System

Abstract

A system is provided.SOLUTION: The system includes a means for acquiring a voucher list, a means for randomly selecting a voucher from the acquired voucher list, a means for generating and transmitting a request for collecting the selected voucher, a means for storing the collected voucher and checking consistency, and a means for displaying voucher data so that a user can confirm and approve the voucher data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Responding to audits at listed companies requires a huge amount of time and effort, and the unproductive work of collecting and evaluating supporting documents is a significant burden on the entire company. Furthermore, because audit response work involves repeating roughly the same procedures every year, there is a strong need for automation. Furthermore, audit expertise tends to be highly dependent on individuals, creating a need for greater efficiency in management evaluations and internal control evaluations. The objective of this invention is to solve these problems and improve the efficiency of audit response and reduce the amount of effort required. [Means for solving the problem]

[0005] The present invention provides a system including means for acquiring a list of evidential documents, means for randomly selecting evidential documents from the acquired list, means for generating and sending a request to collect the selected evidential documents, means for storing the collected evidential documents and checking their consistency, and means for displaying the evidential data so that the user can confirm and approve it. The system also includes means for evaluating the evidential data based on preset evaluation criteria, means for generating evaluation results and creating an evaluation result report, and means for notifying and displaying the evaluation result report so that the user can view and confirm it. The system also includes means for allowing the user to send additional collection requests, and means for the user to determine actions based on the evaluation results and notify relevant departments.

[0006] This system will streamline the automated collection and evaluation of supporting documents, significantly reducing the amount of work required to respond to audits. Furthermore, by automating management evaluation and internal control evaluation, it will prevent reliance on individuals and enable the sharing and standardization of audit knowledge. This will reduce the audit response burden for listed companies as a whole, allowing resources to be focused on more productive tasks.

[0007] A "list of supporting documents" refers to a list of various supporting documents and data required for audit responses and internal control evaluations.

[0008] "Random selection" refers to a process of random selection based on a specific algorithm, without any specific rules or bias.

[0009] "Request" means a request message sent to obtain or collect specific information or data.

[0010] "Data integrity" refers to ensuring that data is accurate, consistent, and conforms to expected format and content.

[0011] "Evaluation criteria" refers to pre-established standards or rules for making specific evaluations or judgments.

[0012] "Evaluation results report" refers to documents and data that compile and record the results of the evaluation process.

[0013] "Additional Collection Request" refers to a request message for further evidence or data when the initial collection is insufficient.

[0014] "Notifying relevant departments" refers to conveying specific information or instructions to specific departments within an organization. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] Automatic document collection tool

[0037] The present invention is a system for improving the efficiency of audit responses, and includes an automatic document collection tool and an evaluation automation tool. First, the automatic document collection tool will be described.

[0038] The server first obtains a list of documents to be audited. This list is collected from an ERP system or database. Next, the server generates a random sample from the obtained list of documents. This random sample generation algorithm randomly selects any document.

[0039] The server generates a request to collect the selected evidence and sends it to the relevant department or system. This request specifies the type and quantity of evidence and includes a collection request. The terminal receives this request, collects the evidence in real time, and sends it back to the server.

[0040] The server stores the received supporting data in an internal database and checks its consistency. This consistency check identifies missing or abnormal data. The user uses the terminal to review and approve the collected supporting data. If additional collection is required, the user can send an additional collection request through the terminal.

[0041] Specific examples

[0042] For example, a server retrieves a list of supporting documents for a monthly report from an ERP system. This list contains purchase statements for a given month. The server uses a random algorithm to select 50 purchasing statements and sends requests to each department to collect these supporting documents.

[0043] The terminal receives this request, extracts the specified purchase details from the database, and sends them to the server. The server saves the received supporting data and performs a consistency check. The user then checks and approves the data on the terminal.

[0044] Evaluation automation tool

[0045] Next, we will explain the evaluation automation tool. The server receives supporting data and starts the evaluation process. The server executes an automatic evaluation algorithm based on pre-set evaluation criteria. These evaluation criteria include various criteria for internal control evaluation.

[0046] The server generates the results of the evaluation process and creates an evaluation result report, which is stored in a database for the user to review. The server then sends a notification of the evaluation result to the terminal, prompting the user to review the evaluation result.

[0047] Users can check the evaluation results report through their terminal and determine the necessary actions. For example, if an abnormality is discovered, the user can issue instructions to the relevant department for investigation or correction.

[0048] Specific examples

[0049] The server retrieves the previously collected purchase statement data and evaluates each statement for consistency and validity based on the evaluation criteria set. Evaluation algorithms perform this and identify outliers and inconsistent data.

[0050] A report of the evaluation results is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and instruct the purchasing department to conduct further investigations into any inconsistencies in the data.

[0051] In this way, the present invention realizes automatic collection of supporting documents and automated evaluation, thereby significantly reducing the amount of work required to respond to audits and improving efficiency.

[0052] The processing flow will be explained below.

[0053] Automatic document collection tool

[0054] Step 1:

[0055] The server automatically retrieves the list of evidence to be audited from the ERP system or database, and the retrieved list of evidence is saved in the internal database.

[0056] Step 2:

[0057] The server executes an algorithm to randomly select a particular document from the obtained document list. A random sample is selected.

[0058] Step 3:

[0059] The server generates a request to collect the selected evidence, which is then sent to the relevant department or system.

[0060] Step 4:

[0061] The terminal receives the request and extracts the specified evidence from the associated database, and the extracted evidence data is sent from the terminal to the server.

[0062] Step 5:

[0063] The server stores the received supporting data in an internal database and checks the integrity of the stored data.

[0064] Step 6:

[0065] The user checks the collected evidence data through the terminal and approves the checked data.

[0066] Step 7:

[0067] If the user needs to collect additional evidence, the terminal sends an additional collection request to the server.

[0068] Evaluation automation tool

[0069] Step 1:

[0070] The server retrieves the supporting document data received from the automated supporting document collection tool from the database, and rechecks the consistency of the retrieved data.

[0071] Step 2:

[0072] The server evaluates the supporting data based on the set evaluation criteria, and executes the evaluation algorithm to evaluate the effectiveness of internal controls.

[0073] Step 3:

[0074] The server generates the evaluation results and creates an evaluation result report, which is stored in an internal database.

[0075] Step 4:

[0076] The server sends a notification of the evaluation result to the terminal, which then displays the evaluation result to the user.

[0077] Step 5:

[0078] The user checks the evaluation result report through the terminal, determines the necessary actions, and notifies the relevant departments of correction instructions and investigation requests.

[0079] Through these steps, the automated collection and evaluation of supporting documents is achieved, reducing the amount of work required and improving efficiency in responding to audits.

[0080] Example 1

[0081] 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."

[0082] In conventional audit response systems, the process of collecting and evaluating supporting documents is manual, requiring time and effort. Furthermore, manual collection and evaluation is prone to human error, and data integrity cannot be guaranteed. Furthermore, there are inefficiencies in the process of reviewing and approving the evaluation results, creating a need for greater efficiency in the entire audit process.

[0083] 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.

[0084] In this invention, the server includes a means for acquiring a list of supporting documents from a data management system, a means for randomly selecting supporting documents from the acquired list using a random algorithm, and a means for generating a request to collect the selected supporting documents and sending it to each department via a network. This automates the process of collecting supporting documents, eliminates manual errors, and enables efficient audit response. The server also stores the collected supporting document data in a database and has a means for checking its consistency, ensuring the consistency and reliability of the data. Furthermore, the server includes a means for displaying the supporting document data so that users can confirm and approve it using a terminal, thereby realizing rapid confirmation of evaluation results and the approval process.

[0085] A "list of supporting documents" is a list that summarizes the types and details of supporting documents required for audit responses and business evaluations.

[0086] A "data management system" is an information system that manages and stores business data in a company or organization, and allows access and retrieval for specific purposes.

[0087] A "random algorithm" is a computational method for randomly drawing samples from a data set, used to ensure a fair and unbiased selection.

[0088] A "network" is an information transmission mechanism that connects multiple computers and terminals so that they can communicate with each other.

[0089] A "request" is a command to request specific data or an operation, and is used to obtain or send information between systems.

[0090] A "database" is a structured collection of data that can efficiently manage and store large amounts of data and can be quickly accessed and searched when needed.

[0091] "Integrity" is a property that ensures that data is consistent and free of errors and omissions, and is important for ensuring the accuracy and reliability of data.

[0092] An "automated evaluation algorithm" is a calculation method that allows a program to automatically analyze and evaluate collected data based on pre-set evaluation criteria.

[0093] "Evaluation criteria" are a set of rules and indicators that are used as standards when evaluating and judging data, and they define the appropriateness and problems of the subject of evaluation.

[0094] An "evaluation result report" is a document or data file that summarizes the results of the evaluation process, and indicates the status of the subject of evaluation and whether or not there are any abnormalities.

[0095] A "terminal" refers to a device such as a computer or mobile device that can be directly operated by a user, and is used to input data into the system and display results.

[0096] "User" refers to a person or role who operates the system to perform actual work or audits, and is the entity that uses the various functions of the system.

[0097] "Notification" means a message or signal that informs a user of particular information or results.

[0098] "Verification" refers to the act of checking the content of data or information to confirm whether it is accurate.

[0099] "Approval" refers to the act of acknowledging the correctness and validity of confirmed data or information.

[0100] "Action" refers to specific measures or steps taken based on the evaluation results, and means actions taken to solve problems or make improvements.

[0101] Automatic document collection tool

[0102] Server Processing

[0103] The server first obtains a list of evidence to be audited from the data management system or internal database. This process involves extracting the necessary data using, for example, an SQL query. Based on the obtained list of evidence, a random algorithm is used to randomly select evidence, using an algorithm such as Python's random.sample function. During this process, a request to collect the selected evidence is generated and sent to each department via the network. This request is often sent using an HTTP request.

[0104] Terminal handling

[0105] The terminal receives a request for collecting supporting documents from the server, extracts the specified supporting documents from the database, and sends them to the server. The terminal also returns the extracted data to the server as an HTTP response. During this process, the necessary database queries are executed to ensure that the supporting document data is accurately sent to the server.

[0106] User Action

[0107] Users can use their devices to check and approve the supporting data stored on the server. They can view and manipulate the data through a GUI, and can send requests for additional supporting data to the server as needed. This increases the accuracy and reliability of audits.

[0108] Specific examples

[0109] For example, the server retrieves a list of supporting documents required for monthly reports from the ERP system. Based on the retrieved list, a random sample generation algorithm is used to select 50 purchasing details. A request is generated for each selected supporting document and a request to collect the supporting documents is sent to each department. The terminal receives this request, extracts the specified purchasing details from the database, and sends them to the server. The server stores the received supporting document data and checks its consistency. The user uses the terminal to check and approve the data. If there are any problems, the user can send additional collection requests.

[0110] Prompt Sentence Examples

[0111] Based on the document list obtained from the ERP system, 50 purchasing details are randomly selected and a document collection request is sent to each department. The terminal then retrieves the document from the database and sends it to the server. The server saves the data and checks its integrity. The user then uses the terminal to check and approve the document data.

[0112] Evaluation automation tool

[0113] Server Processing

[0114] The server retrieves the collected supporting data from the database and starts the evaluation process. This process includes an automated evaluation algorithm based on pre-defined evaluation criteria, including the consistency of internal control standards and business processes. Evaluation results are generated and an evaluation result report is created based on the results. This report is saved in the database and notified to the user.

[0115] User Action

[0116] Users can check the evaluation result report through their terminal and decide on the necessary actions. If an abnormality is found in the evaluation results, users can send instructions for investigation or correction to the relevant department through their terminal. This allows for quick confirmation and response of audit results.

[0117] Specific examples

[0118] The server evaluates the collected purchasing specification data based on the evaluation criteria and identifies outliers and inconsistent data. An evaluation result report is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and issue instructions to the purchasing department for further investigation or correction of inconsistent data.

[0119] Prompt Sentence Examples

[0120] The collected purchasing specification data is evaluated based on evaluation criteria to identify outliers and inconsistencies. An evaluation result report is created and notified to the user. The user can check the evaluation results via their terminal, and if an abnormality is found, they can issue instructions to the purchasing department for investigation or correction.

[0121] In this way, the present invention realizes automatic collection of supporting documents and automated evaluation, thereby reducing the number of steps required for audits and improving efficiency.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Automatic document collection tool

[0124] Server Processing Steps

[0125] Step 1:

[0126] The server retrieves the list of supporting documents to be audited from the data management system. The input is raw data retrieved from the ERP system or internal database, and the necessary data is extracted using SQL queries. The output is a list of supporting documents required for the audit.

[0127] Specifically, the server executes a query such as "SELECT FROM evidence_list WHERE month='2023-10';" to retrieve the target evidence list from the database.

[0128] Step 2:

[0129] The server randomly selects a voucher from the obtained list of vouchers using a random algorithm. The input is the list of vouchers obtained in step 1, and it processes the algorithm to randomly extract data. The output is a sample list of randomly selected vouchers.

[0130] Specifically, for example, 50 supporting documents are selected using Python's random.sample function.

[0131] Step 3:

[0132] The server generates a request to collect the selected evidence and sends it to each department via the network. The input is the list of evidence selected in step 2, and the output is the collection request sent to each department.

[0133] Specifically, an HTTP request is generated and sent to the URL of each department.

[0134] Step 4:

[0135] The terminal receives the collection request sent from the server and extracts the specified evidence from the database. The input is the collection request from the server, and the output is the extracted evidence data.

[0136] Specifically, the terminal executes the query "SELECT FROM evidences WHERE id=?" and sends the extracted results to the server.

[0137] Step 5:

[0138] The server stores the received supporting data in an internal database and checks its consistency. The input is the supporting data sent from the terminal, and the output is the consistency check result and the stored data.

[0139] Specifically, the system stores supporting data in a database and runs a consistency check algorithm, detecting missing or anomalous data.

[0140] Step 6:

[0141] The user uses a terminal to check the evidence data stored on the server and give approval. The input is the evidence data stored on the server, and the output is the user's confirmation and approval results.

[0142] Specifically, the GUI screen displays the data, allows the user to review and approve it, and allows the user to submit additional collection requests if necessary.

[0143] Evaluation automation tool

[0144] Server Processing Steps

[0145] Step 1:

[0146] The server retrieves the collected supporting data from the database and starts the evaluation process. The input is the collected supporting data and the output is the data ready to run the evaluation process.

[0147] Specifically, a database query is executed to extract the data to be evaluated.

[0148] Step 2:

[0149] The server executes an automatic evaluation algorithm based on pre-defined evaluation criteria. The input is the supporting data obtained in step 1, and the output is the evaluation result.

[0150] Specifically, it runs evaluation algorithms implemented in languages ​​such as Python to assess the integrity and validity of the data.

[0151] Step 3:

[0152] The server creates an evaluation result report based on the results of the evaluation process. The input is the evaluation result, and the output is the evaluation result report.

[0153] Specifically, a report is generated based on the evaluation results and stored in a database.

[0154] Step 4:

[0155] The server notifies the user of the evaluation result report and allows the user to check it on the terminal. The input is the evaluation result report, and the output is a notification message to the user.

[0156] Specifically, an HTTP request for notification is generated and sent to the user's terminal.

[0157] User processing steps

[0158] Step 5:

[0159] The user checks the evaluation result report through the terminal and decides on the necessary action. The input is the evaluation result report, and the output is the user's action instructions.

[0160] Specifically, the report is viewed using a GUI that displays the evaluation results, and if any abnormalities or inconsistencies are found, instructions are issued to the purchasing department or other department to investigate or correct the issues.

[0161] As described above, the processing steps of the present invention have been explained together with specific operations. This clarifies the process of automatic collection of supporting documents and automated evaluation, and is expected to enable efficient audit response.

[0162] (Application example 1)

[0163] 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."

[0164] Logistics centers are required to manage a huge number of supporting documents (receipts, shipping certificates, inventory lists, etc.), and collecting and evaluating these documents takes a lot of time and effort. In particular, consistency checks and anomaly detection for these documents are often done manually, so there is a need for efficiency improvements. There is also a need for a system that can reduce the workload of on-site workers and quickly collect and evaluate supporting documents.

[0165] 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.

[0166] In this invention, the server includes means for acquiring a list of evidence, means for randomly selecting evidence from the acquired list of evidence, means for generating and sending a request to collect the selected evidence, means for saving the collected evidence and checking its consistency, means for displaying the evidence data so that the user can confirm and approve it, means for creating a request for evidence collection and sending it to the relevant department, and means for checking the consistency and evaluating the acquired evidence data. This makes it possible to efficiently collect evidence at a logistics center and automatically evaluate it.

[0167] A "list of supporting documents" is a list of supporting documents required for audits and business processes, and is obtained from an ERP system or database.

[0168] "Randomly selecting evidence" means randomly selecting evidence from a list of evidence based on a pre-set algorithm.

[0169] "Generate and send a request" refers to automatically creating a request to collect the selected evidence and sending it to the relevant department or system.

[0170] "Consistency checking" is the process of verifying that the collected supporting data is appropriate and free of inconsistencies or anomalies.

[0171] "Evidence data" refers to the specific information and content of each evidence obtained and collected.

[0172] "Evaluating supporting data based on evaluation criteria" refers to the process of automatically evaluating the accuracy and suitability of collected supporting data according to pre-set criteria and conditions.

[0173] An "evaluation result report" is a report summarizing the results of the evaluation process of supporting data.

[0174] "Instructing investigation and correction" means that if any inconsistencies or abnormalities are discovered based on the evaluation results, the relevant department will be asked to carry out the necessary investigation and correction work.

[0175] "On-site workers collect and upload supporting documents using smartphones" refers to the process in which on-site workers at the logistics center collect supporting documents using smartphones and upload them to a server via a dedicated application.

[0176] "Login and user authentication" refers to entering the user authentication information required to access the system and taking appropriate security measures.

[0177] "Generating prompts using a generative AI model and providing automated assistance" refers to an assistance function that uses AI technology to create prompts and simplify user operations.

[0178] As an embodiment of the present invention, the specific configuration and procedures of a document management system used in a logistics center are described below. This system has functions such as obtaining a document list, randomly selecting documents, generating and sending document collection requests, checking the integrity of documents, evaluating data based on evaluation criteria, generating and notifying result reports, and even issuing investigation and correction instructions.

[0179] First, the server retrieves the list of evidence from the ERP system or database. From the retrieved list of evidence, the server randomly selects evidence, generates a request to collect it, and sends it to the relevant department. This process is implemented using a Python program and the "requests" module. For example, the list of evidence can be obtained through an API endpoint, and evidence can be randomly selected using the "random" module.

[0180] The server then sends requests to each department to collect the selected evidence, and field workers use their smartphones to collect the evidence. The collected evidence data is then uploaded from the smartphone to the server. The smartphone application plays an important role in this process, making it possible to collect and upload evidence in real time. It also has security features such as login and user authentication, and appropriate access control is performed by entering authentication information.

[0181] The collected supporting data is stored on a server and a consistency check is performed. This consistency check, which includes checking the correct date format and numeric range, is implemented using the Python datetime module, for example. Once the consistency of the supporting data is confirmed, it is evaluated based on pre-set evaluation criteria. The evaluation results are generated as an evaluation result report and notified to the user.

[0182] After reviewing the evaluation results, users can instruct the relevant department to investigate and correct any abnormal supporting documentation data. Generative AI models can also be used to automatically create prompts, simplifying user operations. For example, a prompt could be generated such as, "Please explain the system for automatically collecting and evaluating supporting documentation at a logistics center. Please provide a detailed explanation of the integrity check and evaluation process for randomly selected supporting documentation."

[0183] In this way, the present invention can improve the efficiency of document management at logistics centers and reduce the workload. It also enables real-time collection and evaluation of documented evidence, enabling immediate problem detection and countermeasures.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] The server retrieves the document list from the ERP system or database. In this step, it accesses the API endpoint using the Python requests module to retrieve the document list. The input is the API endpoint URL, and the output is the document list data in JSON format.

[0187] Step 2:

[0188] The server randomly selects evidence from the obtained evidence list. In this step, the Python random module is used to randomly select a specified number of evidence from the evidence list. The input is the evidence list data, and the output is the selected evidence data.

[0189] Step 3:

[0190] The server generates and sends a request to collect the selected evidence. The request specifies the type and quantity of evidence and is sent to the relevant departments and parties. The input is the selected evidence data, and the output is a request message sent to each department.

[0191] Step 4:

[0192] The terminal receives a request from the server, and the on-site worker collects the evidence using a smartphone. The worker takes a photo of the evidence with a camera and uploads it along with location and time information. The input is the request message, and the output is the evidence image data and accompanying information.

[0193] Step 5:

[0194] The server stores the supporting data uploaded by field workers and checks its consistency. It uses the Python datetime module to check the correct date format and numeric range. The input is the supporting data image data and accompanying information, and the output is the consistency check results.

[0195] Step 6:

[0196] The server evaluates the integrity-checked supporting data based on pre-defined evaluation criteria, generates evaluation results, and creates a result report. It runs an automated evaluation algorithm based on the evaluation criteria to identify outliers and inconsistent data. The input is the integrity-checked supporting data, and the output is an evaluation result report.

[0197] Step 7:

[0198] The server notifies the user of the evaluation result report, allowing the user to check the results. The user can review the evaluation results and determine the necessary actions. The input is the evaluation result report, and the output is notification and display on the user screen.

[0199] Step 8:

[0200] If the user finds any abnormal supporting data, they can instruct the relevant department to investigate and correct it. A generative AI model is used to automatically create prompts, simplifying user operations. The input is the evaluation results and the prompts generated by the generative AI model, and the output is instructions to the relevant department to investigate and correct the abnormality.

[0201] In this way, by linking each processing step, automatic collection and evaluation of supporting documents at the logistics center is realized.

[0202] 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.

[0203] Overall overview

[0204] This invention is a system for streamlining audit response, which includes an automatic document collection tool and an evaluation automation tool, and also combines an emotion engine that recognizes user emotions and adjusts various system processes.

[0205] Automatic document collection tool

[0206] The server first automatically retrieves the list of documents to be audited from the ERP system or database. This list is stored in an internal database. The server then runs an algorithm to randomly select specific documents from the list of documents to generate a random sample.

[0207] The server generates a request to collect the selected evidence and sends it to the relevant department or system. The terminal receives the request, extracts the specified evidence from the relevant database, and sends it to the server. The server stores the received evidence data in an internal database and checks its consistency. The user uses the terminal to check and approve the collected evidence data. If additional collection is required, the user can send an additional collection request through the terminal.

[0208] Specific examples

[0209] For example, the server retrieves a list of supporting documents required for a monthly report from the ERP system. This list includes purchasing details for a specified month. The server selects 50 purchasing details using a random algorithm and sends a request to each department to collect these supporting documents. The terminal receives this request, extracts the specified purchasing details from the database, and sends them to the server. The server saves the received supporting document data and performs a consistency check. The user checks and approves the data on the terminal.

[0210] Evaluation automation tool

[0211] Next, we will explain the evaluation automation tool. The server receives supporting data and starts the evaluation process. Based on pre-set evaluation criteria, the server executes an automatic evaluation algorithm. These evaluation criteria include various standards for internal control evaluation. The server generates the results of the evaluation process and creates an evaluation result report. This report is saved in a database so that the user can check it. The server sends a notification of the evaluation result to the terminal, prompting the user to check the evaluation result. The user checks the evaluation result report through the terminal and determines the necessary actions. For example, if an abnormality is discovered, the user can issue instructions for investigation or correction to the relevant department.

[0212] Specific examples

[0213] The server retrieves the previously collected purchasing statement data and evaluates the consistency and validity of each statement based on the evaluation criteria that have been set. The evaluation algorithm executes this and identifies outliers and inconsistent data. A report of the evaluation results is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and instruct the purchasing department to conduct further investigations on inconsistent data.

[0214] Emotion engine integration

[0215] The emotion engine recognizes the user's emotional state and adjusts various system processes. The emotion engine evaluates the user's stress level and concentration level in real time when verifying and approving supporting documents. This emotional data is reflected in the configuration of the supporting document verification process, additional collection requests, and evaluation process.

[0216] Specific examples

[0217] For example, if a user feels stressed while reviewing supporting data, the emotion engine can detect this and make automatic suggestions to simplify the review process. Also, if the user is highly focused, the engine can prompt the user to review more detailed data. Furthermore, the engine can dynamically adjust evaluation criteria based on emotion data and suggest actions based on the evaluation results. The emotion engine can recommend users with high stress levels to send additional collection requests.

[0218] Through these steps, the system will enable the automatic collection of supporting documents, automated evaluation, and process adjustments based on user feedback, resulting in a significant reduction in audit response time and increased efficiency.

[0219] The processing flow will be explained below.

[0220] Automatic document collection tool

[0221] Step 1:

[0222] The server automatically retrieves the list of evidence to be audited from the ERP system or database, and the retrieved list of evidence is saved in the internal database.

[0223] Step 2:

[0224] The server executes an algorithm to randomly select a particular document from the obtained document list. A random sample is selected.

[0225] Step 3:

[0226] The server generates a request to collect the selected evidence and sends the request to the relevant department or system.

[0227] Step 4:

[0228] The terminal receives the request and extracts the specified evidence from the associated database, and the extracted evidence data is sent from the terminal to the server.

[0229] Step 5:

[0230] The server stores the received supporting data in an internal database and checks the integrity of the stored data.

[0231] Step 6:

[0232] The user checks the collected evidence data through the terminal and approves the checked data.

[0233] Step 7:

[0234] If the user needs to collect additional evidence, the terminal sends an additional collection request to the server.

[0235] Evaluation automation tool

[0236] Step 1:

[0237] The server retrieves the supporting document data received from the automated supporting document collection tool from the database, and rechecks the consistency of the retrieved data.

[0238] Step 2:

[0239] The server evaluates the supporting data based on the set evaluation criteria, and executes the evaluation algorithm to evaluate the effectiveness of internal controls.

[0240] Step 3:

[0241] The server generates the evaluation results and creates an evaluation result report, which is stored in an internal database.

[0242] Step 4:

[0243] The server sends a notification of the evaluation result to the terminal, which then displays the evaluation result to the user.

[0244] Step 5:

[0245] The user checks the evaluation result report through the terminal, determines the necessary actions, and notifies the relevant departments of correction instructions and investigation requests.

[0246] Emotion engine integration

[0247] Step 1:

[0248] The emotion engine recognizes the user's emotional state. The emotion engine analyzes the user's facial expressions, tone of voice, typing speed, etc. to collect emotional data in real time.

[0249] Step 2:

[0250] The emotion engine analyzes the collected emotional data to determine the user's stress level and concentration, which is reflected in the verification and approval process of supporting data.

[0251] Step 3:

[0252] When a user checks the evidence data, the emotion engine adjusts the initial settings according to the user's emotional state. For example, if the user is feeling stressed, the emotion engine provides an assistance function to simplify the checking process.

[0253] Step 4:

[0254] The server dynamically adjusts the evaluation criteria. The evaluation criteria are flexibly changed based on the emotional data acquired by the emotion engine. When the user is highly focused, a stricter evaluation is performed.

[0255] Step 5:

[0256] The server generates the evaluation report, and the emotion engine adjusts the report display based on the user's emotional state: if stress is high, the report is summarized.

[0257] Step 6:

[0258] The emotion engine suggests additional collection requests and actions based on the user's emotional state. For example, if the user is impatient, the emotion engine suggests sequenced next steps.

[0259] These steps will enable the automatic collection of supporting documents, the automation of assessment, and the adjustment of the process based on user feedback, resulting in a significant reduction in audit response time and increased efficiency. This will also reduce user stress and enable more accurate assessments.

[0260] Example 2

[0261] 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."

[0262] In conventional audit response systems, the collection and evaluation of supporting documents is often done manually, resulting in a significant amount of labor and time. It has also been pointed out that the evaluation of supporting documents is prone to human error and subjective judgment, resulting in a lack of reliability. Another problem is that the user's emotions and state can affect system operation, resulting in a decrease in the efficiency of audit work. The present invention aims to solve these problems and provide a system that streamlines audit response.

[0263] 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.

[0264] In this invention, the server includes a means for acquiring a list of information, a means for randomly selecting information from the acquired list of information, and a means for generating and transmitting a request to collect the selected information. This enables the automatic collection of evidence. The server also includes a means for storing the collected information and checking its consistency, a means for displaying the information data so that the user can confirm and approve it, a means for evaluating the user's emotional state, and a means for making suggestions to adjust the process based on the evaluated emotional state. This ensures the reliability of the information and enables adaptive operation according to the user's emotions. The server also includes a means for evaluating the information data based on pre-set evaluation criteria, a means for generating evaluation results and creating an evaluation result report, and a means for notifying and displaying the evaluation result report so that the user can view and confirm it. This enables an automatic evaluation process, improving the efficiency and reliability of evaluation work.

[0265] "Information list" refers to a list of supporting documents and related data to be audited, and is obtained from an ERP system or database.

[0266] "Selecting information" refers to the operation of selecting specific information from the list of acquired information randomly or based on arbitrary criteria.

[0267] "Generate and send a request" refers to the act of creating a request to collect selected information and sending it to the relevant department or system.

[0268] "Collected information" refers to evidence and data obtained in response to a server request.

[0269] "Checking consistency" refers to the act of verifying whether the collected information is accurate and consistent.

[0270] "Information data" refers to supporting evidence and related data collected for the audit.

[0271] "User" refers to the person who operates the system and reviews and approves the audit process.

[0272] "Emotional state" refers to the psychological state of the user when operating the system, including, for example, stress level and concentration level.

[0273] "Suggestions to adjust processes" refers to suggestions to change or optimize various system operations or processes depending on the user's emotional state.

[0274] "Evaluation criteria" refers to the pre-established standards and rules for conducting evaluations in internal control and audits.

[0275] "Evaluation result" refers to the result calculated by an automated evaluation algorithm based on the evaluation criteria.

[0276] "Evaluation results report" refers to a written or digital report summarizing the evaluation results.

[0277] "Notification" refers to the operation of informing the user about the evaluation result report generated by the system.

[0278] "Display" refers to the operation of showing the collected information and evaluation results on a screen or the like so that the user can check them.

[0279] MODE FOR CARRYING OUT THE INVENTION

[0280] The present invention is a system for improving the efficiency of audit responses, and is implemented in a form that combines an automatic document collection tool, an automatic evaluation tool, and an emotion engine.

[0281] Automatic document collection tool

[0282] First, the server automatically retrieves the list of documents to be audited from the ERP system or database (e.g., SAP, Oracle Database). This list of documents is stored in an internal database. The server then uses a Python random module to randomly select specific documents from the list of documents and generate a random sample.

[0283] The server generates a request to collect the selected evidence and sends it to the relevant departments and systems via email or API. The terminal receives the request and extracts the specified evidence from the relevant database. The extracted evidence data is sent to the server in CSV format. The server stores the received evidence data in an internal database and performs a consistency check (e.g., checksum value comparison). The user uses a dedicated terminal application to check and approve the collected evidence data. If additional collection is required, the user can send an additional collection request from the terminal.

[0284] Specific examples

[0285] The server obtains a list of supporting documents for monthly reports from SAP. This list contains purchasing details for the specified month. The server uses a random module to select 50 purchasing details. It uses the SMTP protocol to send a request to each department to collect these supporting documents. The terminal receives the request, executes an SQL query to extract the specified purchasing details from the Oracle Database, and sends them to the server. The server saves the received supporting document data and verifies its integrity using a checksum value. The user checks and approves the data on the terminal. If additional collection is required, the user sends a new collection request from the terminal.

[0286] Example prompt: "I need supporting monthly statements from SAP. Specifically, I need 50 random purchase statements."

[0287] Evaluation automation tool

[0288] The server retrieves the collected supporting data from the internal database and performs an evaluation based on pre-set evaluation criteria (e.g., internal control evaluation criteria). It evaluates the data using Python evaluation algorithms to check consistency and validity. It creates an evaluation result report and stores it in the internal database. The server sends a notification about the evaluation result to the terminal, prompting the user to confirm it. The user uses the terminal to check the evaluation result report and decides on necessary actions. If any abnormalities are found, the user instructs the relevant department to carry out further investigation or corrections.

[0289] Specific examples

[0290] The server retrieves the collected purchasing statement data and evaluates it based on internal control evaluation criteria. An outlier or inconsistent data is identified using a Python evaluation algorithm. A report of the evaluation results is created and a notification is sent to the user. The user can then check the report on their device and instruct the purchasing department to investigate any inconsistent data.

[0291] Example prompt: "Evaluate the consistency and validity of the collected purchasing statements based on the internal control evaluation criteria and generate a report of the evaluation results."

[0292] Emotion engine integration

[0293] The emotion engine evaluates the user's emotional state in real time when reviewing and approving supporting data. The emotion engine analyzes the user's camera footage and uses facial recognition technology to measure stress and concentration levels. Based on the emotional data, it makes suggestions to adjust the system process. If the stress level is high, the emotion engine will suggest simplifying the review process, while if the concentration level is high, it will prompt a more detailed review.

[0294] Specific examples

[0295] If a user is feeling stressed while reviewing supporting data, the emotion engine will detect this and offer options to simplify the review process, or if the user is highly focused, the emotion engine will prompt the user to review the data in more detail.

[0296] Example prompt: "Assess the stress level of users when reviewing supporting data and adjust the review process as needed."

[0297] This enables the automatic collection of supporting documents, automated evaluation, and process adjustment using an emotion engine, thereby achieving more efficient audit response.

[0298] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0299] Step 1:

[0300] The server obtains the evidence list. The server accesses the API endpoint of the ERP system and requests the latest evidence list. The obtained evidence list is saved in the server's internal database.

[0301] Input: Evidence data request from ERP system

[0302] Output: List of evidence stored in the internal database

[0303] Specific operation: The server sends an HTTP request to the ERP system's API, processes the list of evidence returned in JSON format, and inserts it into the PostgreSQL database.

[0304] Step 2:

[0305] The server randomly selects evidence from the evidence list. Using the Python random module, it randomly selects a specific number of evidence from the obtained evidence list. The selected evidence is then saved in the server's internal database again.

[0306] Input: List of evidence obtained in Step 1

[0307] Output: A randomly selected list of evidence

[0308] Specific operation: The server uses a Python script to randomly select 50 documents from the document list and save the list in an internal database.

[0309] Step 3:

[0310] The server generates and sends a request for collection of evidence. The server uses the SMTP protocol to send the request to the email address of the relevant department. It may also send the request directly to the department's system using an API.

[0311] Input: List of evidence selected in step 2

[0312] Output: Sending a request for evidence collection to the relevant department or system

[0313] Specific operation: The server uses the SMTP library to generate collection request emails and send them to each department. It also sends collection requests to other systems via the RESTful API.

[0314] Step 4:

[0315] The terminal extracts and sends the supporting evidence. The terminal receives the request and extracts the specified supporting evidence from the relevant database (e.g., Oracle Database). The extracted supporting evidence data is sent to the server in CSV format.

[0316] Input: Voucher collection request received from the server

[0317] Output: Send extracted supporting data to the server

[0318] Specific operation: The device receives a notification, the user executes an SQL query to extract supporting data, and uploads it to the server as a CSV file.

[0319] Step 5:

[0320] The server stores the supporting data and performs integrity checks. The server stores the received supporting data in an internal database and verifies the integrity of the data using a checksum algorithm.

[0321] Input: Evidence data sent in step 4

[0322] Output: Stored supporting data after integrity check

[0323] What happens: The server processes the uploaded CSV file, calculates the checksum to verify its integrity, and then inserts it into the PostgreSQL database.

[0324] Step 6:

[0325] The user checks and approves the supporting data. The user uses a dedicated terminal application to check and approve the collected supporting data. If additional collection is required, an additional collection request is sent from the terminal.

[0326] Input: Evidence data whose integrity was confirmed in Step 5

[0327] Output: Approved supporting data or additional collection requests

[0328] Specific operation: The user displays the supporting data in the terminal application, confirms it, and then clicks the approval button to send the approval status to the server. If additional collection is required, a new collection request is sent from the terminal.

[0329] Step 7:

[0330] The server retrieves the supporting data. The server executes SQL queries to retrieve the necessary supporting data from the internal database. The retrieved data is loaded into memory.

[0331] Input: Evidence data on the internal database

[0332] Output: Evidence data loaded into memory

[0333] Specific operation: The server periodically (for example, daily) executes SQL queries against the internal database and loads the necessary supporting data into memory.

[0334] Step 8:

[0335] The server performs the evaluation. The server evaluates the supporting data based on the evaluation criteria set. It executes a Python evaluation algorithm to automatically check the consistency and validity of the data.

[0336] Input: The supporting data loaded into memory in step 7

[0337] Output: Evaluation results

[0338] Specific operation: The server executes a Python script to evaluate the integrity and validity of the supporting data based on the specified evaluation criteria.

[0339] Step 9:

[0340] The server creates an evaluation result report and sends a notification. The server aggregates the results of the evaluation process and creates an evaluation result report in Excel format. This report is saved in an internal database and an email notification is sent to the user.

[0341] Input: Evaluation results generated in step 8

[0342] Output: Evaluation result report and notification to the user

[0343] Specific operation: The server compiles the evaluation results, generates a report based on an Excel template, saves the report in an internal database, and notifies the user via the SMTP protocol.

[0344] Step 10:

[0345] The user checks the evaluation results. The user opens the evaluation result report on the terminal and checks the contents. If an abnormality is found, the user sends an email to the relevant department instructing them to conduct further investigation.

[0346] Input: Notification of the evaluation result report sent in step 9

[0347] Output: Review the assessment report and any required actions

[0348] Specific operation: The user opens the evaluation result report in the terminal application and gives instructions for investigating and correcting inconsistent data.

[0349] Step 11:

[0350] The emotion engine evaluates the user's emotional state. The emotion engine analyzes the user's camera footage and uses facial recognition technology to assess stress and concentration levels in real time.

[0351] Input: User's camera image

[0352] Output: Evaluated emotional state data

[0353] How it works: The emotion engine captures camera footage and uses facial recognition algorithms to assess stress levels and concentration.

[0354] Step 12:

[0355] The emotion engine makes suggestions to adjust the process. Based on the evaluated emotional state data, the system makes suggestions to adjust the process. For example, if stress levels are high, it will make suggestions to simplify the confirmation process, and if concentration levels are high, it will encourage detailed confirmation.

[0356] Input: Emotional state data assessed in step 11

[0357] Output: Suggested process adjustments

[0358] What it does: The emotion engine analyzes the evaluated emotional state data and presents the user with options for adjusting the process as needed.

[0359] (Application example 2)

[0360] 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."

[0361] Modern logistics centers process a huge number of purchase specifications and delivery notes every day, requiring effective collection and evaluation of supporting documents. However, existing systems have low efficiency in collecting and evaluating supporting documents, and do not adequately manage employee stress or adjust processes. Therefore, in addition to improving work efficiency, flexible process adjustments based on employees' emotional states are necessary.

[0362] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring a list of evidence, means for randomly selecting evidence from the acquired list of evidence, means for generating and transmitting a request to collect the selected evidence, means for saving the collected evidence and checking its consistency, means for displaying the evidence data so that the user can confirm and approve it, and means for recognizing the emotional state and adjusting the process. This enables efficient collection and evaluation of evidence, and also enables flexibly adjusting the business process based on the user's emotional state.

[0363] The "means for obtaining a list of supporting documents" refers to a device or program that automatically obtains a list of supporting documents to be audited from an ERP system or database.

[0364] The "means for randomly selecting a voucher from the list of acquired vouchers" refers to a device or program that randomly selects a voucher from the list of acquired vouchers using a specific algorithm.

[0365] "Means for generating and sending requests to collect selected evidence" refers to a device or program that generates requests to collect selected evidence and sends them to the relevant departments or systems.

[0366] The "means for storing collected supporting documents and checking their consistency" refers to a device or program that stores collected supporting document data in an internal database and checks its consistency.

[0367] The "means for displaying supporting data so that the user can confirm and approve it" refers to a device or program that displays supporting data so that the user can confirm and approve it through a terminal.

[0368] The "means for recognizing emotional states and adjusting processes" refers to a device or program that recognizes the emotional state of a user in real time and dynamically adjusts the system processes based on that state.

[0369] The "means for evaluating supporting data based on a preset evaluation criterion" refers to a device or program for automatically evaluating supporting data based on a preset evaluation criterion.

[0370] The "means for generating evaluation results and creating an evaluation result report" refers to a device or program that generates evaluation results and creates an evaluation result report based on the results.

[0371] "Means for notifying and displaying the evaluation result report so that the user can view and confirm it" refers to a device or program that notifies the user of the evaluation result report so that the user can view and confirm it.

[0372] The "means for suggesting process adjustments based on the emotional state of the user" refers to a device or program that senses the emotional state of the user and suggests optimal process adjustments based on that state.

[0373] The "means by which a user can send an additional collection request" refers to a device or program that allows a user to send an additional document collection request as needed.

[0374] "Means for users to determine actions based on evaluation results and notify relevant departments" refers to a device or program that allows users to check evaluation results, specify necessary actions based on the results, and notify relevant departments.

[0375] The "means for monitoring the emotional state of a user using an emotion engine" is a device or program that uses an emotion engine to monitor the emotional state of a user in real time.

[0376] The present invention is a system aimed at improving the efficiency of audit responses at logistics centers. The present invention has the following configuration. First, as a means of obtaining a list of evidence, the server automatically obtains a list of evidence for audit targets from an ERP system or database. This list of evidence is saved in an internal database.

[0377] Next, the server randomly selects evidence from the obtained evidence list using a specific algorithm. To collect this selected evidence, the server generates a request and sends it to the relevant department or system (e.g., each department's terminal). The terminal receives this request, extracts the specified evidence from the database, and sends it to the server. The server stores the collected evidence in its internal database and checks its consistency.

[0378] The collected supporting data is displayed on the terminal for the user to review and approve. In addition, the server automatically evaluates the supporting data based on pre-set evaluation criteria and generates an evaluation result. This evaluation result is created as an evaluation result report and notified to the user's terminal. The user can check the evaluation result, determine actions as necessary, and notify relevant departments.

[0379] A distinctive feature of the present invention is the integration of an emotion engine. The emotion engine recognizes the user's emotional state in real time and provides the ability to adjust the process based on that data. For example, if the user is feeling stressed, the emotion engine can make automatic suggestions to simplify the review process. Also, if the user is highly focused, the emotion engine can prompt the user to review more detailed data.

[0380] For example, logistics center employees wearing smart glasses use the system to review and evaluate purchase order data automatically extracted from the ERP system. The employee's emotional state is monitored by the emotion engine, and the process is dynamically adjusted as needed.

[0381] An example of a prompt sentence is as follows:

[0382] Develop a smart glasses application that retrieves target purchase order data from an ERP system and monitors it in real time using an emotion engine. We provide code that enables automatic evaluation based on evaluation criteria and process adjustments based on employees' emotional state.

[0383] By using this prompt, it is possible to convey exactly what kind of application is required along with a concrete image.

[0384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0385] Step 1:

[0386] The server automatically retrieves the list of auditable evidence from the ERP system or database. Specifically, the server makes an API call to the ERP system to retrieve a list of purchase statements for a specified period. This list is saved in the server's internal database. The input is instructions from the ERP system, and the output is the retrieved list of evidence.

[0387] Step 2:

[0388] The server randomly selects evidence from the acquired evidence list using a specific algorithm. Specifically, the server executes a random sampling algorithm from the acquired list to select, for example, 50 evidences. The input is the acquired evidence list, and the output is the randomly selected evidence list.

[0389] Step 3:

[0390] The server generates a request to collect the selected evidence and sends it to the relevant departments and systems. Specifically, the server sends a request to each department's terminal, clearly indicating what evidence needs to be collected. The input is a list of randomly selected evidence, and the output is the sent request.

[0391] Step 4:

[0392] The terminal receives a request from the server, extracts the specified evidence from the database, and sends it to the server. The terminal executes a database query, extracts the specified evidence, and sends it to the server. The input is the collection request from the server, and the output is the extracted evidence data.

[0393] Step 5:

[0394] The server stores the collected evidence in an internal database and checks its integrity. Specifically, the server passes the received evidence data through a verification algorithm to check the consistency and completeness of the data. The input is the extracted evidence data, and the output is the evidence data whose integrity has been confirmed.

[0395] Step 6:

[0396] The server displays the collected supporting data on the terminal so that the user can confirm and approve it. The terminal displays the supporting data through a user interface, and the user confirms and approves it. The input is the confirmation request and supporting data, and the output is feedback of approval or rejection by the user.

[0397] Step 7:

[0398] The server automatically evaluates the supporting data based on pre-defined evaluation criteria. The evaluation algorithm examines the supporting data and determines whether it meets the pre-defined criteria. The input is the supporting data and evaluation criteria, and the output is the evaluation result.

[0399] Step 8:

[0400] The server generates evaluation results and creates an evaluation result report. Specifically, the server aggregates the evaluation results and generates a report in a format that is easy for users to understand. The input is the evaluation results, and the output is the evaluation result report.

[0401] Step 9:

[0402] The server notifies the user of the evaluation result report and prompts them to confirm it. The user checks the report on their device and determines the necessary actions. The input is the evaluation result report, and the output is the user's confirmation and feedback.

[0403] Step 10:

[0404] After the user specifies an action, the server notifies the relevant departments. Specifically, the server generates notification content and sends it to the relevant department's terminal. The input is the user's instruction to take an action, and the output is a notification to the relevant department.

[0405] Step 11:

[0406] The emotion engine recognizes the user's emotional state in real time and adjusts the process appropriately. The emotion engine monitors the user's stress and concentration level and generates appropriate suggestions. The input is the user's real-time emotional data, and the output is adjustment suggestions and their implementation.

[0407] Step 12:

[0408] If the user accepts the emotion engine's suggestion, the server dynamically adjusts the process based on the suggestion. The input is the emotion engine's suggestion, and the output is the adjusted process.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] [Second embodiment]

[0413] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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).

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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."

[0425] Automatic document collection tool

[0426] The present invention is a system for improving the efficiency of audit responses, and includes an automatic document collection tool and an evaluation automation tool. First, the automatic document collection tool will be described.

[0427] The server first obtains a list of documents to be audited. This list is collected from an ERP system or database. Next, the server generates a random sample from the obtained list of documents. This random sample generation algorithm randomly selects any document.

[0428] The server generates a request to collect the selected evidence and sends it to the relevant department or system. This request specifies the type and quantity of evidence and includes a collection request. The terminal receives this request, collects the evidence in real time, and sends it back to the server.

[0429] The server stores the received supporting data in an internal database and checks its consistency. This consistency check identifies missing or abnormal data. The user uses the terminal to review and approve the collected supporting data. If additional collection is required, the user can send an additional collection request through the terminal.

[0430] Specific examples

[0431] For example, a server retrieves a list of supporting documents for a monthly report from an ERP system. This list contains purchase statements for a given month. The server uses a random algorithm to select 50 purchasing statements and sends requests to each department to collect these supporting documents.

[0432] The terminal receives this request, extracts the specified purchase details from the database, and sends them to the server. The server saves the received supporting data and performs a consistency check. The user then checks and approves the data on the terminal.

[0433] Evaluation automation tool

[0434] Next, we will explain the evaluation automation tool. The server receives supporting data and starts the evaluation process. The server executes an automatic evaluation algorithm based on pre-set evaluation criteria. These evaluation criteria include various criteria for internal control evaluation.

[0435] The server generates the results of the evaluation process and creates an evaluation result report, which is stored in a database for the user to review. The server then sends a notification of the evaluation result to the terminal, prompting the user to review the evaluation result.

[0436] Users can check the evaluation results report through their terminal and determine the necessary actions. For example, if an abnormality is discovered, the user can issue instructions to the relevant department for investigation or correction.

[0437] Specific examples

[0438] The server retrieves the previously collected purchase statement data and evaluates each statement for consistency and validity based on the evaluation criteria set. Evaluation algorithms perform this and identify outliers and inconsistent data.

[0439] A report of the evaluation results is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and instruct the purchasing department to conduct further investigations into any inconsistencies in the data.

[0440] In this way, the present invention realizes automatic collection of supporting documents and automated evaluation, thereby significantly reducing the amount of work required to respond to audits and improving efficiency.

[0441] The processing flow will be explained below.

[0442] Automatic document collection tool

[0443] Step 1:

[0444] The server automatically retrieves the list of evidence to be audited from the ERP system or database, and the retrieved list of evidence is saved in the internal database.

[0445] Step 2:

[0446] The server executes an algorithm to randomly select a particular document from the obtained document list. A random sample is selected.

[0447] Step 3:

[0448] The server generates a request to collect the selected evidence, which is then sent to the relevant department or system.

[0449] Step 4:

[0450] The terminal receives the request and extracts the specified evidence from the associated database, and the extracted evidence data is sent from the terminal to the server.

[0451] Step 5:

[0452] The server stores the received supporting data in an internal database and checks the integrity of the stored data.

[0453] Step 6:

[0454] The user checks the collected evidence data through the terminal and approves the checked data.

[0455] Step 7:

[0456] If the user needs to collect additional evidence, the terminal sends an additional collection request to the server.

[0457] Evaluation automation tool

[0458] Step 1:

[0459] The server retrieves the supporting document data received from the automated supporting document collection tool from the database, and rechecks the consistency of the retrieved data.

[0460] Step 2:

[0461] The server evaluates the supporting data based on the set evaluation criteria, and executes the evaluation algorithm to evaluate the effectiveness of internal controls.

[0462] Step 3:

[0463] The server generates the evaluation results and creates an evaluation result report, which is stored in an internal database.

[0464] Step 4:

[0465] The server sends a notification of the evaluation result to the terminal, which then displays the evaluation result to the user.

[0466] Step 5:

[0467] The user checks the evaluation result report through the terminal, determines the necessary actions, and notifies the relevant departments of correction instructions and investigation requests.

[0468] Through these steps, the automated collection and evaluation of supporting documents is achieved, reducing the amount of work required and improving efficiency in responding to audits.

[0469] Example 1

[0470] 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."

[0471] In conventional audit response systems, the process of collecting and evaluating supporting documents is manual, requiring time and effort. Furthermore, manual collection and evaluation is prone to human error, and data integrity cannot be guaranteed. Furthermore, there are inefficiencies in the process of reviewing and approving the evaluation results, creating a need for greater efficiency in the entire audit process.

[0472] 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.

[0473] In this invention, the server includes a means for acquiring a list of supporting documents from a data management system, a means for randomly selecting supporting documents from the acquired list using a random algorithm, and a means for generating a request to collect the selected supporting documents and sending it to each department via a network. This automates the process of collecting supporting documents, eliminates manual errors, and enables efficient audit response. The server also stores the collected supporting document data in a database and has a means for checking its consistency, ensuring the consistency and reliability of the data. Furthermore, the server includes a means for displaying the supporting document data so that users can confirm and approve it using a terminal, thereby realizing rapid confirmation of evaluation results and the approval process.

[0474] A "list of supporting documents" is a list that summarizes the types and details of supporting documents required for audit responses and business evaluations.

[0475] A "data management system" is an information system that manages and stores business data in a company or organization, and allows access and retrieval for specific purposes.

[0476] A "random algorithm" is a computational method for randomly drawing samples from a data set, used to ensure a fair and unbiased selection.

[0477] A "network" is an information transmission mechanism that connects multiple computers and terminals so that they can communicate with each other.

[0478] A "request" is a command to request specific data or an operation, and is used to obtain or send information between systems.

[0479] A "database" is a structured collection of data that can efficiently manage and store large amounts of data and can be quickly accessed and searched when needed.

[0480] "Integrity" is a property that ensures that data is consistent and free of errors and omissions, and is important for ensuring the accuracy and reliability of data.

[0481] An "automated evaluation algorithm" is a calculation method that allows a program to automatically analyze and evaluate collected data based on pre-set evaluation criteria.

[0482] "Evaluation criteria" are a set of rules and indicators that are used as standards when evaluating and judging data, and they define the appropriateness and problems of the subject of evaluation.

[0483] An "evaluation result report" is a document or data file that summarizes the results of the evaluation process, and indicates the status of the subject of evaluation and whether or not there are any abnormalities.

[0484] A "terminal" refers to a device such as a computer or mobile device that can be directly operated by a user, and is used to input data into the system and display results.

[0485] "User" refers to a person or role who operates the system to perform actual work or audits, and is the entity that uses the various functions of the system.

[0486] "Notification" means a message or signal that informs a user of particular information or results.

[0487] "Verification" refers to the act of checking the content of data or information to confirm whether it is accurate.

[0488] "Approval" refers to the act of acknowledging the correctness and validity of confirmed data or information.

[0489] "Action" refers to specific measures or steps taken based on the evaluation results, and means actions taken to solve problems or make improvements.

[0490] Automatic document collection tool

[0491] Server Processing

[0492] The server first obtains a list of evidence to be audited from the data management system or internal database. This process involves extracting the necessary data using, for example, an SQL query. Based on the obtained list of evidence, a random algorithm is used to randomly select evidence, using an algorithm such as Python's random.sample function. During this process, a request to collect the selected evidence is generated and sent to each department via the network. This request is often sent using an HTTP request.

[0493] Terminal handling

[0494] The terminal receives a request for collecting supporting documents from the server, extracts the specified supporting documents from the database, and sends them to the server. The terminal also returns the extracted data to the server as an HTTP response. During this process, the necessary database queries are executed to ensure that the supporting document data is accurately sent to the server.

[0495] User Action

[0496] Users can use their devices to check and approve the supporting data stored on the server. They can view and manipulate the data through a GUI, and can send requests for additional supporting data to the server as needed. This increases the accuracy and reliability of audits.

[0497] Specific examples

[0498] For example, the server retrieves a list of supporting documents required for monthly reports from the ERP system. Based on the retrieved list, a random sample generation algorithm is used to select 50 purchasing details. A request is generated for each selected supporting document and a request to collect the supporting documents is sent to each department. The terminal receives this request, extracts the specified purchasing details from the database, and sends them to the server. The server stores the received supporting document data and checks its consistency. The user uses the terminal to check and approve the data. If there are any problems, the user can send additional collection requests.

[0499] Prompt Sentence Examples

[0500] Based on the document list obtained from the ERP system, 50 purchasing details are randomly selected and a document collection request is sent to each department. The terminal then retrieves the document from the database and sends it to the server. The server saves the data and checks its integrity. The user then uses the terminal to check and approve the document data.

[0501] Evaluation automation tool

[0502] Server Processing

[0503] The server retrieves the collected supporting data from the database and starts the evaluation process. This process includes an automated evaluation algorithm based on pre-defined evaluation criteria, including the consistency of internal control standards and business processes. Evaluation results are generated and an evaluation result report is created based on the results. This report is saved in the database and notified to the user.

[0504] User Action

[0505] Users can check the evaluation result report through their terminal and decide on the necessary actions. If an abnormality is found in the evaluation results, users can send instructions for investigation or correction to the relevant department through their terminal. This allows for quick confirmation and response of audit results.

[0506] Specific examples

[0507] The server evaluates the collected purchasing specification data based on the evaluation criteria and identifies outliers and inconsistent data. An evaluation result report is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and issue instructions to the purchasing department for further investigation or correction of inconsistent data.

[0508] Prompt Sentence Examples

[0509] The collected purchasing specification data is evaluated based on evaluation criteria to identify outliers and inconsistencies. An evaluation result report is created and notified to the user. The user can check the evaluation results via their terminal, and if an abnormality is found, they can issue instructions to the purchasing department for investigation or correction.

[0510] In this way, the present invention realizes automatic collection of supporting documents and automated evaluation, thereby reducing the number of steps required for audits and improving efficiency.

[0511] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0512] Automatic document collection tool

[0513] Server Processing Steps

[0514] Step 1:

[0515] The server retrieves the list of supporting documents to be audited from the data management system. The input is raw data retrieved from the ERP system or internal database, and the necessary data is extracted using SQL queries. The output is a list of supporting documents required for the audit.

[0516] Specifically, the server executes a query such as "SELECT FROM evidence_list WHERE month='2023-10';" to retrieve the target evidence list from the database.

[0517] Step 2:

[0518] The server randomly selects a voucher from the obtained list of vouchers using a random algorithm. The input is the list of vouchers obtained in step 1, and it processes the algorithm to randomly extract data. The output is a sample list of randomly selected vouchers.

[0519] Specifically, for example, 50 supporting documents are selected using Python's random.sample function.

[0520] Step 3:

[0521] The server generates a request to collect the selected evidence and sends it to each department via the network. The input is the list of evidence selected in step 2, and the output is the collection request sent to each department.

[0522] Specifically, an HTTP request is generated and sent to the URL of each department.

[0523] Step 4:

[0524] The terminal receives the collection request sent from the server and extracts the specified evidence from the database. The input is the collection request from the server, and the output is the extracted evidence data.

[0525] Specifically, the terminal executes the query "SELECT FROM evidences WHERE id=?" and sends the extracted results to the server.

[0526] Step 5:

[0527] The server stores the received supporting data in an internal database and checks its consistency. The input is the supporting data sent from the terminal, and the output is the consistency check result and the stored data.

[0528] Specifically, the system stores supporting data in a database and runs a consistency check algorithm, detecting missing or anomalous data.

[0529] Step 6:

[0530] The user uses a terminal to check the evidence data stored on the server and give approval. The input is the evidence data stored on the server, and the output is the user's confirmation and approval results.

[0531] Specifically, the GUI screen displays the data, allows the user to review and approve it, and allows the user to submit additional collection requests if necessary.

[0532] Evaluation automation tool

[0533] Server Processing Steps

[0534] Step 1:

[0535] The server retrieves the collected supporting data from the database and starts the evaluation process. The input is the collected supporting data and the output is the data ready to run the evaluation process.

[0536] Specifically, a database query is executed to extract the data to be evaluated.

[0537] Step 2:

[0538] The server executes an automatic evaluation algorithm based on pre-defined evaluation criteria. The input is the supporting data obtained in step 1, and the output is the evaluation result.

[0539] Specifically, it runs evaluation algorithms implemented in languages ​​such as Python to assess the integrity and validity of the data.

[0540] Step 3:

[0541] The server creates an evaluation result report based on the results of the evaluation process. The input is the evaluation result, and the output is the evaluation result report.

[0542] Specifically, a report is generated based on the evaluation results and stored in a database.

[0543] Step 4:

[0544] The server notifies the user of the evaluation result report and allows the user to check it on the terminal. The input is the evaluation result report, and the output is a notification message to the user.

[0545] Specifically, an HTTP request for notification is generated and sent to the user's terminal.

[0546] User processing steps

[0547] Step 5:

[0548] The user checks the evaluation result report through the terminal and decides on the necessary action. The input is the evaluation result report, and the output is the user's action instructions.

[0549] Specifically, the report is viewed using a GUI that displays the evaluation results, and if any abnormalities or inconsistencies are found, instructions are issued to the purchasing department or other department to investigate or correct the issues.

[0550] As described above, the processing steps of the present invention have been explained together with specific operations. This clarifies the process of automatic collection of supporting documents and automated evaluation, and is expected to enable efficient audit response.

[0551] (Application example 1)

[0552] 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."

[0553] Logistics centers are required to manage a huge number of supporting documents (receipts, shipping certificates, inventory lists, etc.), and collecting and evaluating these documents takes a lot of time and effort. In particular, consistency checks and anomaly detection for these documents are often done manually, so there is a need for efficiency improvements. There is also a need for a system that can reduce the workload of on-site workers and quickly collect and evaluate supporting documents.

[0554] 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.

[0555] In this invention, the server includes means for acquiring a list of evidence, means for randomly selecting evidence from the acquired list of evidence, means for generating and sending a request to collect the selected evidence, means for saving the collected evidence and checking its consistency, means for displaying the evidence data so that the user can confirm and approve it, means for creating a request for evidence collection and sending it to the relevant department, and means for checking the consistency and evaluating the acquired evidence data. This makes it possible to efficiently collect evidence at a logistics center and automatically evaluate it.

[0556] A "list of supporting documents" is a list of supporting documents required for audits and business processes, and is obtained from an ERP system or database.

[0557] "Randomly selecting evidence" means randomly selecting evidence from a list of evidence based on a pre-set algorithm.

[0558] "Generate and send a request" refers to automatically creating a request to collect the selected evidence and sending it to the relevant department or system.

[0559] "Consistency checking" is the process of verifying that the collected supporting data is appropriate and free of inconsistencies or anomalies.

[0560] "Evidence data" refers to the specific information and content of each evidence obtained and collected.

[0561] "Evaluating supporting data based on evaluation criteria" refers to the process of automatically evaluating the accuracy and suitability of collected supporting data according to pre-set criteria and conditions.

[0562] An "evaluation result report" is a report summarizing the results of the evaluation process of supporting data.

[0563] "Instructing investigation and correction" means that if any inconsistencies or abnormalities are discovered based on the evaluation results, the relevant department will be asked to carry out the necessary investigation and correction work.

[0564] "On-site workers collect and upload supporting documents using smartphones" refers to the process in which on-site workers at the logistics center collect supporting documents using smartphones and upload them to a server via a dedicated application.

[0565] "Login and user authentication" refers to entering the user authentication information required to access the system and taking appropriate security measures.

[0566] "Generating prompts using a generative AI model and providing automated assistance" refers to an assistance function that uses AI technology to create prompts and simplify user operations.

[0567] As an embodiment of the present invention, the specific configuration and procedures of a document management system used in a logistics center are described below. This system has functions such as obtaining a document list, randomly selecting documents, generating and sending document collection requests, checking the integrity of documents, evaluating data based on evaluation criteria, generating and notifying result reports, and even issuing investigation and correction instructions.

[0568] First, the server retrieves the list of evidence from the ERP system or database. From the retrieved list of evidence, the server randomly selects evidence, generates a request to collect it, and sends it to the relevant department. This process is implemented using a Python program and the "requests" module. For example, the list of evidence can be obtained through an API endpoint, and evidence can be randomly selected using the "random" module.

[0569] The server then sends requests to each department to collect the selected evidence, and field workers use their smartphones to collect the evidence. The collected evidence data is then uploaded from the smartphone to the server. The smartphone application plays an important role in this process, making it possible to collect and upload evidence in real time. It also has security features such as login and user authentication, and appropriate access control is performed by entering authentication information.

[0570] The collected supporting data is stored on a server and a consistency check is performed. This consistency check, which includes checking the correct date format and numeric range, is implemented using the Python datetime module, for example. Once the consistency of the supporting data is confirmed, it is evaluated based on pre-set evaluation criteria. The evaluation results are generated as an evaluation result report and notified to the user.

[0571] After reviewing the evaluation results, users can instruct the relevant department to investigate and correct any abnormal supporting documentation data. Generative AI models can also be used to automatically create prompts, simplifying user operations. For example, a prompt could be generated such as, "Please explain the system for automatically collecting and evaluating supporting documentation at a logistics center. Please provide a detailed explanation of the integrity check and evaluation process for randomly selected supporting documentation."

[0572] In this way, the present invention can improve the efficiency of document management at logistics centers and reduce the workload. It also enables real-time collection and evaluation of documented evidence, enabling immediate problem detection and countermeasures.

[0573] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0574] Step 1:

[0575] The server retrieves the document list from the ERP system or database. In this step, it accesses the API endpoint using the Python requests module to retrieve the document list. The input is the API endpoint URL, and the output is the document list data in JSON format.

[0576] Step 2:

[0577] The server randomly selects evidence from the obtained evidence list. In this step, the Python random module is used to randomly select a specified number of evidence from the evidence list. The input is the evidence list data, and the output is the selected evidence data.

[0578] Step 3:

[0579] The server generates and sends a request to collect the selected evidence. The request specifies the type and quantity of evidence and is sent to the relevant departments and parties. The input is the selected evidence data, and the output is a request message sent to each department.

[0580] Step 4:

[0581] The terminal receives a request from the server, and the on-site worker collects the evidence using a smartphone. The worker takes a photo of the evidence with a camera and uploads it along with location and time information. The input is the request message, and the output is the evidence image data and accompanying information.

[0582] Step 5:

[0583] The server stores the supporting data uploaded by field workers and checks its consistency. It uses the Python datetime module to check the correct date format and numeric range. The input is the supporting data image data and accompanying information, and the output is the consistency check results.

[0584] Step 6:

[0585] The server evaluates the integrity-checked supporting data based on pre-defined evaluation criteria, generates evaluation results, and creates a result report. It runs an automated evaluation algorithm based on the evaluation criteria to identify outliers and inconsistent data. The input is the integrity-checked supporting data, and the output is an evaluation result report.

[0586] Step 7:

[0587] The server notifies the user of the evaluation result report, allowing the user to check the results. The user can review the evaluation results and determine the necessary actions. The input is the evaluation result report, and the output is notification and display on the user screen.

[0588] Step 8:

[0589] If the user finds any abnormal supporting data, they can instruct the relevant department to investigate and correct it. A generative AI model is used to automatically create prompts, simplifying user operations. The input is the evaluation results and the prompts generated by the generative AI model, and the output is instructions to the relevant department to investigate and correct the abnormality.

[0590] In this way, by linking each processing step, automatic collection and evaluation of supporting documents at the logistics center is realized.

[0591] 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.

[0592] Overall overview

[0593] This invention is a system for streamlining audit response, which includes an automatic document collection tool and an evaluation automation tool, and also combines an emotion engine that recognizes user emotions and adjusts various system processes.

[0594] Automatic document collection tool

[0595] The server first automatically retrieves the list of documents to be audited from the ERP system or database. This list is stored in an internal database. The server then runs an algorithm to randomly select specific documents from the list of documents to generate a random sample.

[0596] The server generates a request to collect the selected evidence and sends it to the relevant department or system. The terminal receives the request, extracts the specified evidence from the relevant database, and sends it to the server. The server stores the received evidence data in an internal database and checks its consistency. The user uses the terminal to check and approve the collected evidence data. If additional collection is required, the user can send an additional collection request through the terminal.

[0597] Specific examples

[0598] For example, the server retrieves a list of supporting documents required for a monthly report from the ERP system. This list includes purchasing details for a specified month. The server selects 50 purchasing details using a random algorithm and sends a request to each department to collect these supporting documents. The terminal receives this request, extracts the specified purchasing details from the database, and sends them to the server. The server saves the received supporting document data and performs a consistency check. The user checks and approves the data on the terminal.

[0599] Evaluation automation tool

[0600] Next, we will explain the evaluation automation tool. The server receives supporting data and starts the evaluation process. Based on pre-set evaluation criteria, the server executes an automatic evaluation algorithm. These evaluation criteria include various standards for internal control evaluation. The server generates the results of the evaluation process and creates an evaluation result report. This report is saved in a database so that the user can check it. The server sends a notification of the evaluation result to the terminal, prompting the user to check the evaluation result. The user checks the evaluation result report through the terminal and determines the necessary actions. For example, if an abnormality is discovered, the user can issue instructions for investigation or correction to the relevant department.

[0601] Specific examples

[0602] The server retrieves the previously collected purchasing statement data and evaluates the consistency and validity of each statement based on the evaluation criteria that have been set. The evaluation algorithm executes this and identifies outliers and inconsistent data. A report of the evaluation results is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and instruct the purchasing department to conduct further investigations on inconsistent data.

[0603] Emotion engine integration

[0604] The emotion engine recognizes the user's emotional state and adjusts various system processes. The emotion engine evaluates the user's stress level and concentration level in real time when verifying and approving supporting documents. This emotional data is reflected in the configuration of the supporting document verification process, additional collection requests, and evaluation process.

[0605] Specific examples

[0606] For example, if a user feels stressed while reviewing supporting data, the emotion engine can detect this and make automatic suggestions to simplify the review process. Also, if the user is highly focused, the engine can prompt the user to review more detailed data. Furthermore, the engine can dynamically adjust evaluation criteria based on emotion data and suggest actions based on the evaluation results. The emotion engine can recommend users with high stress levels to send additional collection requests.

[0607] Through these steps, the system will enable the automatic collection of supporting documents, automated evaluation, and process adjustments based on user feedback, resulting in a significant reduction in audit response time and increased efficiency.

[0608] The processing flow will be explained below.

[0609] Automatic document collection tool

[0610] Step 1:

[0611] The server automatically retrieves the list of evidence to be audited from the ERP system or database, and the retrieved list of evidence is saved in the internal database.

[0612] Step 2:

[0613] The server executes an algorithm to randomly select a particular document from the obtained document list. A random sample is selected.

[0614] Step 3:

[0615] The server generates a request to collect the selected evidence and sends the request to the relevant department or system.

[0616] Step 4:

[0617] The terminal receives the request and extracts the specified evidence from the associated database, and the extracted evidence data is sent from the terminal to the server.

[0618] Step 5:

[0619] The server stores the received supporting data in an internal database and checks the integrity of the stored data.

[0620] Step 6:

[0621] The user checks the collected evidence data through the terminal and approves the checked data.

[0622] Step 7:

[0623] If the user needs to collect additional evidence, the terminal sends an additional collection request to the server.

[0624] Evaluation automation tool

[0625] Step 1:

[0626] The server retrieves the supporting document data received from the automated supporting document collection tool from the database, and rechecks the consistency of the retrieved data.

[0627] Step 2:

[0628] The server evaluates the supporting data based on the set evaluation criteria, and executes the evaluation algorithm to evaluate the effectiveness of internal controls.

[0629] Step 3:

[0630] The server generates the evaluation results and creates an evaluation result report, which is stored in an internal database.

[0631] Step 4:

[0632] The server sends a notification of the evaluation result to the terminal, which then displays the evaluation result to the user.

[0633] Step 5:

[0634] The user checks the evaluation result report through the terminal, determines the necessary actions, and notifies the relevant departments of correction instructions and investigation requests.

[0635] Emotion engine integration

[0636] Step 1:

[0637] The emotion engine recognizes the user's emotional state. The emotion engine analyzes the user's facial expressions, tone of voice, typing speed, etc. to collect emotional data in real time.

[0638] Step 2:

[0639] The emotion engine analyzes the collected emotional data to determine the user's stress level and concentration, which is reflected in the verification and approval process of supporting data.

[0640] Step 3:

[0641] When a user checks the evidence data, the emotion engine adjusts the initial settings according to the user's emotional state. For example, if the user is feeling stressed, the emotion engine provides an assistance function to simplify the checking process.

[0642] Step 4:

[0643] The server dynamically adjusts the evaluation criteria. The evaluation criteria are flexibly changed based on the emotional data acquired by the emotion engine. When the user is highly focused, a stricter evaluation is performed.

[0644] Step 5:

[0645] The server generates the evaluation report, and the emotion engine adjusts the report display based on the user's emotional state: if stress is high, the report is summarized.

[0646] Step 6:

[0647] The emotion engine suggests additional collection requests and actions based on the user's emotional state. For example, if the user is impatient, the emotion engine suggests sequenced next steps.

[0648] These steps will enable the automatic collection of supporting documents, the automation of assessment, and the adjustment of the process based on user feedback, resulting in a significant reduction in audit response time and increased efficiency. This will also reduce user stress and enable more accurate assessments.

[0649] Example 2

[0650] 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."

[0651] In conventional audit response systems, the collection and evaluation of supporting documents is often done manually, resulting in a significant amount of labor and time. It has also been pointed out that the evaluation of supporting documents is prone to human error and subjective judgment, resulting in a lack of reliability. Another problem is that the user's emotions and state can affect system operation, resulting in a decrease in the efficiency of audit work. The present invention aims to solve these problems and provide a system that streamlines audit response.

[0652] 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.

[0653] In this invention, the server includes a means for acquiring a list of information, a means for randomly selecting information from the acquired list of information, and a means for generating and transmitting a request to collect the selected information. This enables the automatic collection of evidence. The server also includes a means for storing the collected information and checking its consistency, a means for displaying the information data so that the user can confirm and approve it, a means for evaluating the user's emotional state, and a means for making suggestions to adjust the process based on the evaluated emotional state. This ensures the reliability of the information and enables adaptive operation according to the user's emotions. The server also includes a means for evaluating the information data based on pre-set evaluation criteria, a means for generating evaluation results and creating an evaluation result report, and a means for notifying and displaying the evaluation result report so that the user can view and confirm it. This enables an automatic evaluation process, improving the efficiency and reliability of evaluation work.

[0654] "Information list" refers to a list of supporting documents and related data to be audited, and is obtained from an ERP system or database.

[0655] "Selecting information" refers to the operation of selecting specific information from the list of acquired information randomly or based on arbitrary criteria.

[0656] "Generate and send a request" refers to the act of creating a request to collect selected information and sending it to the relevant department or system.

[0657] "Collected information" refers to evidence and data obtained in response to a server request.

[0658] "Checking consistency" refers to the act of verifying whether the collected information is accurate and consistent.

[0659] "Information data" refers to supporting evidence and related data collected for the audit.

[0660] "User" refers to the person who operates the system and reviews and approves the audit process.

[0661] "Emotional state" refers to the psychological state of the user when operating the system, including, for example, stress level and concentration level.

[0662] "Suggestions to adjust processes" refers to suggestions to change or optimize various system operations or processes depending on the user's emotional state.

[0663] "Evaluation criteria" refers to the pre-established standards and rules for conducting evaluations in internal control and audits.

[0664] "Evaluation result" refers to the result calculated by an automated evaluation algorithm based on the evaluation criteria.

[0665] "Evaluation results report" refers to a written or digital report summarizing the evaluation results.

[0666] "Notification" refers to the operation of informing the user about the evaluation result report generated by the system.

[0667] "Display" refers to the operation of showing the collected information and evaluation results on a screen or the like so that the user can check them.

[0668] MODE FOR CARRYING OUT THE INVENTION

[0669] The present invention is a system for improving the efficiency of audit responses, and is implemented in a form that combines an automatic document collection tool, an automatic evaluation tool, and an emotion engine.

[0670] Automatic document collection tool

[0671] First, the server automatically retrieves the list of documents to be audited from the ERP system or database (e.g., SAP, Oracle Database). This list of documents is stored in an internal database. The server then uses a Python random module to randomly select specific documents from the list of documents and generate a random sample.

[0672] The server generates a request to collect the selected evidence and sends it to the relevant departments and systems via email or API. The terminal receives the request and extracts the specified evidence from the relevant database. The extracted evidence data is sent to the server in CSV format. The server stores the received evidence data in an internal database and performs a consistency check (e.g., checksum value comparison). The user uses a dedicated terminal application to check and approve the collected evidence data. If additional collection is required, the user can send an additional collection request from the terminal.

[0673] Specific examples

[0674] The server obtains a list of supporting documents for monthly reports from SAP. This list contains purchasing details for the specified month. The server uses a random module to select 50 purchasing details. It uses the SMTP protocol to send a request to each department to collect these supporting documents. The terminal receives the request, executes an SQL query to extract the specified purchasing details from the Oracle Database, and sends them to the server. The server saves the received supporting document data and verifies its integrity using a checksum value. The user checks and approves the data on the terminal. If additional collection is required, the user sends a new collection request from the terminal.

[0675] Example prompt: "I need supporting monthly statements from SAP. Specifically, I need 50 random purchase statements."

[0676] Evaluation automation tool

[0677] The server retrieves the collected supporting data from the internal database and performs an evaluation based on pre-set evaluation criteria (e.g., internal control evaluation criteria). It evaluates the data using Python evaluation algorithms to check consistency and validity. It creates an evaluation result report and stores it in the internal database. The server sends a notification about the evaluation result to the terminal, prompting the user to confirm it. The user uses the terminal to check the evaluation result report and decides on necessary actions. If any abnormalities are found, the user instructs the relevant department to carry out further investigation or corrections.

[0678] Specific examples

[0679] The server retrieves the collected purchasing statement data and evaluates it based on internal control evaluation criteria. An outlier or inconsistent data is identified using a Python evaluation algorithm. A report of the evaluation results is created and a notification is sent to the user. The user can then check the report on their device and instruct the purchasing department to investigate any inconsistent data.

[0680] Example prompt: "Evaluate the consistency and validity of the collected purchasing statements based on the internal control evaluation criteria and generate a report of the evaluation results."

[0681] Emotion engine integration

[0682] The emotion engine evaluates the user's emotional state in real time when reviewing and approving supporting data. The emotion engine analyzes the user's camera footage and uses facial recognition technology to measure stress and concentration levels. Based on the emotional data, it makes suggestions to adjust the system process. If the stress level is high, the emotion engine will suggest simplifying the review process, while if the concentration level is high, it will prompt a more detailed review.

[0683] Specific examples

[0684] If a user is feeling stressed while reviewing supporting data, the emotion engine will detect this and offer options to simplify the review process, or if the user is highly focused, the emotion engine will prompt the user to review the data in more detail.

[0685] Example prompt: "Assess the stress level of users when reviewing supporting data and adjust the review process as needed."

[0686] This enables the automatic collection of supporting documents, automated evaluation, and process adjustment using an emotion engine, thereby achieving more efficient audit response.

[0687] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0688] Step 1:

[0689] The server obtains the evidence list. The server accesses the API endpoint of the ERP system and requests the latest evidence list. The obtained evidence list is saved in the server's internal database.

[0690] Input: Evidence data request from ERP system

[0691] Output: List of evidence stored in the internal database

[0692] Specific operation: The server sends an HTTP request to the ERP system's API, processes the list of evidence returned in JSON format, and inserts it into the PostgreSQL database.

[0693] Step 2:

[0694] The server randomly selects evidence from the evidence list. Using the Python random module, it randomly selects a specific number of evidence from the obtained evidence list. The selected evidence is then saved in the server's internal database again.

[0695] Input: List of evidence obtained in Step 1

[0696] Output: A randomly selected list of evidence

[0697] Specific operation: The server uses a Python script to randomly select 50 documents from the document list and save the list in an internal database.

[0698] Step 3:

[0699] The server generates and sends a request for collection of evidence. The server uses the SMTP protocol to send the request to the email address of the relevant department. It may also send the request directly to the department's system using an API.

[0700] Input: List of evidence selected in step 2

[0701] Output: Sending a request for evidence collection to the relevant department or system

[0702] Specific operation: The server uses the SMTP library to generate collection request emails and send them to each department. It also sends collection requests to other systems via the RESTful API.

[0703] Step 4:

[0704] The terminal extracts and sends the supporting evidence. The terminal receives the request and extracts the specified supporting evidence from the relevant database (e.g., Oracle Database). The extracted supporting evidence data is sent to the server in CSV format.

[0705] Input: Voucher collection request received from the server

[0706] Output: Send extracted supporting data to the server

[0707] Specific operation: The device receives a notification, the user executes an SQL query to extract supporting data, and uploads it to the server as a CSV file.

[0708] Step 5:

[0709] The server stores the supporting data and performs integrity checks. The server stores the received supporting data in an internal database and verifies the integrity of the data using a checksum algorithm.

[0710] Input: Evidence data sent in step 4

[0711] Output: Stored supporting data after integrity check

[0712] What happens: The server processes the uploaded CSV file, calculates the checksum to verify its integrity, and then inserts it into the PostgreSQL database.

[0713] Step 6:

[0714] The user checks and approves the supporting data. The user uses a dedicated terminal application to check and approve the collected supporting data. If additional collection is required, an additional collection request is sent from the terminal.

[0715] Input: Evidence data whose integrity was confirmed in Step 5

[0716] Output: Approved supporting data or additional collection requests

[0717] Specific operation: The user displays the supporting data in the terminal application, confirms it, and then clicks the approval button to send the approval status to the server. If additional collection is required, a new collection request is sent from the terminal.

[0718] Step 7:

[0719] The server retrieves the supporting data. The server executes SQL queries to retrieve the necessary supporting data from the internal database. The retrieved data is loaded into memory.

[0720] Input: Evidence data on the internal database

[0721] Output: Evidence data loaded into memory

[0722] Specific operation: The server periodically (for example, daily) executes SQL queries against the internal database and loads the necessary supporting data into memory.

[0723] Step 8:

[0724] The server performs the evaluation. The server evaluates the supporting data based on the evaluation criteria set. It executes a Python evaluation algorithm to automatically check the consistency and validity of the data.

[0725] Input: The supporting data loaded into memory in step 7

[0726] Output: Evaluation results

[0727] Specific operation: The server executes a Python script to evaluate the integrity and validity of the supporting data based on the specified evaluation criteria.

[0728] Step 9:

[0729] The server creates an evaluation result report and sends a notification. The server aggregates the results of the evaluation process and creates an evaluation result report in Excel format. This report is saved in an internal database and an email notification is sent to the user.

[0730] Input: Evaluation results generated in step 8

[0731] Output: Evaluation result report and notification to the user

[0732] Specific operation: The server compiles the evaluation results, generates a report based on an Excel template, saves the report in an internal database, and notifies the user via the SMTP protocol.

[0733] Step 10:

[0734] The user checks the evaluation results. The user opens the evaluation result report on the terminal and checks the contents. If an abnormality is found, the user sends an email to the relevant department instructing them to conduct further investigation.

[0735] Input: Notification of the evaluation result report sent in step 9

[0736] Output: Review the assessment report and any required actions

[0737] Specific operation: The user opens the evaluation result report in the terminal application and gives instructions for investigating and correcting inconsistent data.

[0738] Step 11:

[0739] The emotion engine evaluates the user's emotional state. The emotion engine analyzes the user's camera footage and uses facial recognition technology to assess stress and concentration levels in real time.

[0740] Input: User's camera image

[0741] Output: Evaluated emotional state data

[0742] How it works: The emotion engine captures camera footage and uses facial recognition algorithms to assess stress levels and concentration.

[0743] Step 12:

[0744] The emotion engine makes suggestions to adjust the process. Based on the evaluated emotional state data, the system makes suggestions to adjust the process. For example, if stress levels are high, it will make suggestions to simplify the confirmation process, and if concentration levels are high, it will encourage detailed confirmation.

[0745] Input: Emotional state data assessed in step 11

[0746] Output: Suggested process adjustments

[0747] What it does: The emotion engine analyzes the evaluated emotional state data and presents the user with options for adjusting the process as needed.

[0748] (Application example 2)

[0749] 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."

[0750] Modern logistics centers process a huge number of purchase specifications and delivery notes every day, requiring effective collection and evaluation of supporting documents. However, existing systems have low efficiency in collecting and evaluating supporting documents, and do not adequately manage employee stress or adjust processes. Therefore, in addition to improving work efficiency, flexible process adjustments based on employees' emotional states are necessary.

[0751] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring a list of evidence, means for randomly selecting evidence from the acquired list of evidence, means for generating and transmitting a request to collect the selected evidence, means for saving the collected evidence and checking its consistency, means for displaying the evidence data so that the user can confirm and approve it, and means for recognizing the emotional state and adjusting the process. This enables efficient collection and evaluation of evidence, and also enables flexibly adjusting the business process based on the user's emotional state.

[0752] The "means for obtaining a list of supporting documents" refers to a device or program that automatically obtains a list of supporting documents to be audited from an ERP system or database.

[0753] The "means for randomly selecting a voucher from the list of acquired vouchers" refers to a device or program that randomly selects a voucher from the list of acquired vouchers using a specific algorithm.

[0754] "Means for generating and sending requests to collect selected evidence" refers to a device or program that generates requests to collect selected evidence and sends them to the relevant departments or systems.

[0755] The "means for storing collected supporting documents and checking their consistency" refers to a device or program that stores collected supporting document data in an internal database and checks its consistency.

[0756] The "means for displaying supporting data so that the user can confirm and approve it" refers to a device or program that displays supporting data so that the user can confirm and approve it through a terminal.

[0757] The "means for recognizing emotional states and adjusting processes" refers to a device or program that recognizes the emotional state of a user in real time and dynamically adjusts the system processes based on that state.

[0758] The "means for evaluating supporting data based on a preset evaluation criterion" refers to a device or program for automatically evaluating supporting data based on a preset evaluation criterion.

[0759] The "means for generating evaluation results and creating an evaluation result report" refers to a device or program that generates evaluation results and creates an evaluation result report based on the results.

[0760] "Means for notifying and displaying the evaluation result report so that the user can view and confirm it" refers to a device or program that notifies the user of the evaluation result report so that the user can view and confirm it.

[0761] The "means for suggesting process adjustments based on the emotional state of the user" refers to a device or program that senses the emotional state of the user and suggests optimal process adjustments based on that state.

[0762] The "means by which a user can send an additional collection request" refers to a device or program that allows a user to send an additional document collection request as needed.

[0763] "Means for users to determine actions based on evaluation results and notify relevant departments" refers to a device or program that allows users to check evaluation results, specify necessary actions based on the results, and notify relevant departments.

[0764] The "means for monitoring the emotional state of a user using an emotion engine" is a device or program that uses an emotion engine to monitor the emotional state of a user in real time.

[0765] The present invention is a system aimed at improving the efficiency of audit responses at logistics centers. The present invention has the following configuration. First, as a means of obtaining a list of evidence, the server automatically obtains a list of evidence for audit targets from an ERP system or database. This list of evidence is saved in an internal database.

[0766] Next, the server randomly selects evidence from the obtained evidence list using a specific algorithm. To collect this selected evidence, the server generates a request and sends it to the relevant department or system (e.g., each department's terminal). The terminal receives this request, extracts the specified evidence from the database, and sends it to the server. The server stores the collected evidence in its internal database and checks its consistency.

[0767] The collected supporting data is displayed on the terminal for the user to review and approve. In addition, the server automatically evaluates the supporting data based on pre-set evaluation criteria and generates an evaluation result. This evaluation result is created as an evaluation result report and notified to the user's terminal. The user can check the evaluation result, determine actions as necessary, and notify relevant departments.

[0768] A distinctive feature of the present invention is the integration of an emotion engine. The emotion engine recognizes the user's emotional state in real time and provides the ability to adjust the process based on that data. For example, if the user is feeling stressed, the emotion engine can make automatic suggestions to simplify the review process. Also, if the user is highly focused, the emotion engine can prompt the user to review more detailed data.

[0769] For example, logistics center employees wearing smart glasses use the system to review and evaluate purchase order data automatically extracted from the ERP system. The employee's emotional state is monitored by the emotion engine, and the process is dynamically adjusted as needed.

[0770] An example of a prompt sentence is as follows:

[0771] Develop a smart glasses application that retrieves target purchase order data from an ERP system and monitors it in real time using an emotion engine. We provide code that enables automatic evaluation based on evaluation criteria and process adjustments based on employees' emotional state.

[0772] By using this prompt, it is possible to convey exactly what kind of application is required along with a concrete image.

[0773] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0774] Step 1:

[0775] The server automatically retrieves the list of auditable evidence from the ERP system or database. Specifically, the server makes an API call to the ERP system to retrieve a list of purchase statements for a specified period. This list is saved in the server's internal database. The input is instructions from the ERP system, and the output is the retrieved list of evidence.

[0776] Step 2:

[0777] The server randomly selects evidence from the acquired evidence list using a specific algorithm. Specifically, the server executes a random sampling algorithm from the acquired list to select, for example, 50 evidences. The input is the acquired evidence list, and the output is the randomly selected evidence list.

[0778] Step 3:

[0779] The server generates a request to collect the selected evidence and sends it to the relevant departments and systems. Specifically, the server sends a request to each department's terminal, clearly indicating what evidence needs to be collected. The input is a list of randomly selected evidence, and the output is the sent request.

[0780] Step 4:

[0781] The terminal receives a request from the server, extracts the specified evidence from the database, and sends it to the server. The terminal executes a database query, extracts the specified evidence, and sends it to the server. The input is the collection request from the server, and the output is the extracted evidence data.

[0782] Step 5:

[0783] The server stores the collected evidence in an internal database and checks its integrity. Specifically, the server passes the received evidence data through a verification algorithm to check the consistency and completeness of the data. The input is the extracted evidence data, and the output is the evidence data whose integrity has been confirmed.

[0784] Step 6:

[0785] The server displays the collected supporting data on the terminal so that the user can confirm and approve it. The terminal displays the supporting data through a user interface, and the user confirms and approves it. The input is the confirmation request and supporting data, and the output is feedback of approval or rejection by the user.

[0786] Step 7:

[0787] The server automatically evaluates the supporting data based on pre-defined evaluation criteria. The evaluation algorithm examines the supporting data and determines whether it meets the pre-defined criteria. The input is the supporting data and evaluation criteria, and the output is the evaluation result.

[0788] Step 8:

[0789] The server generates evaluation results and creates an evaluation result report. Specifically, the server aggregates the evaluation results and generates a report in a format that is easy for users to understand. The input is the evaluation results, and the output is the evaluation result report.

[0790] Step 9:

[0791] The server notifies the user of the evaluation result report and prompts them to confirm it. The user checks the report on their device and determines the necessary actions. The input is the evaluation result report, and the output is the user's confirmation and feedback.

[0792] Step 10:

[0793] After the user specifies an action, the server notifies the relevant departments. Specifically, the server generates notification content and sends it to the relevant department's terminal. The input is the user's instruction to take an action, and the output is a notification to the relevant department.

[0794] Step 11:

[0795] The emotion engine recognizes the user's emotional state in real time and adjusts the process appropriately. The emotion engine monitors the user's stress and concentration level and generates appropriate suggestions. The input is the user's real-time emotional data, and the output is adjustment suggestions and their implementation.

[0796] Step 12:

[0797] If the user accepts the emotion engine's suggestion, the server dynamically adjusts the process based on the suggestion. The input is the emotion engine's suggestion, and the output is the adjusted process.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] [Third embodiment]

[0802] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0803] 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.

[0804] 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).

[0805] 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.

[0806] 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.

[0807] 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).

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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."

[0814] Automatic document collection tool

[0815] The present invention is a system for improving the efficiency of audit responses, and includes an automatic document collection tool and an evaluation automation tool. First, the automatic document collection tool will be described.

[0816] The server first obtains a list of documents to be audited. This list is collected from an ERP system or database. Next, the server generates a random sample from the obtained list of documents. This random sample generation algorithm randomly selects any document.

[0817] The server generates a request to collect the selected evidence and sends it to the relevant department or system. This request specifies the type and quantity of evidence and includes a collection request. The terminal receives this request, collects the evidence in real time, and sends it back to the server.

[0818] The server stores the received supporting data in an internal database and checks its consistency. This consistency check identifies missing or abnormal data. The user uses the terminal to review and approve the collected supporting data. If additional collection is required, the user can send an additional collection request through the terminal.

[0819] Specific examples

[0820] For example, a server retrieves a list of supporting documents for a monthly report from an ERP system. This list contains purchase statements for a given month. The server uses a random algorithm to select 50 purchasing statements and sends requests to each department to collect these supporting documents.

[0821] The terminal receives this request, extracts the specified purchase details from the database, and sends them to the server. The server saves the received supporting data and performs a consistency check. The user then checks and approves the data on the terminal.

[0822] Evaluation automation tool

[0823] Next, we will explain the evaluation automation tool. The server receives supporting data and starts the evaluation process. The server executes an automatic evaluation algorithm based on pre-set evaluation criteria. These evaluation criteria include various criteria for internal control evaluation.

[0824] The server generates the results of the evaluation process and creates an evaluation result report, which is stored in a database for the user to review. The server then sends a notification of the evaluation result to the terminal, prompting the user to review the evaluation result.

[0825] Users can check the evaluation results report through their terminal and determine the necessary actions. For example, if an abnormality is discovered, the user can issue instructions to the relevant department for investigation or correction.

[0826] Specific examples

[0827] The server retrieves the previously collected purchase statement data and evaluates each statement for consistency and validity based on the evaluation criteria set. Evaluation algorithms perform this and identify outliers and inconsistent data.

[0828] A report of the evaluation results is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and instruct the purchasing department to conduct further investigations into any inconsistencies in the data.

[0829] In this way, the present invention realizes automatic collection of supporting documents and automated evaluation, thereby significantly reducing the amount of work required to respond to audits and improving efficiency.

[0830] The processing flow will be explained below.

[0831] Automatic document collection tool

[0832] Step 1:

[0833] The server automatically retrieves the list of evidence to be audited from the ERP system or database, and the retrieved list of evidence is saved in the internal database.

[0834] Step 2:

[0835] The server executes an algorithm to randomly select a particular document from the obtained document list. A random sample is selected.

[0836] Step 3:

[0837] The server generates a request to collect the selected evidence, which is then sent to the relevant department or system.

[0838] Step 4:

[0839] The terminal receives the request and extracts the specified evidence from the associated database, and the extracted evidence data is sent from the terminal to the server.

[0840] Step 5:

[0841] The server stores the received supporting data in an internal database and checks the integrity of the stored data.

[0842] Step 6:

[0843] The user checks the collected evidence data through the terminal and approves the checked data.

[0844] Step 7:

[0845] If the user needs to collect additional evidence, the terminal sends an additional collection request to the server.

[0846] Evaluation automation tool

[0847] Step 1:

[0848] The server retrieves the supporting document data received from the automated supporting document collection tool from the database, and rechecks the consistency of the retrieved data.

[0849] Step 2:

[0850] The server evaluates the supporting data based on the set evaluation criteria, and executes the evaluation algorithm to evaluate the effectiveness of internal controls.

[0851] Step 3:

[0852] The server generates the evaluation results and creates an evaluation result report, which is stored in an internal database.

[0853] Step 4:

[0854] The server sends a notification of the evaluation result to the terminal, which then displays the evaluation result to the user.

[0855] Step 5:

[0856] The user checks the evaluation result report through the terminal, determines the necessary actions, and notifies the relevant departments of correction instructions and investigation requests.

[0857] Through these steps, the automated collection and evaluation of supporting documents is achieved, reducing the amount of work required and improving efficiency in responding to audits.

[0858] Example 1

[0859] 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."

[0860] In conventional audit response systems, the process of collecting and evaluating supporting documents is manual, requiring time and effort. Furthermore, manual collection and evaluation is prone to human error, and data integrity cannot be guaranteed. Furthermore, there are inefficiencies in the process of reviewing and approving the evaluation results, creating a need for greater efficiency in the entire audit process.

[0861] 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.

[0862] In this invention, the server includes a means for acquiring a list of supporting documents from a data management system, a means for randomly selecting supporting documents from the acquired list using a random algorithm, and a means for generating a request to collect the selected supporting documents and sending it to each department via a network. This automates the process of collecting supporting documents, eliminates manual errors, and enables efficient audit response. The server also stores the collected supporting document data in a database and has a means for checking its consistency, ensuring the consistency and reliability of the data. Furthermore, the server includes a means for displaying the supporting document data so that users can confirm and approve it using a terminal, thereby realizing rapid confirmation of evaluation results and the approval process.

[0863] A "list of supporting documents" is a list that summarizes the types and details of supporting documents required for audit responses and business evaluations.

[0864] A "data management system" is an information system that manages and stores business data in a company or organization, and allows access and retrieval for specific purposes.

[0865] A "random algorithm" is a computational method for randomly drawing samples from a data set, used to ensure a fair and unbiased selection.

[0866] A "network" is an information transmission mechanism that connects multiple computers and terminals so that they can communicate with each other.

[0867] A "request" is a command to request specific data or an operation, and is used to obtain or send information between systems.

[0868] A "database" is a structured collection of data that can efficiently manage and store large amounts of data and can be quickly accessed and searched when needed.

[0869] "Integrity" is a property that ensures that data is consistent and free of errors and omissions, and is important for ensuring the accuracy and reliability of data.

[0870] An "automated evaluation algorithm" is a calculation method that allows a program to automatically analyze and evaluate collected data based on pre-set evaluation criteria.

[0871] "Evaluation criteria" are a set of rules and indicators that are used as standards when evaluating and judging data, and they define the appropriateness and problems of the subject of evaluation.

[0872] An "evaluation result report" is a document or data file that summarizes the results of the evaluation process, and indicates the status of the subject of evaluation and whether or not there are any abnormalities.

[0873] A "terminal" refers to a device such as a computer or mobile device that can be directly operated by a user, and is used to input data into the system and display results.

[0874] "User" refers to a person or role who operates the system to perform actual work or audits, and is the entity that uses the various functions of the system.

[0875] "Notification" means a message or signal that informs a user of particular information or results.

[0876] "Verification" refers to the act of checking the content of data or information to confirm whether it is accurate.

[0877] "Approval" refers to the act of acknowledging the correctness and validity of confirmed data or information.

[0878] "Action" refers to specific measures or steps taken based on the evaluation results, and means actions taken to solve problems or make improvements.

[0879] Automatic document collection tool

[0880] Server Processing

[0881] The server first obtains a list of evidence to be audited from the data management system or internal database. This process involves extracting the necessary data using, for example, an SQL query. Based on the obtained list of evidence, a random algorithm is used to randomly select evidence, using an algorithm such as Python's random.sample function. During this process, a request to collect the selected evidence is generated and sent to each department via the network. This request is often sent using an HTTP request.

[0882] Terminal handling

[0883] The terminal receives a request for collecting supporting documents from the server, extracts the specified supporting documents from the database, and sends them to the server. The terminal also returns the extracted data to the server as an HTTP response. During this process, the necessary database queries are executed to ensure that the supporting document data is accurately sent to the server.

[0884] User Action

[0885] Users can use their devices to check and approve the supporting data stored on the server. They can view and manipulate the data through a GUI, and can send requests for additional supporting data to the server as needed. This increases the accuracy and reliability of audits.

[0886] Specific examples

[0887] For example, the server retrieves a list of supporting documents required for monthly reports from the ERP system. Based on the retrieved list, a random sample generation algorithm is used to select 50 purchasing details. A request is generated for each selected supporting document and a request to collect the supporting documents is sent to each department. The terminal receives this request, extracts the specified purchasing details from the database, and sends them to the server. The server stores the received supporting document data and checks its consistency. The user uses the terminal to check and approve the data. If there are any problems, the user can send additional collection requests.

[0888] Prompt Sentence Examples

[0889] Based on the document list obtained from the ERP system, 50 purchasing details are randomly selected and a document collection request is sent to each department. The terminal then retrieves the document from the database and sends it to the server. The server saves the data and checks its integrity. The user then uses the terminal to check and approve the document data.

[0890] Evaluation automation tool

[0891] Server Processing

[0892] The server retrieves the collected supporting data from the database and starts the evaluation process. This process includes an automated evaluation algorithm based on pre-defined evaluation criteria, including the consistency of internal control standards and business processes. Evaluation results are generated and an evaluation result report is created based on the results. This report is saved in the database and notified to the user.

[0893] User Action

[0894] Users can check the evaluation result report through their terminal and decide on the necessary actions. If an abnormality is found in the evaluation results, users can send instructions for investigation or correction to the relevant department through their terminal. This allows for quick confirmation and response of audit results.

[0895] Specific examples

[0896] The server evaluates the collected purchasing specification data based on the evaluation criteria and identifies outliers and inconsistent data. An evaluation result report is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and issue instructions to the purchasing department for further investigation or correction of inconsistent data.

[0897] Prompt Sentence Examples

[0898] The collected purchasing specification data is evaluated based on evaluation criteria to identify outliers and inconsistencies. An evaluation result report is created and notified to the user. The user can check the evaluation results via their terminal, and if an abnormality is found, they can issue instructions to the purchasing department for investigation or correction.

[0899] In this way, the present invention realizes automatic collection of supporting documents and automated evaluation, thereby reducing the number of steps required for audits and improving efficiency.

[0900] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0901] Automatic document collection tool

[0902] Server Processing Steps

[0903] Step 1:

[0904] The server retrieves the list of supporting documents to be audited from the data management system. The input is raw data retrieved from the ERP system or internal database, and the necessary data is extracted using SQL queries. The output is a list of supporting documents required for the audit.

[0905] Specifically, the server executes a query such as "SELECT FROM evidence_list WHERE month='2023-10';" to retrieve the target evidence list from the database.

[0906] Step 2:

[0907] The server randomly selects a voucher from the obtained list of vouchers using a random algorithm. The input is the list of vouchers obtained in step 1, and it processes the algorithm to randomly extract data. The output is a sample list of randomly selected vouchers.

[0908] Specifically, for example, 50 supporting documents are selected using Python's random.sample function.

[0909] Step 3:

[0910] The server generates a request to collect the selected evidence and sends it to each department via the network. The input is the list of evidence selected in step 2, and the output is the collection request sent to each department.

[0911] Specifically, an HTTP request is generated and sent to the URL of each department.

[0912] Step 4:

[0913] The terminal receives the collection request sent from the server and extracts the specified evidence from the database. The input is the collection request from the server, and the output is the extracted evidence data.

[0914] Specifically, the terminal executes the query "SELECT FROM evidences WHERE id=?" and sends the extracted results to the server.

[0915] Step 5:

[0916] The server stores the received supporting data in an internal database and checks its consistency. The input is the supporting data sent from the terminal, and the output is the consistency check result and the stored data.

[0917] Specifically, the system stores supporting data in a database and runs a consistency check algorithm, detecting missing or anomalous data.

[0918] Step 6:

[0919] The user uses a terminal to check the evidence data stored on the server and give approval. The input is the evidence data stored on the server, and the output is the user's confirmation and approval results.

[0920] Specifically, the GUI screen displays the data, allows the user to review and approve it, and allows the user to submit additional collection requests if necessary.

[0921] Evaluation automation tool

[0922] Server Processing Steps

[0923] Step 1:

[0924] The server retrieves the collected supporting data from the database and starts the evaluation process. The input is the collected supporting data and the output is the data ready to run the evaluation process.

[0925] Specifically, a database query is executed to extract the data to be evaluated.

[0926] Step 2:

[0927] The server executes an automatic evaluation algorithm based on pre-defined evaluation criteria. The input is the supporting data obtained in step 1, and the output is the evaluation result.

[0928] Specifically, it runs evaluation algorithms implemented in languages ​​such as Python to assess the integrity and validity of the data.

[0929] Step 3:

[0930] The server creates an evaluation result report based on the results of the evaluation process. The input is the evaluation result, and the output is the evaluation result report.

[0931] Specifically, a report is generated based on the evaluation results and stored in a database.

[0932] Step 4:

[0933] The server notifies the user of the evaluation result report and allows the user to check it on the terminal. The input is the evaluation result report, and the output is a notification message to the user.

[0934] Specifically, an HTTP request for notification is generated and sent to the user's terminal.

[0935] User processing steps

[0936] Step 5:

[0937] The user checks the evaluation result report through the terminal and decides on the necessary action. The input is the evaluation result report, and the output is the user's action instructions.

[0938] Specifically, the report is viewed using a GUI that displays the evaluation results, and if any abnormalities or inconsistencies are found, instructions are issued to the purchasing department or other department to investigate or correct the issues.

[0939] As described above, the processing steps of the present invention have been explained together with specific operations. This clarifies the process of automatic collection of supporting documents and automated evaluation, and is expected to enable efficient audit response.

[0940] (Application example 1)

[0941] 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."

[0942] Logistics centers are required to manage a huge number of supporting documents (receipts, shipping certificates, inventory lists, etc.), and collecting and evaluating these documents takes a lot of time and effort. In particular, consistency checks and anomaly detection for these documents are often done manually, so there is a need for efficiency improvements. There is also a need for a system that can reduce the workload of on-site workers and quickly collect and evaluate supporting documents.

[0943] 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.

[0944] In this invention, the server includes means for acquiring a list of evidence, means for randomly selecting evidence from the acquired list of evidence, means for generating and sending a request to collect the selected evidence, means for saving the collected evidence and checking its consistency, means for displaying the evidence data so that the user can confirm and approve it, means for creating a request for evidence collection and sending it to the relevant department, and means for checking the consistency and evaluating the acquired evidence data. This makes it possible to efficiently collect evidence at a logistics center and automatically evaluate it.

[0945] A "list of supporting documents" is a list of supporting documents required for audits and business processes, and is obtained from an ERP system or database.

[0946] "Randomly selecting evidence" means randomly selecting evidence from a list of evidence based on a pre-set algorithm.

[0947] "Generate and send a request" refers to automatically creating a request to collect the selected evidence and sending it to the relevant department or system.

[0948] "Consistency checking" is the process of verifying that the collected supporting data is appropriate and free of inconsistencies or anomalies.

[0949] "Evidence data" refers to the specific information and content of each evidence obtained and collected.

[0950] "Evaluating supporting data based on evaluation criteria" refers to the process of automatically evaluating the accuracy and suitability of collected supporting data according to pre-set criteria and conditions.

[0951] An "evaluation result report" is a report summarizing the results of the evaluation process of supporting data.

[0952] "Instructing investigation and correction" means that if any inconsistencies or abnormalities are discovered based on the evaluation results, the relevant department will be asked to carry out the necessary investigation and correction work.

[0953] "On-site workers collect and upload supporting documents using smartphones" refers to the process in which on-site workers at the logistics center collect supporting documents using smartphones and upload them to a server via a dedicated application.

[0954] "Login and user authentication" refers to entering the user authentication information required to access the system and taking appropriate security measures.

[0955] "Generating prompts using a generative AI model and providing automated assistance" refers to an assistance function that uses AI technology to create prompts and simplify user operations.

[0956] As an embodiment of the present invention, the specific configuration and procedures of a document management system used in a logistics center are described below. This system has functions such as obtaining a document list, randomly selecting documents, generating and sending document collection requests, checking the integrity of documents, evaluating data based on evaluation criteria, generating and notifying result reports, and even issuing investigation and correction instructions.

[0957] First, the server retrieves the list of evidence from the ERP system or database. From the retrieved list of evidence, the server randomly selects evidence, generates a request to collect it, and sends it to the relevant department. This process is implemented using a Python program and the "requests" module. For example, the list of evidence can be obtained through an API endpoint, and evidence can be randomly selected using the "random" module.

[0958] The server then sends requests to each department to collect the selected evidence, and field workers use their smartphones to collect the evidence. The collected evidence data is then uploaded from the smartphone to the server. The smartphone application plays an important role in this process, making it possible to collect and upload evidence in real time. It also has security features such as login and user authentication, and appropriate access control is performed by entering authentication information.

[0959] The collected supporting data is stored on a server and a consistency check is performed. This consistency check, which includes checking the correct date format and numeric range, is implemented using the Python datetime module, for example. Once the consistency of the supporting data is confirmed, it is evaluated based on pre-set evaluation criteria. The evaluation results are generated as an evaluation result report and notified to the user.

[0960] After reviewing the evaluation results, users can instruct the relevant department to investigate and correct any abnormal supporting documentation data. Generative AI models can also be used to automatically create prompts, simplifying user operations. For example, a prompt could be generated such as, "Please explain the system for automatically collecting and evaluating supporting documentation at a logistics center. Please provide a detailed explanation of the integrity check and evaluation process for randomly selected supporting documentation."

[0961] In this way, the present invention can improve the efficiency of document management at logistics centers and reduce the workload. It also enables real-time collection and evaluation of documented evidence, enabling immediate problem detection and countermeasures.

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

[0963] Step 1:

[0964] The server retrieves the document list from the ERP system or database. In this step, it accesses the API endpoint using the Python requests module to retrieve the document list. The input is the API endpoint URL, and the output is the document list data in JSON format.

[0965] Step 2:

[0966] The server randomly selects evidence from the obtained evidence list. In this step, the Python random module is used to randomly select a specified number of evidence from the evidence list. The input is the evidence list data, and the output is the selected evidence data.

[0967] Step 3:

[0968] The server generates and sends a request to collect the selected evidence. The request specifies the type and quantity of evidence and is sent to the relevant departments and parties. The input is the selected evidence data, and the output is a request message sent to each department.

[0969] Step 4:

[0970] The terminal receives a request from the server, and the on-site worker collects the evidence using a smartphone. The worker takes a photo of the evidence with a camera and uploads it along with location and time information. The input is the request message, and the output is the evidence image data and accompanying information.

[0971] Step 5:

[0972] The server stores the supporting data uploaded by field workers and checks its consistency. It uses the Python datetime module to check the correct date format and numeric range. The input is the supporting data image data and accompanying information, and the output is the consistency check results.

[0973] Step 6:

[0974] The server evaluates the integrity-checked supporting data based on pre-defined evaluation criteria, generates evaluation results, and creates a result report. It runs an automated evaluation algorithm based on the evaluation criteria to identify outliers and inconsistent data. The input is the integrity-checked supporting data, and the output is an evaluation result report.

[0975] Step 7:

[0976] The server notifies the user of the evaluation result report, allowing the user to check the results. The user can review the evaluation results and determine the necessary actions. The input is the evaluation result report, and the output is notification and display on the user screen.

[0977] Step 8:

[0978] If the user finds any abnormal supporting data, they can instruct the relevant department to investigate and correct it. A generative AI model is used to automatically create prompts, simplifying user operations. The input is the evaluation results and the prompts generated by the generative AI model, and the output is instructions to the relevant department to investigate and correct the abnormality.

[0979] In this way, by linking each processing step, automatic collection and evaluation of supporting documents at the logistics center is realized.

[0980] 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.

[0981] Overall overview

[0982] This invention is a system for streamlining audit response, which includes an automatic document collection tool and an evaluation automation tool, and also combines an emotion engine that recognizes user emotions and adjusts various system processes.

[0983] Automatic document collection tool

[0984] The server first automatically retrieves the list of documents to be audited from the ERP system or database. This list is stored in an internal database. The server then runs an algorithm to randomly select specific documents from the list of documents to generate a random sample.

[0985] The server generates a request to collect the selected evidence and sends it to the relevant department or system. The terminal receives the request, extracts the specified evidence from the relevant database, and sends it to the server. The server stores the received evidence data in an internal database and checks its consistency. The user uses the terminal to check and approve the collected evidence data. If additional collection is required, the user can send an additional collection request through the terminal.

[0986] Specific examples

[0987] For example, the server retrieves a list of supporting documents required for a monthly report from the ERP system. This list includes purchasing details for a specified month. The server selects 50 purchasing details using a random algorithm and sends a request to each department to collect these supporting documents. The terminal receives this request, extracts the specified purchasing details from the database, and sends them to the server. The server saves the received supporting document data and performs a consistency check. The user checks and approves the data on the terminal.

[0988] Evaluation automation tool

[0989] Next, we will explain the evaluation automation tool. The server receives supporting data and starts the evaluation process. Based on pre-set evaluation criteria, the server executes an automatic evaluation algorithm. These evaluation criteria include various standards for internal control evaluation. The server generates the results of the evaluation process and creates an evaluation result report. This report is saved in a database so that the user can check it. The server sends a notification of the evaluation result to the terminal, prompting the user to check the evaluation result. The user checks the evaluation result report through the terminal and determines the necessary actions. For example, if an abnormality is discovered, the user can issue instructions for investigation or correction to the relevant department.

[0990] Specific examples

[0991] The server retrieves the previously collected purchasing statement data and evaluates the consistency and validity of each statement based on the evaluation criteria that have been set. The evaluation algorithm executes this and identifies outliers and inconsistent data. A report of the evaluation results is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and instruct the purchasing department to conduct further investigations on inconsistent data.

[0992] Emotion engine integration

[0993] The emotion engine recognizes the user's emotional state and adjusts various system processes. The emotion engine evaluates the user's stress level and concentration level in real time when verifying and approving supporting documents. This emotional data is reflected in the configuration of the supporting document verification process, additional collection requests, and evaluation process.

[0994] Specific examples

[0995] For example, if a user feels stressed while reviewing supporting data, the emotion engine can detect this and make automatic suggestions to simplify the review process. Also, if the user is highly focused, the engine can prompt the user to review more detailed data. Furthermore, the engine can dynamically adjust evaluation criteria based on emotion data and suggest actions based on the evaluation results. The emotion engine can recommend users with high stress levels to send additional collection requests.

[0996] Through these steps, the system will enable the automatic collection of supporting documents, automated evaluation, and process adjustments based on user feedback, resulting in a significant reduction in audit response time and increased efficiency.

[0997] The processing flow will be explained below.

[0998] Automatic document collection tool

[0999] Step 1:

[1000] The server automatically retrieves the list of evidence to be audited from the ERP system or database, and the retrieved list of evidence is saved in the internal database.

[1001] Step 2:

[1002] The server executes an algorithm to randomly select a particular document from the obtained document list. A random sample is selected.

[1003] Step 3:

[1004] The server generates a request to collect the selected evidence and sends the request to the relevant department or system.

[1005] Step 4:

[1006] The terminal receives the request and extracts the specified evidence from the associated database, and the extracted evidence data is sent from the terminal to the server.

[1007] Step 5:

[1008] The server stores the received supporting data in an internal database and checks the integrity of the stored data.

[1009] Step 6:

[1010] The user checks the collected evidence data through the terminal and approves the checked data.

[1011] Step 7:

[1012] If the user needs to collect additional evidence, the terminal sends an additional collection request to the server.

[1013] Evaluation automation tool

[1014] Step 1:

[1015] The server retrieves the supporting document data received from the automated supporting document collection tool from the database, and rechecks the consistency of the retrieved data.

[1016] Step 2:

[1017] The server evaluates the supporting data based on the set evaluation criteria, and executes the evaluation algorithm to evaluate the effectiveness of internal controls.

[1018] Step 3:

[1019] The server generates the evaluation results and creates an evaluation result report, which is stored in an internal database.

[1020] Step 4:

[1021] The server sends a notification of the evaluation result to the terminal, which then displays the evaluation result to the user.

[1022] Step 5:

[1023] The user checks the evaluation result report through the terminal, determines the necessary actions, and notifies the relevant departments of correction instructions and investigation requests.

[1024] Emotion engine integration

[1025] Step 1:

[1026] The emotion engine recognizes the user's emotional state. The emotion engine analyzes the user's facial expressions, tone of voice, typing speed, etc. to collect emotional data in real time.

[1027] Step 2:

[1028] The emotion engine analyzes the collected emotional data to determine the user's stress level and concentration, which is reflected in the verification and approval process of supporting data.

[1029] Step 3:

[1030] When a user checks the evidence data, the emotion engine adjusts the initial settings according to the user's emotional state. For example, if the user is feeling stressed, the emotion engine provides an assistance function to simplify the checking process.

[1031] Step 4:

[1032] The server dynamically adjusts the evaluation criteria. The evaluation criteria are flexibly changed based on the emotional data acquired by the emotion engine. When the user is highly focused, a stricter evaluation is performed.

[1033] Step 5:

[1034] The server generates the evaluation report, and the emotion engine adjusts the report display based on the user's emotional state: if stress is high, the report is summarized.

[1035] Step 6:

[1036] The emotion engine suggests additional collection requests and actions based on the user's emotional state. For example, if the user is impatient, the emotion engine suggests sequenced next steps.

[1037] These steps will enable the automatic collection of supporting documents, the automation of assessment, and the adjustment of the process based on user feedback, resulting in a significant reduction in audit response time and increased efficiency. This will also reduce user stress and enable more accurate assessments.

[1038] Example 2

[1039] 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."

[1040] In conventional audit response systems, the collection and evaluation of supporting documents is often done manually, resulting in a significant amount of labor and time. It has also been pointed out that the evaluation of supporting documents is prone to human error and subjective judgment, resulting in a lack of reliability. Another problem is that the user's emotions and state can affect system operation, resulting in a decrease in the efficiency of audit work. The present invention aims to solve these problems and provide a system that streamlines audit response.

[1041] 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.

[1042] In this invention, the server includes a means for acquiring a list of information, a means for randomly selecting information from the acquired list of information, and a means for generating and transmitting a request to collect the selected information. This enables the automatic collection of evidence. The server also includes a means for storing the collected information and checking its consistency, a means for displaying the information data so that the user can confirm and approve it, a means for evaluating the user's emotional state, and a means for making suggestions to adjust the process based on the evaluated emotional state. This ensures the reliability of the information and enables adaptive operation according to the user's emotions. The server also includes a means for evaluating the information data based on pre-set evaluation criteria, a means for generating evaluation results and creating an evaluation result report, and a means for notifying and displaying the evaluation result report so that the user can view and confirm it. This enables an automatic evaluation process, improving the efficiency and reliability of evaluation work.

[1043] "Information list" refers to a list of supporting documents and related data to be audited, and is obtained from an ERP system or database.

[1044] "Selecting information" refers to the operation of selecting specific information from the list of acquired information randomly or based on arbitrary criteria.

[1045] "Generate and send a request" refers to the act of creating a request to collect selected information and sending it to the relevant department or system.

[1046] "Collected information" refers to evidence and data obtained in response to a server request.

[1047] "Checking consistency" refers to the act of verifying whether the collected information is accurate and consistent.

[1048] "Information data" refers to supporting evidence and related data collected for the audit.

[1049] "User" refers to the person who operates the system and reviews and approves the audit process.

[1050] "Emotional state" refers to the psychological state of the user when operating the system, including, for example, stress level and concentration level.

[1051] "Suggestions to adjust processes" refers to suggestions to change or optimize various system operations or processes depending on the user's emotional state.

[1052] "Evaluation criteria" refers to the pre-established standards and rules for conducting evaluations in internal control and audits.

[1053] "Evaluation result" refers to the result calculated by an automated evaluation algorithm based on the evaluation criteria.

[1054] "Evaluation results report" refers to a written or digital report summarizing the evaluation results.

[1055] "Notification" refers to the operation of informing the user about the evaluation result report generated by the system.

[1056] "Display" refers to the operation of showing the collected information and evaluation results on a screen or the like so that the user can check them.

[1057] MODE FOR CARRYING OUT THE INVENTION

[1058] The present invention is a system for improving the efficiency of audit responses, and is implemented in a form that combines an automatic document collection tool, an automatic evaluation tool, and an emotion engine.

[1059] Automatic document collection tool

[1060] First, the server automatically retrieves the list of documents to be audited from the ERP system or database (e.g., SAP, Oracle Database). This list of documents is stored in an internal database. The server then uses a Python random module to randomly select specific documents from the list of documents and generate a random sample.

[1061] The server generates a request to collect the selected evidence and sends it to the relevant departments and systems via email or API. The terminal receives the request and extracts the specified evidence from the relevant database. The extracted evidence data is sent to the server in CSV format. The server stores the received evidence data in an internal database and performs a consistency check (e.g., checksum value comparison). The user uses a dedicated terminal application to check and approve the collected evidence data. If additional collection is required, the user can send an additional collection request from the terminal.

[1062] Specific examples

[1063] The server obtains a list of supporting documents for monthly reports from SAP. This list contains purchasing details for the specified month. The server uses a random module to select 50 purchasing details. It uses the SMTP protocol to send a request to each department to collect these supporting documents. The terminal receives the request, executes an SQL query to extract the specified purchasing details from the Oracle Database, and sends them to the server. The server saves the received supporting document data and verifies its integrity using a checksum value. The user checks and approves the data on the terminal. If additional collection is required, the user sends a new collection request from the terminal.

[1064] Example prompt: "I need supporting monthly statements from SAP. Specifically, I need 50 random purchase statements."

[1065] Evaluation automation tool

[1066] The server retrieves the collected supporting data from the internal database and performs an evaluation based on pre-set evaluation criteria (e.g., internal control evaluation criteria). It evaluates the data using Python evaluation algorithms to check consistency and validity. It creates an evaluation result report and stores it in the internal database. The server sends a notification about the evaluation result to the terminal, prompting the user to confirm it. The user uses the terminal to check the evaluation result report and decides on necessary actions. If any abnormalities are found, the user instructs the relevant department to carry out further investigation or corrections.

[1067] Specific examples

[1068] The server retrieves the collected purchasing statement data and evaluates it based on internal control evaluation criteria. An outlier or inconsistent data is identified using a Python evaluation algorithm. A report of the evaluation results is created and a notification is sent to the user. The user can then check the report on their device and instruct the purchasing department to investigate any inconsistent data.

[1069] Example prompt: "Evaluate the consistency and validity of the collected purchasing statements based on the internal control evaluation criteria and generate a report of the evaluation results."

[1070] Emotion engine integration

[1071] The emotion engine evaluates the user's emotional state in real time when reviewing and approving supporting data. The emotion engine analyzes the user's camera footage and uses facial recognition technology to measure stress and concentration levels. Based on the emotional data, it makes suggestions to adjust the system process. If the stress level is high, the emotion engine will suggest simplifying the review process, while if the concentration level is high, it will prompt a more detailed review.

[1072] Specific examples

[1073] If a user is feeling stressed while reviewing supporting data, the emotion engine will detect this and offer options to simplify the review process, or if the user is highly focused, the emotion engine will prompt the user to review the data in more detail.

[1074] Example prompt: "Assess the stress level of users when reviewing supporting data and adjust the review process as needed."

[1075] This enables the automatic collection of supporting documents, automated evaluation, and process adjustment using an emotion engine, thereby achieving more efficient audit response.

[1076] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1077] Step 1:

[1078] The server obtains the list of evidence. The server accesses the API endpoint of the ERP system and requests the latest list of evidence. The obtained list of evidence is saved in the server's internal database.

[1079] Input: Evidence data request from ERP system

[1080] Output: List of evidence stored in the internal database

[1081] Specific operation: The server sends an HTTP request to the ERP system's API, processes the list of evidence returned in JSON format, and inserts it into the PostgreSQL database.

[1082] Step 2:

[1083] The server randomly selects evidence from the evidence list. Using the Python random module, a specific number of evidences are randomly selected from the obtained evidence list. The selected evidences are then stored in the server's internal database again.

[1084] Input: List of evidence obtained in Step 1

[1085] Output: A randomly selected list of evidence

[1086] Specific operation: The server uses a Python script to randomly select 50 documents from the document list and save the list in an internal database.

[1087] Step 3:

[1088] The server generates and sends a request for collection of evidence. The server uses the SMTP protocol to send the request to the email address of the relevant department. It may also send the request directly to the department's system using an API.

[1089] Input: List of evidence selected in step 2

[1090] Output: Sending a request for evidence collection to the relevant department or system

[1091] Specific operation: The server uses the SMTP library to generate collection request emails and send them to each department. It also sends collection requests to other systems via the RESTful API.

[1092] Step 4:

[1093] The terminal extracts and sends the supporting evidence. The terminal receives the request and extracts the specified supporting evidence from the relevant database (e.g., Oracle Database). The extracted supporting evidence data is sent to the server in CSV format.

[1094] Input: Voucher collection request received from the server

[1095] Output: Send extracted supporting data to the server

[1096] Specific operation: The device receives a notification, the user executes an SQL query to extract supporting data, and uploads it to the server as a CSV file.

[1097] Step 5:

[1098] The server stores the supporting data and performs integrity checks. The server stores the received supporting data in an internal database and verifies the integrity of the data using a checksum algorithm.

[1099] Input: Evidence data sent in step 4

[1100] Output: Stored supporting data after integrity check

[1101] What happens: The server processes the uploaded CSV file, calculates the checksum to verify its integrity, and then inserts it into the PostgreSQL database.

[1102] Step 6:

[1103] The user checks and approves the supporting data. The user uses a dedicated terminal application to check and approve the collected supporting data. If additional collection is required, an additional collection request is sent from the terminal.

[1104] Input: Evidence data whose integrity was confirmed in Step 5

[1105] Output: Approved supporting data or additional collection requests

[1106] Specific operation: The user displays the supporting data in the terminal application, confirms it, and then clicks the approval button to send the approval status to the server. If additional collection is required, a new collection request is sent from the terminal.

[1107] Step 7:

[1108] The server retrieves the supporting data. The server executes SQL queries to retrieve the necessary supporting data from the internal database. The retrieved data is loaded into memory.

[1109] Input: Evidence data on the internal database

[1110] Output: Evidence data loaded into memory

[1111] Specific operation: The server periodically (for example, daily) executes SQL queries against the internal database and loads the necessary supporting data into memory.

[1112] Step 8:

[1113] The server performs the evaluation. The server evaluates the supporting data based on the evaluation criteria set. It executes a Python evaluation algorithm to automatically check the consistency and validity of the data.

[1114] Input: The supporting data loaded into memory in step 7

[1115] Output: Evaluation results

[1116] Specific operation: The server executes a Python script to evaluate the integrity and validity of the supporting data based on the specified evaluation criteria.

[1117] Step 9:

[1118] The server creates an evaluation result report and sends a notification. The server aggregates the results of the evaluation process and creates an evaluation result report in Excel format. This report is saved in an internal database and an email notification is sent to the user.

[1119] Input: Evaluation results generated in step 8

[1120] Output: Evaluation result report and notification to the user

[1121] Specific operation: The server compiles the evaluation results, generates a report based on an Excel template, saves the report in an internal database, and notifies the user via the SMTP protocol.

[1122] Step 10:

[1123] The user checks the evaluation results. The user opens the evaluation result report on the terminal and checks the contents. If an abnormality is found, the user sends an email to the relevant department instructing them to conduct further investigation.

[1124] Input: Notification of the evaluation result report sent in step 9

[1125] Output: Review the assessment report and any required actions

[1126] Specific operation: The user opens the evaluation result report in the terminal application and gives instructions for investigating and correcting inconsistent data.

[1127] Step 11:

[1128] The emotion engine evaluates the user's emotional state. The emotion engine analyzes the user's camera footage and uses facial recognition technology to assess stress and concentration levels in real time.

[1129] Input: User's camera image

[1130] Output: Evaluated emotional state data

[1131] How it works: The emotion engine captures camera footage and uses facial recognition algorithms to assess stress levels and concentration.

[1132] Step 12:

[1133] The emotion engine makes suggestions to adjust the process. Based on the evaluated emotional state data, the system makes suggestions to adjust the process. For example, if stress levels are high, it will make suggestions to simplify the confirmation process, and if concentration levels are high, it will encourage detailed confirmation.

[1134] Input: Emotional state data assessed in step 11

[1135] Output: Suggested process adjustments

[1136] What it does: The emotion engine analyzes the evaluated emotional state data and presents the user with options for adjusting the process as needed.

[1137] (Application example 2)

[1138] 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."

[1139] Modern logistics centers process a huge number of purchase specifications and delivery notes every day, requiring effective collection and evaluation of supporting documents. However, existing systems have low efficiency in collecting and evaluating supporting documents, and do not adequately manage employee stress or adjust processes. Therefore, in addition to improving work efficiency, flexible process adjustments based on employees' emotional states are necessary.

[1140] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring a list of evidence, means for randomly selecting evidence from the acquired list of evidence, means for generating and transmitting a request to collect the selected evidence, means for saving the collected evidence and checking its consistency, means for displaying the evidence data so that the user can confirm and approve it, and means for recognizing the emotional state and adjusting the process. This enables efficient collection and evaluation of evidence, and also enables flexibly adjusting the business process based on the user's emotional state.

[1141] The "means for obtaining a list of supporting documents" refers to a device or program that automatically obtains a list of supporting documents to be audited from an ERP system or database.

[1142] The "means for randomly selecting a voucher from the list of acquired vouchers" refers to a device or program that randomly selects a voucher from the list of acquired vouchers using a specific algorithm.

[1143] "Means for generating and sending requests to collect selected evidence" refers to a device or program that generates requests to collect selected evidence and sends them to the relevant departments or systems.

[1144] The "means for storing collected supporting documents and checking their consistency" refers to a device or program that stores collected supporting document data in an internal database and checks its consistency.

[1145] The "means for displaying supporting data so that the user can confirm and approve it" refers to a device or program that displays supporting data so that the user can confirm and approve it through a terminal.

[1146] The "means for recognizing emotional states and adjusting processes" refers to a device or program that recognizes the emotional state of a user in real time and dynamically adjusts the system processes based on that state.

[1147] The "means for evaluating supporting data based on a preset evaluation criterion" refers to a device or program for automatically evaluating supporting data based on a preset evaluation criterion.

[1148] The "means for generating evaluation results and creating an evaluation result report" refers to a device or program that generates evaluation results and creates an evaluation result report based on the results.

[1149] "Means for notifying and displaying the evaluation result report so that the user can view and confirm it" refers to a device or program that notifies the user of the evaluation result report so that the user can view and confirm it.

[1150] The "means for suggesting process adjustments based on the emotional state of the user" refers to a device or program that senses the emotional state of the user and suggests optimal process adjustments based on that state.

[1151] The "means by which a user can send an additional collection request" refers to a device or program that allows a user to send an additional document collection request as needed.

[1152] "Means for users to determine actions based on evaluation results and notify relevant departments" refers to a device or program that allows users to check evaluation results, specify necessary actions based on the results, and notify relevant departments.

[1153] The "means for monitoring the emotional state of a user using an emotion engine" is a device or program that uses an emotion engine to monitor the emotional state of a user in real time.

[1154] The present invention is a system aimed at improving the efficiency of audit responses at logistics centers. The present invention has the following configuration. First, as a means of obtaining a list of evidence, the server automatically obtains a list of evidence for audit targets from an ERP system or database. This list of evidence is saved in an internal database.

[1155] Next, the server randomly selects evidence from the obtained evidence list using a specific algorithm. To collect this selected evidence, the server generates a request and sends it to the relevant department or system (e.g., each department's terminal). The terminal receives this request, extracts the specified evidence from the database, and sends it to the server. The server stores the collected evidence in its internal database and checks its consistency.

[1156] The collected supporting data is displayed on the terminal for the user to review and approve. In addition, the server automatically evaluates the supporting data based on pre-set evaluation criteria and generates an evaluation result. This evaluation result is created as an evaluation result report and notified to the user's terminal. The user can check the evaluation result, determine actions as necessary, and notify relevant departments.

[1157] A distinctive feature of the present invention is the integration of an emotion engine. The emotion engine recognizes the user's emotional state in real time and provides the ability to adjust the process based on that data. For example, if the user is feeling stressed, the emotion engine can make automatic suggestions to simplify the review process. Also, if the user is highly focused, the emotion engine can prompt the user to review more detailed data.

[1158] For example, logistics center employees wearing smart glasses use the system to review and evaluate purchase order data automatically extracted from the ERP system. The employee's emotional state is monitored by the emotion engine, and the process is dynamically adjusted as needed.

[1159] An example of a prompt sentence is as follows:

[1160] Develop a smart glasses application that retrieves target purchase order data from an ERP system and monitors it in real time using an emotion engine. We provide code that enables automatic evaluation based on evaluation criteria and process adjustments based on employees' emotional state.

[1161] By using this prompt, it is possible to convey exactly what kind of application is required along with a concrete image.

[1162] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1163] Step 1:

[1164] The server automatically retrieves the list of auditable evidence from the ERP system or database. Specifically, the server makes an API call to the ERP system to retrieve a list of purchase statements for a specified period. This list is saved in the server's internal database. The input is instructions from the ERP system, and the output is the retrieved list of evidence.

[1165] Step 2:

[1166] The server randomly selects evidence from the acquired evidence list using a specific algorithm. Specifically, the server executes a random sampling algorithm from the acquired list to select, for example, 50 evidences. The input is the acquired evidence list, and the output is the randomly selected evidence list.

[1167] Step 3:

[1168] The server generates a request to collect the selected evidence and sends it to the relevant departments and systems. Specifically, the server sends a request to each department's terminal, clearly indicating what evidence needs to be collected. The input is a list of randomly selected evidence, and the output is the sent request.

[1169] Step 4:

[1170] The terminal receives a request from the server, extracts the specified evidence from the database, and sends it to the server. The terminal executes a database query, extracts the specified evidence, and sends it to the server. The input is the collection request from the server, and the output is the extracted evidence data.

[1171] Step 5:

[1172] The server stores the collected evidence in an internal database and checks its integrity. Specifically, the server passes the received evidence data through a verification algorithm to check the consistency and completeness of the data. The input is the extracted evidence data, and the output is the evidence data whose integrity has been confirmed.

[1173] Step 6:

[1174] The server displays the collected supporting data on the terminal so that the user can confirm and approve it. The terminal displays the supporting data through a user interface, and the user confirms and approves it. The input is the confirmation request and supporting data, and the output is feedback of approval or rejection by the user.

[1175] Step 7:

[1176] The server automatically evaluates the supporting data based on pre-defined evaluation criteria. The evaluation algorithm examines the supporting data and determines whether it meets the pre-defined criteria. The input is the supporting data and evaluation criteria, and the output is the evaluation result.

[1177] Step 8:

[1178] The server generates evaluation results and creates an evaluation result report. Specifically, the server aggregates the evaluation results and generates a report in a format that is easy for users to understand. The input is the evaluation results, and the output is the evaluation result report.

[1179] Step 9:

[1180] The server notifies the user of the evaluation result report and prompts them to confirm it. The user checks the report on their device and determines the necessary actions. The input is the evaluation result report, and the output is the user's confirmation and feedback.

[1181] Step 10:

[1182] After the user specifies an action, the server notifies the relevant departments. Specifically, the server generates notification content and sends it to the relevant department's terminal. The input is the user's instruction to take an action, and the output is a notification to the relevant department.

[1183] Step 11:

[1184] The emotion engine recognizes the user's emotional state in real time and adjusts the process appropriately. The emotion engine monitors the user's stress and concentration level and generates appropriate suggestions. The input is the user's real-time emotional data, and the output is adjustment suggestions and their implementation.

[1185] Step 12:

[1186] If the user accepts the emotion engine's suggestion, the server dynamically adjusts the process based on the suggestion. The input is the emotion engine's suggestion, and the output is the adjusted process.

[1187] 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.

[1188] 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.

[1189] 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.

[1190] [Fourth embodiment]

[1191] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1192] 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.

[1193] 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).

[1194] 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.

[1195] 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.

[1196] 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).

[1197] 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.

[1198] 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.

[1199] 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.

[1200] 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.

[1201] 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.

[1202] 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.

[1203] 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."

[1204] Automatic document collection tool

[1205] The present invention is a system for improving the efficiency of audit responses, and includes an automatic document collection tool and an evaluation automation tool. First, the automatic document collection tool will be described.

[1206] The server first obtains a list of documents to be audited. This list is collected from an ERP system or database. Next, the server generates a random sample from the obtained list of documents. This random sample generation algorithm randomly selects any document.

[1207] The server generates a request to collect the selected evidence and sends it to the relevant department or system. This request specifies the type and quantity of evidence and includes a collection request. The terminal receives this request, collects the evidence in real time, and sends it back to the server.

[1208] The server stores the received supporting data in an internal database and checks its consistency. This consistency check identifies missing or abnormal data. The user uses the terminal to review and approve the collected supporting data. If additional collection is required, the user can send an additional collection request through the terminal.

[1209] Specific examples

[1210] For example, a server retrieves a list of supporting documents for a monthly report from an ERP system. This list contains purchase statements for a given month. The server uses a random algorithm to select 50 purchasing statements and sends requests to each department to collect these supporting documents.

[1211] The terminal receives this request, extracts the specified purchase details from the database, and sends them to the server. The server saves the received supporting data and performs a consistency check. The user then checks and approves the data on the terminal.

[1212] Evaluation automation tool

[1213] Next, we will explain the evaluation automation tool. The server receives supporting data and starts the evaluation process. The server executes an automatic evaluation algorithm based on pre-set evaluation criteria. These evaluation criteria include various criteria for internal control evaluation.

[1214] The server generates the results of the evaluation process and creates an evaluation result report, which is stored in a database for the user to review. The server then sends a notification of the evaluation result to the terminal, prompting the user to review the evaluation result.

[1215] Users can check the evaluation results report through their terminal and determine the necessary actions. For example, if an abnormality is discovered, the user can issue instructions to the relevant department for investigation or correction.

[1216] Specific examples

[1217] The server retrieves the previously collected purchase statement data and evaluates each statement for consistency and validity based on the evaluation criteria set. Evaluation algorithms perform this and identify outliers and inconsistent data.

[1218] A report of the evaluation results is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and instruct the purchasing department to conduct further investigations into any inconsistencies in the data.

[1219] In this way, the present invention realizes automatic collection of supporting documents and automated evaluation, thereby significantly reducing the amount of work required to respond to audits and improving efficiency.

[1220] The processing flow will be explained below.

[1221] Automatic document collection tool

[1222] Step 1:

[1223] The server automatically retrieves the list of evidence to be audited from the ERP system or database, and the retrieved list of evidence is saved in the internal database.

[1224] Step 2:

[1225] The server executes an algorithm to randomly select a particular document from the obtained document list. A random sample is selected.

[1226] Step 3:

[1227] The server generates a request to collect the selected evidence, which is then sent to the relevant department or system.

[1228] Step 4:

[1229] The terminal receives the request and extracts the specified evidence from the associated database, and the extracted evidence data is sent from the terminal to the server.

[1230] Step 5:

[1231] The server stores the received supporting data in an internal database and checks the integrity of the stored data.

[1232] Step 6:

[1233] The user checks the collected evidence data through the terminal and approves the checked data.

[1234] Step 7:

[1235] If the user needs to collect additional evidence, the terminal sends an additional collection request to the server.

[1236] Evaluation automation tool

[1237] Step 1:

[1238] The server retrieves the supporting document data received from the automated supporting document collection tool from the database, and rechecks the consistency of the retrieved data.

[1239] Step 2:

[1240] The server evaluates the supporting data based on the set evaluation criteria, and executes the evaluation algorithm to evaluate the effectiveness of internal controls.

[1241] Step 3:

[1242] The server generates the evaluation results and creates an evaluation result report, which is stored in an internal database.

[1243] Step 4:

[1244] The server sends a notification of the evaluation result to the terminal, which then displays the evaluation result to the user.

[1245] Step 5:

[1246] The user checks the evaluation result report through the terminal, determines the necessary actions, and notifies the relevant departments of correction instructions and investigation requests.

[1247] Through these steps, the automated collection and evaluation of supporting documents is achieved, reducing the amount of work required and improving efficiency in responding to audits.

[1248] Example 1

[1249] 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."

[1250] In conventional audit response systems, the process of collecting and evaluating supporting documents is manual, requiring time and effort. Furthermore, manual collection and evaluation is prone to human error, and data integrity cannot be guaranteed. Furthermore, there are inefficiencies in the process of reviewing and approving the evaluation results, creating a need for greater efficiency in the entire audit process.

[1251] 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.

[1252] In this invention, the server includes a means for acquiring a list of supporting documents from a data management system, a means for randomly selecting supporting documents from the acquired list using a random algorithm, and a means for generating a request to collect the selected supporting documents and sending it to each department via a network. This automates the process of collecting supporting documents, eliminates manual errors, and enables efficient audit response. The server also stores the collected supporting document data in a database and has a means for checking its consistency, ensuring the consistency and reliability of the data. Furthermore, the server includes a means for displaying the supporting document data so that users can confirm and approve it using a terminal, thereby realizing rapid confirmation of evaluation results and the approval process.

[1253] A "list of supporting documents" is a list that summarizes the types and details of supporting documents required for audit responses and business evaluations.

[1254] A "data management system" is an information system that manages and stores business data in a company or organization, and allows access and retrieval for specific purposes.

[1255] A "random algorithm" is a computational method for randomly drawing samples from a data set, used to ensure a fair and unbiased selection.

[1256] A "network" is an information transmission mechanism that connects multiple computers and terminals so that they can communicate with each other.

[1257] A "request" is a command to request specific data or an operation, and is used to obtain or send information between systems.

[1258] A "database" is a structured collection of data that can efficiently manage and store large amounts of data and can be quickly accessed and searched when needed.

[1259] "Integrity" is a property that ensures that data is consistent and free of errors and omissions, and is important for ensuring the accuracy and reliability of data.

[1260] An "automated evaluation algorithm" is a calculation method that allows a program to automatically analyze and evaluate collected data based on pre-set evaluation criteria.

[1261] "Evaluation criteria" are a set of rules and indicators that are used as standards when evaluating and judging data, and they define the appropriateness and problems of the subject of evaluation.

[1262] An "evaluation result report" is a document or data file that summarizes the results of the evaluation process, and indicates the status of the subject of evaluation and whether or not there are any abnormalities.

[1263] A "terminal" refers to a device such as a computer or mobile device that can be directly operated by a user, and is used to input data into the system and display results.

[1264] "User" refers to a person or role who operates the system to perform actual work or audits, and is the entity that uses the various functions of the system.

[1265] "Notification" means a message or signal that informs a user of particular information or results.

[1266] "Verification" refers to the act of checking the content of data or information to confirm whether it is accurate.

[1267] "Approval" refers to the act of acknowledging the correctness and validity of confirmed data or information.

[1268] "Action" refers to specific measures or steps taken based on the evaluation results, and means actions taken to solve problems or make improvements.

[1269] Automatic document collection tool

[1270] Server Processing

[1271] The server first obtains a list of evidence to be audited from the data management system or internal database. This process involves extracting the necessary data using, for example, an SQL query. Based on the obtained list of evidence, a random algorithm is used to randomly select evidence, using an algorithm such as Python's random.sample function. During this process, a request to collect the selected evidence is generated and sent to each department via the network. This request is often sent using an HTTP request.

[1272] Terminal handling

[1273] The terminal receives a request for collecting supporting documents from the server, extracts the specified supporting documents from the database, and sends them to the server. The terminal also returns the extracted data to the server as an HTTP response. During this process, the necessary database queries are executed to ensure that the supporting document data is accurately sent to the server.

[1274] User Action

[1275] Users can use their devices to check and approve the supporting data stored on the server. They can view and manipulate the data through a GUI, and can send requests for additional supporting data to the server as needed. This increases the accuracy and reliability of audits.

[1276] Specific examples

[1277] For example, the server retrieves a list of supporting documents required for monthly reports from the ERP system. Based on the retrieved list, a random sample generation algorithm is used to select 50 purchasing details. A request is generated for each selected supporting document and a request to collect the supporting documents is sent to each department. The terminal receives this request, extracts the specified purchasing details from the database, and sends them to the server. The server stores the received supporting document data and checks its consistency. The user uses the terminal to check and approve the data. If there are any problems, the user can send additional collection requests.

[1278] Prompt Sentence Examples

[1279] Based on the document list obtained from the ERP system, 50 purchasing details are randomly selected and a document collection request is sent to each department. The terminal then retrieves the document from the database and sends it to the server. The server saves the data and checks its integrity. The user then uses the terminal to check and approve the document data.

[1280] Evaluation automation tool

[1281] Server Processing

[1282] The server retrieves the collected supporting data from the database and starts the evaluation process. This process includes an automated evaluation algorithm based on pre-defined evaluation criteria, including the consistency of internal control standards and business processes. Evaluation results are generated and an evaluation result report is created based on the results. This report is saved in the database and notified to the user.

[1283] User Action

[1284] Users can check the evaluation result report through their terminal and decide on the necessary actions. If an abnormality is found in the evaluation results, users can send instructions for investigation or correction to the relevant department through their terminal. This allows for quick confirmation and response of audit results.

[1285] Specific examples

[1286] The server evaluates the collected purchasing specification data based on the evaluation criteria and identifies outliers and inconsistent data. An evaluation result report is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and issue instructions to the purchasing department for further investigation or correction of inconsistent data.

[1287] Prompt Sentence Examples

[1288] The collected purchasing specification data is evaluated based on evaluation criteria to identify outliers and inconsistencies. An evaluation result report is created and notified to the user. The user can check the evaluation results via their terminal, and if an abnormality is found, they can issue instructions to the purchasing department for investigation or correction.

[1289] In this way, the present invention realizes automatic collection of supporting documents and automated evaluation, thereby reducing the number of steps required for audits and improving efficiency.

[1290] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1291] Automatic document collection tool

[1292] Server Processing Steps

[1293] Step 1:

[1294] The server retrieves the list of supporting documents to be audited from the data management system. The input is raw data retrieved from the ERP system or internal database, and the necessary data is extracted using SQL queries. The output is a list of supporting documents required for the audit.

[1295] Specifically, the server executes a query such as "SELECT FROM evidence_list WHERE month='2023-10';" to retrieve the target evidence list from the database.

[1296] Step 2:

[1297] The server randomly selects a voucher from the obtained list of vouchers using a random algorithm. The input is the list of vouchers obtained in step 1, and it processes the algorithm to randomly extract data. The output is a sample list of randomly selected vouchers.

[1298] Specifically, for example, 50 supporting documents are selected using Python's random.sample function.

[1299] Step 3:

[1300] The server generates a request to collect the selected evidence and sends it to each department via the network. The input is the list of evidence selected in step 2, and the output is the collection request sent to each department.

[1301] Specifically, an HTTP request is generated and sent to the URL of each department.

[1302] Step 4:

[1303] The terminal receives the collection request sent from the server and extracts the specified evidence from the database. The input is the collection request from the server, and the output is the extracted evidence data.

[1304] Specifically, the terminal executes the query "SELECT FROM evidences WHERE id=?" and sends the extracted results to the server.

[1305] Step 5:

[1306] The server stores the received supporting data in an internal database and checks its consistency. The input is the supporting data sent from the terminal, and the output is the consistency check result and the stored data.

[1307] Specifically, the system stores supporting data in a database and runs a consistency check algorithm, detecting missing or anomalous data.

[1308] Step 6:

[1309] The user uses a terminal to check the evidence data stored on the server and give approval. The input is the evidence data stored on the server, and the output is the user's confirmation and approval results.

[1310] Specifically, the GUI screen displays the data, allows the user to review and approve it, and allows the user to submit additional collection requests if necessary.

[1311] Evaluation automation tool

[1312] Server Processing Steps

[1313] Step 1:

[1314] The server retrieves the collected supporting data from the database and starts the evaluation process. The input is the collected supporting data and the output is the data ready to run the evaluation process.

[1315] Specifically, a database query is executed to extract the data to be evaluated.

[1316] Step 2:

[1317] The server executes an automatic evaluation algorithm based on pre-defined evaluation criteria. The input is the supporting data obtained in step 1, and the output is the evaluation result.

[1318] Specifically, it runs evaluation algorithms implemented in languages ​​such as Python to assess the integrity and validity of the data.

[1319] Step 3:

[1320] The server creates an evaluation result report based on the results of the evaluation process. The input is the evaluation result, and the output is the evaluation result report.

[1321] Specifically, a report is generated based on the evaluation results and stored in a database.

[1322] Step 4:

[1323] The server notifies the user of the evaluation result report and allows the user to check it on the terminal. The input is the evaluation result report, and the output is a notification message to the user.

[1324] Specifically, an HTTP request for notification is generated and sent to the user's terminal.

[1325] User processing steps

[1326] Step 5:

[1327] The user checks the evaluation result report through the terminal and decides on the necessary action. The input is the evaluation result report, and the output is the user's action instructions.

[1328] Specifically, the report is viewed using a GUI that displays the evaluation results, and if any abnormalities or inconsistencies are found, instructions are issued to the purchasing department or other department to investigate or correct the issues.

[1329] As described above, the processing steps of the present invention have been explained together with specific operations. This clarifies the process of automatic collection of supporting documents and automated evaluation, and is expected to enable efficient audit response.

[1330] (Application example 1)

[1331] 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."

[1332] Logistics centers are required to manage a huge number of supporting documents (receipts, shipping certificates, inventory lists, etc.), and collecting and evaluating these documents takes a lot of time and effort. In particular, consistency checks and anomaly detection for these documents are often done manually, so there is a need for efficiency improvements. There is also a need for a system that can reduce the workload of on-site workers and quickly collect and evaluate supporting documents.

[1333] 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.

[1334] In this invention, the server includes means for acquiring a list of evidence, means for randomly selecting evidence from the acquired list of evidence, means for generating and sending a request to collect the selected evidence, means for saving the collected evidence and checking its consistency, means for displaying the evidence data so that the user can confirm and approve it, means for creating a request for evidence collection and sending it to the relevant department, and means for checking the consistency and evaluating the acquired evidence data. This makes it possible to efficiently collect evidence at a logistics center and automatically evaluate it.

[1335] A "list of supporting documents" is a list of supporting documents required for audits and business processes, and is obtained from an ERP system or database.

[1336] "Randomly selecting evidence" means randomly selecting evidence from a list of evidence based on a pre-set algorithm.

[1337] "Generate and send a request" refers to automatically creating a request to collect the selected evidence and sending it to the relevant department or system.

[1338] "Consistency checking" is the process of verifying that the collected supporting data is appropriate and free of inconsistencies or anomalies.

[1339] "Evidence data" refers to the specific information and content of each evidence obtained and collected.

[1340] "Evaluating supporting data based on evaluation criteria" refers to the process of automatically evaluating the accuracy and suitability of collected supporting data according to pre-set criteria and conditions.

[1341] An "evaluation result report" is a report summarizing the results of the evaluation process of supporting data.

[1342] "Instructing investigation and correction" means that if any inconsistencies or abnormalities are discovered based on the evaluation results, the relevant department will be asked to carry out the necessary investigation and correction work.

[1343] "On-site workers collect and upload supporting documents using smartphones" refers to the process in which on-site workers at the logistics center collect supporting documents using smartphones and upload them to a server via a dedicated application.

[1344] "Login and user authentication" refers to entering the user authentication information required to access the system and taking appropriate security measures.

[1345] "Generating prompts using a generative AI model and providing automated assistance" refers to an assistance function that uses AI technology to create prompts and simplify user operations.

[1346] As an embodiment of the present invention, the specific configuration and procedures of a document management system used in a logistics center are described below. This system has functions such as obtaining a document list, randomly selecting documents, generating and sending document collection requests, checking the integrity of documents, evaluating data based on evaluation criteria, generating and notifying result reports, and even issuing investigation and correction instructions.

[1347] First, the server retrieves the list of evidence from the ERP system or database. From the retrieved list of evidence, the server randomly selects evidence, generates a request to collect it, and sends it to the relevant department. This process is implemented using a Python program and the "requests" module. For example, the list of evidence can be obtained through an API endpoint, and evidence can be randomly selected using the "random" module.

[1348] The server then sends requests to each department to collect the selected evidence, and field workers use their smartphones to collect the evidence. The collected evidence data is then uploaded from the smartphone to the server. The smartphone application plays an important role in this process, making it possible to collect and upload evidence in real time. It also has security features such as login and user authentication, and appropriate access control is performed by entering authentication information.

[1349] The collected supporting data is stored on a server and a consistency check is performed. This consistency check, which includes checking the correct date format and numeric range, is implemented using the Python datetime module, for example. Once the consistency of the supporting data is confirmed, it is evaluated based on pre-set evaluation criteria. The evaluation results are generated as an evaluation result report and notified to the user.

[1350] After reviewing the evaluation results, users can instruct the relevant department to investigate and correct any abnormal supporting documentation data. Generative AI models can also be used to automatically create prompts, simplifying user operations. For example, a prompt could be generated such as, "Please explain the system for automatically collecting and evaluating supporting documentation at a logistics center. Please provide a detailed explanation of the integrity check and evaluation process for randomly selected supporting documentation."

[1351] In this way, the present invention can improve the efficiency of document management at logistics centers and reduce the workload. It also enables real-time collection and evaluation of documented evidence, enabling immediate problem detection and countermeasures.

[1352] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1353] Step 1:

[1354] The server retrieves the document list from the ERP system or database. In this step, it accesses the API endpoint using the Python requests module to retrieve the document list. The input is the API endpoint URL, and the output is the document list data in JSON format.

[1355] Step 2:

[1356] The server randomly selects evidence from the obtained evidence list. In this step, the Python random module is used to randomly select a specified number of evidence from the evidence list. The input is the evidence list data, and the output is the selected evidence data.

[1357] Step 3:

[1358] The server generates and sends a request to collect the selected evidence. The request specifies the type and quantity of evidence and is sent to the relevant departments and parties. The input is the selected evidence data, and the output is a request message sent to each department.

[1359] Step 4:

[1360] The terminal receives a request from the server, and the on-site worker collects the evidence using a smartphone. The worker takes a photo of the evidence with a camera and uploads it along with location and time information. The input is the request message, and the output is the evidence image data and accompanying information.

[1361] Step 5:

[1362] The server stores the supporting data uploaded by field workers and checks its consistency. It uses the Python datetime module to check the correct date format and numeric range. The input is the supporting data image data and accompanying information, and the output is the consistency check results.

[1363] Step 6:

[1364] The server evaluates the integrity-checked supporting data based on pre-defined evaluation criteria, generates evaluation results, and creates a result report. It runs an automated evaluation algorithm based on the evaluation criteria to identify outliers and inconsistent data. The input is the integrity-checked supporting data, and the output is an evaluation result report.

[1365] Step 7:

[1366] The server notifies the user of the evaluation result report, allowing the user to check the results. The user can review the evaluation results and determine the necessary actions. The input is the evaluation result report, and the output is notification and display on the user screen.

[1367] Step 8:

[1368] If the user finds any abnormal supporting data, they can instruct the relevant department to investigate and correct it. A generative AI model is used to automatically create prompts, simplifying user operations. The input is the evaluation results and the prompts generated by the generative AI model, and the output is instructions to the relevant department to investigate and correct the abnormality.

[1369] In this way, by linking each processing step, automatic collection and evaluation of supporting documents at the logistics center is realized.

[1370] 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.

[1371] Overall overview

[1372] This invention is a system for streamlining audit response, which includes an automatic document collection tool and an evaluation automation tool, and also combines an emotion engine that recognizes user emotions and adjusts various system processes.

[1373] Automatic document collection tool

[1374] The server first automatically retrieves the list of documents to be audited from the ERP system or database. This list is stored in an internal database. The server then runs an algorithm to randomly select specific documents from the list of documents to generate a random sample.

[1375] The server generates a request to collect the selected evidence and sends it to the relevant department or system. The terminal receives the request, extracts the specified evidence from the relevant database, and sends it to the server. The server stores the received evidence data in an internal database and checks its consistency. The user uses the terminal to check and approve the collected evidence data. If additional collection is required, the user can send an additional collection request through the terminal.

[1376] Specific examples

[1377] For example, the server retrieves a list of supporting documents required for a monthly report from the ERP system. This list includes purchasing details for a specified month. The server selects 50 purchasing details using a random algorithm and sends a request to each department to collect these supporting documents. The terminal receives this request, extracts the specified purchasing details from the database, and sends them to the server. The server saves the received supporting document data and performs a consistency check. The user checks and approves the data on the terminal.

[1378] Evaluation automation tool

[1379] Next, we will explain the evaluation automation tool. The server receives supporting data and starts the evaluation process. Based on pre-set evaluation criteria, the server executes an automatic evaluation algorithm. These evaluation criteria include various standards for internal control evaluation. The server generates the results of the evaluation process and creates an evaluation result report. This report is saved in a database so that the user can check it. The server sends a notification of the evaluation result to the terminal, prompting the user to check the evaluation result. The user checks the evaluation result report through the terminal and determines the necessary actions. For example, if an abnormality is discovered, the user can issue instructions for investigation or correction to the relevant department.

[1380] Specific examples

[1381] The server retrieves the previously collected purchasing statement data and evaluates the consistency and validity of each statement based on the evaluation criteria that have been set. The evaluation algorithm executes this and identifies outliers and inconsistent data. A report of the evaluation results is generated and sent from the server to the terminal. The user can check the evaluation results through the terminal and instruct the purchasing department to conduct further investigations on inconsistent data.

[1382] Emotion engine integration

[1383] The emotion engine recognizes the user's emotional state and adjusts various system processes. The emotion engine evaluates the user's stress level and concentration level in real time when verifying and approving supporting documents. This emotional data is reflected in the configuration of the supporting document verification process, additional collection requests, and evaluation process.

[1384] Specific examples

[1385] For example, if a user feels stressed while reviewing supporting data, the emotion engine can detect this and make automatic suggestions to simplify the review process. Also, if the user is highly focused, the engine can prompt the user to review more detailed data. Furthermore, the engine can dynamically adjust evaluation criteria based on emotion data and suggest actions based on the evaluation results. The emotion engine can recommend users with high stress levels to send additional collection requests.

[1386] Through these steps, the system will enable the automatic collection of supporting documents, automated evaluation, and process adjustments based on user feedback, resulting in a significant reduction in audit response time and increased efficiency.

[1387] The processing flow will be explained below.

[1388] Automatic document collection tool

[1389] Step 1:

[1390] The server automatically retrieves the list of evidence to be audited from the ERP system or database, and the retrieved list of evidence is saved in the internal database.

[1391] Step 2:

[1392] The server executes an algorithm to randomly select a particular document from the obtained document list. A random sample is selected.

[1393] Step 3:

[1394] The server generates a request to collect the selected evidence and sends the request to the relevant department or system.

[1395] Step 4:

[1396] The terminal receives the request and extracts the specified evidence from the associated database, and the extracted evidence data is sent from the terminal to the server.

[1397] Step 5:

[1398] The server stores the received supporting data in an internal database and checks the integrity of the stored data.

[1399] Step 6:

[1400] The user checks the collected evidence data through the terminal and approves the checked data.

[1401] Step 7:

[1402] If the user needs to collect additional evidence, the terminal sends an additional collection request to the server.

[1403] Evaluation automation tool

[1404] Step 1:

[1405] The server retrieves the supporting document data received from the automated supporting document collection tool from the database, and rechecks the consistency of the retrieved data.

[1406] Step 2:

[1407] The server evaluates the supporting data based on the set evaluation criteria, and executes the evaluation algorithm to evaluate the effectiveness of internal controls.

[1408] Step 3:

[1409] The server generates the evaluation results and creates an evaluation result report, which is stored in an internal database.

[1410] Step 4:

[1411] The server sends a notification of the evaluation result to the terminal, which then displays the evaluation result to the user.

[1412] Step 5:

[1413] The user checks the evaluation result report through the terminal, determines the necessary actions, and notifies the relevant departments of correction instructions and investigation requests.

[1414] Emotion engine integration

[1415] Step 1:

[1416] The emotion engine recognizes the user's emotional state. The emotion engine analyzes the user's facial expressions, tone of voice, typing speed, etc. to collect emotional data in real time.

[1417] Step 2:

[1418] The emotion engine analyzes the collected emotional data to determine the user's stress level and concentration, which is reflected in the verification and approval process of supporting data.

[1419] Step 3:

[1420] When a user checks the evidence data, the emotion engine adjusts the initial settings according to the user's emotional state. For example, if the user is feeling stressed, the emotion engine provides an assistance function to simplify the checking process.

[1421] Step 4:

[1422] The server dynamically adjusts the evaluation criteria. The evaluation criteria are flexibly changed based on the emotional data acquired by the emotion engine. When the user is highly focused, a stricter evaluation is performed.

[1423] Step 5:

[1424] The server generates the evaluation report, and the emotion engine adjusts the report display based on the user's emotional state: if stress is high, the report is summarized.

[1425] Step 6:

[1426] The emotion engine suggests additional collection requests and actions based on the user's emotional state. For example, if the user is impatient, the emotion engine suggests sequenced next steps.

[1427] These steps will enable the automatic collection of supporting documents, the automation of assessment, and the adjustment of the process based on user feedback, resulting in a significant reduction in audit response time and increased efficiency. This will also reduce user stress and enable more accurate assessments.

[1428] Example 2

[1429] 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."

[1430] In conventional audit response systems, the collection and evaluation of supporting documents is often done manually, resulting in a significant amount of labor and time. It has also been pointed out that the evaluation of supporting documents is prone to human error and subjective judgment, resulting in a lack of reliability. Another problem is that the user's emotions and state can affect system operation, resulting in a decrease in the efficiency of audit work. The present invention aims to solve these problems and provide a system that streamlines audit response.

[1431] 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.

[1432] In this invention, the server includes a means for acquiring a list of information, a means for randomly selecting information from the acquired list of information, and a means for generating and transmitting a request to collect the selected information. This enables the automatic collection of evidence. The server also includes a means for storing the collected information and checking its consistency, a means for displaying the information data so that the user can confirm and approve it, a means for evaluating the user's emotional state, and a means for making suggestions to adjust the process based on the evaluated emotional state. This ensures the reliability of the information and enables adaptive operation according to the user's emotions. The server also includes a means for evaluating the information data based on pre-set evaluation criteria, a means for generating evaluation results and creating an evaluation result report, and a means for notifying and displaying the evaluation result report so that the user can view and confirm it. This enables an automatic evaluation process, improving the efficiency and reliability of evaluation work.

[1433] "Information list" refers to a list of supporting documents and related data to be audited, and is obtained from an ERP system or database.

[1434] "Selecting information" refers to the operation of selecting specific information from the list of acquired information randomly or based on arbitrary criteria.

[1435] "Generate and send a request" refers to the act of creating a request to collect selected information and sending it to the relevant department or system.

[1436] "Collected information" refers to evidence and data obtained in response to a server request.

[1437] "Checking consistency" refers to the act of verifying whether the collected information is accurate and consistent.

[1438] "Information data" refers to supporting evidence and related data collected for the audit.

[1439] "User" refers to the person who operates the system and reviews and approves the audit process.

[1440] "Emotional state" refers to the psychological state of the user when operating the system, including, for example, stress level and concentration level.

[1441] "Suggestions to adjust processes" refers to suggestions to change or optimize various system operations or processes depending on the user's emotional state.

[1442] "Evaluation criteria" refers to the pre-established standards and rules for conducting evaluations in internal control and audits.

[1443] "Evaluation result" refers to the result calculated by an automated evaluation algorithm based on the evaluation criteria.

[1444] "Evaluation results report" refers to a written or digital report summarizing the evaluation results.

[1445] "Notification" refers to the operation of informing the user about the evaluation result report generated by the system.

[1446] "Display" refers to the operation of showing the collected information and evaluation results on a screen or the like so that the user can check them.

[1447] MODE FOR CARRYING OUT THE INVENTION

[1448] The present invention is a system for improving the efficiency of audit responses, and is implemented in a form that combines an automatic document collection tool, an automatic evaluation tool, and an emotion engine.

[1449] Automatic document collection tool

[1450] First, the server automatically retrieves the list of documents to be audited from the ERP system or database (e.g., SAP, Oracle Database). This list of documents is stored in an internal database. The server then uses a Python random module to randomly select specific documents from the list of documents and generate a random sample.

[1451] The server generates a request to collect the selected evidence and sends it to the relevant departments and systems via email or API. The terminal receives the request and extracts the specified evidence from the relevant database. The extracted evidence data is sent to the server in CSV format. The server stores the received evidence data in an internal database and performs a consistency check (e.g., checksum value comparison). The user uses a dedicated terminal application to check and approve the collected evidence data. If additional collection is required, the user can send an additional collection request from the terminal.

[1452] Specific examples

[1453] The server obtains a list of supporting documents for monthly reports from SAP. This list contains purchasing details for the specified month. The server uses a random module to select 50 purchasing details. It uses the SMTP protocol to send a request to each department to collect these supporting documents. The terminal receives the request, executes an SQL query to extract the specified purchasing details from the Oracle Database, and sends them to the server. The server saves the received supporting document data and verifies its integrity using a checksum value. The user checks and approves the data on the terminal. If additional collection is required, the user sends a new collection request from the terminal.

[1454] Example prompt: "I need supporting monthly statements from SAP. Specifically, I need 50 random purchase statements."

[1455] Evaluation automation tool

[1456] The server retrieves the collected supporting data from the internal database and performs an evaluation based on pre-set evaluation criteria (e.g., internal control evaluation criteria). It evaluates the data using Python evaluation algorithms to check consistency and validity. It creates an evaluation result report and stores it in the internal database. The server sends a notification about the evaluation result to the terminal, prompting the user to confirm it. The user uses the terminal to check the evaluation result report and decides on necessary actions. If any abnormalities are found, the user instructs the relevant department to carry out further investigation or corrections.

[1457] Specific examples

[1458] The server retrieves the collected purchasing statement data and evaluates it based on internal control evaluation criteria. An outlier or inconsistent data is identified using a Python evaluation algorithm. A report of the evaluation results is created and a notification is sent to the user. The user can then check the report on their device and instruct the purchasing department to investigate any inconsistent data.

[1459] Example prompt: "Evaluate the consistency and validity of the collected purchasing statements based on the internal control evaluation criteria and generate a report of the evaluation results."

[1460] Emotion engine integration

[1461] The emotion engine evaluates the user's emotional state in real time when reviewing and approving supporting data. The emotion engine analyzes the user's camera footage and uses facial recognition technology to measure stress and concentration levels. Based on the emotional data, it makes suggestions to adjust the system process. If the stress level is high, the emotion engine will suggest simplifying the review process, while if the concentration level is high, it will prompt a more detailed review.

[1462] Specific examples

[1463] If a user is feeling stressed while reviewing supporting data, the emotion engine will detect this and offer options to simplify the review process, or if the user is highly focused, the emotion engine will prompt the user to review the data in more detail.

[1464] Example prompt: "Assess the stress level of users when reviewing supporting data and adjust the review process as needed."

[1465] This enables the automatic collection of supporting documents, automated evaluation, and process adjustment using an emotion engine, thereby achieving more efficient audit response.

[1466] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1467] Step 1:

[1468] The server obtains the evidence list. The server accesses the API endpoint of the ERP system and requests the latest evidence list. The obtained evidence list is saved in the server's internal database.

[1469] Input: Evidence data request from ERP system

[1470] Output: List of evidence stored in the internal database

[1471] Specific operation: The server sends an HTTP request to the ERP system's API, processes the list of evidence returned in JSON format, and inserts it into the PostgreSQL database.

[1472] Step 2:

[1473] The server randomly selects evidence from the evidence list. Using the Python random module, it randomly selects a specific number of evidence from the obtained evidence list. The selected evidence is then saved in the server's internal database again.

[1474] Input: List of evidence obtained in Step 1

[1475] Output: A randomly selected list of evidence

[1476] Specific operation: The server uses a Python script to randomly select 50 documents from the document list and save the list in an internal database.

[1477] Step 3:

[1478] The server generates and sends a request for collection of evidence. The server uses the SMTP protocol to send the request to the email address of the relevant department. It may also send the request directly to the department's system using an API.

[1479] Input: List of evidence selected in step 2

[1480] Output: Sending a request for evidence collection to the relevant department or system

[1481] Specific operation: The server uses the SMTP library to generate collection request emails and send them to each department. It also sends collection requests to other systems via the RESTful API.

[1482] Step 4:

[1483] The terminal extracts and sends the supporting evidence. The terminal receives the request and extracts the specified supporting evidence from the relevant database (e.g., Oracle Database). The extracted supporting evidence data is sent to the server in CSV format.

[1484] Input: Voucher collection request received from the server

[1485] Output: Send extracted supporting data to the server

[1486] Specific operation: The device receives a notification, the user executes an SQL query to extract supporting data, and uploads it to the server as a CSV file.

[1487] Step 5:

[1488] The server stores the supporting data and performs integrity checks. The server stores the received supporting data in an internal database and verifies the integrity of the data using a checksum algorithm.

[1489] Input: Evidence data sent in step 4

[1490] Output: Stored supporting data after integrity check

[1491] What happens: The server processes the uploaded CSV file, calculates the checksum to verify its integrity, and then inserts it into the PostgreSQL database.

[1492] Step 6:

[1493] The user checks and approves the supporting data. The user uses a dedicated terminal application to check and approve the collected supporting data. If additional collection is required, an additional collection request is sent from the terminal.

[1494] Input: Evidence data whose integrity was confirmed in Step 5

[1495] Output: Approved supporting data or additional collection requests

[1496] Specific operation: The user displays the supporting data in the terminal application, confirms it, and then clicks the approval button to send the approval status to the server. If additional collection is required, a new collection request is sent from the terminal.

[1497] Step 7:

[1498] The server retrieves the supporting data. The server executes SQL queries to retrieve the necessary supporting data from the internal database. The retrieved data is loaded into memory.

[1499] Input: Evidence data on the internal database

[1500] Output: Evidence data loaded into memory

[1501] Specific operation: The server periodically (for example, daily) executes SQL queries against the internal database and loads the necessary supporting data into memory.

[1502] Step 8:

[1503] The server performs the evaluation. The server evaluates the supporting data based on the evaluation criteria set. It executes a Python evaluation algorithm to automatically check the consistency and validity of the data.

[1504] Input: The supporting data loaded into memory in step 7

[1505] Output: Evaluation results

[1506] Specific operation: The server executes a Python script to evaluate the integrity and validity of the supporting data based on the specified evaluation criteria.

[1507] Step 9:

[1508] The server creates an evaluation result report and sends a notification. The server aggregates the results of the evaluation process and creates an evaluation result report in Excel format. This report is saved in an internal database and an email notification is sent to the user.

[1509] Input: Evaluation results generated in step 8

[1510] Output: Evaluation result report and notification to the user

[1511] Specific operation: The server compiles the evaluation results, generates a report based on an Excel template, saves the report in an internal database, and notifies the user via the SMTP protocol.

[1512] Step 10:

[1513] The user checks the evaluation results. The user opens the evaluation result report on the terminal and checks the contents. If an abnormality is found, the user sends an email to the relevant department instructing them to conduct further investigation.

[1514] Input: Notification of the evaluation result report sent in step 9

[1515] Output: Review the assessment report and any required actions

[1516] Specific operation: The user opens the evaluation result report in the terminal application and gives instructions for investigating and correcting inconsistent data.

[1517] Step 11:

[1518] The emotion engine evaluates the user's emotional state. The emotion engine analyzes the user's camera footage and uses facial recognition technology to assess stress and concentration levels in real time.

[1519] Input: User's camera image

[1520] Output: Evaluated emotional state data

[1521] How it works: The emotion engine captures camera footage and uses facial recognition algorithms to assess stress levels and concentration.

[1522] Step 12:

[1523] The emotion engine makes suggestions to adjust the process. Based on the evaluated emotional state data, the system makes suggestions to adjust the process. For example, if stress levels are high, it will make suggestions to simplify the confirmation process, and if concentration levels are high, it will encourage detailed confirmation.

[1524] Input: Emotional state data assessed in step 11

[1525] Output: Suggested process adjustments

[1526] What it does: The emotion engine analyzes the evaluated emotional state data and presents the user with options for adjusting the process as needed.

[1527] (Application example 2)

[1528] 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."

[1529] Modern logistics centers process a huge number of purchase specifications and delivery notes every day, requiring effective collection and evaluation of supporting documents. However, existing systems have low efficiency in collecting and evaluating supporting documents, and do not adequately manage employee stress or adjust processes. Therefore, in addition to improving work efficiency, flexible process adjustments based on employees' emotional states are necessary.

[1530] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring a list of evidence, means for randomly selecting evidence from the acquired list of evidence, means for generating and transmitting a request to collect the selected evidence, means for saving the collected evidence and checking its consistency, means for displaying the evidence data so that the user can confirm and approve it, and means for recognizing the emotional state and adjusting the process. This enables efficient collection and evaluation of evidence, and also enables flexibly adjusting the business process based on the user's emotional state.

[1531] The "means for obtaining a list of supporting documents" refers to a device or program that automatically obtains a list of supporting documents to be audited from an ERP system or database.

[1532] The "means for randomly selecting a voucher from the list of acquired vouchers" refers to a device or program that randomly selects a voucher from the list of acquired vouchers using a specific algorithm.

[1533] "Means for generating and sending requests to collect selected evidence" refers to a device or program that generates requests to collect selected evidence and sends them to the relevant departments or systems.

[1534] The "means for storing collected supporting documents and checking their consistency" refers to a device or program that stores collected supporting document data in an internal database and checks its consistency.

[1535] The "means for displaying supporting data so that the user can confirm and approve it" refers to a device or program that displays supporting data so that the user can confirm and approve it through a terminal.

[1536] The "means for recognizing emotional states and adjusting processes" refers to a device or program that recognizes the emotional state of a user in real time and dynamically adjusts the system processes based on that state.

[1537] The "means for evaluating supporting data based on a preset evaluation criterion" refers to a device or program for automatically evaluating supporting data based on a preset evaluation criterion.

[1538] The "means for generating evaluation results and creating an evaluation result report" refers to a device or program that generates evaluation results and creates an evaluation result report based on the results.

[1539] "Means for notifying and displaying the evaluation result report so that the user can view and confirm it" refers to a device or program that notifies the user of the evaluation result report so that the user can view and confirm it.

[1540] The "means for suggesting process adjustments based on the emotional state of the user" refers to a device or program that senses the emotional state of the user and suggests optimal process adjustments based on that state.

[1541] The "means by which a user can send an additional collection request" refers to a device or program that allows a user to send an additional document collection request as needed.

[1542] "Means for users to determine actions based on evaluation results and notify relevant departments" refers to a device or program that allows users to check evaluation results, specify necessary actions based on the results, and notify relevant departments.

[1543] The "means for monitoring the emotional state of a user using an emotion engine" is a device or program that uses an emotion engine to monitor the emotional state of a user in real time.

[1544] The present invention is a system aimed at improving the efficiency of audit responses at logistics centers. The present invention has the following configuration. First, as a means of obtaining a list of evidence, the server automatically obtains a list of evidence for audit targets from an ERP system or database. This list of evidence is saved in an internal database.

[1545] Next, the server randomly selects evidence from the obtained evidence list using a specific algorithm. To collect this selected evidence, the server generates a request and sends it to the relevant department or system (e.g., each department's terminal). The terminal receives this request, extracts the specified evidence from the database, and sends it to the server. The server stores the collected evidence in its internal database and checks its consistency.

[1546] The collected supporting data is displayed on the terminal for the user to review and approve. In addition, the server automatically evaluates the supporting data based on pre-set evaluation criteria and generates an evaluation result. This evaluation result is created as an evaluation result report and notified to the user's terminal. The user can check the evaluation result, determine actions as necessary, and notify relevant departments.

[1547] A distinctive feature of the present invention is the integration of an emotion engine. The emotion engine recognizes the user's emotional state in real time and provides the ability to adjust the process based on that data. For example, if the user is feeling stressed, the emotion engine can make automatic suggestions to simplify the review process. Also, if the user is highly focused, the emotion engine can prompt the user to review more detailed data.

[1548] For example, logistics center employees wearing smart glasses use the system to review and evaluate purchase order data automatically extracted from the ERP system. The employee's emotional state is monitored by the emotion engine, and the process is dynamically adjusted as needed.

[1549] An example of a prompt sentence is as follows:

[1550] Develop a smart glasses application that retrieves target purchase order data from an ERP system and monitors it in real time using an emotion engine. We provide code that enables automatic evaluation based on evaluation criteria and process adjustments based on employees' emotional state.

[1551] By using this prompt, it is possible to convey exactly what kind of application is required along with a concrete image.

[1552] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1553] Step 1:

[1554] The server automatically retrieves the list of auditable evidence from the ERP system or database. Specifically, the server makes an API call to the ERP system to retrieve a list of purchase statements for a specified period. This list is saved in the server's internal database. The input is instructions from the ERP system, and the output is the retrieved list of evidence.

[1555] Step 2:

[1556] The server randomly selects evidence from the acquired evidence list using a specific algorithm. Specifically, the server executes a random sampling algorithm from the acquired list to select, for example, 50 evidences. The input is the acquired evidence list, and the output is the randomly selected evidence list.

[1557] Step 3:

[1558] The server generates a request to collect the selected evidence and sends it to the relevant departments and systems. Specifically, the server sends a request to each department's terminal, clearly indicating what evidence needs to be collected. The input is a list of randomly selected evidence, and the output is the sent request.

[1559] Step 4:

[1560] The terminal receives a request from the server, extracts the specified evidence from the database, and sends it to the server. The terminal executes a database query, extracts the specified evidence, and sends it to the server. The input is the collection request from the server, and the output is the extracted evidence data.

[1561] Step 5:

[1562] The server stores the collected evidence in an internal database and checks its integrity. Specifically, the server passes the received evidence data through a verification algorithm to check the consistency and completeness of the data. The input is the extracted evidence data, and the output is the evidence data whose integrity has been confirmed.

[1563] Step 6:

[1564] The server displays the collected supporting data on the terminal so that the user can confirm and approve it. The terminal displays the supporting data through a user interface, and the user confirms and approves it. The input is the confirmation request and supporting data, and the output is feedback of approval or rejection by the user.

[1565] Step 7:

[1566] The server automatically evaluates the supporting data based on pre-defined evaluation criteria. The evaluation algorithm examines the supporting data and determines whether it meets the pre-defined criteria. The input is the supporting data and evaluation criteria, and the output is the evaluation result.

[1567] Step 8:

[1568] The server generates evaluation results and creates an evaluation result report. Specifically, the server aggregates the evaluation results and generates a report in a format that is easy for users to understand. The input is the evaluation results, and the output is the evaluation result report.

[1569] Step 9:

[1570] The server notifies the user of the evaluation result report and prompts them to confirm it. The user checks the report on their device and determines the necessary actions. The input is the evaluation result report, and the output is the user's confirmation and feedback.

[1571] Step 10:

[1572] After the user specifies an action, the server notifies the relevant departments. Specifically, the server generates notification content and sends it to the relevant department's terminal. The input is the user's instruction to take an action, and the output is a notification to the relevant department.

[1573] Step 11:

[1574] The emotion engine recognizes the user's emotional state in real time and adjusts the process appropriately. The emotion engine monitors the user's stress and concentration level and generates appropriate suggestions. The input is the user's real-time emotional data, and the output is adjustment suggestions and their implementation.

[1575] Step 12:

[1576] If the user accepts the emotion engine's suggestion, the server dynamically adjusts the process based on the suggestion. The input is the emotion engine's suggestion, and the output is the adjusted process.

[1577] 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.

[1578] 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.

[1579] 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.

[1580] 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.

[1581] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes bot...

Claims

1. a means for obtaining a list of evidence; means for randomly selecting a document from the list of obtained documents; means for generating and transmitting a request to collect the selected evidence; A means of storing and checking the integrity of collected evidence; a means for displaying the supporting data so that the user can review and approve it; A system including:

2. means for evaluating the supporting data based on pre-established evaluation criteria; means for generating evaluation results and creating an evaluation result report; A means for notifying and displaying the evaluation result report so that the user can view and confirm it; The system of claim 1 further comprising:

3. a means by which the user can submit additional collection requests; A means for users to determine actions based on the evaluation results and notify relevant departments; The system of claim 1 further comprising:

Images