system

Abstract

Provide a system. A means for receiving material data input by a user; means for detecting missing portions of evidence based on the document data; means for detecting a missing part of the explanation based on the material data; means for displaying the missing portion detection result to a user; A system including:

Description

[Technical Field]

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

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

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

[0004] Traditional document creation processes lack the ability to automatically detect missing evidence or explanations, so it takes a lot of time and effort to check whether the content of the document is sufficient. Furthermore, document review and revision work is also done manually, so there is a high risk of missing details being overlooked. This leads to problems such as a decline in document quality and a deterioration in the efficiency of business processes. [Means for solving the problem]

[0005] To solve the above problems, the present invention proposes the following means. A system is provided that includes a means for receiving document data input by a user, a means for detecting missing parts of evidence based on the document data, a means for detecting missing parts of explanation based on the document data, and a means for displaying the results of the missing parts detection to the user. This system makes it possible to automatically point out missing parts of evidence or explanation when creating documents, thereby improving the quality of documents and work efficiency. Furthermore, document data is sent to a server in JSON format, and by checking whether the document data contains the word "evidence" as a means for detecting missing parts of evidence, missing parts can be detected specifically and efficiently.

[0006] "User" means an individual or organization that operates the system, inputs material data, submits data, and reviews results.

[0007] "Document data" refers to text information of content that users input into the system, such as presentation slides and requirements definition documents.

[0008] "Evidence" refers to the evidence or supporting information that should be shown in the data, and the word that refers to it.

[0009] "Explanation" refers to the specific content and detailed information that should be shown within the document data.

[0010] A "server" is a computer system that receives material data from a user, analyzes it to detect missing parts, and returns the results to the client terminal.

[0011] A "gap" is missing or insufficient evidence or explanatory information within the data source.

[0012] "Detection" is the process of identifying and identifying gaps in the material data based on specific criteria.

[0013] The "JSON format" is a text-based data exchange format that represents data as key-value pairs.

[0014] A "client terminal" is an electronic device such as a computer or smartphone that is operated by a user to send document data to a server and receive results from the server.

[0015] An "HTTP POST request" is an Internet protocol that allows a client terminal to send data to a server. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention is a system that automatically detects missing evidence or explanations in presentation slides, requirements definition documents, and other documents, and notifies the user of these. This system is configured as follows.

[0038] First, the user inputs the document data from their own device. The document data is written data such as presentation slides and requirements specifications, and is input in text format. Once the user has finished inputting the document data, the device converts the data into JSON format and sends it to a specific endpoint on the server as an HTTP POST request.

[0039] The server receives an HTTP POST request from the device and extracts the JSON-formatted document data from the request body. Based on the extracted document data, the server analyzes the content of the document. This analysis focuses on detecting missing pieces of evidence and explanation.

[0040] To detect missing evidence, the server first checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Evidence is missing."

[0041] To detect missing explanations, the data is divided into words and the total number of words is counted. If the number of words is less than 100, the server generates a message saying "There is insufficient explanation."

[0042] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[0043] The terminal receives the response from the server and displays the analysis results to the user. The display includes a message pointing out specific areas that are lacking. The user can use this information to correct the document.

[0044] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. The user can then view the results and revise the document.

[0045] The system of the present invention can automatically detect missing evidence and explanations and quickly and effectively improve the quality of documents, thereby significantly reducing the manual review work required in the past and improving the efficiency of business processes.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] Users use their devices to input data, specifically, the contents of presentation slides and requirements specifications, using a text editor or a dedicated web form.

[0049] Step 2:

[0050] When the user has finished entering the document data, he or she clicks the "Send" button on the terminal. This operation causes the document data to proceed to the next process.

[0051] Step 3:

[0052] The device converts the document data into JSON format. The program on the device converts the document content into a format such as {"document": "document content here"}.

[0053] Step 4:

[0054] The device sends the JSON-formatted data to the server as an HTTP POST request, which is sent to a specific endpoint on the server, such as / analyze.

[0055] Step 5:

[0056] The server receives an HTTP POST request and extracts the document data in JSON format from the request body.

[0057] Step 6:

[0058] The server calls the analyze_document function to analyze the document data, which detects missing evidence and explanations based on the document data.

[0059] Step 7:

[0060] The server calls the find_evidence_issues function to check whether the document data contains the word "evidence." If it does not, it generates a warning message saying "Insufficient evidence."

[0061] Step 8:

[0062] The server calls the find_explanation_issues function, splits the document data into words, and counts the number of words. If the number of words is less than 100, it generates a warning message saying "Insufficient explanation."

[0063] Step 9:

[0064] The server compiles the results of the missing evidence and explanation in JSON format, including a detailed message of the missing part.

[0065] Step 10:

[0066] The server returns the generated analysis results to the client terminal as an HTTP response, which includes a 200 status code (OK) and the analysis results.

[0067] Step 11:

[0068] The terminal receives the HTTP response and extracts the analysis results in JSON format from the response body.

[0069] Step 12:

[0070] The device displays the extracted analysis results to the user. Specifically, a warning message such as "Insufficient evidence" or "Insufficient explanation" is displayed on the screen.

[0071] Step 13:

[0072] The user can check the missing parts displayed and correct the materials. If necessary, they can re-enter new material data and resubmit it to the system.

[0073] Through the above steps, missing parts of evidence or explanations in documents such as presentation slides or requirements specifications are efficiently detected, allowing users to quickly and effectively revise the documents.

[0074] Example 1

[0075] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0076] Conventional document verification systems require users to manually check for missing evidence and explanations after creating documents, which is time-consuming and labor-intensive. Human error can easily lead to oversights, potentially resulting in a decline in document quality. Furthermore, an efficient method is required when verifying multiple documents in a short period of time.

[0077] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0078] In this invention, the server includes means for inputting material data from a user, means for converting the material data into JSON format, means for transmitting the JSON-formatted material data to the server as an HTTP POST request, means for receiving the transmitted material data and extracting the JSON-formatted material data from the request body, means for detecting missing parts of evidence based on the material data, means for detecting missing parts of explanation based on the material data, means for generating results of the missing evidence and missing explanation in JSON format and returning the analysis results to the terminal, and means for displaying the missing part detection results to the user. This makes it possible to automatically detect missing parts of evidence and explanation and quickly and effectively improve the quality of materials.

[0079] "User" means an individual or organization that uses this system.

[0080] "Document data" refers to document information such as presentation slides and requirements definition documents, and is text data entered by the user.

[0081] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and is a lightweight data exchange format for describing data in a structured manner.

[0082] An "HTTP POST request" is a method of sending data using the Hypertext Transfer Protocol, and is a request to send data to a server.

[0083] A "server" is a computer system that receives requests via a network and analyzes the data.

[0084] "Evidence" refers to the evidence or reasoning provided to support a fact or claim within a document.

[0085] An "endpoint" refers to a server-side URL or URI that provides a specific function when communicating.

[0086] The "request body" is the data payload portion included in the HTTP request, and is the portion that contains the content of the document data.

[0087] "Number of words" refers to the result of counting the total number of words in the material data.

[0088] "Analysis results" refers to data compiled in JSON format that identifies the results of detection of insufficient evidence or explanation based on document data.

[0089] A "response" refers to response data returned from a server to a client.

[0090] A "client terminal" is a computer system used by a user, and is a device that communicates with a server to send material data and receive analysis results.

[0091] "Display" refers to visually providing the analysis results to the user, specifically to displaying a message on the screen.

[0092] The present invention is a system that automatically detects missing evidence and explanations in document data and notifies the user. This system operates in cooperation with both the user terminal and the server.

[0093] First, the user inputs the data using their own device. This data is entered in text format as document information such as presentation slides or requirements definition documents. For example, it might look like this: "This is the outline of a new project. The objective is to meet market needs. The next step is to complete the requirements definition and design phases."

[0094] The terminal then converts the input data into JSON format and sends it as an HTTP POST request to a specific endpoint on the server, using common software libraries (e.g., Python's json library or requests library) for the conversion and transmission.

[0095] The server receives the HTTP POST request sent from the device. It extracts the JSON-formatted document data from the received request and prepares it for analysis. The analysis begins by checking whether the document data contains the word "evidence." If it does not, it generates a message saying "Insufficient evidence."

[0096] The server then divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a message saying "Insufficient explanation." As a result, it generates a JSON format summary of the results of insufficient evidence and explanation, and returns the analysis results to the terminal as an HTTP response.

[0097] The terminal receives the response from the server and displays the analysis results to the user, including a message indicating which specific parts are missing, so that the user can correct the document based on this information.

[0098] As a concrete example, if a user inputs the following document data, "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase," the document data contains no evidence and lacks explanation. When this document data is analyzed by the server, the server generates messages such as "Evidence is insufficient" and "Explanation is insufficient" and returns them to the terminal. The user can refer to the analysis results and revise the document.

[0099] When using a generative AI model, you can use the following as a prompt:

[0100] "When a user enters the following data, such as 'This is a description of a new project. The objective is to address a market need. The next steps are to define the requirements and complete the design phase,' please write Python code that will enable the system to detect missing evidence and explanations and generate analysis results."

[0101] The present invention makes it possible to automate the process of detecting insufficient evidence and explanations during the document creation process, thereby improving the quality of documents and increasing the efficiency of the work.

[0102] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0103] Step 1:

[0104] The user inputs the data.

[0105] The user uses an input form on their own device to input data such as presentation slides and requirements definition documents in text format. In concrete terms, the user might input the following: "This is an outline of a new project. The objective is to meet market needs. The next step is to complete the requirements definition and design phases." This input is captured on the device. Input: Data (text format) Output: Data (text format)

[0106] Step 2:

[0107] The device converts the data into JSON format.

[0108] The device converts the captured data into JSON format. Specifically, the device uses a conversion library to serialize the data into JSON format. Input: Data (text format) Output: Data (JSON format)

[0109] Step 3:

[0110] The device sends an HTTP POST request to the server

[0111] The terminal sends the converted JSON data as an HTTP POST request to a specific endpoint on the server. Specifically, the terminal uses the HTTP library to construct the request header and body and send it to the server. Input: Document data (JSON format) Output: HTTP POST request (JSON data)

[0112] Step 4:

[0113] The server receives the data.

[0114] The server receives the HTTP POST request sent from the terminal and extracts the document data in JSON format from the request body. Specifically, the server analyzes the request and loads the document data into memory. Input: HTTP POST request (JSON data) Output: Document data (JSON format)

[0115] Step 5:

[0116] The server analyzes the data.

[0117] The server analyzes the data and detects missing evidence and explanations. This analysis process includes detecting missing evidence and missing explanations. Input: Data (JSON format) Output: Messages about missing evidence and missing explanations

[0118] Step 6:

[0119] Detecting evidence gaps

[0120] The server checks whether the word "evidence" is included in the document data. Specifically, it performs a string search using a text analysis library. If it is not included, it generates a message saying "Insufficient evidence." Input: Document data (JSON format) Output: Insufficient evidence message

[0121] Step 7:

[0122] Detecting Missing Explanations

[0123] The server splits the data into words and counts the total number of words. Specifically, it uses a text tokenization library to split the data into words and count the total number. If the number of words is less than 100, it generates a message saying "Insufficient explanation." Input: Data (JSON format) Output: Insufficient explanation message

[0124] Step 8:

[0125] The server generates the analysis results.

[0126] The server aggregates messages with insufficient evidence and insufficient explanation and generates analysis results in JSON format. Input: messages with insufficient evidence, messages with insufficient explanation Output: analysis results (JSON format)

[0127] Step 9:

[0128] The server returns the analysis results to the device.

[0129] The server returns the generated analysis results to the terminal as an HTTP response. Specifically, the server uses an HTTP library to construct the response header and body and return the response. Input: Analysis results (JSON format) Output: HTTP response (analysis results)

[0130] Step 10:

[0131] The device displays the analysis results.

[0132] The terminal receives the response from the server and displays the analysis results to the user. Specifically, the terminal uses a UI component to visually display the analysis results. Input: HTTP response (analysis results) Output: Display of analysis results

[0133] (Application example 1)

[0134] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0135] In the past, store staff found it difficult to provide customers with reliable information when talking to customers or creating promotional materials due to a lack of evidence or explanation for the content. This led to missed sales opportunities and a decline in customer satisfaction. Solving this issue was an urgent need, especially in store operations, where quick responses on-site are required.

[0136] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0137] In this invention, the server includes means for receiving material data input by a user, means for detecting missing portions of evidence based on the material data, means for detecting missing portions of explanation based on the material data, means for automatically detecting missing portions of evidence and explanation based on the text of customer service talks and promotional materials, and means for displaying the results of the detection of missing portions to the user, thereby enabling store staff to quickly and efficiently create reliable customer service talks and promotional materials that include sufficient evidence and explanation.

[0138] A "user" is someone who uses this system to input material data and utilizes the results of evidence and explanation detection.

[0139] "Document data" refers to written data such as presentation slides, requirements definition documents, customer service talks, and sales promotion materials, which are input by users into the system.

[0140] "Evidence" refers to evidence or data used to support claims or explanations in source data.

[0141] "Means for detecting missing evidence" refers to the function of checking whether evidence is contained in the document data and detecting if evidence is missing.

[0142] "Means for detecting insufficient explanations" refers to a function that checks whether the explanations in the document data are sufficient and detects any insufficiency of the explanations.

[0143] "Customer service talk" refers to verbal explanations and guidance given by store staff to customers.

[0144] "Sales promotion materials" are materials intended to promote sales of products, and are text data that users can input into the system.

[0145] The "means for displaying" refers to a means for visually outputting to the user the evidence received from the server and the results of detection of missing parts of the explanation.

[0146] "Mobile device" refers to a portable computer device such as a smartphone or tablet.

[0147] "Server" refers to a computer system that receives document data sent by users and analyzes the data to detect missing evidence or explanations.

[0148] The present invention is a system that automatically detects missing evidence and explanations based on document data entered by a user, and is intended for use in brick-and-mortar stores in particular. A specific description of an embodiment of the present invention is given below.

[0149] This system mainly uses smartphones, tablets, and cloud servers. Users input text for customer service talk and sales promotion materials from their own devices, and the input data is converted to JSON format and sent to the server.

[0150] Hardware and Software Used

[0151] Smartphone / tablet device: ANDROID (registered trademark) or iOS device

[0152] Server: Cloud server (AWS (registered trademark), Google (registered trademark), Microsoft (registered trademark), Azure (registered trademark), etc.)

[0153] API calls: Communicating with the server using HTTP requests

[0154] Natural Language Processing (NLP) libraries: spaCy, NLTK, or GPT-4® series (OpenAI® API)

[0155] Program processing

[0156] Input and submit data

[0157] Users input text data such as customer service chat and sales promotion materials in text format through the application on their device. This data is automatically converted to JSON format and sent to the cloud server as an HTTP POST request.

[0158] Data analysis on the server

[0159] The server parses the received JSON data, specifically performing the following steps:

[0160] 1. Evidence detection:

[0161] Check whether the word "evidence" is included in the source data.

[0162] If not, generate a "missing evidence" message.

[0163] 2. Description detection:

[0164] The data is divided into words and the total number of words is counted.

[0165] If the word count is less than 100, generate a "Not enough description" message.

[0166] The generated detection results are packaged again in JSON format and sent to the user's device as an HTTP response.

[0167] Displaying the results

[0168] The user device receives the detection results sent from the server and visually displays them, including a message indicating which specific parts are missing.

[0169] Examples and prompts

[0170] For example, a store staff member may enter, "This product uses the latest technology." When this document data is sent to the server, it is detected as lacking evidence and a message is displayed saying, "There is insufficient evidence. Please add references or market data."

[0171] Examples of prompt sentences

[0172] This product uses the latest technology.

[0173] This text is entered as data and analyzed on the server.

[0174] Through this system, store staff can quickly and efficiently create reliable customer service talks and promotional materials that are fully packed with evidence and explanations, which is expected to increase sales and customer satisfaction.

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1:

[0177] The user starts the application on their own device and inputs text data for customer service conversations and sales promotion materials. The input text data is saved on the user's device.

[0178] input:

[0179] Text data of customer service talk and promotional materials

[0180] output:

[0181] Input text data stored on the device

[0182] Specific behavior:

[0183] The user enters text into an application input field and presses the "Submit" button.

[0184] Step 2:

[0185] The terminal converts the input text data into JSON format, which makes the data suitable for sending to the server.

[0186] input:

[0187] Input text data stored on the device

[0188] output:

[0189] Data converted to JSON format

[0190] Specific behavior:

[0191] Format text data into JSON format within the device application.

[0192] Step 3:

[0193] The terminal sends the data converted into JSON format to the cloud server as an HTTP POST request.

[0194] input:

[0195] Data converted to JSON format

[0196] output:

[0197] Data sent as an HTTP POST request

[0198] Specific behavior:

[0199] The device generates an HTTP POST request and sends it to a specific endpoint on the cloud server.

[0200] Step 4:

[0201] The server receives the HTTP POST request, extracts the JSON data from the request body, and prepares this data for parsing.

[0202] input:

[0203] JSON data included in HTTP POST requests

[0204] output:

[0205] JSON data prepared for parsing

[0206] Specific behavior:

[0207] The server reads the HTTP request body and passes the JSON data to the parsing process.

[0208] Step 5:

[0209] The server uses NLP libraries (e.g., spaCy, NLTK, GPT-4) to detect missing evidence and explanations in the material data.

[0210] Evidence detection: Checks whether the word "evidence" is included in the data. If not, generates a message saying "Insufficient evidence."

[0211] Description detection: Counts the number of words in the data and generates a "description is insufficient" message if there are fewer than 100 words.

[0212] input:

[0213] JSON data prepared for parsing

[0214] output:

[0215] Findings of missing evidence and explanations

[0216] Specific behavior:

[0217] Analyze the data using an NLP library and detect missing parts based on specific conditions.

[0218] Step 6:

[0219] The server packages the results of detecting missing evidence and explanations in JSON format and sends it to the user's device as an HTTP response.

[0220] input:

[0221] Findings of missing evidence and explanations

[0222] output:

[0223] Detection results sent as HTTP responses

[0224] Specific behavior:

[0225] The server converts the detection results into JSON format and sends them to the terminal as an HTTP response.

[0226] Step 7:

[0227] The device analyzes the detection results received from the server and visually displays them to the user, specifically, by displaying messages pointing out missing evidence or explanations.

[0228] input:

[0229] Detection results received as an HTTP response

[0230] output:

[0231] Detection result message displayed on the device

[0232] Specific behavior:

[0233] The application on the terminal analyzes the received data and displays a warning message on the user interface.

[0234] Step 8:

[0235] The user can refer to the displayed message to revise the content of the customer service talk or sales promotion material and re-enter it into the system. By repeating this process, the quality of the material can be improved.

[0236] input:

[0237] Feedback from users who received the message

[0238] output:

[0239] Corrected data

[0240] Specific behavior:

[0241] The user reviews the comments, corrects the material, and re-enters it.

[0242] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0243] The present invention is a system that automatically detects missing evidence or explanations in presentation slides, requirements definition documents, and other documents, and notifies the user of this, as well as a system that recognizes the user's emotions and displays the results accordingly. This system is configured as follows:

[0244] First, the user inputs the document data from their own device. The document data is text data such as presentation slides or requirements specifications, and is input in text format. Once input is complete, the device converts the document data into JSON format and sends it to the server as an HTTP POST request.

[0245] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted data from the request body. Based on the extracted data, the server analyzes the evidence and explanation for any missing parts.

[0246] To detect missing evidence, the server checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the document data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation."

[0247] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[0248] Additionally, the present invention includes an emotion engine that recognizes the user's emotions by analyzing the user's input data, response time, and even biometric information. For example, the emotion engine can estimate the user's emotional state based on whether the user is typing quickly or there is a delay.

[0249] Based on the estimated emotion, the device can customize how the detection results are displayed: for example, if the user is anxious, it will display more detailed and thorough explanations, whereas if the user is in a hurry, it will display only the important points concisely.

[0250] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection results are adjusted to be displayed concisely.

[0251] This system allows users to quickly and efficiently check for missing evidence or explanations and revise their materials. Furthermore, the introduction of an emotion engine enables flexible responses to match the user's emotional state, improving the user experience.

[0252] The processing flow will be explained below.

[0253] Step 1:

[0254] Users use their devices to input data, such as presentation slides and requirements specifications, using a text editor or a dedicated web form.

[0255] Step 2:

[0256] When the user has finished entering the document data, he or she clicks the "Send" button on the terminal. This operation causes the document data to proceed to the next process.

[0257] Step 3:

[0258] The device converts the document data into JSON format. The program on the device converts the document content into a format such as {"document": "document content here"}.

[0259] Step 4:

[0260] The device sends the JSON-formatted document data to the server as an HTTP POST request, which is sent to a specific endpoint on the server.

[0261] Step 5:

[0262] The server receives the HTTP POST request and extracts the document data in JSON format from the request body.

[0263] Step 6:

[0264] The server calls the analyze_document function to analyze the document data, which detects missing evidence and explanations based on the document data.

[0265] Step 7:

[0266] The server calls the find_evidence_issues function to check whether the document data contains the word "evidence." If it does not, it generates a warning message saying "Insufficient evidence."

[0267] Step 8:

[0268] The server calls the find_explanation_issues function, splits the document data into words, and counts the number of words. If the number of words is less than 100, it generates a warning message saying "Insufficient explanation."

[0269] Step 9:

[0270] The server compiles the results of the missing evidence and explanation in JSON format, including a detailed message about the missing parts.

[0271] Step 10:

[0272] The server returns the generated analysis results to the client terminal as an HTTP response, which includes a 200 status code (OK) and the analysis results.

[0273] Step 11:

[0274] The terminal receives the HTTP response and extracts the analysis results in JSON format from the response body.

[0275] Step 12:

[0276] In addition to the analysis results extracted by the device, the emotion engine is called to recognize the user's emotions. The emotion engine analyzes emotions based on the user's input data and response time.

[0277] Step 13:

[0278] Based on the analysis results of the emotion engine, the device customizes the way it displays the results of the detection of missing evidence and explanations. For example, if the user is in a hurry, it will briefly display only the important points.

[0279] Step 14:

[0280] The terminal displays the final missing part to the user, who can then check the missing part and begin correcting the document.

[0281] Step 15:

[0282] If necessary, the user can modify the material and then resubmit the new material data to the system.

[0283] Through these steps, users can quickly and efficiently identify missing evidence and explanations, and enjoy a better user experience through customized display by the emotion engine.

[0284] Example 2

[0285] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0286] Currently, many users create documents with insufficient evidence and explanations. However, manually detecting and correcting these insufficient parts is a time-consuming and labor-intensive task. In addition, the user's emotional state when creating documents can affect the final product, and conventional detection systems have not been able to respond flexibly to the user's emotions.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0288] In this invention, the server includes means for receiving document data input by a user, means for converting the document data into JSON format and transmitting the converted data to the server, means for detecting missing portions of evidence based on the document data, means for detecting missing portions of explanation based on the document data, and means for displaying the detection results of missing portions of the document data in a customized manner based on the emotional state of the user. This not only enables users to efficiently detect and correct missing portions of evidence or explanation in the document, but also enables flexible responses that are adapted to the emotional state of each individual user.

[0289] "User" refers to the entity that uses this system to input material data and receive the results.

[0290] "Document data" refers to document information entered in text format, such as presentation slides or requirements specifications.

[0291] "JSON format" is an abbreviation for JavaScript Object Notation, and is a format for structuring and representing data.

[0292] The "server" refers to a device that analyzes the document data received from the terminal, detects missing evidence or explanations, and uses an emotion engine to recognize the user's emotional state.

[0293] "Means for detecting missing evidence" refers to the function of checking whether the word "evidence" is included in the source data and detecting any missing parts.

[0294] "Means for detecting missing parts of explanation" refers to a function that counts the total number of words in the document data and detects the missing parts if they do not meet the required standard.

[0295] "Emotional state" refers to the user's mental and psychological state, estimated based on the user's input data, response time, biometric information, etc.

[0296] The "means for customizing the display" refers to a function for displaying the results of the missing part detection in different formats depending on the emotional state of the user.

[0297] This invention is a system that automatically detects missing evidence and explanations in presentation slides, requirements specifications, and other documents, notifying the user of this, and also recognizes the user's emotions and displays the results accordingly.The system of this invention mainly uses three components: the user, the terminal, and the server.

[0298] First, the user inputs the document data using his / her own terminal. The document data is, for example, data in the following text format.

[0299] Example prompt sentence:

[0300] "This is the outline of a new project. The objective is to meet a market need. The next steps are to define the requirements and complete the design phase."

[0301] The terminal then converts the input data into JSON format and sends it to the server as an HTTP POST request. The terminal is equipped with software for data conversion and transmission, such as a programming language like Python and a library for sending HTTP requests (e.g., Requests).

[0302] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted document data from the request body. Specifically, an application server (e.g., Flask or Django) running on the server processes the HTTP request and parses the JSON data. At this time, the server runs an analysis program to detect missing evidence and explanations.

[0303] To detect missing evidence, the server checks whether the word "evidence" is included in the material data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the material data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation." A natural language processing library (e.g., NLTK or spaCy) can be used for this analysis.

[0304] Furthermore, the server uses an emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's input data and response time to estimate the user's emotional state. For example, a machine learning library such as TENSORFLOW® or PyTorch can be used to build a predictive model. This can identify whether the user is in a hurry or feeling anxious.

[0305] Finally, the server generates the analysis results in JSON format and sends them back to the client device as an HTTP response. The device receives this response and displays a customized version according to the user's emotional state. Specifically, if the user is feeling anxious, it displays a detailed, thorough explanation, but if the user is in a hurry, it adjusts the display to display only the important points concisely. This display is achieved using a GUI (Graphical User Interface) application running on the device.

[0306] In this way, the system of the present invention helps users quickly and efficiently detect and correct missing parts of materials, and by introducing an emotion engine, it enables flexible responses according to the user's emotional state.

[0307] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0308] Step 1:

[0309] The user inputs the material data into the terminal.

[0310] Specifically, the user manually inputs text data such as presentation slides and requirements specifications into an input field on the terminal.

[0311] Input: The user enters text data.

[0312] Output: Text data is displayed on the terminal.

[0313] Step 2:

[0314] The terminal converts the input data into JSON format.

[0315] Specifically, the terminal application parses the text-formatted document data and calls a function to convert it into JSON format.

[0316] Input: Text material data entered into the terminal.

[0317] Output: Data converted to JSON format.

[0318] Step 3:

[0319] The terminal sends the document data converted into JSON format to the server as an HTTP POST request.

[0320] Specifically, the generated JSON data is sent to the server using an HTTP library on the terminal (e.g., Requests).

[0321] Input: Material data converted to JSON format.

[0322] Output: The HTTP POST request sent to the server.

[0323] Step 4:

[0324] The server receives the HTTP POST request sent from the terminal and extracts the document data in JSON format from the request body.

[0325] Specifically, the server's HTTP server software (e.g., Apache (registered trademark) or NGINX) receives the request, and the application server (e.g., Flask or Django) parses the JSON data.

[0326] Input: The HTTP request sent from the terminal.

[0327] Output: Extracted material data in JSON format.

[0328] Step 5:

[0329] The server detects missing parts of evidence based on the document data.

[0330] Specifically, the server searches the text in the JSON data to see if it contains the word "evidence," and if it doesn't, generates a corresponding error message.

[0331] Input: Material data in JSON format.

[0332] Output: The message "Insufficient evidence."

[0333] Step 6:

[0334] The server detects missing parts of the explanation based on the document data.

[0335] Specifically, the server divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a corresponding error message.

[0336] Input: Material data in JSON format.

[0337] Output: The message "Description is missing."

[0338] Step 7:

[0339] The server aggregates both evidence-deficient and explanation-deficient results and generates the analysis results in JSON format.

[0340] Specifically, the server's analysis module converts the detection results into JSON format.

[0341] Input: "Insufficient evidence" and "Insufficient explanation" messages.

[0342] Output: JSON data of the generated analysis results.

[0343] Step 8:

[0344] The server returns the generated analysis results to the client terminal as an HTTP response.

[0345] Specifically, the server's HTTP library generates a response and sends it to the client terminal.

[0346] Input: JSON data of the generated analysis results.

[0347] Output: The HTTP response sent to the client device.

[0348] Step 9:

[0349] The server uses an emotion engine to recognize the user's emotional state.

[0350] Specifically, the server analyzes the user's input data and response time, and uses a machine learning model to estimate the user's emotional state.

[0351] Input: User input data and response times.

[0352] Output: Estimated user emotional state.

[0353] Step 10:

[0354] The device customizes how the detection results are displayed based on the user's emotional state.

[0355] Specifically, the GUI application on the device receives the emotional state data and adjusts the display content accordingly. For example, it may display detailed and thorough explanations to a user who is feeling anxious, or it may display only the important points concisely to a user who is in a hurry.

[0356] Input: Estimated user emotional state and analysis results from the server.

[0357] Output: A customized display of the findings.

[0358] (Application example 2)

[0359] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0360] In factories, work reports and data logs are often insufficient, which reduces work efficiency and productivity. Furthermore, the lack of feedback based on the emotional state of workers makes it difficult to make effective corrections or take action. To solve this problem, a system that automatically detects missing information and provides flexible feedback based on the emotional state of workers is needed.

[0361] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0362] In this invention, the server includes means for receiving document data input by a user, means for detecting missing parts of evidence based on the document data, means for detecting missing parts of explanation based on the document data, means for displaying the detection results of the missing parts to the user, means for recognizing the emotion of the user, and means for customizing the display method of the detection results based on the emotion recognition. This makes it possible to automatically correct defects in the document data and immediately provide appropriate feedback according to the emotion of the worker.

[0363] "Document data" refers to data such as documents and reports entered by the user, and is the basis for the system's analysis.

[0364] "Evidence" refers to the evidence or supporting information mentioned in the document data, and the system will detect any lack of this information.

[0365] "Emotion recognition" is a technology that analyzes a user's input data and biometric information to identify the user's emotional state.

[0366] "Customizing the display method" means changing the display format of the detection results depending on the user's emotional state, for example, providing a detailed explanation if the user is feeling anxious, or a concise explanation if the user is in a hurry.

[0367] The present invention realizes a "smart reporting assistant" system installed on factory robots that analyzes reports and data logs entered by workers, automatically detects gaps in evidence and explanations, and customizes feedback based on the worker's emotional state.

[0368] First, the user inputs the data from their own device. The data is text data such as a work report or data log, and is input in text format. Once input is complete, the device converts the data into JSON format and sends it to the server as an HTTP POST request.

[0369] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted data from the request body. Based on the extracted data, the server analyzes the evidence and explanation for any missing parts and identifies the missing parts.

[0370] To detect missing evidence, the server checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the document data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation."

[0371] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[0372] Furthermore, the present invention includes an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotions by analyzing the user's input data and biometric information. For example, the emotion engine infers the user's emotional state from when the user is typing quickly or when there is a delay.

[0373] Based on this inferred emotion, the server customizes the way the detection results are displayed: for example, if the user is anxious, it will display more detailed and thorough explanations, whereas if the user is in a hurry, it will display only the important points in a concise manner.

[0374] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection results are adjusted to be displayed concisely.

[0375] This invention allows users to quickly and efficiently check for missing evidence or explanations and revise materials. Furthermore, the introduction of an emotion engine enables flexible responses to match the user's emotional state, improving the user experience.

[0376] Examples of prompts include "We're in a hurry" and "This is an overview of a new project. The objective is to meet a market need. The next steps are to define requirements and complete the design phase."

[0377] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0378] Step 1:

[0379] The user inputs material data from the terminal. The material data is text data such as work reports and data logs. This material data is input in text format. After input, the terminal converts the material data into JSON format. The input here is material data in text format, and the output is material data in JSON format. The terminal sends the material data converted to JSON format to the server as an HTTP POST request.

[0380] Step 2:

[0381] The server receives the HTTP POST request sent from the terminal and extracts the JSON formatted data from the request body. The input in this step is the HTTP POST request and the output is the JSON formatted data. The server converts the data into text format and prepares it for the next analysis.

[0382] Step 3:

[0383] The server detects missing evidence. Specifically, it checks whether the word "evidence" is included in the document data. This check may result in the generation of a message saying "Insufficient evidence." The input here is text-formatted document data, and the output is a message indicating insufficient evidence.

[0384] Step 4:

[0385] The server detects missing parts of the explanation. It divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a message saying "There is insufficient explanation." The input in this step is the data in text format, and the output is a message saying there is insufficient explanation.

[0386] Step 5:

[0387] The server compiles both the lack of evidence and the lack of explanation results and generates an analysis result in JSON format. The server returns this analysis result to the client device as an HTTP response. The input in this step is the lack of evidence and the lack of explanation message, and the output is the analysis result in JSON format.

[0388] Step 6:

[0389] To recognize the user's emotions, the server uses an emotion engine. The emotion engine analyzes the user's input data and biometric information to identify the user's emotional state. For example, it can estimate whether the user is in a hurry or anxious based on input speed and delay. The input here is the user's input data and biometric information, and the output is the user's emotional state.

[0390] Step 7:

[0391] The server customizes the display of the detection results based on the user's emotional state. For example, if the user is anxious, it will display more detailed explanations, and if the user is in a hurry, it will display only the important points in a concise manner. The input for this step is the user's emotional state and the analysis results in JSON format, and the output is a message in a customized display format.

[0392] As a concrete example, if a user enters the following document data, "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase," this document data contains no evidence and has fewer than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient explanation," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection result is displayed concisely.

[0393] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0394] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0395] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0396] [Second embodiment]

[0397] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0398] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0399] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0400] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0401] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0402] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0403] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0404] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0405] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0406] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0407] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0408] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0409] The present invention is a system that automatically detects missing evidence or explanations in presentation slides, requirements definition documents, and other documents, and notifies the user of these. This system is configured as follows.

[0410] First, the user inputs the document data from their own device. The document data is written data such as presentation slides and requirements specifications, and is input in text format. Once the user has finished inputting the document data, the device converts the data into JSON format and sends it to a specific endpoint on the server as an HTTP POST request.

[0411] The server receives an HTTP POST request from the device and extracts the JSON-formatted document data from the request body. Based on the extracted document data, the server analyzes the content of the document. This analysis focuses on detecting missing pieces of evidence and explanation.

[0412] To detect missing evidence, the server first checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Evidence is missing."

[0413] To detect missing explanations, the data is divided into words and the total number of words is counted. If the number of words is less than 100, the server generates a message saying "There is insufficient explanation."

[0414] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[0415] The terminal receives the response from the server and displays the analysis results to the user. The display includes a message pointing out specific areas that are lacking. The user can use this information to correct the document.

[0416] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. The user can then view the results and revise the document.

[0417] The system of the present invention can automatically detect missing evidence and explanations and quickly and effectively improve the quality of documents, thereby significantly reducing the manual review work required in the past and improving the efficiency of business processes.

[0418] The processing flow will be explained below.

[0419] Step 1:

[0420] Users use their devices to input data, specifically, the contents of presentation slides and requirements specifications, using a text editor or a dedicated web form.

[0421] Step 2:

[0422] When the user has finished entering the document data, he or she clicks the "Send" button on the terminal. This operation causes the document data to proceed to the next process.

[0423] Step 3:

[0424] The device converts the document data into JSON format. The program on the device converts the document content into a format such as {"document": "document content here"}.

[0425] Step 4:

[0426] The device sends the JSON-formatted data to the server as an HTTP POST request, which is sent to a specific endpoint on the server, such as / analyze.

[0427] Step 5:

[0428] The server receives an HTTP POST request and extracts the document data in JSON format from the request body.

[0429] Step 6:

[0430] The server calls the analyze_document function to analyze the document data, which detects missing evidence and explanations based on the document data.

[0431] Step 7:

[0432] The server calls the find_evidence_issues function to check whether the document data contains the word "evidence." If it does not, it generates a warning message saying "Insufficient evidence."

[0433] Step 8:

[0434] The server calls the find_explanation_issues function, splits the document data into words, and counts the number of words. If the number of words is less than 100, it generates a warning message saying "Insufficient explanation."

[0435] Step 9:

[0436] The server compiles the results of the missing evidence and explanation in JSON format, including a detailed message of the missing part.

[0437] Step 10:

[0438] The server returns the generated analysis results to the client terminal as an HTTP response, which includes a 200 status code (OK) and the analysis results.

[0439] Step 11:

[0440] The terminal receives the HTTP response and extracts the analysis results in JSON format from the response body.

[0441] Step 12:

[0442] The device displays the extracted analysis results to the user. Specifically, a warning message such as "Insufficient evidence" or "Insufficient explanation" is displayed on the screen.

[0443] Step 13:

[0444] The user can check the missing parts displayed and correct the materials. If necessary, they can re-enter new material data and resubmit it to the system.

[0445] Through the above steps, missing parts of evidence or explanations in documents such as presentation slides or requirements specifications are efficiently detected, allowing users to quickly and effectively revise the documents.

[0446] Example 1

[0447] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0448] Conventional document verification systems require users to manually check for missing evidence and explanations after creating documents, which is time-consuming and labor-intensive. Human error can easily lead to oversights, potentially resulting in a decline in document quality. Furthermore, an efficient method is required when verifying multiple documents in a short period of time.

[0449] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0450] In this invention, the server includes means for inputting material data from a user, means for converting the material data into JSON format, means for transmitting the JSON-formatted material data to the server as an HTTP POST request, means for receiving the transmitted material data and extracting the JSON-formatted material data from the request body, means for detecting missing parts of evidence based on the material data, means for detecting missing parts of explanation based on the material data, means for generating results of the missing evidence and missing explanation in JSON format and returning the analysis results to the terminal, and means for displaying the missing part detection results to the user. This makes it possible to automatically detect missing parts of evidence and explanation and quickly and effectively improve the quality of materials.

[0451] "User" means an individual or organization that uses this system.

[0452] "Document data" refers to document information such as presentation slides and requirements definition documents, and is text data entered by the user.

[0453] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format for describing data in a structured manner.

[0454] An "HTTP POST request" is a method of sending data using the Hypertext Transfer Protocol, and is a request to send data to a server.

[0455] A "server" is a computer system that receives requests via a network and analyzes the data.

[0456] "Evidence" refers to the evidence or reasoning provided to support a fact or claim within a document.

[0457] An "endpoint" refers to a server-side URL or URI that provides a specific function when communicating.

[0458] The "request body" is the data payload portion included in the HTTP request, and is the portion that contains the content of the document data.

[0459] "Number of words" refers to the result of counting the total number of words in the material data.

[0460] "Analysis results" refers to data compiled in JSON format that identifies the results of detection of insufficient evidence or explanation based on document data.

[0461] A "response" refers to response data returned from a server to a client.

[0462] A "client terminal" is a computer system used by a user, and is a device that communicates with a server to send material data and receive analysis results.

[0463] "Display" refers to visually providing the analysis results to the user, specifically to displaying a message on the screen.

[0464] The present invention is a system that automatically detects missing evidence and explanations in document data and notifies the user. This system operates in cooperation with both the user terminal and the server.

[0465] First, the user inputs the data using their own device. This data is entered in text format as document information such as presentation slides or requirements definition documents. For example, it might look like this: "This is the outline of a new project. The objective is to meet market needs. The next step is to complete the requirements definition and design phases."

[0466] The terminal then converts the input data into JSON format and sends it as an HTTP POST request to a specific endpoint on the server, using common software libraries (e.g., Python's json library or requests library) for the conversion and transmission.

[0467] The server receives the HTTP POST request sent from the device. It extracts the JSON-formatted document data from the received request and prepares it for analysis. The analysis begins by checking whether the document data contains the word "evidence." If it does not, it generates a message saying "Insufficient evidence."

[0468] The server then divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a message saying "Insufficient explanation." As a result, it generates a JSON format summary of the results of insufficient evidence and explanation, and returns the analysis results to the terminal as an HTTP response.

[0469] The terminal receives the response from the server and displays the analysis results to the user, including a message indicating which specific parts are missing, so that the user can correct the document based on this information.

[0470] As a concrete example, if a user inputs the following document data, "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase," the document data contains no evidence and lacks explanation. When this document data is analyzed by the server, the server generates messages such as "Evidence is insufficient" and "Explanation is insufficient" and returns them to the terminal. The user can refer to the analysis results and revise the document.

[0471] When using a generative AI model, you can use the following as a prompt:

[0472] "When a user enters the following data, such as 'This is a description of a new project. The objective is to address a market need. The next steps are to define the requirements and complete the design phase,' please write Python code that will enable the system to detect missing evidence and explanations and generate analysis results."

[0473] The present invention makes it possible to automate the process of detecting insufficient evidence and explanations during the document creation process, thereby improving the quality of documents and increasing the efficiency of the work.

[0474] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0475] Step 1:

[0476] The user inputs the data.

[0477] The user uses an input form on their own device to input data such as presentation slides and requirements definition documents in text format. In concrete terms, the user might input the following: "This is an outline of a new project. The objective is to meet market needs. The next step is to complete the requirements definition and design phases." This input is captured on the device. Input: Data (text format) Output: Data (text format)

[0478] Step 2:

[0479] The device converts the data into JSON format.

[0480] The device converts the captured data into JSON format. Specifically, the device uses a conversion library to serialize the data into JSON format. Input: Data (text format) Output: Data (JSON format)

[0481] Step 3:

[0482] The device sends an HTTP POST request to the server

[0483] The terminal sends the converted JSON data as an HTTP POST request to a specific endpoint on the server. Specifically, the terminal uses the HTTP library to construct the request header and body and send it to the server. Input: Document data (JSON format) Output: HTTP POST request (JSON data)

[0484] Step 4:

[0485] The server receives the data.

[0486] The server receives the HTTP POST request sent from the terminal and extracts the document data in JSON format from the request body. Specifically, the server analyzes the request and loads the document data into memory. Input: HTTP POST request (JSON data) Output: Document data (JSON format)

[0487] Step 5:

[0488] The server analyzes the data.

[0489] The server analyzes the data and detects missing evidence and explanations. This analysis process includes detecting missing evidence and missing explanations. Input: Data (JSON format) Output: Messages about missing evidence and missing explanations

[0490] Step 6:

[0491] Detecting evidence gaps

[0492] The server checks whether the word "evidence" is included in the document data. Specifically, it performs a string search using a text analysis library. If it is not included, it generates a message saying "Insufficient evidence." Input: Document data (JSON format) Output: Insufficient evidence message

[0493] Step 7:

[0494] Detecting Missing Explanations

[0495] The server splits the data into words and counts the total number of words. Specifically, it uses a text tokenization library to split the data into words and count the total number. If the number of words is less than 100, it generates a message saying "Insufficient explanation." Input: Data (JSON format) Output: Insufficient explanation message

[0496] Step 8:

[0497] The server generates the analysis results.

[0498] The server aggregates messages with insufficient evidence and insufficient explanation and generates analysis results in JSON format. Input: messages with insufficient evidence, messages with insufficient explanation Output: analysis results (JSON format)

[0499] Step 9:

[0500] The server returns the analysis results to the device.

[0501] The server returns the generated analysis results to the terminal as an HTTP response. Specifically, the server uses an HTTP library to construct the response header and body and return the response. Input: Analysis results (JSON format) Output: HTTP response (analysis results)

[0502] Step 10:

[0503] The device displays the analysis results.

[0504] The terminal receives the response from the server and displays the analysis results to the user. Specifically, the terminal uses a UI component to visually display the analysis results. Input: HTTP response (analysis results) Output: Display of analysis results

[0505] (Application example 1)

[0506] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0507] In the past, store staff found it difficult to provide customers with reliable information when talking to customers or creating promotional materials due to a lack of evidence or explanation for the content. This led to missed sales opportunities and a decline in customer satisfaction. Solving this issue was an urgent need, especially in store operations, where quick responses on-site are required.

[0508] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0509] In this invention, the server includes means for receiving material data input by a user, means for detecting missing portions of evidence based on the material data, means for detecting missing portions of explanation based on the material data, means for automatically detecting missing portions of evidence and explanation based on the text of customer service talks and promotional materials, and means for displaying the results of the detection of missing portions to the user, thereby enabling store staff to quickly and efficiently create reliable customer service talks and promotional materials that include sufficient evidence and explanation.

[0510] A "user" is someone who uses this system to input material data and utilizes the results of evidence and explanation detection.

[0511] "Document data" refers to written data such as presentation slides, requirements definition documents, customer service talks, and sales promotion materials, which are input by users into the system.

[0512] "Evidence" refers to evidence or data used to support claims or explanations in source data.

[0513] "Means for detecting missing evidence" refers to the function of checking whether evidence is contained in the document data and detecting if evidence is missing.

[0514] "Means for detecting insufficient explanations" refers to a function that checks whether the explanations in the document data are sufficient and detects any insufficiency of the explanations.

[0515] "Customer service talk" refers to verbal explanations and guidance given by store staff to customers.

[0516] "Sales promotion materials" are materials intended to promote sales of products, and are text data that users can input into the system.

[0517] The "means for displaying" refers to a means for visually outputting to the user the evidence received from the server and the results of detection of missing parts of the explanation.

[0518] "Mobile device" refers to a portable computer device such as a smartphone or tablet.

[0519] "Server" refers to a computer system that receives document data sent by users and analyzes the data to detect missing evidence or explanations.

[0520] The present invention is a system that automatically detects missing evidence and explanations based on document data entered by a user, and is intended for use in brick-and-mortar stores in particular. A specific description of an embodiment of the present invention is given below.

[0521] This system mainly uses smartphones, tablets, and cloud servers. Users input text for customer service talk and sales promotion materials from their own devices, and the input data is converted to JSON format and sent to the server.

[0522] Hardware and Software Used

[0523] Smartphone / Tablet: Android or iOS device

[0524] Server: Cloud server (AWS, Google Cloud, Microsoft Azure, etc.)

[0525] API calls: Communicating with the server using HTTP requests

[0526] Natural Language Processing (NLP) library: spaCy, NLTK, or GPT-4 series (OpenAI API)

[0527] Program processing

[0528] Input and submit data

[0529] Users input text data such as customer service chat and sales promotion materials in text format through the application on their device. This data is automatically converted to JSON format and sent to the cloud server as an HTTP POST request.

[0530] Data analysis on the server

[0531] The server parses the received JSON data, specifically performing the following steps:

[0532] 1. Evidence detection:

[0533] Check whether the word "evidence" is included in the source data.

[0534] If not, generate a "missing evidence" message.

[0535] 2. Description detection:

[0536] The data is divided into words and the total number of words is counted.

[0537] If the word count is less than 100, generate a "Not enough description" message.

[0538] The generated detection results are packaged again in JSON format and sent to the user's device as an HTTP response.

[0539] Displaying the results

[0540] The user device receives the detection results sent from the server and visually displays them, including a message indicating which specific parts are missing.

[0541] Examples and prompts

[0542] For example, a store staff member may enter, "This product uses the latest technology." When this document data is sent to the server, it is detected as lacking evidence and a message is displayed saying, "There is insufficient evidence. Please add references or market data."

[0543] Examples of prompt sentences

[0544] This product uses the latest technology.

[0545] This text is entered as data and analyzed on the server.

[0546] Through this system, store staff can quickly and efficiently create reliable customer service talks and promotional materials that are fully packed with evidence and explanations, which is expected to increase sales and customer satisfaction.

[0547] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0548] Step 1:

[0549] The user starts the application on their own device and inputs text data for customer service conversations and sales promotion materials. The input text data is saved on the user's device.

[0550] input:

[0551] Text data of customer service talk and promotional materials

[0552] output:

[0553] Input text data stored on the device

[0554] Specific behavior:

[0555] The user enters text into an application input field and presses the "Submit" button.

[0556] Step 2:

[0557] The terminal converts the input text data into JSON format, which makes the data suitable for sending to the server.

[0558] input:

[0559] Input text data stored on the device

[0560] output:

[0561] Data converted to JSON format

[0562] Specific behavior:

[0563] Format text data into JSON format within the device application.

[0564] Step 3:

[0565] The terminal sends the data converted into JSON format to the cloud server as an HTTP POST request.

[0566] input:

[0567] Data converted to JSON format

[0568] output:

[0569] Data sent as an HTTP POST request

[0570] Specific behavior:

[0571] The device generates an HTTP POST request and sends it to a specific endpoint on the cloud server.

[0572] Step 4:

[0573] The server receives the HTTP POST request, extracts the JSON data from the request body, and prepares this data for parsing.

[0574] input:

[0575] JSON data included in HTTP POST requests

[0576] output:

[0577] JSON data prepared for parsing

[0578] Specific behavior:

[0579] The server reads the HTTP request body and passes the JSON data to the parsing process.

[0580] Step 5:

[0581] The server uses NLP libraries (e.g., spaCy, NLTK, GPT-4) to detect missing evidence and explanations in the material data.

[0582] Evidence detection: Checks whether the word "evidence" is included in the data. If not, generates a message saying "Insufficient evidence."

[0583] Description detection: Counts the number of words in the data and generates a "description is insufficient" message if there are fewer than 100 words.

[0584] input:

[0585] JSON data prepared for parsing

[0586] output:

[0587] Findings of missing evidence and explanations

[0588] Specific behavior:

[0589] Analyze the data using an NLP library and detect missing parts based on specific conditions.

[0590] Step 6:

[0591] The server packages the results of detecting missing evidence and explanations in JSON format and sends it to the user's device as an HTTP response.

[0592] input:

[0593] Findings of missing evidence and explanations

[0594] output:

[0595] Detection results sent as HTTP responses

[0596] Specific behavior:

[0597] The server converts the detection results into JSON format and sends them to the terminal as an HTTP response.

[0598] Step 7:

[0599] The device analyzes the detection results received from the server and visually displays them to the user, specifically, by displaying messages pointing out missing evidence or explanations.

[0600] input:

[0601] Detection results received as an HTTP response

[0602] output:

[0603] Detection result message displayed on the device

[0604] Specific behavior:

[0605] The application on the terminal analyzes the received data and displays a warning message on the user interface.

[0606] Step 8:

[0607] The user can refer to the displayed message to revise the content of the customer service talk or sales promotion material and re-enter it into the system. By repeating this process, the quality of the material can be improved.

[0608] input:

[0609] Feedback from users who received the message

[0610] output:

[0611] Corrected data

[0612] Specific behavior:

[0613] The user reviews the comments, corrects the material, and re-enters it.

[0614] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0615] The present invention is a system that automatically detects missing evidence or explanations in presentation slides, requirements definition documents, and other documents, and notifies the user of this, as well as a system that recognizes the user's emotions and displays the results accordingly. This system is configured as follows:

[0616] First, the user inputs the document data from their own device. The document data is text data such as presentation slides or requirements specifications, and is input in text format. Once input is complete, the device converts the document data into JSON format and sends it to the server as an HTTP POST request.

[0617] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted data from the request body. Based on the extracted data, the server analyzes the evidence and explanation for any missing parts.

[0618] To detect missing evidence, the server checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the document data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation."

[0619] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[0620] Additionally, the present invention includes an emotion engine that recognizes the user's emotions by analyzing the user's input data, response time, and even biometric information. For example, the emotion engine can estimate the user's emotional state based on whether the user is typing quickly or there is a delay.

[0621] Based on the estimated emotion, the device can customize how the detection results are displayed: for example, if the user is anxious, it will display more detailed and thorough explanations, whereas if the user is in a hurry, it will display only the important points concisely.

[0622] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection results are adjusted to be displayed concisely.

[0623] This system allows users to quickly and efficiently check for missing evidence or explanations and revise their materials. Furthermore, the introduction of an emotion engine enables flexible responses to match the user's emotional state, improving the user experience.

[0624] The processing flow will be explained below.

[0625] Step 1:

[0626] Users use their devices to input data, such as presentation slides and requirements specifications, using a text editor or a dedicated web form.

[0627] Step 2:

[0628] When the user has finished entering the document data, he or she clicks the "Send" button on the terminal. This operation causes the document data to proceed to the next process.

[0629] Step 3:

[0630] The device converts the document data into JSON format. The program on the device converts the document content into a format such as {"document": "document content here"}.

[0631] Step 4:

[0632] The device sends the JSON-formatted document data to the server as an HTTP POST request, which is sent to a specific endpoint on the server.

[0633] Step 5:

[0634] The server receives the HTTP POST request and extracts the document data in JSON format from the request body.

[0635] Step 6:

[0636] The server calls the analyze_document function to analyze the document data, which detects missing evidence and explanations based on the document data.

[0637] Step 7:

[0638] The server calls the find_evidence_issues function to check whether the document data contains the word "evidence." If it does not, it generates a warning message saying "Insufficient evidence."

[0639] Step 8:

[0640] The server calls the find_explanation_issues function, splits the document data into words, and counts the number of words. If the number of words is less than 100, it generates a warning message saying "Insufficient explanation."

[0641] Step 9:

[0642] The server compiles the results of the missing evidence and explanation in JSON format, including a detailed message about the missing parts.

[0643] Step 10:

[0644] The server returns the generated analysis results to the client terminal as an HTTP response, which includes a 200 status code (OK) and the analysis results.

[0645] Step 11:

[0646] The terminal receives the HTTP response and extracts the analysis results in JSON format from the response body.

[0647] Step 12:

[0648] In addition to the analysis results extracted by the device, the emotion engine is called to recognize the user's emotions. The emotion engine analyzes emotions based on the user's input data and response time.

[0649] Step 13:

[0650] Based on the analysis results of the emotion engine, the device customizes the way it displays the results of the detection of missing evidence and explanations. For example, if the user is in a hurry, it will briefly display only the important points.

[0651] Step 14:

[0652] The terminal displays the final missing part to the user, who can then check the missing part and begin correcting the document.

[0653] Step 15:

[0654] If necessary, the user can modify the material and then resubmit the new material data to the system.

[0655] Through these steps, users can quickly and efficiently identify missing evidence and explanations, and enjoy a better user experience through customized display by the emotion engine.

[0656] Example 2

[0657] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0658] Currently, many users create documents with insufficient evidence and explanations. However, manually detecting and correcting these insufficient parts is a time-consuming and labor-intensive task. In addition, the user's emotional state when creating documents can affect the final product, and conventional detection systems have not been able to respond flexibly to the user's emotions.

[0659] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0660] In this invention, the server includes means for receiving document data input by a user, means for converting the document data into JSON format and transmitting the converted data to the server, means for detecting missing portions of evidence based on the document data, means for detecting missing portions of explanation based on the document data, and means for displaying the detection results of missing portions of the document data in a customized manner based on the emotional state of the user. This not only enables users to efficiently detect and correct missing portions of evidence or explanation in the document, but also enables flexible responses that are adapted to the emotional state of each individual user.

[0661] "User" refers to the entity that uses this system to input material data and receive the results.

[0662] "Document data" refers to document information entered in text format, such as presentation slides or requirements specifications.

[0663] "JSON format" is an abbreviation for JavaScript Object Notation, and is a format for structuring and representing data.

[0664] The "server" refers to a device that analyzes the document data received from the terminal, detects missing evidence or explanations, and uses an emotion engine to recognize the user's emotional state.

[0665] "Means for detecting missing evidence" refers to the function of checking whether the word "evidence" is included in the source data and detecting any missing parts.

[0666] "Means for detecting missing parts of explanation" refers to a function that counts the total number of words in the document data and detects the missing parts if they do not meet the required standard.

[0667] "Emotional state" refers to the user's mental and psychological state, estimated based on the user's input data, response time, biometric information, etc.

[0668] The "means for customizing the display" refers to a function for displaying the results of the missing part detection in different formats depending on the emotional state of the user.

[0669] This invention is a system that automatically detects missing evidence and explanations in presentation slides, requirements specifications, and other documents, notifying the user of this, and also recognizes the user's emotions and displays the results accordingly.The system of this invention mainly uses three components: the user, the terminal, and the server.

[0670] First, the user inputs the document data using his / her own terminal. The document data is, for example, data in the following text format.

[0671] Example prompt sentence:

[0672] "This is the outline of a new project. The objective is to meet a market need. The next steps are to define the requirements and complete the design phase."

[0673] The terminal then converts the input data into JSON format and sends it to the server as an HTTP POST request. The terminal is equipped with software for data conversion and transmission, such as a programming language like Python and a library for sending HTTP requests (e.g., Requests).

[0674] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted document data from the request body. Specifically, an application server (e.g., Flask or Django) running on the server processes the HTTP request and parses the JSON data. At this time, the server runs an analysis program to detect missing evidence and explanations.

[0675] To detect missing evidence, the server checks whether the word "evidence" is included in the material data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the material data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation." A natural language processing library (e.g., NLTK or spaCy) can be used for this analysis.

[0676] Additionally, the server uses an emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's input data and response time to estimate their emotional state. For example, machine learning libraries such as TensorFlow and PyTorch can be used to build a predictive model. This can identify whether the user is in a hurry or feeling anxious.

[0677] Finally, the server generates the analysis results in JSON format and sends them back to the client device as an HTTP response. The device receives this response and displays a customized version according to the user's emotional state. Specifically, if the user is feeling anxious, it displays a detailed, thorough explanation, but if the user is in a hurry, it adjusts the display to display only the important points concisely. This display is achieved using a GUI (Graphical User Interface) application running on the device.

[0678] In this way, the system of the present invention helps users quickly and efficiently detect and correct missing parts of materials, and by introducing an emotion engine, it enables flexible responses according to the user's emotional state.

[0679] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0680] Step 1:

[0681] The user inputs the material data into the terminal.

[0682] Specifically, the user manually inputs text data such as presentation slides and requirements specifications into an input field on the terminal.

[0683] Input: The user enters text data.

[0684] Output: Text data is displayed on the terminal.

[0685] Step 2:

[0686] The terminal converts the input data into JSON format.

[0687] Specifically, the terminal application parses the text-formatted document data and calls a function to convert it into JSON format.

[0688] Input: Text material data entered into the terminal.

[0689] Output: Data converted to JSON format.

[0690] Step 3:

[0691] The terminal sends the document data converted into JSON format to the server as an HTTP POST request.

[0692] Specifically, the generated JSON data is sent to the server using an HTTP library on the terminal (e.g., Requests).

[0693] Input: Material data converted to JSON format.

[0694] Output: The HTTP POST request sent to the server.

[0695] Step 4:

[0696] The server receives the HTTP POST request sent from the terminal and extracts the document data in JSON format from the request body.

[0697] Specifically, the server's HTTP server software (e.g., Apache or NGINX) receives the request, and the application server (e.g., Flask or Django) parses the JSON data.

[0698] Input: The HTTP request sent from the terminal.

[0699] Output: Extracted material data in JSON format.

[0700] Step 5:

[0701] The server detects missing parts of evidence based on the document data.

[0702] Specifically, the server searches the text in the JSON data to see if it contains the word "evidence," and if it doesn't, generates a corresponding error message.

[0703] Input: Material data in JSON format.

[0704] Output: The message "Insufficient evidence."

[0705] Step 6:

[0706] The server detects missing parts of the explanation based on the document data.

[0707] Specifically, the server divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a corresponding error message.

[0708] Input: Material data in JSON format.

[0709] Output: The message "Description is missing."

[0710] Step 7:

[0711] The server aggregates both evidence-deficient and explanation-deficient results and generates the analysis results in JSON format.

[0712] Specifically, the server's analysis module converts the detection results into JSON format.

[0713] Input: "Insufficient evidence" and "Insufficient explanation" messages.

[0714] Output: JSON data of the generated analysis results.

[0715] Step 8:

[0716] The server returns the generated analysis results to the client terminal as an HTTP response.

[0717] Specifically, the server's HTTP library generates a response and sends it to the client terminal.

[0718] Input: JSON data of the generated analysis results.

[0719] Output: The HTTP response sent to the client device.

[0720] Step 9:

[0721] The server uses an emotion engine to recognize the user's emotional state.

[0722] Specifically, the server analyzes the user's input data and response time, and uses a machine learning model to estimate the user's emotional state.

[0723] Input: User input data and response times.

[0724] Output: Estimated user emotional state.

[0725] Step 10:

[0726] The device customizes how the detection results are displayed based on the user's emotional state.

[0727] Specifically, the GUI application on the device receives the emotional state data and adjusts the display content accordingly. For example, it may display detailed and thorough explanations to a user who is feeling anxious, or it may display only the important points concisely to a user who is in a hurry.

[0728] Input: Estimated user emotional state and analysis results from the server.

[0729] Output: A customized display of the findings.

[0730] (Application example 2)

[0731] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0732] In factories, work reports and data logs are often insufficient, which reduces work efficiency and productivity. Furthermore, the lack of feedback based on the emotional state of workers makes it difficult to make effective corrections or take action. To solve this problem, a system that automatically detects missing information and provides flexible feedback based on the emotional state of workers is needed.

[0733] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0734] In this invention, the server includes means for receiving document data input by a user, means for detecting missing parts of evidence based on the document data, means for detecting missing parts of explanation based on the document data, means for displaying the detection results of the missing parts to the user, means for recognizing the emotion of the user, and means for customizing the display method of the detection results based on the emotion recognition. This makes it possible to automatically correct defects in the document data and immediately provide appropriate feedback according to the emotion of the worker.

[0735] "Document data" refers to data such as documents and reports entered by the user, and is the basis for the system's analysis.

[0736] "Evidence" refers to the evidence or supporting information mentioned in the document data, and the system will detect any lack of this information.

[0737] "Emotion recognition" is a technology that analyzes a user's input data and biometric information to identify the user's emotional state.

[0738] "Customizing the display method" means changing the display format of the detection results depending on the user's emotional state, for example, providing a detailed explanation if the user is feeling anxious, or a concise explanation if the user is in a hurry.

[0739] The present invention realizes a "smart reporting assistant" system installed on factory robots that analyzes reports and data logs entered by workers, automatically detects gaps in evidence and explanations, and customizes feedback based on the worker's emotional state.

[0740] First, the user inputs the data from their own device. The data is text data such as a work report or data log, and is input in text format. Once input is complete, the device converts the data into JSON format and sends it to the server as an HTTP POST request.

[0741] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted data from the request body. Based on the extracted data, the server analyzes the evidence and explanation for any missing parts and identifies the missing parts.

[0742] To detect missing evidence, the server checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the document data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation."

[0743] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[0744] Furthermore, the present invention includes an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotions by analyzing the user's input data and biometric information. For example, the emotion engine infers the user's emotional state from when the user is typing quickly or when there is a delay.

[0745] Based on this inferred emotion, the server customizes the way the detection results are displayed: for example, if the user is anxious, it will display more detailed and thorough explanations, whereas if the user is in a hurry, it will display only the important points in a concise manner.

[0746] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection results are adjusted to be displayed concisely.

[0747] This invention allows users to quickly and efficiently check for missing evidence or explanations and revise materials. Furthermore, the introduction of an emotion engine enables flexible responses to match the user's emotional state, improving the user experience.

[0748] Examples of prompts include "We're in a hurry" and "This is an overview of a new project. The objective is to meet a market need. The next steps are to define requirements and complete the design phase."

[0749] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0750] Step 1:

[0751] The user inputs material data from the terminal. The material data is text data such as work reports and data logs. This material data is input in text format. After input, the terminal converts the material data into JSON format. The input here is material data in text format, and the output is material data in JSON format. The terminal sends the material data converted to JSON format to the server as an HTTP POST request.

[0752] Step 2:

[0753] The server receives the HTTP POST request sent from the terminal and extracts the JSON formatted data from the request body. The input in this step is the HTTP POST request and the output is the JSON formatted data. The server converts the data into text format and prepares it for the next analysis.

[0754] Step 3:

[0755] The server detects missing evidence. Specifically, it checks whether the word "evidence" is included in the document data. This check may result in the generation of a message saying "Insufficient evidence." The input here is text-formatted document data, and the output is a message indicating insufficient evidence.

[0756] Step 4:

[0757] The server detects missing parts of the explanation. It divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a message saying "There is insufficient explanation." The input in this step is the data in text format, and the output is a message saying there is insufficient explanation.

[0758] Step 5:

[0759] The server compiles both the lack of evidence and the lack of explanation results and generates an analysis result in JSON format. The server returns this analysis result to the client device as an HTTP response. The input in this step is the lack of evidence and the lack of explanation message, and the output is the analysis result in JSON format.

[0760] Step 6:

[0761] To recognize the user's emotions, the server uses an emotion engine. The emotion engine analyzes the user's input data and biometric information to identify the user's emotional state. For example, it can estimate whether the user is in a hurry or anxious based on input speed and delay. The input here is the user's input data and biometric information, and the output is the user's emotional state.

[0762] Step 7:

[0763] The server customizes the display of the detection results based on the user's emotional state. For example, if the user is anxious, it will display more detailed explanations, and if the user is in a hurry, it will display only the important points in a concise manner. The input for this step is the user's emotional state and the analysis results in JSON format, and the output is a message in a customized display format.

[0764] As a concrete example, if a user enters the following document data, "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase," this document data contains no evidence and has fewer than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient explanation," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection result is displayed concisely.

[0765] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0766] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0767] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0768] [Third embodiment]

[0769] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0770] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0771] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0772] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0773] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0774] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0775] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0776] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0777] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0778] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0779] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0780] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0781] The present invention is a system that automatically detects missing evidence or explanations in presentation slides, requirements definition documents, and other documents, and notifies the user of these. This system is configured as follows.

[0782] First, the user inputs the document data from their own device. The document data is written data such as presentation slides and requirements specifications, and is input in text format. Once the user has finished inputting the document data, the device converts the data into JSON format and sends it to a specific endpoint on the server as an HTTP POST request.

[0783] The server receives an HTTP POST request from the device and extracts the JSON-formatted document data from the request body. Based on the extracted document data, the server analyzes the content of the document. This analysis focuses on detecting missing pieces of evidence and explanation.

[0784] To detect missing evidence, the server first checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Evidence is missing."

[0785] To detect missing explanations, the data is divided into words and the total number of words is counted. If the number of words is less than 100, the server generates a message saying "There is insufficient explanation."

[0786] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[0787] The terminal receives the response from the server and displays the analysis results to the user. The display includes a message pointing out specific areas that are lacking. The user can use this information to correct the document.

[0788] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. The user can then view the results and revise the document.

[0789] The system of the present invention can automatically detect missing evidence and explanations and quickly and effectively improve the quality of documents, thereby significantly reducing the manual review work required in the past and improving the efficiency of business processes.

[0790] The processing flow will be explained below.

[0791] Step 1:

[0792] Users use their devices to input data, specifically, the contents of presentation slides and requirements specifications, using a text editor or a dedicated web form.

[0793] Step 2:

[0794] When the user has finished entering the document data, he or she clicks the "Send" button on the terminal. This operation causes the document data to proceed to the next process.

[0795] Step 3:

[0796] The device converts the document data into JSON format. The program on the device converts the document content into a format such as {"document": "document content here"}.

[0797] Step 4:

[0798] The device sends the JSON-formatted data to the server as an HTTP POST request, which is sent to a specific endpoint on the server, such as / analyze.

[0799] Step 5:

[0800] The server receives an HTTP POST request and extracts the document data in JSON format from the request body.

[0801] Step 6:

[0802] The server calls the analyze_document function to analyze the document data, which detects missing evidence and explanations based on the document data.

[0803] Step 7:

[0804] The server calls the find_evidence_issues function to check whether the document data contains the word "evidence." If it does not, it generates a warning message saying "Insufficient evidence."

[0805] Step 8:

[0806] The server calls the find_explanation_issues function, splits the document data into words, and counts the number of words. If the number of words is less than 100, it generates a warning message saying "Insufficient explanation."

[0807] Step 9:

[0808] The server compiles the results of the missing evidence and explanation in JSON format, including a detailed message of the missing part.

[0809] Step 10:

[0810] The server returns the generated analysis results to the client terminal as an HTTP response, which includes a 200 status code (OK) and the analysis results.

[0811] Step 11:

[0812] The terminal receives the HTTP response and extracts the analysis results in JSON format from the response body.

[0813] Step 12:

[0814] The device displays the extracted analysis results to the user. Specifically, a warning message such as "Insufficient evidence" or "Insufficient explanation" is displayed on the screen.

[0815] Step 13:

[0816] The user can check the missing parts displayed and correct the materials. If necessary, they can re-enter new material data and resubmit it to the system.

[0817] Through the above steps, missing parts of evidence or explanations in documents such as presentation slides or requirements specifications are efficiently detected, allowing users to quickly and effectively revise the documents.

[0818] Example 1

[0819] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0820] Conventional document verification systems require users to manually check for missing evidence and explanations after creating documents, which is time-consuming and labor-intensive. Human error can easily lead to oversights, potentially resulting in a decline in document quality. Furthermore, an efficient method is required when verifying multiple documents in a short period of time.

[0821] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0822] In this invention, the server includes means for inputting material data from a user, means for converting the material data into JSON format, means for transmitting the JSON-formatted material data to the server as an HTTP POST request, means for receiving the transmitted material data and extracting the JSON-formatted material data from the request body, means for detecting missing parts of evidence based on the material data, means for detecting missing parts of explanation based on the material data, means for generating results of the missing evidence and missing explanation in JSON format and returning the analysis results to the terminal, and means for displaying the missing part detection results to the user. This makes it possible to automatically detect missing parts of evidence and explanation and quickly and effectively improve the quality of materials.

[0823] "User" means an individual or organization that uses this system.

[0824] "Document data" refers to document information such as presentation slides and requirements definition documents, and is text data entered by the user.

[0825] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format for describing data in a structured manner.

[0826] An "HTTP POST request" is a method of sending data using the Hypertext Transfer Protocol, and is a request to send data to a server.

[0827] A "server" is a computer system that receives requests via a network and analyzes the data.

[0828] "Evidence" refers to the evidence or reasoning provided to support a fact or claim within a document.

[0829] An "endpoint" refers to a server-side URL or URI that provides a specific function when communicating.

[0830] The "request body" is the data payload portion included in the HTTP request, and is the portion that contains the content of the document data.

[0831] "Number of words" refers to the result of counting the total number of words in the material data.

[0832] "Analysis results" refers to data compiled in JSON format that identifies the results of detection of insufficient evidence or explanation based on document data.

[0833] A "response" refers to response data returned from a server to a client.

[0834] A "client terminal" is a computer system used by a user, and is a device that communicates with a server to send material data and receive analysis results.

[0835] "Display" refers to visually providing the analysis results to the user, specifically to displaying a message on the screen.

[0836] The present invention is a system that automatically detects missing evidence and explanations in document data and notifies the user. This system operates in cooperation with both the user terminal and the server.

[0837] First, the user inputs the data using their own device. This data is entered in text format as document information such as presentation slides or requirements definition documents. For example, it might look like this: "This is the outline of a new project. The objective is to meet market needs. The next step is to complete the requirements definition and design phases."

[0838] The terminal then converts the input data into JSON format and sends it as an HTTP POST request to a specific endpoint on the server, using common software libraries (e.g., Python's json library or requests library) for the conversion and transmission.

[0839] The server receives the HTTP POST request sent from the device. It extracts the JSON-formatted document data from the received request and prepares it for analysis. The analysis begins by checking whether the document data contains the word "evidence." If it does not, it generates a message saying "Insufficient evidence."

[0840] The server then divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a message saying "Insufficient explanation." As a result, it generates a JSON format summary of the results of insufficient evidence and explanation, and returns the analysis results to the terminal as an HTTP response.

[0841] The terminal receives the response from the server and displays the analysis results to the user, including a message indicating which specific parts are missing, so that the user can correct the document based on this information.

[0842] As a concrete example, if a user inputs the following document data, "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase," the document data contains no evidence and lacks explanation. When this document data is analyzed by the server, the server generates messages such as "Evidence is insufficient" and "Explanation is insufficient" and returns them to the terminal. The user can refer to the analysis results and revise the document.

[0843] When using a generative AI model, you can use the following as a prompt:

[0844] "When a user enters the following data, such as 'This is a description of a new project. The objective is to address a market need. The next steps are to define the requirements and complete the design phase,' please write Python code that will enable the system to detect missing evidence and explanations and generate analysis results."

[0845] The present invention makes it possible to automate the process of detecting insufficient evidence and explanations during the document creation process, thereby improving the quality of documents and increasing the efficiency of the work.

[0846] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0847] Step 1:

[0848] The user inputs the data.

[0849] The user uses an input form on their own device to input data such as presentation slides and requirements definition documents in text format. In concrete terms, the user might input the following: "This is an outline of a new project. The objective is to meet market needs. The next step is to complete the requirements definition and design phases." This input is captured on the device. Input: Data (text format) Output: Data (text format)

[0850] Step 2:

[0851] The device converts the data into JSON format.

[0852] The device converts the captured data into JSON format. Specifically, the device uses a conversion library to serialize the data into JSON format. Input: Data (text format) Output: Data (JSON format)

[0853] Step 3:

[0854] The device sends an HTTP POST request to the server

[0855] The terminal sends the converted JSON data as an HTTP POST request to a specific endpoint on the server. Specifically, the terminal uses the HTTP library to construct the request header and body and send it to the server. Input: Document data (JSON format) Output: HTTP POST request (JSON data)

[0856] Step 4:

[0857] The server receives the data.

[0858] The server receives the HTTP POST request sent from the terminal and extracts the document data in JSON format from the request body. Specifically, the server analyzes the request and loads the document data into memory. Input: HTTP POST request (JSON data) Output: Document data (JSON format)

[0859] Step 5:

[0860] The server analyzes the data.

[0861] The server analyzes the data and detects missing evidence and explanations. This analysis process includes detecting missing evidence and missing explanations. Input: Data (JSON format) Output: Messages about missing evidence and missing explanations

[0862] Step 6:

[0863] Detecting evidence gaps

[0864] The server checks whether the word "evidence" is included in the document data. Specifically, it performs a string search using a text analysis library. If it is not included, it generates a message saying "Insufficient evidence." Input: Document data (JSON format) Output: Insufficient evidence message

[0865] Step 7:

[0866] Detecting Missing Explanations

[0867] The server splits the data into words and counts the total number of words. Specifically, it uses a text tokenization library to split the data into words and count the total number. If the number of words is less than 100, it generates a message saying "Insufficient explanation." Input: Data (JSON format) Output: Insufficient explanation message

[0868] Step 8:

[0869] The server generates the analysis results.

[0870] The server aggregates messages with insufficient evidence and insufficient explanation and generates analysis results in JSON format. Input: messages with insufficient evidence, messages with insufficient explanation Output: analysis results (JSON format)

[0871] Step 9:

[0872] The server returns the analysis results to the device.

[0873] The server returns the generated analysis results to the terminal as an HTTP response. Specifically, the server uses an HTTP library to construct the response header and body and return the response. Input: Analysis results (JSON format) Output: HTTP response (analysis results)

[0874] Step 10:

[0875] The device displays the analysis results.

[0876] The terminal receives the response from the server and displays the analysis results to the user. Specifically, the terminal uses a UI component to visually display the analysis results. Input: HTTP response (analysis results) Output: Display of analysis results

[0877] (Application example 1)

[0878] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0879] In the past, store staff found it difficult to provide customers with reliable information when talking to customers or creating promotional materials due to a lack of evidence or explanation for the content. This led to missed sales opportunities and a decline in customer satisfaction. Solving this issue was an urgent need, especially in store operations, where quick responses on-site are required.

[0880] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0881] In this invention, the server includes means for receiving material data input by a user, means for detecting missing portions of evidence based on the material data, means for detecting missing portions of explanation based on the material data, means for automatically detecting missing portions of evidence and explanation based on the text of customer service talks and promotional materials, and means for displaying the results of the detection of missing portions to the user, thereby enabling store staff to quickly and efficiently create reliable customer service talks and promotional materials that include sufficient evidence and explanation.

[0882] A "user" is someone who uses this system to input material data and utilizes the results of evidence and explanation detection.

[0883] "Document data" refers to written data such as presentation slides, requirements definition documents, customer service talks, and sales promotion materials, which are input by users into the system.

[0884] "Evidence" refers to evidence or data used to support claims or explanations in source data.

[0885] "Means for detecting missing evidence" refers to the function of checking whether evidence is contained in the document data and detecting if evidence is missing.

[0886] "Means for detecting insufficient explanations" refers to a function that checks whether the explanations in the document data are sufficient and detects any insufficiency of the explanations.

[0887] "Customer service talk" refers to verbal explanations and guidance given by store staff to customers.

[0888] "Sales promotion materials" are materials intended to promote sales of products, and are text data that users can input into the system.

[0889] The "means for displaying" refers to a means for visually outputting to the user the evidence received from the server and the results of detection of missing parts of the explanation.

[0890] "Mobile device" refers to a portable computer device such as a smartphone or tablet.

[0891] "Server" refers to a computer system that receives document data sent by users and analyzes the data to detect missing evidence or explanations.

[0892] The present invention is a system that automatically detects missing evidence and explanations based on document data entered by a user, and is intended for use in brick-and-mortar stores in particular. A specific description of an embodiment of the present invention is given below.

[0893] This system mainly uses smartphones, tablets, and cloud servers. Users input text for customer service talk and sales promotion materials from their own devices, and the input data is converted to JSON format and sent to the server.

[0894] Hardware and Software Used

[0895] Smartphone / Tablet: Android or iOS device

[0896] Server: Cloud server (AWS, Google Cloud, Microsoft Azure, etc.)

[0897] API calls: Communicating with the server using HTTP requests

[0898] Natural Language Processing (NLP) library: spaCy, NLTK, or GPT-4 series (OpenAI API)

[0899] Program processing

[0900] Input and submit data

[0901] Users input text data such as customer service chat and sales promotion materials in text format through the application on their device. This data is automatically converted to JSON format and sent to the cloud server as an HTTP POST request.

[0902] Data analysis on the server

[0903] The server parses the received JSON data, specifically performing the following steps:

[0904] 1. Evidence detection:

[0905] Check whether the word "evidence" is included in the source data.

[0906] If not, generate a "missing evidence" message.

[0907] 2. Description detection:

[0908] The data is divided into words and the total number of words is counted.

[0909] If the word count is less than 100, generate a "Not enough description" message.

[0910] The generated detection results are packaged again in JSON format and sent to the user's device as an HTTP response.

[0911] Displaying the results

[0912] The user device receives the detection results sent from the server and visually displays them, including a message indicating which specific parts are missing.

[0913] Examples and prompts

[0914] For example, a store staff member may enter, "This product uses the latest technology." When this document data is sent to the server, it is detected as lacking evidence and a message is displayed saying, "There is insufficient evidence. Please add references or market data."

[0915] Examples of prompt sentences

[0916] This product uses the latest technology.

[0917] This text is entered as data and analyzed on the server.

[0918] Through this system, store staff can quickly and efficiently create reliable customer service talks and promotional materials that are fully packed with evidence and explanations, which is expected to increase sales and customer satisfaction.

[0919] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0920] Step 1:

[0921] The user starts the application on their own device and inputs text data for customer service conversations and sales promotion materials. The input text data is saved on the user's device.

[0922] input:

[0923] Text data of customer service talk and promotional materials

[0924] output:

[0925] Input text data stored on the device

[0926] Specific behavior:

[0927] The user enters text into an application input field and presses the "Submit" button.

[0928] Step 2:

[0929] The terminal converts the input text data into JSON format, which makes the data suitable for sending to the server.

[0930] input:

[0931] Input text data stored on the device

[0932] output:

[0933] Data converted to JSON format

[0934] Specific behavior:

[0935] Format text data into JSON format within the device application.

[0936] Step 3:

[0937] The terminal sends the data converted into JSON format to the cloud server as an HTTP POST request.

[0938] input:

[0939] Data converted to JSON format

[0940] output:

[0941] Data sent as an HTTP POST request

[0942] Specific behavior:

[0943] The device generates an HTTP POST request and sends it to a specific endpoint on the cloud server.

[0944] Step 4:

[0945] The server receives the HTTP POST request, extracts the JSON data from the request body, and prepares this data for parsing.

[0946] input:

[0947] JSON data included in HTTP POST requests

[0948] output:

[0949] JSON data prepared for parsing

[0950] Specific behavior:

[0951] The server reads the HTTP request body and passes the JSON data to the parsing process.

[0952] Step 5:

[0953] The server uses NLP libraries (e.g., spaCy, NLTK, GPT-4) to detect missing evidence and explanations in the material data.

[0954] Evidence detection: Checks whether the word "evidence" is included in the data. If not, generates a message saying "Insufficient evidence."

[0955] Description detection: Counts the number of words in the data and generates a "description is insufficient" message if there are fewer than 100 words.

[0956] input:

[0957] JSON data prepared for parsing

[0958] output:

[0959] Findings of missing evidence and explanations

[0960] Specific behavior:

[0961] Analyze the data using an NLP library and detect missing parts based on specific conditions.

[0962] Step 6:

[0963] The server packages the results of detecting missing evidence and explanations in JSON format and sends it to the user's device as an HTTP response.

[0964] input:

[0965] Findings of missing evidence and explanations

[0966] output:

[0967] Detection results sent as HTTP responses

[0968] Specific behavior:

[0969] The server converts the detection results into JSON format and sends them to the terminal as an HTTP response.

[0970] Step 7:

[0971] The device analyzes the detection results received from the server and visually displays them to the user, specifically, by displaying messages pointing out missing evidence or explanations.

[0972] input:

[0973] Detection results received as an HTTP response

[0974] output:

[0975] Detection result message displayed on the device

[0976] Specific behavior:

[0977] The application on the terminal analyzes the received data and displays a warning message on the user interface.

[0978] Step 8:

[0979] The user can refer to the displayed message to revise the content of the customer service talk or sales promotion material and re-enter it into the system. By repeating this process, the quality of the material can be improved.

[0980] input:

[0981] Feedback from users who received the message

[0982] output:

[0983] Corrected data

[0984] Specific behavior:

[0985] The user reviews the comments, corrects the material, and re-enters it.

[0986] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0987] The present invention is a system that automatically detects missing evidence or explanations in presentation slides, requirements definition documents, and other documents, and notifies the user of this, as well as a system that recognizes the user's emotions and displays the results accordingly. This system is configured as follows:

[0988] First, the user inputs the document data from their own device. The document data is text data such as presentation slides or requirements specifications, and is input in text format. Once input is complete, the device converts the document data into JSON format and sends it to the server as an HTTP POST request.

[0989] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted data from the request body. Based on the extracted data, the server analyzes the evidence and explanation for any missing parts.

[0990] To detect missing evidence, the server checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the document data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation."

[0991] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[0992] Additionally, the present invention includes an emotion engine that recognizes the user's emotions by analyzing the user's input data, response time, and even biometric information. For example, the emotion engine can estimate the user's emotional state based on whether the user is typing quickly or there is a delay.

[0993] Based on the estimated emotion, the device can customize how the detection results are displayed: for example, if the user is anxious, it will display more detailed and thorough explanations, whereas if the user is in a hurry, it will display only the important points concisely.

[0994] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection results are adjusted to be displayed concisely.

[0995] This system allows users to quickly and efficiently check for missing evidence or explanations and revise their materials. Furthermore, the introduction of an emotion engine enables flexible responses to match the user's emotional state, improving the user experience.

[0996] The processing flow will be explained below.

[0997] Step 1:

[0998] Users use their devices to input data, such as presentation slides and requirements specifications, using a text editor or a dedicated web form.

[0999] Step 2:

[1000] When the user has finished entering the document data, he or she clicks the "Send" button on the terminal. This operation causes the document data to proceed to the next process.

[1001] Step 3:

[1002] The device converts the document data into JSON format. The program on the device converts the document content into a format such as {"document": "document content here"}.

[1003] Step 4:

[1004] The device sends the JSON-formatted document data to the server as an HTTP POST request, which is sent to a specific endpoint on the server.

[1005] Step 5:

[1006] The server receives the HTTP POST request and extracts the document data in JSON format from the request body.

[1007] Step 6:

[1008] The server calls the analyze_document function to analyze the document data, which detects missing evidence and explanations based on the document data.

[1009] Step 7:

[1010] The server calls the find_evidence_issues function to check whether the document data contains the word "evidence." If it does not, it generates a warning message saying "Insufficient evidence."

[1011] Step 8:

[1012] The server calls the find_explanation_issues function, splits the document data into words, and counts the number of words. If the number of words is less than 100, it generates a warning message saying "Insufficient explanation."

[1013] Step 9:

[1014] The server compiles the results of the missing evidence and explanation in JSON format, including a detailed message about the missing parts.

[1015] Step 10:

[1016] The server returns the generated analysis results to the client terminal as an HTTP response, which includes a 200 status code (OK) and the analysis results.

[1017] Step 11:

[1018] The terminal receives the HTTP response and extracts the analysis results in JSON format from the response body.

[1019] Step 12:

[1020] In addition to the analysis results extracted by the device, the emotion engine is called to recognize the user's emotions. The emotion engine analyzes emotions based on the user's input data and response time.

[1021] Step 13:

[1022] Based on the analysis results of the emotion engine, the device customizes the way it displays the results of the detection of missing evidence and explanations. For example, if the user is in a hurry, it will briefly display only the important points.

[1023] Step 14:

[1024] The terminal displays the final missing part to the user, who can then check the missing part and begin correcting the document.

[1025] Step 15:

[1026] If necessary, the user can modify the material and then resubmit the new material data to the system.

[1027] Through these steps, users can quickly and efficiently identify missing evidence and explanations, and enjoy a better user experience through customized display by the emotion engine.

[1028] Example 2

[1029] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1030] Currently, many users create documents with insufficient evidence and explanations. However, manually detecting and correcting these insufficient parts is a time-consuming and labor-intensive task. In addition, the user's emotional state when creating documents can affect the final product, and conventional detection systems have not been able to respond flexibly to the user's emotions.

[1031] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1032] In this invention, the server includes means for receiving document data input by a user, means for converting the document data into JSON format and transmitting the converted data to the server, means for detecting missing portions of evidence based on the document data, means for detecting missing portions of explanation based on the document data, and means for displaying the detection results of missing portions of the document data in a customized manner based on the emotional state of the user. This not only enables users to efficiently detect and correct missing portions of evidence or explanation in the document, but also enables flexible responses that are adapted to the emotional state of each individual user.

[1033] "User" refers to the entity that uses this system to input material data and receive the results.

[1034] "Document data" refers to document information entered in text format, such as presentation slides or requirements specifications.

[1035] "JSON format" is an abbreviation for JavaScript Object Notation, and is a format for structuring and representing data.

[1036] The "server" refers to a device that analyzes the document data received from the terminal, detects missing evidence or explanations, and uses an emotion engine to recognize the user's emotional state.

[1037] "Means for detecting missing evidence" refers to the function of checking whether the word "evidence" is included in the source data and detecting any missing parts.

[1038] "Means for detecting missing parts of explanation" refers to a function that counts the total number of words in the document data and detects the missing parts if they do not meet the required standard.

[1039] "Emotional state" refers to the user's mental and psychological state, estimated based on the user's input data, response time, biometric information, etc.

[1040] The "means for customizing the display" refers to a function for displaying the results of the missing part detection in different formats depending on the emotional state of the user.

[1041] This invention is a system that automatically detects missing evidence and explanations in presentation slides, requirements specifications, and other documents, notifying the user of this, and also recognizes the user's emotions and displays the results accordingly.The system of this invention mainly uses three components: the user, the terminal, and the server.

[1042] First, the user inputs the document data using his / her own terminal. The document data is, for example, data in the following text format.

[1043] Example prompt sentence:

[1044] "This is the outline of a new project. The objective is to meet a market need. The next steps are to define the requirements and complete the design phase."

[1045] The terminal then converts the input data into JSON format and sends it to the server as an HTTP POST request. The terminal is equipped with software for data conversion and transmission, such as a programming language like Python and a library for sending HTTP requests (e.g., Requests).

[1046] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted document data from the request body. Specifically, an application server (e.g., Flask or Django) running on the server processes the HTTP request and parses the JSON data. At this time, the server runs an analysis program to detect missing evidence and explanations.

[1047] To detect missing evidence, the server checks whether the word "evidence" is included in the material data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the material data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation." A natural language processing library (e.g., NLTK or spaCy) can be used for this analysis.

[1048] Additionally, the server uses an emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's input data and response time to estimate their emotional state. For example, machine learning libraries such as TensorFlow and PyTorch can be used to build a predictive model. This can identify whether the user is in a hurry or feeling anxious.

[1049] Finally, the server generates the analysis results in JSON format and sends them back to the client device as an HTTP response. The device receives this response and displays a customized version according to the user's emotional state. Specifically, if the user is feeling anxious, it displays a detailed, thorough explanation, but if the user is in a hurry, it adjusts the display to display only the important points concisely. This display is achieved using a GUI (Graphical User Interface) application running on the device.

[1050] In this way, the system of the present invention helps users quickly and efficiently detect and correct missing parts of materials, and by introducing an emotion engine, it enables flexible responses according to the user's emotional state.

[1051] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1052] Step 1:

[1053] The user inputs the material data into the terminal.

[1054] Specifically, the user manually inputs text data such as presentation slides and requirements specifications into an input field on the terminal.

[1055] Input: The user enters text data.

[1056] Output: Text data is displayed on the terminal.

[1057] Step 2:

[1058] The terminal converts the input data into JSON format.

[1059] Specifically, the terminal application parses the text-formatted document data and calls a function to convert it into JSON format.

[1060] Input: Text material data entered into the terminal.

[1061] Output: Data converted to JSON format.

[1062] Step 3:

[1063] The terminal sends the document data converted into JSON format to the server as an HTTP POST request.

[1064] Specifically, the generated JSON data is sent to the server using an HTTP library on the terminal (e.g., Requests).

[1065] Input: Material data converted to JSON format.

[1066] Output: The HTTP POST request sent to the server.

[1067] Step 4:

[1068] The server receives the HTTP POST request sent from the terminal and extracts the document data in JSON format from the request body.

[1069] Specifically, the server's HTTP server software (e.g., Apache or NGINX) receives the request, and the application server (e.g., Flask or Django) parses the JSON data.

[1070] Input: The HTTP request sent from the terminal.

[1071] Output: Extracted material data in JSON format.

[1072] Step 5:

[1073] The server detects missing parts of evidence based on the document data.

[1074] Specifically, the server searches the text in the JSON data to see if it contains the word "evidence," and if it doesn't, generates a corresponding error message.

[1075] Input: Material data in JSON format.

[1076] Output: The message "Insufficient evidence."

[1077] Step 6:

[1078] The server detects missing parts of the explanation based on the document data.

[1079] Specifically, the server divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a corresponding error message.

[1080] Input: Material data in JSON format.

[1081] Output: The message "Description is missing."

[1082] Step 7:

[1083] The server aggregates both evidence-deficient and explanation-deficient results and generates the analysis results in JSON format.

[1084] Specifically, the server's analysis module converts the detection results into JSON format.

[1085] Input: "Insufficient evidence" and "Insufficient explanation" messages.

[1086] Output: JSON data of the generated analysis results.

[1087] Step 8:

[1088] The server returns the generated analysis results to the client terminal as an HTTP response.

[1089] Specifically, the server's HTTP library generates a response and sends it to the client terminal.

[1090] Input: JSON data of the generated analysis results.

[1091] Output: The HTTP response sent to the client device.

[1092] Step 9:

[1093] The server uses an emotion engine to recognize the user's emotional state.

[1094] Specifically, the server analyzes the user's input data and response time, and uses a machine learning model to estimate the user's emotional state.

[1095] Input: User input data and response times.

[1096] Output: Estimated user emotional state.

[1097] Step 10:

[1098] The device customizes how the detection results are displayed based on the user's emotional state.

[1099] Specifically, the GUI application on the device receives the emotional state data and adjusts the display content accordingly. For example, it may display detailed and thorough explanations to a user who is feeling anxious, or it may display only the important points concisely to a user who is in a hurry.

[1100] Input: Estimated user emotional state and analysis results from the server.

[1101] Output: A customized display of the findings.

[1102] (Application example 2)

[1103] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1104] In factories, work reports and data logs are often insufficient, which reduces work efficiency and productivity. Furthermore, the lack of feedback based on the emotional state of workers makes it difficult to make effective corrections or take action. To solve this problem, a system that automatically detects missing information and provides flexible feedback based on the emotional state of workers is needed.

[1105] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1106] In this invention, the server includes means for receiving document data input by a user, means for detecting missing parts of evidence based on the document data, means for detecting missing parts of explanation based on the document data, means for displaying the detection results of the missing parts to the user, means for recognizing the emotion of the user, and means for customizing the display method of the detection results based on the emotion recognition. This makes it possible to automatically correct defects in the document data and immediately provide appropriate feedback according to the emotion of the worker.

[1107] "Document data" refers to data such as documents and reports entered by the user, and is the basis for the system's analysis.

[1108] "Evidence" refers to the evidence or supporting information mentioned in the document data, and the system will detect any lack of this information.

[1109] "Emotion recognition" is a technology that analyzes a user's input data and biometric information to identify the user's emotional state.

[1110] "Customizing the display method" means changing the display format of the detection results depending on the user's emotional state, for example, providing a detailed explanation if the user is feeling anxious, or a concise explanation if the user is in a hurry.

[1111] The present invention realizes a "smart reporting assistant" system installed on factory robots that analyzes reports and data logs entered by workers, automatically detects gaps in evidence and explanations, and customizes feedback based on the worker's emotional state.

[1112] First, the user inputs the data from their own device. The data is text data such as a work report or data log, and is input in text format. Once input is complete, the device converts the data into JSON format and sends it to the server as an HTTP POST request.

[1113] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted data from the request body. Based on the extracted data, the server analyzes the evidence and explanation for any missing parts and identifies the missing parts.

[1114] To detect missing evidence, the server checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the document data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation."

[1115] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[1116] Furthermore, the present invention includes an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotions by analyzing the user's input data and biometric information. For example, the emotion engine infers the user's emotional state from when the user is typing quickly or when there is a delay.

[1117] Based on this inferred emotion, the server customizes the way the detection results are displayed: for example, if the user is anxious, it will display more detailed and thorough explanations, whereas if the user is in a hurry, it will display only the important points in a concise manner.

[1118] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection results are adjusted to be displayed concisely.

[1119] This invention allows users to quickly and efficiently check for missing evidence or explanations and revise materials. Furthermore, the introduction of an emotion engine enables flexible responses to match the user's emotional state, improving the user experience.

[1120] Examples of prompts include "We're in a hurry" and "This is an overview of a new project. The objective is to meet a market need. The next steps are to define requirements and complete the design phase."

[1121] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1122] Step 1:

[1123] The user inputs material data from the terminal. The material data is text data such as work reports and data logs. This material data is input in text format. After input, the terminal converts the material data into JSON format. The input here is material data in text format, and the output is material data in JSON format. The terminal sends the material data converted to JSON format to the server as an HTTP POST request.

[1124] Step 2:

[1125] The server receives the HTTP POST request sent from the terminal and extracts the JSON formatted data from the request body. The input in this step is the HTTP POST request and the output is the JSON formatted data. The server converts the data into text format and prepares it for the next analysis.

[1126] Step 3:

[1127] The server detects missing evidence. Specifically, it checks whether the word "evidence" is included in the document data. This check may result in the generation of a message saying "Insufficient evidence." The input here is text-formatted document data, and the output is a message indicating insufficient evidence.

[1128] Step 4:

[1129] The server detects missing parts of the explanation. It divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a message saying "There is insufficient explanation." The input in this step is the data in text format, and the output is a message saying there is insufficient explanation.

[1130] Step 5:

[1131] The server compiles both the lack of evidence and the lack of explanation results and generates an analysis result in JSON format. The server returns this analysis result to the client device as an HTTP response. The input in this step is the lack of evidence and the lack of explanation message, and the output is the analysis result in JSON format.

[1132] Step 6:

[1133] To recognize the user's emotions, the server uses an emotion engine. The emotion engine analyzes the user's input data and biometric information to identify the user's emotional state. For example, it can estimate whether the user is in a hurry or anxious based on input speed and delay. The input here is the user's input data and biometric information, and the output is the user's emotional state.

[1134] Step 7:

[1135] The server customizes the display of the detection results based on the user's emotional state. For example, if the user is anxious, it will display more detailed explanations, and if the user is in a hurry, it will display only the important points in a concise manner. The input for this step is the user's emotional state and the analysis results in JSON format, and the output is a message in a customized display format.

[1136] As a concrete example, if a user enters the following document data, "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase," this document data contains no evidence and has fewer than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient explanation," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection result is displayed concisely.

[1137] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1138] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1139] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1140] [Fourth embodiment]

[1141] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1142] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1144] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1145] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1148] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1149] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1150] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1152] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1153] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1154] The present invention is a system that automatically detects missing evidence or explanations in presentation slides, requirements definition documents, and other documents, and notifies the user of these. This system is configured as follows.

[1155] First, the user inputs the document data from their own device. The document data is written data such as presentation slides and requirements specifications, and is input in text format. Once the user has finished inputting the document data, the device converts the data into JSON format and sends it to a specific endpoint on the server as an HTTP POST request.

[1156] The server receives an HTTP POST request from the device and extracts the JSON-formatted document data from the request body. Based on the extracted document data, the server analyzes the content of the document. This analysis focuses on detecting missing pieces of evidence and explanation.

[1157] To detect missing evidence, the server first checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Evidence is missing."

[1158] To detect missing explanations, the data is divided into words and the total number of words is counted. If the number of words is less than 100, the server generates a message saying "There is insufficient explanation."

[1159] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[1160] The terminal receives the response from the server and displays the analysis results to the user. The display includes a message pointing out specific areas that are lacking. The user can use this information to correct the document.

[1161] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. The user can then view the results and revise the document.

[1162] The system of the present invention can automatically detect missing evidence and explanations and quickly and effectively improve the quality of documents, thereby significantly reducing the manual review work required in the past and improving the efficiency of business processes.

[1163] The processing flow will be explained below.

[1164] Step 1:

[1165] Users use their devices to input data, specifically, the contents of presentation slides and requirements specifications, using a text editor or a dedicated web form.

[1166] Step 2:

[1167] When the user has finished entering the document data, he or she clicks the "Send" button on the terminal. This operation causes the document data to proceed to the next process.

[1168] Step 3:

[1169] The device converts the document data into JSON format. The program on the device converts the document content into a format such as {"document": "document content here"}.

[1170] Step 4:

[1171] The device sends the JSON-formatted data to the server as an HTTP POST request, which is sent to a specific endpoint on the server, such as / analyze.

[1172] Step 5:

[1173] The server receives an HTTP POST request and extracts the document data in JSON format from the request body.

[1174] Step 6:

[1175] The server calls the analyze_document function to analyze the document data, which detects missing evidence and explanations based on the document data.

[1176] Step 7:

[1177] The server calls the find_evidence_issues function to check whether the document data contains the word "evidence." If it does not, it generates a warning message saying "Insufficient evidence."

[1178] Step 8:

[1179] The server calls the find_explanation_issues function, splits the document data into words, and counts the number of words. If the number of words is less than 100, it generates a warning message saying "Insufficient explanation."

[1180] Step 9:

[1181] The server compiles the results of the missing evidence and explanation in JSON format, including a detailed message of the missing part.

[1182] Step 10:

[1183] The server returns the generated analysis results to the client terminal as an HTTP response, which includes a 200 status code (OK) and the analysis results.

[1184] Step 11:

[1185] The terminal receives the HTTP response and extracts the analysis results in JSON format from the response body.

[1186] Step 12:

[1187] The device displays the extracted analysis results to the user. Specifically, a warning message such as "Insufficient evidence" or "Insufficient explanation" is displayed on the screen.

[1188] Step 13:

[1189] The user can check the missing parts displayed and correct the materials. If necessary, they can re-enter new material data and resubmit it to the system.

[1190] Through the above steps, missing parts of evidence or explanations in documents such as presentation slides or requirements specifications are efficiently detected, allowing users to quickly and effectively revise the documents.

[1191] Example 1

[1192] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1193] Conventional document verification systems require users to manually check for missing evidence and explanations after creating documents, which is time-consuming and labor-intensive. Human error can easily lead to oversights, potentially resulting in a decline in document quality. Furthermore, an efficient method is required when verifying multiple documents in a short period of time.

[1194] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1195] In this invention, the server includes means for inputting material data from a user, means for converting the material data into JSON format, means for transmitting the JSON-formatted material data to the server as an HTTP POST request, means for receiving the transmitted material data and extracting the JSON-formatted material data from the request body, means for detecting missing parts of evidence based on the material data, means for detecting missing parts of explanation based on the material data, means for generating results of the missing evidence and missing explanation in JSON format and returning the analysis results to the terminal, and means for displaying the missing part detection results to the user. This makes it possible to automatically detect missing parts of evidence and explanation and quickly and effectively improve the quality of materials.

[1196] "User" means an individual or organization that uses this system.

[1197] "Document data" refers to document information such as presentation slides and requirements definition documents, and is text data entered by the user.

[1198] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format for describing data in a structured manner.

[1199] An "HTTP POST request" is a method of sending data using the Hypertext Transfer Protocol, and is a request to send data to a server.

[1200] A "server" is a computer system that receives requests via a network and analyzes the data.

[1201] "Evidence" refers to the evidence or reasoning provided to support a fact or claim within a document.

[1202] An "endpoint" refers to a server-side URL or URI that provides a specific function when communicating.

[1203] The "request body" is the data payload portion included in the HTTP request, and is the portion that contains the content of the document data.

[1204] "Number of words" refers to the result of counting the total number of words in the material data.

[1205] "Analysis results" refers to data compiled in JSON format that identifies the results of detection of insufficient evidence or explanation based on document data.

[1206] A "response" refers to response data returned from a server to a client.

[1207] A "client terminal" is a computer system used by a user, and is a device that communicates with a server to send material data and receive analysis results.

[1208] "Display" refers to visually providing the analysis results to the user, specifically to displaying a message on the screen.

[1209] The present invention is a system that automatically detects missing evidence and explanations in document data and notifies the user. This system operates in cooperation with both the user terminal and the server.

[1210] First, the user inputs the data using their own device. This data is entered in text format as document information such as presentation slides or requirements definition documents. For example, it might look like this: "This is the outline of a new project. The objective is to meet market needs. The next step is to complete the requirements definition and design phases."

[1211] The terminal then converts the input data into JSON format and sends it as an HTTP POST request to a specific endpoint on the server, using common software libraries (e.g., Python's json library or requests library) for the conversion and transmission.

[1212] The server receives the HTTP POST request sent from the device. It extracts the JSON-formatted document data from the received request and prepares it for analysis. The analysis begins by checking whether the document data contains the word "evidence." If it does not, it generates a message saying "Insufficient evidence."

[1213] The server then divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a message saying "Insufficient explanation." As a result, it generates a JSON format summary of the results of insufficient evidence and explanation, and returns the analysis results to the terminal as an HTTP response.

[1214] The terminal receives the response from the server and displays the analysis results to the user, including a message indicating which specific parts are missing, so that the user can correct the document based on this information.

[1215] As a concrete example, if a user inputs the following document data, "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase," the document data contains no evidence and lacks explanation. When this document data is analyzed by the server, the server generates messages such as "Evidence is insufficient" and "Explanation is insufficient" and returns them to the terminal. The user can refer to the analysis results and revise the document.

[1216] When using a generative AI model, you can use the following as a prompt:

[1217] "When a user enters the following data, such as 'This is a description of a new project. The objective is to address a market need. The next steps are to define the requirements and complete the design phase,' please write Python code that will enable the system to detect missing evidence and explanations and generate analysis results."

[1218] The present invention makes it possible to automate the process of detecting insufficient evidence and explanations during the document creation process, thereby improving the quality of documents and increasing the efficiency of the work.

[1219] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1220] Step 1:

[1221] The user inputs the data.

[1222] The user uses an input form on their own device to input data such as presentation slides and requirements definition documents in text format. In concrete terms, the user might input the following: "This is an outline of a new project. The objective is to meet market needs. The next step is to complete the requirements definition and design phases." This input is captured on the device. Input: Data (text format) Output: Data (text format)

[1223] Step 2:

[1224] The device converts the data into JSON format.

[1225] The device converts the captured data into JSON format. Specifically, the device uses a conversion library to serialize the data into JSON format. Input: Data (text format) Output: Data (JSON format)

[1226] Step 3:

[1227] The device sends an HTTP POST request to the server

[1228] The terminal sends the converted JSON data as an HTTP POST request to a specific endpoint on the server. Specifically, the terminal uses the HTTP library to construct the request header and body and send it to the server. Input: Document data (JSON format) Output: HTTP POST request (JSON data)

[1229] Step 4:

[1230] The server receives the data.

[1231] The server receives the HTTP POST request sent from the terminal and extracts the document data in JSON format from the request body. Specifically, the server analyzes the request and loads the document data into memory. Input: HTTP POST request (JSON data) Output: Document data (JSON format)

[1232] Step 5:

[1233] The server analyzes the data.

[1234] The server analyzes the data and detects missing evidence and explanations. This analysis process includes detecting missing evidence and missing explanations. Input: Data (JSON format) Output: Messages about missing evidence and missing explanations

[1235] Step 6:

[1236] Detecting evidence gaps

[1237] The server checks whether the word "evidence" is included in the document data. Specifically, it performs a string search using a text analysis library. If it is not included, it generates a message saying "Insufficient evidence." Input: Document data (JSON format) Output: Insufficient evidence message

[1238] Step 7:

[1239] Detecting Missing Explanations

[1240] The server splits the data into words and counts the total number of words. Specifically, it uses a text tokenization library to split the data into words and count the total number. If the number of words is less than 100, it generates a message saying "Insufficient explanation." Input: Data (JSON format) Output: Insufficient explanation message

[1241] Step 8:

[1242] The server generates the analysis results.

[1243] The server aggregates messages with insufficient evidence and insufficient explanation and generates analysis results in JSON format. Input: messages with insufficient evidence, messages with insufficient explanation Output: analysis results (JSON format)

[1244] Step 9:

[1245] The server returns the analysis results to the device.

[1246] The server returns the generated analysis results to the terminal as an HTTP response. Specifically, the server uses an HTTP library to construct the response header and body and return the response. Input: Analysis results (JSON format) Output: HTTP response (analysis results)

[1247] Step 10:

[1248] The device displays the analysis results.

[1249] The terminal receives the response from the server and displays the analysis results to the user. Specifically, the terminal uses a UI component to visually display the analysis results. Input: HTTP response (analysis results) Output: Display of analysis results

[1250] (Application example 1)

[1251] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1252] In the past, store staff found it difficult to provide customers with reliable information when talking to customers or creating promotional materials due to a lack of evidence or explanation for the content. This led to missed sales opportunities and a decline in customer satisfaction. Solving this issue was an urgent need, especially in store operations, where quick responses on-site are required.

[1253] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1254] In this invention, the server includes means for receiving material data input by a user, means for detecting missing portions of evidence based on the material data, means for detecting missing portions of explanation based on the material data, means for automatically detecting missing portions of evidence and explanation based on the text of customer service talks and promotional materials, and means for displaying the results of the detection of missing portions to the user, thereby enabling store staff to quickly and efficiently create reliable customer service talks and promotional materials that include sufficient evidence and explanation.

[1255] A "user" is someone who uses this system to input material data and utilizes the results of evidence and explanation detection.

[1256] "Document data" refers to written data such as presentation slides, requirements definition documents, customer service talks, and sales promotion materials, which are input by users into the system.

[1257] "Evidence" refers to evidence or data used to support claims or explanations in source data.

[1258] "Means for detecting missing evidence" refers to the function of checking whether evidence is contained in the document data and detecting if evidence is missing.

[1259] "Means for detecting insufficient explanations" refers to a function that checks whether the explanations in the document data are sufficient and detects any insufficiency of the explanations.

[1260] "Customer service talk" refers to verbal explanations and guidance given by store staff to customers.

[1261] "Sales promotion materials" are materials intended to promote sales of products, and are text data that users can input into the system.

[1262] The "means for displaying" refers to a means for visually outputting to the user the evidence received from the server and the results of detection of missing parts of the explanation.

[1263] "Mobile device" refers to a portable computer device such as a smartphone or tablet.

[1264] "Server" refers to a computer system that receives document data sent by users and analyzes the data to detect missing evidence or explanations.

[1265] The present invention is a system that automatically detects missing evidence and explanations based on document data entered by a user, and is intended for use in brick-and-mortar stores in particular. A specific description of an embodiment of the present invention is given below.

[1266] This system mainly uses smartphones, tablets, and cloud servers. Users input text for customer service talk and sales promotion materials from their own devices, and the input data is converted to JSON format and sent to the server.

[1267] Hardware and Software Used

[1268] Smartphone / Tablet: Android or iOS device

[1269] Server: Cloud server (AWS, Google Cloud, Microsoft Azure, etc.)

[1270] API calls: Communicating with the server using HTTP requests

[1271] Natural Language Processing (NLP) library: spaCy, NLTK, or GPT-4 series (OpenAI API)

[1272] Program processing

[1273] Input and submit data

[1274] Users input text data such as customer service chat and sales promotion materials in text format through the application on their device. This data is automatically converted to JSON format and sent to the cloud server as an HTTP POST request.

[1275] Data analysis on the server

[1276] The server parses the received JSON data, specifically performing the following steps:

[1277] 1. Evidence detection:

[1278] Check whether the word "evidence" is included in the source data.

[1279] If not, generate a "missing evidence" message.

[1280] 2. Description detection:

[1281] The data is divided into words and the total number of words is counted.

[1282] If the word count is less than 100, generate a "Not enough description" message.

[1283] The generated detection results are packaged again in JSON format and sent to the user's device as an HTTP response.

[1284] Displaying the results

[1285] The user device receives the detection results sent from the server and visually displays them, including a message indicating which specific parts are missing.

[1286] Examples and prompts

[1287] For example, a store staff member may enter, "This product uses the latest technology." When this document data is sent to the server, it is detected as lacking evidence and a message is displayed saying, "There is insufficient evidence. Please add references or market data."

[1288] Examples of prompt sentences

[1289] This product uses the latest technology.

[1290] This text is entered as data and analyzed on the server.

[1291] Through this system, store staff can quickly and efficiently create reliable customer service talks and promotional materials that are fully packed with evidence and explanations, which is expected to increase sales and customer satisfaction.

[1292] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1293] Step 1:

[1294] The user starts the application on their own device and inputs text data for customer service conversations and sales promotion materials. The input text data is saved on the user's device.

[1295] input:

[1296] Text data of customer service talk and promotional materials

[1297] output:

[1298] Input text data stored on the device

[1299] Specific behavior:

[1300] The user enters text into an application input field and presses the "Submit" button.

[1301] Step 2:

[1302] The terminal converts the input text data into JSON format, which makes the data suitable for sending to the server.

[1303] input:

[1304] Input text data stored on the device

[1305] output:

[1306] Data converted to JSON format

[1307] Specific behavior:

[1308] Format text data into JSON format within the device application.

[1309] Step 3:

[1310] The terminal sends the data converted into JSON format to the cloud server as an HTTP POST request.

[1311] input:

[1312] Data converted to JSON format

[1313] output:

[1314] Data sent as an HTTP POST request

[1315] Specific behavior:

[1316] The device generates an HTTP POST request and sends it to a specific endpoint on the cloud server.

[1317] Step 4:

[1318] The server receives the HTTP POST request, extracts the JSON data from the request body, and prepares this data for parsing.

[1319] input:

[1320] JSON data included in HTTP POST requests

[1321] output:

[1322] JSON data prepared for parsing

[1323] Specific behavior:

[1324] The server reads the HTTP request body and passes the JSON data to the parsing process.

[1325] Step 5:

[1326] The server uses NLP libraries (e.g., spaCy, NLTK, GPT-4) to detect missing evidence and explanations in the material data.

[1327] Evidence detection: Checks whether the word "evidence" is included in the data. If not, generates a message saying "Insufficient evidence."

[1328] Description detection: Counts the number of words in the data and generates a "description is insufficient" message if there are fewer than 100 words.

[1329] input:

[1330] JSON data prepared for parsing

[1331] output:

[1332] Findings of missing evidence and explanations

[1333] Specific behavior:

[1334] Analyze the data using an NLP library and detect missing parts based on specific conditions.

[1335] Step 6:

[1336] The server packages the results of detecting missing evidence and explanations in JSON format and sends it to the user's device as an HTTP response.

[1337] input:

[1338] Findings of missing evidence and explanations

[1339] output:

[1340] Detection results sent as HTTP responses

[1341] Specific behavior:

[1342] The server converts the detection results into JSON format and sends them to the terminal as an HTTP response.

[1343] Step 7:

[1344] The device analyzes the detection results received from the server and visually displays them to the user, specifically, by displaying messages pointing out missing evidence or explanations.

[1345] input:

[1346] Detection results received as an HTTP response

[1347] output:

[1348] Detection result message displayed on the device

[1349] Specific behavior:

[1350] The application on the terminal analyzes the received data and displays a warning message on the user interface.

[1351] Step 8:

[1352] The user can refer to the displayed message to revise the content of the customer service talk or sales promotion material and re-enter it into the system. By repeating this process, the quality of the material can be improved.

[1353] input:

[1354] Feedback from users who received the message

[1355] output:

[1356] Corrected data

[1357] Specific behavior:

[1358] The user reviews the comments, corrects the material, and re-enters it.

[1359] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1360] The present invention is a system that automatically detects missing evidence or explanations in presentation slides, requirements definition documents, and other documents, and notifies the user of this, as well as a system that recognizes the user's emotions and displays the results accordingly. This system is configured as follows:

[1361] First, the user inputs the document data from their own device. The document data is text data such as presentation slides or requirements specifications, and is input in text format. Once input is complete, the device converts the document data into JSON format and sends it to the server as an HTTP POST request.

[1362] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted data from the request body. Based on the extracted data, the server analyzes the evidence and explanation for any missing parts.

[1363] To detect missing evidence, the server checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the document data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation."

[1364] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[1365] Additionally, the present invention includes an emotion engine that recognizes the user's emotions by analyzing the user's input data, response time, and even biometric information. For example, the emotion engine can estimate the user's emotional state based on whether the user is typing quickly or there is a delay.

[1366] Based on the estimated emotion, the device can customize how the detection results are displayed: for example, if the user is anxious, it will display more detailed and thorough explanations, whereas if the user is in a hurry, it will display only the important points concisely.

[1367] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection results are adjusted to be displayed concisely.

[1368] This system allows users to quickly and efficiently check for missing evidence or explanations and revise their materials. Furthermore, the introduction of an emotion engine enables flexible responses to match the user's emotional state, improving the user experience.

[1369] The processing flow will be explained below.

[1370] Step 1:

[1371] Users use their devices to input data, such as presentation slides and requirements specifications, using a text editor or a dedicated web form.

[1372] Step 2:

[1373] When the user has finished entering the document data, he or she clicks the "Send" button on the terminal. This operation causes the document data to proceed to the next process.

[1374] Step 3:

[1375] The device converts the document data into JSON format. The program on the device converts the document content into a format such as {"document": "document content here"}.

[1376] Step 4:

[1377] The device sends the JSON-formatted document data to the server as an HTTP POST request, which is sent to a specific endpoint on the server.

[1378] Step 5:

[1379] The server receives the HTTP POST request and extracts the document data in JSON format from the request body.

[1380] Step 6:

[1381] The server calls the analyze_document function to analyze the document data, which detects missing evidence and explanations based on the document data.

[1382] Step 7:

[1383] The server calls the find_evidence_issues function to check whether the document data contains the word "evidence." If it does not, it generates a warning message saying "Insufficient evidence."

[1384] Step 8:

[1385] The server calls the find_explanation_issues function, splits the document data into words, and counts the number of words. If the number of words is less than 100, it generates a warning message saying "Insufficient explanation."

[1386] Step 9:

[1387] The server compiles the results of the missing evidence and explanation in JSON format, including a detailed message about the missing parts.

[1388] Step 10:

[1389] The server returns the generated analysis results to the client terminal as an HTTP response, which includes a 200 status code (OK) and the analysis results.

[1390] Step 11:

[1391] The terminal receives the HTTP response and extracts the analysis results in JSON format from the response body.

[1392] Step 12:

[1393] In addition to the analysis results extracted by the device, the emotion engine is called to recognize the user's emotions. The emotion engine analyzes emotions based on the user's input data and response time.

[1394] Step 13:

[1395] Based on the analysis results of the emotion engine, the device customizes the way it displays the results of the detection of missing evidence and explanations. For example, if the user is in a hurry, it will briefly display only the important points.

[1396] Step 14:

[1397] The terminal displays the final missing part to the user, who can then check the missing part and begin correcting the document.

[1398] Step 15:

[1399] If necessary, the user can modify the material and then resubmit the new material data to the system.

[1400] Through these steps, users can quickly and efficiently identify missing evidence and explanations, and enjoy a better user experience through customized display by the emotion engine.

[1401] Example 2

[1402] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1403] Currently, many users create documents with insufficient evidence and explanations. However, manually detecting and correcting these insufficient parts is a time-consuming and labor-intensive task. In addition, the user's emotional state when creating documents can affect the final product, and conventional detection systems have not been able to respond flexibly to the user's emotions.

[1404] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1405] In this invention, the server includes means for receiving document data input by a user, means for converting the document data into JSON format and transmitting the converted data to the server, means for detecting missing portions of evidence based on the document data, means for detecting missing portions of explanation based on the document data, and means for displaying the detection results of missing portions of the document data in a customized manner based on the emotional state of the user. This not only enables users to efficiently detect and correct missing portions of evidence or explanation in the document, but also enables flexible responses that are adapted to the emotional state of each individual user.

[1406] "User" refers to the entity that uses this system to input material data and receive the results.

[1407] "Document data" refers to document information entered in text format, such as presentation slides or requirements specifications.

[1408] "JSON format" is an abbreviation for JavaScript Object Notation, and is a format for structuring and representing data.

[1409] The "server" refers to a device that analyzes the document data received from the terminal, detects missing evidence or explanations, and uses an emotion engine to recognize the user's emotional state.

[1410] "Means for detecting missing evidence" refers to the function of checking whether the word "evidence" is included in the source data and detecting any missing parts.

[1411] "Means for detecting missing parts of explanation" refers to a function that counts the total number of words in the document data and detects the missing parts if they do not meet the required standard.

[1412] "Emotional state" refers to the user's mental and psychological state, estimated based on the user's input data, response time, biometric information, etc.

[1413] The "means for customizing the display" refers to a function for displaying the results of the missing part detection in different formats depending on the emotional state of the user.

[1414] This invention is a system that automatically detects missing evidence and explanations in presentation slides, requirements specifications, and other documents, notifying the user of this, and also recognizes the user's emotions and displays the results accordingly.The system of this invention mainly uses three components: the user, the terminal, and the server.

[1415] First, the user inputs the document data using his / her own terminal. The document data is, for example, data in the following text format.

[1416] Example prompt sentence:

[1417] "This is the outline of a new project. The objective is to meet a market need. The next steps are to define the requirements and complete the design phase."

[1418] The terminal then converts the input data into JSON format and sends it to the server as an HTTP POST request. The terminal is equipped with software for data conversion and transmission, such as a programming language like Python and a library for sending HTTP requests (e.g., Requests).

[1419] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted document data from the request body. Specifically, an application server (e.g., Flask or Django) running on the server processes the HTTP request and parses the JSON data. At this time, the server runs an analysis program to detect missing evidence and explanations.

[1420] To detect missing evidence, the server checks whether the word "evidence" is included in the material data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the material data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation." A natural language processing library (e.g., NLTK or spaCy) can be used for this analysis.

[1421] Additionally, the server uses an emotion engine to recognize the user's emotional state. This emotion engine analyzes the user's input data and response time to estimate their emotional state. For example, machine learning libraries such as TensorFlow and PyTorch can be used to build a predictive model. This can identify whether the user is in a hurry or feeling anxious.

[1422] Finally, the server generates the analysis results in JSON format and sends them back to the client device as an HTTP response. The device receives this response and displays a customized version according to the user's emotional state. Specifically, if the user is feeling anxious, it displays a detailed, thorough explanation, but if the user is in a hurry, it adjusts the display to display only the important points concisely. This display is achieved using a GUI (Graphical User Interface) application running on the device.

[1423] In this way, the system of the present invention helps users quickly and efficiently detect and correct missing parts of materials, and by introducing an emotion engine, it enables flexible responses according to the user's emotional state.

[1424] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1425] Step 1:

[1426] The user inputs the material data into the terminal.

[1427] Specifically, the user manually inputs text data such as presentation slides and requirements specifications into an input field on the terminal.

[1428] Input: The user enters text data.

[1429] Output: Text data is displayed on the terminal.

[1430] Step 2:

[1431] The terminal converts the input data into JSON format.

[1432] Specifically, the terminal application parses the text-formatted document data and calls a function to convert it into JSON format.

[1433] Input: Text material data entered into the terminal.

[1434] Output: Data converted to JSON format.

[1435] Step 3:

[1436] The terminal sends the document data converted into JSON format to the server as an HTTP POST request.

[1437] Specifically, the generated JSON data is sent to the server using an HTTP library on the terminal (e.g., Requests).

[1438] Input: Material data converted to JSON format.

[1439] Output: The HTTP POST request sent to the server.

[1440] Step 4:

[1441] The server receives the HTTP POST request sent from the terminal and extracts the document data in JSON format from the request body.

[1442] Specifically, the server's HTTP server software (e.g., Apache or NGINX) receives the request, and the application server (e.g., Flask or Django) parses the JSON data.

[1443] Input: The HTTP request sent from the terminal.

[1444] Output: Extracted material data in JSON format.

[1445] Step 5:

[1446] The server detects missing parts of evidence based on the document data.

[1447] Specifically, the server searches the text in the JSON data to see if it contains the word "evidence," and if it doesn't, generates a corresponding error message.

[1448] Input: Material data in JSON format.

[1449] Output: The message "Insufficient evidence."

[1450] Step 6:

[1451] The server detects missing parts of the explanation based on the document data.

[1452] Specifically, the server divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a corresponding error message.

[1453] Input: Material data in JSON format.

[1454] Output: The message "Description is missing."

[1455] Step 7:

[1456] The server aggregates both evidence-deficient and explanation-deficient results and generates the analysis results in JSON format.

[1457] Specifically, the server's analysis module converts the detection results into JSON format.

[1458] Input: "Insufficient evidence" and "Insufficient explanation" messages.

[1459] Output: JSON data of the generated analysis results.

[1460] Step 8:

[1461] The server returns the generated analysis results to the client terminal as an HTTP response.

[1462] Specifically, the server's HTTP library generates a response and sends it to the client terminal.

[1463] Input: JSON data of the generated analysis results.

[1464] Output: The HTTP response sent to the client device.

[1465] Step 9:

[1466] The server uses an emotion engine to recognize the user's emotional state.

[1467] Specifically, the server analyzes the user's input data and response time, and uses a machine learning model to estimate the user's emotional state.

[1468] Input: User input data and response times.

[1469] Output: Estimated user emotional state.

[1470] Step 10:

[1471] The device customizes how the detection results are displayed based on the user's emotional state.

[1472] Specifically, the GUI application on the device receives the emotional state data and adjusts the display content accordingly. For example, it may display detailed and thorough explanations to a user who is feeling anxious, or it may display only the important points concisely to a user who is in a hurry.

[1473] Input: Estimated user emotional state and analysis results from the server.

[1474] Output: A customized display of the findings.

[1475] (Application example 2)

[1476] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1477] In factories, work reports and data logs are often insufficient, which reduces work efficiency and productivity. Furthermore, the lack of feedback based on the emotional state of workers makes it difficult to make effective corrections or take action. To solve this problem, a system that automatically detects missing information and provides flexible feedback based on the emotional state of workers is needed.

[1478] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1479] In this invention, the server includes means for receiving document data input by a user, means for detecting missing parts of evidence based on the document data, means for detecting missing parts of explanation based on the document data, means for displaying the detection results of the missing parts to the user, means for recognizing the emotion of the user, and means for customizing the display method of the detection results based on the emotion recognition. This makes it possible to automatically correct defects in the document data and immediately provide appropriate feedback according to the emotion of the worker.

[1480] "Document data" refers to data such as documents and reports entered by the user, and is the basis for the system's analysis.

[1481] "Evidence" refers to the evidence or supporting information mentioned in the document data, and the system will detect any lack of this information.

[1482] "Emotion recognition" is a technology that analyzes a user's input data and biometric information to identify the user's emotional state.

[1483] "Customizing the display method" means changing the display format of the detection results depending on the user's emotional state, for example, providing a detailed explanation if the user is feeling anxious, or a concise explanation if the user is in a hurry.

[1484] The present invention realizes a "smart reporting assistant" system installed on factory robots that analyzes reports and data logs entered by workers, automatically detects gaps in evidence and explanations, and customizes feedback based on the worker's emotional state.

[1485] First, the user inputs the data from their own device. The data is text data such as a work report or data log, and is input in text format. Once input is complete, the device converts the data into JSON format and sends it to the server as an HTTP POST request.

[1486] The server receives the HTTP POST request sent from the device and extracts the JSON-formatted data from the request body. Based on the extracted data, the server analyzes the evidence and explanation for any missing parts and identifies the missing parts.

[1487] To detect missing evidence, the server checks whether the word "evidence" is included in the document data. If this word is not included, the server generates a message saying "Insufficient evidence." To detect missing explanations, the server divides the document data into words and counts their total number. If the number of words is less than 100, the server generates a message saying "Insufficient explanation."

[1488] The server aggregates both evidence-deficient and explanation-deficient results and generates analysis results in JSON format, which are then sent back to the client device as an HTTP response.

[1489] Furthermore, the present invention includes an emotion engine that recognizes the user's emotions. This emotion engine recognizes the user's emotions by analyzing the user's input data and biometric information. For example, the emotion engine infers the user's emotional state from when the user is typing quickly or when there is a delay.

[1490] Based on this inferred emotion, the server customizes the way the detection results are displayed: for example, if the user is anxious, it will display more detailed and thorough explanations, whereas if the user is in a hurry, it will display only the important points in a concise manner.

[1491] As a concrete example, consider the case where a user enters the following document data: "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase." This document data does not contain any evidence, and the description is less than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient description," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection results are adjusted to be displayed concisely.

[1492] This invention allows users to quickly and efficiently check for missing evidence or explanations and revise materials. Furthermore, the introduction of an emotion engine enables flexible responses to match the user's emotional state, improving the user experience.

[1493] Examples of prompts include "We're in a hurry" and "This is an overview of a new project. The objective is to meet a market need. The next steps are to define requirements and complete the design phase."

[1494] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1495] Step 1:

[1496] The user inputs material data from the terminal. The material data is text data such as work reports and data logs. This material data is input in text format. After input, the terminal converts the material data into JSON format. The input here is material data in text format, and the output is material data in JSON format. The terminal sends the material data converted to JSON format to the server as an HTTP POST request.

[1497] Step 2:

[1498] The server receives the HTTP POST request sent from the terminal and extracts the JSON formatted data from the request body. The input in this step is the HTTP POST request and the output is the JSON formatted data. The server converts the data into text format and prepares it for the next analysis.

[1499] Step 3:

[1500] The server detects missing evidence. Specifically, it checks whether the word "evidence" is included in the document data. This check may result in the generation of a message saying "Insufficient evidence." The input here is text-formatted document data, and the output is a message indicating insufficient evidence.

[1501] Step 4:

[1502] The server detects missing parts of the explanation. It divides the data into words and counts the total number of words. If the number of words is less than 100, it generates a message saying "There is insufficient explanation." The input in this step is the data in text format, and the output is a message saying there is insufficient explanation.

[1503] Step 5:

[1504] The server compiles both the lack of evidence and the lack of explanation results and generates an analysis result in JSON format. The server returns this analysis result to the client device as an HTTP response. The input in this step is the lack of evidence and the lack of explanation message, and the output is the analysis result in JSON format.

[1505] Step 6:

[1506] To recognize the user's emotions, the server uses an emotion engine. The emotion engine analyzes the user's input data and biometric information to identify the user's emotional state. For example, it can estimate whether the user is in a hurry or anxious based on input speed and delay. The input here is the user's input data and biometric information, and the output is the user's emotional state.

[1507] Step 7:

[1508] The server customizes the display of the detection results based on the user's emotional state. For example, if the user is anxious, it will display more detailed explanations, and if the user is in a hurry, it will display only the important points in a concise manner. The input for this step is the user's emotional state and the analysis results in JSON format, and the output is a message in a customized display format.

[1509] As a concrete example, if a user enters the following document data, "This is an outline of a new project. The objective is to meet market needs. The next steps are to define requirements and complete the design phase," this document data contains no evidence and has fewer than 100 words. When this document data is sent to the server and analyzed, the server generates messages such as "Insufficient evidence" and "Insufficient explanation," and returns them to the client terminal. On the other hand, if the emotion engine detects that the user is in a hurry, the detection result is displayed concisely.

[1510] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1511] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1512] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1513] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1514] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1515] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1516] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1517] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1518] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1519] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1520] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1521] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1522] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1523] 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.

[1524] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1525] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1526] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1527] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1528] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1529] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1530] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1531] The following is further disclosed regarding the above embodiment.

[1532] (Claim 1)

[1533] means for receiving material data input by a user;

[1534] means for detecting missing portions of evidence based on the document data;

[1535] means for detecting a missing part of the explanation based on the material data;

[1536] means for displaying the missing portion detection result to a user;

[1537] A system including:

[1538] (Claim 2)

[1539] 2. The system of claim 1, wherein the material data is transmitted to the server in JSON format.

[1540] (Claim 3)

[1541] 2. The system according to claim 1, wherein the means for detecting missing portions of evidence checks whether the material data contains the word "evidence."

[1542] "Example 1"

[1543] (Claim 1)

[1544] A means for inputting document data from a user;

[1545] A means for converting the material data into a JSON format;

[1546] means for transmitting the JSON formatted material data to a server as an HTTP POST request;

[1547] a means for receiving the transmitted document data and extracting the document data in JSON format from the request body;

[1548] means for detecting missing portions of evidence based on the document data;

[1549] means for detecting a missing part of the explanation based on the material data;

[1550] means for generating the results of the lack of evidence and lack of explanation in JSON format and returning the analysis results to the terminal;

[1551] means for displaying the missing portion detection result to a user;

[1552] A system including:

[1553] (Claim 2)

[1554] 2. The system of claim 1, wherein the material data is transmitted to the server in JSON format.

[1555] (Claim 3)

[1556] 2. The system according to claim 1, wherein the means for detecting missing portions of evidence checks whether the material data contains the word "evidence."

[1557] "Application Example 1"

[1558] (Claim 1)

[1559] means for receiving material data input by a user;

[1560] means for detecting missing portions of evidence based on the document data;

[1561] means for detecting a missing part of the explanation based on the material data;

[1562] A method to automatically detect missing evidence and explanations based on customer service talk and promotional materials text,

[1563] means for displaying the missing portion detection result to a user;

[1564] A system including:

[1565] (Claim 2)

[1566] 2. The system of claim 1, wherein the material data is transmitted to the server in JSON format.

[1567] (Claim 3)

[1568] 2. The system according to claim 1, wherein the means for detecting missing portions of evidence checks whether the material data contains the word "evidence."

[1569] "Example 2: Combining Emotion Engines"

[1570] (Claim 1)

[1571] means for receiving material data input by a user;

[1572] means for converting the material data into a JSON format and transmitting the JSON format to a server;

[1573] means for detecting missing portions of evidence based on the document data;

[1574] means for detecting a missing part of the explanation based on the material data;

[1575] a means for customizing and displaying the missing part detection result based on the emotional state of the user;

[1576] A system including:

[1577] (Claim 2)

[1578] 2. The system of claim 1, wherein the material data is transmitted to the server in JSON format.

[1579] (Claim 3)

[1580] 2. The system according to claim 1, wherein the means for detecting missing portions of the evidence checks whether the material data contains the word "evidence."

[1581] "Application example 2 when combining emotion engines"

[1582] (Claim 1)

[1583] means for receiving material data input by a user;

[1584] means for detecting missing portions of evidence based on the document data;

[1585] means for detecting a missing part of the explanation based on the material data;

[1586] means for displaying the missing portion detection result to a user;

[1587] means for recognizing the emotion of the user;

[1588] a means for customizing how detection results are displayed based on emotion recognition;

[1589] A system including:

[1590] (Claim 2)

[1591] 2. The system of claim 1, wherein the material data is transmitted to the server in JSON format.

[1592] (Claim 3)

[1593] 2. The system according to claim 1, wherein the means for detecting missing portions of evidence checks whether the material data contains the word "evidence." [Explanation of symbols]

[1594] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving material data input by a user; means for detecting missing portions of evidence based on the document data; means for detecting a missing part of the explanation based on the material data; means for displaying the missing portion detection result to a user; A system including:

2. The system of claim 1 , wherein the document data is transmitted to the server in JSON format.

3. 2. The system according to claim 1, wherein the means for detecting a missing portion of evidence checks whether the material data contains the word "evidence."

Images