms.

[1328] The "recommendation suggestion method that presents recommended countermeasures based on the most similar past cases" refers to a function that presents the user with the most similar past cases and their solutions based on a calculated similarity score. This allows the user to quickly obtain appropriate countermeasures.

[1329] Modes for carrying out the invention

[1330] This invention is a system that quickly analyzes user-inputted failure events and appropriately presents past cases and corresponding solutions. The specific implementation of this system is described below.

[1331] System Overview

[1332] This system allows users to input incidents using smartphones or other devices, processes the information, and quickly presents relevant past cases and solutions. The main components of the system include input means, processing means, search means, display means, similarity calculation means, and recommendation suggestion means.

[1333] Hardware and software to be used

[1334] Hardware: Smartphones, computers, tablets

[1335] Software: Python, scikit-learn, web browser

[1336] Program Processing Overview

[1337] 1. The user enters the error message.

[1338] Users access a dedicated application or web interface via their smartphone or computer and enter details of the problem into a text box. This input method is designed to be intuitive for users.

[1339] 2. Receiving and pre-processing of failure events

[1340] The terminal sends the user-entered error information to the server in JSON format. The server preprocesses the received text by performing tokenization, stop word removal, stemming, etc., to properly organize the text data.

[1341] 3. Database search and similarity calculation

[1342] The server uses pre-processed text data to search a database containing records of past failure events and how they were handled. Algorithms such as the TF-IDF method and cosine similarity are used in the search to calculate the similarity between the input failure event and past cases.

[1343] 4. Presentation of search results and recommendations

[1344] The server identifies the most similar past cases from the search results and generates recommended countermeasures based on them. The terminal displays the results to the user, including the relevant past cases and how they were handled.

[1345] Specific example

[1346] For example, if a user enters a problem report stating "Unauthorized access detected, warning displayed," the terminal sends this information to the server. The server performs preprocessing and a database search, and if a record of "unauthorized access detected" is found in the database, a solution such as "immediately change your password and check your login history" is suggested. In this way, the user can quickly obtain appropriate countermeasures.

[1347] Example of a prompt

[1348] "If unauthorized access is detected and a warning is displayed, what countermeasures are effective?"

[1349] This invention enables users to quickly find appropriate countermeasures and deal with failure events.

[1350] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1351] Program processing flow

[1352] Step 1: The user enters the fault report.

[1353] Users enter details of the incident into text boxes using smartphone or computer applications or web interfaces. The entered information is converted to JSON format for use in subsequent processing.

[1354] Input: Details of the incident (text)

[1355] Output: Input data in JSON format

[1356] Action: The user enters "Unauthorized access has been detected and a warning has been displayed."

[1357] Step 2: Receiving and pre-processing of the failure event

[1358] The terminal sends the input error event to the server in JSON format. The server preprocesses the received text by performing tokenization, stop word removal, stemming, etc., to properly organize the text data.

[1359] Input: Failure event data in JSON format

[1360] Output: Preprocessed text data

[1361] Operation: The server splits the received text into words such as "malicious," "access," "detect," "warning," and "display," removes unnecessary words, and converts them into core words.

[1362] Step 3: Database search and similarity calculation

[1363] The server uses pre-processed text data to search a database containing records of past failure events and their resolution methods. Algorithms such as the TF-IDF method and cosine similarity are used for the search. The server calculates the similarity between the input failure event and past cases.

[1364] Input: Preprocessed text data

[1365] Output: List of similar past cases and countermeasures

[1366] Operation: The server searches a database of past cases, extracts relevant cases based on the keyword "unauthorized access," and performs a similarity calculation.

[1367] Step 4: Presentation of search results and recommendations

[1368] The server identifies the most similar past cases from the search results and generates recommended countermeasures based on them. The terminal then displays these results to the user.

[1369] Input: List of similar past cases and countermeasures

[1370] Output: Recommended countermeasures and their display

[1371] Action: The server generates a recommendation to "change your password immediately and check your login history" and sends it to the terminal. The terminal displays this to the user.

[1372] In this way, users can quickly obtain appropriate countermeasures.

[1373] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1374] This invention provides a system that quickly analyzes user-inputted failure events and appropriately presents past cases and response methods, further incorporating an emotion engine that recognizes the user's emotions. This system includes an interface for the user to input failure events and multiple functions for processing them.

[1375] User error event input and emotion recognition

[1376] Users access the system via a web browser or dedicated application and enter details of the problem into a text box. This text box is intuitive to use and allows users to describe the problem in detail. Furthermore, an emotion engine operates to recognize emotions from the text data entered by the user.

[1377] Transmission and preprocessing of failure events

[1378] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server. The data sent is in the following format:

[1379] json

[1380] {

[1381] "event_description": "Internet connection frequently drops",

[1382] "user_emotion": "frustration"

[1383] }

[1384] Analysis of disturbance events and emotional processing

[1385] The server receives the request data and extracts a description of the incident and the user's sentiment from the JSON data. Then, it performs preprocessing on the incident description (tokenization, stop word removal, stemming). This preprocessing organizes the text data, enabling more efficient search operations.

[1386] Database search and emotionally conscious adjustments

[1387] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. Furthermore, the search results and suggested solutions are adjusted based on sentiment data recognized by the sentiment engine. For example, if a user indicates "frustration," the server prioritizes presenting solutions and procedures that can resolve the issue more quickly.

[1388] Presenting results to the user

[1389] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own. Advice and warnings tailored to the user's feelings are also displayed.

[1390] Specific example

[1391] For example, suppose a user enters a problem report such as "My internet connection keeps dropping," and the emotion engine detects "frustration." The terminal sends this to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this will be presented to the user. Furthermore, emotion-based advice such as "If you need a quick solution, we recommend contacting manufacturer support" will also be displayed.

[1392] In this way, by quickly analyzing the problems users encounter and providing appropriate solutions, as well as offering information that takes users' feelings into consideration, troubleshooting can be carried out more efficiently, and an improvement in user satisfaction can be expected.

[1393] The following describes the processing flow.

[1394] Step 1:

[1395] The user opens the system interface and enters details of the problem into the text box. For example, they might enter, "The internet connection frequently drops."

[1396] Step 2:

[1397] The device retrieves text entered by the user and uses an emotion engine to recognize the emotion from the text. In this case, the emotion engine detects "frustration."

[1398] Step 3:

[1399] The terminal converts the entered text and recognized emotions into JSON-formatted request data. The format will be as follows:

[1400] json

[1401] {

[1402] "event_description": "Internet connection frequently drops",

[1403] "user_emotion": "frustration"

[1404] }

[1405] Step 4:

[1406] The device sends request data in JSON format to the server.

[1407] Step 5:

[1408] The server receives the request data and extracts "event_description" (description of the incident) and "user_emotion" (user's emotion) from the JSON data.

[1409] Step 6:

[1410] The server performs preprocessing on "event_description". The following processes are carried out:

[1411] Tokenization: Dividing text into individual words. Examples: "Internet," "connection," "frequent," "disconnect."

[1412] Stop word removal: Remove words with little meaning. For example, "ga" is removed.

[1413] Stemming: Extracting the base form of a word. "Connection" becomes "connection," and "break" becomes "break."

[1414] Step 7:

[1415] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses the TF-IDF method and cosine similarity.

[1416] Step 8:

[1417] The server identifies the most similar past cases and their corresponding solutions from the search results, and creates a response data in JSON format. Furthermore, based on the emotions recognized by the emotion engine, it adds advice for quick action if the user is irritated.

[1418] json

[1419] {

[1420] "past_event": "The internet connection frequently drops due to insufficient router firmware updates",

[1421] "solution": "Update the router's firmware to the latest version",

[1422] "emotion_based_advice": "If you need a quick solution, we recommend contacting manufacturer support."

[1423] }

[1424] Step 9:

[1425] The server sends response data to the terminal.

[1426] Step 10:

[1427] The terminal receives response data from the server, analyzes it, and displays it on the screen in a format that is easy for the user to understand. For example, it might display: "In past cases, there have been problems with frequent internet connection drops due to insufficient router firmware updates. As a solution, it is recommended to update the router firmware to the latest version. If a quick solution is needed, it is recommended to contact manufacturer support."

[1428] This allows users to quickly resolve problems in their environment based on the information presented and emotionally-driven advice.

[1429] (Example 2)

[1430] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1431] Conventional failure event analysis systems not only analyze the details of failure events entered by users, but also fail to adequately provide solutions that take into account the user's feelings. As a result, this can increase user dissatisfaction. Therefore, a system is needed that not only analyzes the failure events entered by users but also provides information that responds to the user's feelings, thereby improving user satisfaction.

[1432] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1433] In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving the details and emotions of the input failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event and adjusting the search results based on emotions, and a display means for presenting the adjusted search results to the user. This enables the user to analyze the failure event and provide information that takes emotions into consideration.

[1434] "Input means" refers to an interface for users to input details of a failure event into the system, and includes web browsers and dedicated applications.

[1435] The "processing means" is a component that receives the details of the input failure event and the user's sentiment data, and has the function of organizing and analyzing the text data, performing tokenization, stop word removal, and stemming.

[1436] The "search method" involves searching a database based on processed text data to identify past failure cases and their solutions, and adjusting the search results based on the user's sentiment. It utilizes methods such as TF-IDF and cosine similarity.

[1437] "Display means" refers to an interface for presenting search results and adjusted responses to the user, and includes web screens and application displays.

[1438] "Emotions" refer to the psychological state expressed by the user in relation to the incidents they have entered, and are part of the data that the system analyzes and considers.

[1439] "Preprocessing" refers to a series of processes to organize input data into an analyzable format, specifically including tokenization, stop word removal, and stemming.

[1440] A "database" is a place where information is collected, recording past incidents and countermeasures for failures, and is accessed through search methods.

[1441] "Tokenization" is the process of dividing text data into words and phrases, and it is performed in the initial stages of text analysis.

[1442] "Stop word removal" is the process of removing words that are considered to be of low importance during searching or analysis (for example, "no" or "toita").

[1443] Stemming is the process of extracting the root of a word, and it is performed to combine words with different forms into a single word.

[1444] The "TF-IDF method" is a numerical method for calculating the importance of words within a document and evaluating their relevance.

[1445] "Cosine similarity" is a method for calculating the similarity between documents based on a vector space, and is used to improve the accuracy of search results.

[1446] This invention provides a system that quickly analyzes user-inputted failure events, appropriately presents past cases and solutions, and further incorporates an emotion engine that recognizes the user's emotions. This system is implemented using the following hardware and software.

[1447] Hardware and software used

[1448] The system includes terminals (such as PCs and smartphones) for user access and servers for processing.

[1449] Input Interface: Users access the system via a web browser or dedicated application and input details of the failure.

[1450] Emotion Engine: Uses the Emotion Recognition API (EmotionAPI) to recognize emotions from text data entered by the user.

[1451] Preprocessing module: The server uses the Natural Language Processing Library (NLTK) to perform tokenization, stop word removal, and stemming on the received text data.

[1452] Database: A relational database (MySQL) is used to store response and accumulated failure event data.

[1453] Search algorithm: When evaluating the relevance of text data and performing searches, methods such as TF-IDF and cosine similarity are used.

[1454] Display Interface: A front-end framework (React.js) is used to present search results and solutions to the user.

[1455] Specific operation of the system

[1456] 1. User error event input and emotion recognition

[1457] Users access the system using a web browser or a dedicated application and enter details of the problem into a text box.

[1458] The emotion engine recognizes emotions from text data entered by the user and generates emotion data (for example, "frustration").

[1459] 2. Transmission of failure events and preprocessing

[1460] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server.

[1461] The server uses "Express.js" to parse the JSON data and extract descriptions of the failure events and sentiment data.

[1462] The server uses the Natural Language Processing Library (NLTK) to perform tokenization, stop word removal, and stemming of text data.

[1463] 3. Database search and adjustment based on sentiment.

[1464] The server searches the MySQL database based on the pre-processed text data.

[1465] The TF-IDF method and cosine similarity are used for the search.

[1466] The server also adjusts search results based on sentiment data, prioritizing responses that correspond to the emotions expressed by the user.

[1467] 4. Presenting results to the user

[1468] The server sends response data to the terminal, including relevant past cases, how they were handled, and emotionally sensitive advice.

[1469] The device uses "React.js" to display this information on the user's screen.

[1470] Specific examples and prompt statements

[1471] For example, suppose a user enters a problem report such as "My internet connection frequently drops," and the emotion engine detects "frustration." The terminal sends this to the server, which parses the JSON data. If the database contains a record of a similar problem occurring in the past due to insufficient router firmware updates, and the suggested solution is to "update the router firmware to the latest version," this will be presented to the user. Furthermore, emotion-based advice such as "If you need a quick solution, we recommend contacting manufacturer support" will also be displayed.

[1472] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1473] Step 1:

[1474] Users enter error messages.

[1475] Specific actions

[1476] Users access the system using a web browser or a dedicated application and enter details of the problem into a text box. For example, they might enter "Internet connection frequently drops." This entered text becomes the input data for the next process.

[1477] Input and Output

[1478] Input: Details of the incident (manually entered by the user)

[1479] Output: Text data (description of the failure event)

[1480] Step 2:

[1481] Recognition of emotions

[1482] Specific actions

[1483] The server receives the text data entered by the user and sends it to the Emotion API. The Emotion API extracts emotions such as "frustration" from the text data. This emotion data is then passed on to the next process.

[1484] Input and Output

[1485] Input: Detailed text of the failure event

[1486] Output: Sentiment data (e.g., "frustration")

[1487] Step 3:

[1488] Sending a failure event

[1489] Specific actions

[1490] The device converts the text data entered by the user and the emotion data returned by the emotion recognition API into JSON-formatted request data. Specifically, it generates JSON data like the following:

[1491] json

[1492] {

[1493] "event_description": "Internet connection frequently drops",

[1494] "user_emotion": "frustration"

[1495] }

[1496] Send this JSON data to the server.

[1497] Input and Output

[1498] Input: Detailed text and sentiment data of the incident.

[1499] Output: JSON data

[1500] Step 4:

[1501] JSON data parsing and preprocessing

[1502] Specific actions

[1503] The server parses the received JSON data and extracts the error description text and user sentiment data. This process uses "Express.js". Next, the error description text undergoes tokenization, stop word removal, and stemming. The "nltk" library is used to organize the text data into a parseable format.

[1504] Input and Output

[1505] Input: JSON data

[1506] Output: Preprocessed text data

[1507] Step 5:

[1508] Database Search

[1509] Specific actions

[1510] The server searches the MySQL database based on pre-processed text data. The search uses methods such as TF-IDF and cosine similarity to identify past cases related to the failure event and their corresponding solutions. If necessary, the search results are refined to take user sentiment data into consideration.

[1511] Input and Output

[1512] Input: Preprocessed text data and sentiment data

[1513] Output: Search results (past cases and countermeasures)

[1514] Step 6:

[1515] Displaying search results

[1516] Specific actions

[1517] The server sends search results to the device, which then displays them on the user's screen. Specifically, the search results, which include suggested actions and advice tailored to the user's emotions, are displayed using a front-end framework (React.js). For example, a past case "The problem was caused by insufficient router firmware updates" and the suggested solution "Update the router firmware to the latest version" might be displayed.

[1518] Input and Output

[1519] Input: Search Results

[1520] Output: Display of results to the user

[1521] (Application Example 2)

[1522] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1523] In recent years, with the proliferation of food delivery services, users are increasingly encountering various problems related to delivery. For example, there are cases of delayed orders, cold food, and misdeliveries. While there is a need to respond quickly and appropriately to these problems, conventional systems have struggled to provide solutions that take user feelings into consideration. Furthermore, there is a lack of systems that can effectively analyze the details of problems entered by users and suggest appropriate solutions based on past cases. This leads to increased user stress and dissatisfaction with the service.

[1524] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an input means for the user to input a failure event, a processing means for receiving details of the failure event and performing preprocessing, a search means for searching a database for past cases and countermeasures related to the failure event, a display means for presenting the search results to the user, an emotion recognition means for recognizing emotions, and an adjustment means for adjusting the presentation method of search results and countermeasures based on emotion data. This enables rapid analysis of delivery-related troubles entered by the user, the presentation of appropriate solutions based on past cases, and the provision of information that takes the user's emotions into consideration.

[1525] A "user" is the entity that accesses the system and inputs error reports.

[1526] A "failure event" refers to a problem or trouble that occurs while using a system or service.

[1527] An "input mechanism" is a function that provides an interface for users to input fault events into the system.

[1528] The "processing means" refers to a function that receives details of a failure event entered by the user and performs preprocessing on the data.

[1529] "Search method" refers to a function that searches a database for past cases and countermeasures related to failure events, based on pre-processed data.

[1530] "Display means" refers to functions for presenting search results to the user.

[1531] "Emotion recognition means" refers to a function that recognizes emotions from text data entered by the user.

[1532] "Adjustment mechanism" refers to a function that adjusts the way search results and response methods are presented based on sentiment data.

[1533] "Past incidents" refer to data that records past incidents and how they were handled.

[1534] "Response method" refers to the procedures and methods for dealing with a failure or malfunction.

[1535] This invention is a system that quickly analyzes user-inputted problems and appropriately presents past cases and solutions, further incorporating an emotion engine that recognizes the user's emotions. This invention is particularly applicable to troubleshooting in food delivery services.

[1536] User error event input and emotion recognition

[1537] Users access the system via a smartphone application and enter details of delivery problems into a text box. This text box is intuitive for users to use and allows for detailed descriptions of problems. Furthermore, an emotion engine operates to recognize emotions from the text data entered by the user.

[1538] Transmission and preprocessing of failure events

[1539] The device converts the text entered by the user and the sentiment data recognized by the sentiment engine into JSON-formatted request data and sends it to the server. For example, the following data is sent:

[1540] json

[1541] {

[1542] "event_description": "The delivery was late, and the order got cold."

[1543] "user_emotion": "frustration"

[1544] }

[1545] Analysis of disturbance events and emotional processing

[1546] The server receives the request data and extracts a description of the incident and the user's sentiment from the JSON data. Then, it performs preprocessing on the incident description (tokenization, stop word removal, stemming). This preprocessing organizes the text data, enabling more efficient search operations.

[1547] Database search and emotionally conscious adjustments

[1548] The server searches a database containing records of past failures and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. Furthermore, the search results and suggested solutions are adjusted based on sentiment data recognized by the sentiment engine. For example, if a user indicates "frustration," the server prioritizes presenting solutions and procedures that can resolve the issue more quickly.

[1549] Presenting results to the user

[1550] After the search results are obtained, the server sends response data to the terminal, including relevant past cases and how they were handled. The terminal displays this information on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve the problem on their own. Advice and warnings tailored to the user's feelings are also displayed.

[1551] Specific example

[1552] For example, suppose a user enters a problem report stating, "The delivery was late and the order got cold," and the emotion engine detects "frustration." The terminal sends this to the server, which performs preprocessing and a database search. If the database contains a record of a similar problem occurring in the past, where a re-cooking request was made and the order was delivered directly, and the suggested solution is "request re-cooking," this is presented to the user. Furthermore, emotion-based advice such as "We recommend issuing an apology coupon" is also displayed. Examples of prompt messages include:

[1553] A user posted the following problem: "The delivery was late and my order got cold 😡"

[1554] Based on this information, search for past cases and solutions, and present solutions and emotion-based advice in the following output format.

[1555] Problem: {Question content}

[1556] Solution:

[1557] 1. {Solution 1}

[1558] 2. {Solution 2}

[1559] Advice: {Emotion-based advice}

[1560] This makes it possible to quickly analyze delivery-related problems that users encounter, provide appropriate solutions, and offer information that is sensitive to the user's feelings.

[1561] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1562] Step 1:

[1563] The user enters details of a delivery issue into a text box in the smartphone application. This input includes problems such as delivery delays, misdeliveries, or cold food. When the user enters the problem into the text box and clicks the submit button, the input data is sent to the device. The input data is a text-based description of the problem.

[1564] Step 2:

[1565] The device receives text data entered by the user and uses an emotion engine to recognize the user's emotions. This process estimates emotions such as "frustration" from emojis like "😡" and the content of the text. The recognition results are prepared in JSON format along with the emotion data. The input is the user's text data, and the output is JSON data including emotions.

[1566] Step 3:

[1567] The terminal sends the prepared JSON data to the server. The data sent will be in the following format:

[1568] json

[1569] {

[1570] "event_description": "The delivery was late, and the order got cold."

[1571] "user_emotion": "frustration"

[1572] }

[1573] The input is JSON data containing emotions, and the output is the status indicating whether the transmission to the server was successful.

[1574] Step 4:

[1575] The server extracts a description of the incident and user sentiment data from the received JSON data. The extracted data is used in the next analysis step. The input is the received JSON data, and the output is a text-formatted problem description and sentiment data.

[1576] Step 5:

[1577] The server preprocesses the description of the failure event. This preprocessing includes tokenization (separating the text into individual words), stop word removal (removing frequently occurring, meaningless words), and stemming (converting words back to their base forms). The input is the problem description text, and the output is the preprocessed text data.

[1578] Step 6:

[1579] The server searches a database containing records of past failure events and their solutions based on pre-processed text. The search uses methods such as TF-IDF and cosine similarity. The input is pre-processed text data, and the output is a list of similar past cases and their solutions.

[1580] Step 7:

[1581] The server adjusts the way search results and suggested solutions are presented based on sentiment data. For example, if a user indicates "frustration," it prioritizes providing quick solutions. This adjustment uses generative AI models and prompts. The input is a list of similar past cases and solutions, along with sentiment data, and the output is a list of adjusted solutions.

[1582] Step 8:

[1583] The server sends response data to the terminal, including tailored solutions. This data includes specific steps and sentiment-based advice. The input is a list of tailored solutions, and the output is the status of the transmission to the terminal.

[1584] Step 9:

[1585] The terminal displays response data received from the server on the user's screen. The display includes details of past cases and specific solutions, providing clues for the user to solve problems independently. Advice and warnings tailored to the user's emotional state are also displayed. Input is the response data, and output is the display to the user.

[1586] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1587] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1588] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1589] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1590] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1591] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1592] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1593] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1594] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1595] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1596] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1597] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1598] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1599] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1600] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1601] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1602] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1603] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1604] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1605] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1606] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1607] The following is further disclosed regarding the embodiments described above.

[1608] (Claim 1)

[1609] An input method for the user to enter a problem,

[1610] A processing means that receives details of a failure event and performs preprocessing,

[1611] A search method for searching a database for past cases and countermeasures related to failure events,

[1612] A means of displaying search results to the user,

[1613] A system that includes this.

[1614] (Claim 2)

[1615] The system according to claim 1, characterized in that the preprocessing means includes tokenization, stop word removal, and stemming.

[1616] (Claim 3)

[1617] The system according to claim 1, characterized in that the search means uses the TF-IDF method or cosine similarity.

[1618] "Example 1"

[1619] (Claim 1)

[1620] An input method for the user to enter a problem,

[1621] A processing means that receives details of a failure event and performs preprocessing,

[1622] A search method for searching a database for past cases and countermeasures related to failure events,

[1623] A means of displaying search results to the user,

[1624] A system that includes this.

[1625] (Claim 2)

[1626] The system according to claim 1, characterized in that the preprocessing means includes tokenization, stop word removal, and stemming.

[1627] (Claim 3)

[1628] The system according to claim 1, characterized in that the search means uses the TF-IDF method or cosine similarity.

[1629] (Claim 4)

[1630] The system according to claim 1, characterized in that, as a means for inputting a failure event, the user inputs details into a text box via a web browser or a dedicated application.

[1631] (Claim 5)

[1632] The system according to claim 1, further comprising a display means for receiving search results in JSON format from a data access means and displaying them on a user's terminal.

[1633] (Claim 6)

[1634] The system according to claim 1, characterized in that the search means includes an algorithm that identifies past cases and corresponding methods using the TF-IDF method or cosine similarity based on preprocessed text.

[1635] "Application Example 1"

[1636] (Claim 1)

[1637] An input method for the user to enter a problem,

[1638] A processing means that receives details of a failure event and performs preprocessing,

[1639] A search method for searching a database for past cases and countermeasures related to failure events,

[1640] A means of displaying search results to the user,

[1641] A similarity calculation means for calculating the similarity between an input failure event and past cases,

[1642] A recommendation system that presents suggested countermeasures based on the most similar past cases,

[1643] A system that includes this.

[1644] (Claim 2)

[1645] The system according to claim 1, characterized in that the preprocessing means includes tokenization, stop word removal, and stemming.

[1646] (Claim 3)

[1647] The system according to claim 1, characterized in that the search means uses the TF-IDF method or cosine similarity.

[1648] "Example 2 of combining an emotion engine"

[1649] (Claim 1)

[1650] An input method for the user to enter a problem,

[1651] A processing means that receives the details and emotions of the input failure event and performs preprocessing,

[1652] A search method that searches a database for past cases and response methods related to incidents and adjusts the search results based on sentiment,

[1653] A display method for presenting adjusted search results to the user,

[1654] A system that includes this.

[1655] (Claim 2)

[1656] The system according to claim 1, characterized in that the preprocessing means includes tokenization, stop word removal, and stemming.

[1657] (Claim 3)

[1658] The system according to claim 1, characterized in that the search means uses the TF-IDF method or cosine similarity.

[1659] "Application example 2 when combining with an emotional engine"

[1660] (Claim 1)

[1661] An input method for the user to enter a problem,

[1662] A processing means that receives details of a failure event and performs preprocessing,

[1663] A search method for searching a database for past cases and countermeasures related to failure events,

[1664] A means of displaying search results to the user,

[1665] A means of recognizing emotions,

[1666] An adjustment mechanism that adjusts the presentation of search results and response methods based on sentiment data,

[1667] A system that includes this.

[1668] (Claim 2)

[1669] The system according to claim 1, characterized in that the preprocessing means includes tokenization, stop word removal, and stemming.

[1670] (Claim 3)

[1671] The system according to claim 1, characterized in that the search means uses the TF-IDF method or cosine similarity.

[1672] (Claim 4)

[1673] The system according to claim 1, characterized in that the adjustment means displays advice or warnings based on the user's emotions. [Explanation of Symbols]

[1674] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An input method for the user to enter a problem, A processing means that receives details of a failure event and performs preprocessing, A search method for searching a database for past cases and countermeasures related to failure events, A means of displaying search results to the user, A system that includes this.

2. The system according to claim 1, characterized in that the preprocessing means includes tokenization, stop word removal, and stemming.

3. The system according to claim 1, characterized in that the search means uses the TF-IDF method or cosine similarity.

Images