system

Abstract

We provide a system that deepens understanding of the "why" of business operations and enables specific business improvements to be realized. [Solution] A system including a means for recording operation logs, a means for transmitting the operation logs to a server, a means for saving the operation logs, a means for analyzing the saved operation logs and visualizing the business flow, a means for detecting operations that occur abnormally frequently, a means for generating hypotheses about abnormal operations, a means for notifying the user of the hypotheses, a means for collecting user responses, a means for generating business improvement proposals based on the user responses, a means for presenting the business improvement proposals to the user, a means for monitoring the usage of the new business flow, a means for verifying the effectiveness of the new business flow, and a means for feeding back the verification results to the user.

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] In conventional business processes, certain workflows are often repeated without any reason, making it difficult to identify the cause and improve the process. This results in reduced business efficiency and unnecessary costs. Furthermore, there are insufficient means to obtain insights for business improvement, and it takes a great deal of time and effort for users to manually review business processes. An efficient and effective means to solve these problems is needed. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system with the following features. First, it includes a means for recording operation logs, which records user operations in detail. It also includes a means for transmitting the recorded operation logs to a server, accumulating data in real time. Next, it provides a means for saving operation logs and a means for analyzing the saved data and visualizing business processes, thereby identifying frequently occurring operations. It also includes a means for detecting abnormally frequent operations, automatically generating hypotheses about the abnormal operations, and notifying the user. It also includes a means for collecting user responses and generating and presenting business improvement proposals based on those responses. It also includes a means for monitoring the usage of new business processes that incorporate improvement proposals and verifying their effectiveness. Finally, it provides feedback on the verification results to establish optimal business processes. This deepens understanding of the "why" of business processes and enables concrete business improvements to be realized.

[0006] An "operation log" is a detailed record of operations performed by a user.

[0007] A "server" is a computer system that receives and stores data and performs processing such as analysis.

[0008] "User" means the person operating the system or end user.

[0009] A "terminal" is a device that a user operates.

[0010] A "database" is a system for systematically storing and managing data such as operation logs.

[0011] "Analysis" is the process of analyzing collected data and extracting meaning.

[0012] "Business flow" refers to a series of steps or procedures for carrying out a specific business operation.

[0013] "Visualization" is the process of visually displaying data to make it easier to understand.

[0014] An "anomaly" refers to unusual data or phenomena that deviate from normal patterns.

[0015] A "hypothesis" is a tentative theory or premise used to explain a particular phenomenon or problem.

[0016] "Feedback" means reporting results and information to users and using them as a reference for improvements and corrections.

[0017] "Business improvement proposals" are specific proposals and plans for improving business efficiency.

[0018] "Monitoring" refers to overseeing the use of the new business process and measuring its effectiveness.

[0019] "Validation" is the process of evaluating the effectiveness of a new workflow. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

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

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

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

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0035] 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.

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

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The system according to the present invention realizes efficient business operations by analyzing and improving business flow. This system includes a terminal that records operation logs, a server that stores and analyzes the operation logs, and a means for providing feedback to users, and is implemented as follows:

[0042] Recording and sending operation logs

[0043] The terminal records each operation performed by the user in detail. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and timestamp are recorded. The recorded operation log is periodically sent to the server. The transmission is performed, for example, every hour, enabling real-time data collection.

[0044] Saving and analyzing operation logs

[0045] The server stores the received operation logs in a database. Based on the stored operation logs, the server analyzes the business flow. Specifically, it analyzes the operation logs and visualizes frequently occurring operations and patterns. Based on the analysis results, the server detects abnormally frequent operations as anomalies.

[0046] Hypothesis generation and user feedback

[0047] The server automatically generates hypotheses for detected anomalies. For example, it may hypothesize that "frequent inventory checks are caused by improper inventory management." The generated hypotheses are fed back to the user. The user can then provide specific reasons and additional information to improve the accuracy of the hypotheses.

[0048] Generate and present business improvement proposals

[0049] The server generates business improvement proposals based on user feedback. For example, it proposes a "dashboard that displays inventory status in real time." These improvement proposals are presented to the user, who evaluates and decides on them. If the user decides to adopt the improvement proposal, a new business flow is designed based on its contents.

[0050] New workflow monitoring and effectiveness verification

[0051] After the proposed improvements are implemented, the server monitors the usage of the new workflow. Specifically, it monitors the frequency and effectiveness of real-time use of the inventory status dashboard. As a result of the monitoring, it verifies whether or not work efficiency has improved, and provides feedback on the results to the user. For example, it reports specific figures such as, "By introducing the dashboard, the number of inventory check operations has decreased by 50%, improving work efficiency."

[0052] Specific examples

[0053] For example, consider a case where "inventory check" operations are frequently performed in a company's inventory management system. When this system is implemented, the terminal records these operations in detail and sends the log to the server. The server analyzes the data, detects that "inventory check" operations are occurring abnormally frequently, and generates hypotheses about the cause. Based on user feedback, the server proposes a dashboard that displays inventory status in real time. If the user evaluates this and decides to implement it, the dashboard will be used as a new business flow. Finally, the server monitors its effectiveness, and if improvements are confirmed, it will be established as a formal business process.

[0054] In this way, the system according to the present invention realizes efficient and rational business flow, and reduces the workload of the user.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The terminal records user operations in real time. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and a timestamp are recorded.

[0058] Step 2:

[0059] The terminal sends the recorded operation log to the server at regular intervals (for example, every hour), allowing data to be collected in real time.

[0060] Step 3:

[0061] The server stores the received operation logs in a database. The data to be stored includes the user ID, operation details, timestamp, etc.

[0062] Step 4:

[0063] The server periodically analyzes the operation logs stored in the database. The main purpose of the analysis is to grasp the overall picture of each business flow and extract frequently occurring operations and specific patterns.

[0064] Step 5:

[0065] Based on the analysis results, the server detects operations that occur abnormally frequently as anomalies. For example, if the "inventory check" operation occurs abnormally frequently compared to other operations, it will mark it as an anomaly.

[0066] Step 6:

[0067] The server generates hypotheses for detected anomalies, for example, "Inventory checks are occurring frequently because inventory management is not being properly performed."

[0068] Step 7:

[0069] The server notifies the user of the generated hypotheses, for example by presenting the user with a question such as "Please tell me why inventory check operations are occurring so frequently."

[0070] Step 8:

[0071] The user responds to the server's question by providing specific reasons and additional information, such as, "The reason we need to check inventory frequently is to prevent products from running out."

[0072] Step 9:

[0073] The server generates business improvement proposals based on user feedback, such as a "dashboard that displays inventory status in real time."

[0074] Step 10:

[0075] The server presents the generated business improvement proposals to the user, who evaluates them and decides whether to implement them.

[0076] Step 11:

[0077] If the user decides to adopt the proposed improvement, the server designs and implements the new workflow, for example, by introducing a real-time inventory status dashboard.

[0078] Step 12:

[0079] The server monitors the usage of the new workflow, for example, how often the dashboard is used.

[0080] Step 13:

[0081] The server verifies the effectiveness of the new workflow, for example, evaluating whether the "inventory check" operation has decreased since the dashboard was introduced.

[0082] Step 14:

[0083] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the number of inventory check operations has decreased by 50% since the introduction of the dashboard."

[0084] Step 15:

[0085] The user and server then formally establish the new business flow, the effectiveness of which has been confirmed based on the evaluation results, as a business process.

[0086] Example 1

[0087] 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."

[0088] In current business management systems, operation logs are recorded and analyzed separately, without any coordination, making it difficult to grasp the overall picture of business flows. Even when abnormal operations or patterns are detected, the causes and improvement plans are often generated manually, making efficient business improvement difficult. Furthermore, there is a lack of means to properly verify the effects of new business flows after they are introduced, making it difficult to ensure the effectiveness of improvements. There is a need for a system that can solve these issues and efficiently and automatically visualize and improve business flows.

[0089] 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.

[0090] In this invention, the server includes means for saving operation logs, means for analyzing the saved operation logs and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating business improvement plans based on the user responses, means for presenting the business improvement plans to the user, means for monitoring the usage status of the new workflow, means for verifying the effectiveness of the new workflow, and means for providing feedback to the user on the effectiveness of the workflow in concrete numerical values. This makes it possible to grasp the overall picture of the workflow, efficiently and automatically generate business improvement plans, and introduce effective workflows and verify their effectiveness.

[0091] An "operation log" is data that records the content of each operation performed by a user and the time at which it was performed.

[0092] A "server" is a central computer device that receives, stores, analyzes, and processes data sent from terminals, and improves business processes.

[0093] "Business flow" refers to a series of procedures that show the specific flow and process of business.

[0094] An "abnormally frequent operation" refers to an operation that is performed significantly more frequently than in the normal workflow, and is an operation that may be a sign of problems with the efficiency or quality of work.

[0095] A "hypothesis" is a guideline for speculating on possible causes or backgrounds based on detected abnormal operations.

[0096] An "improvement proposal" is a specific proposal for changes to make the current business flow more efficient or rational.

[0097] "Monitoring" is the activity of observing in real time how new business processes and improvement proposals are actually being implemented.

[0098] "Feedback" refers to the provision of information to encourage continuous business improvement by communicating monitoring and analysis results to users.

[0099] "Real-time" refers to a situation in which data is collected and processed immediately, and feedback and responses based on that data are provided without delay.

[0100] The system of the present invention realizes efficient business operations by analyzing and improving business flows. This system includes a terminal that records operation logs, a server that stores and analyzes the operation logs, and a means for providing feedback to users, and is specifically implemented as follows.

[0101] Recording and sending operation logs

[0102] The terminal records each operation performed by the user in detail. When a user performs an "inventory check" operation in the inventory management system, the operation content and timestamp are recorded. This operation log is temporarily stored in local storage or temporary memory. The operation log is then periodically (for example, every hour) sent to the server. The transmission is performed using the HTTP or HTTPS protocol. This makes it possible to collect data in real time.

[0103] Saving and analyzing operation logs

[0104] The server stores the received operation logs in a database (for example, MySQL (registered trademark) or PostgreSQL). It then formats the data appropriately according to the database schema. Based on the stored operation logs, the server analyzes the business flow. Specifically, it uses log analysis software (for example, ElasticSearch (registered trademark) or Splunk) to visualize frequently occurring operations and patterns. Based on the analysis results, it detects abnormally frequent operations as anomalies.

[0105] Hypothesis generation and user feedback

[0106] The server automatically generates hypotheses for detected anomalies. For example, it may hypothesize that "frequent inventory checks are caused by improper inventory management." A generative AI model (such as GPT-3 (registered trademark) or BERT) is used to generate hypotheses. The generated hypotheses are notified to the user via email, dashboard alerts, or a dedicated mobile app. The user receives the notification and can provide specific causes or additional information to improve the accuracy of the hypothesis.

[0107] Generate and present business improvement proposals

[0108] The server generates business improvement proposals based on user feedback. Prompt statements such as "How to reduce inventory check operations" are input into the generative AI model, which then generates ideas for a "dashboard that displays inventory status in real time." These business improvement proposals are then proposed to the user. The proposals can be displayed on the dashboard, sent via email, or presented at a meeting. The user reviews and evaluates the proposals, and if a decision is made to adopt them, a new business flow is specifically designed.

[0109] New workflow monitoring and effectiveness verification

[0110] The server monitors the usage of the new business flow in real time. Specifically, it collects the frequency of dashboard use and operation logs, and also collects feedback from users. The server verifies the effectiveness of the new business flow based on the collected data and generates a report with specific figures, such as "By introducing the dashboard, inventory check operations have decreased by 50%, and business efficiency has improved." The results are fed back to the user, helping to improve business operations.

[0111] Prompt Sentence Examples

[0112] 1. "Please explain a specific example of recording and analyzing operation logs in an inventory management system."

[0113] 2. "Please tell me the detailed flow of the system, including the hypothesis generation and feedback process for improving business processes."

[0114] 3. Please explain the specific steps for generating and evaluating business improvement proposals based on user feedback.

[0115] In this way, the system according to the present invention realizes efficient and rational business flow, and reduces the workload of the user.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1:

[0118] The terminal captures each operation performed by the user and generates log data that includes the operation details and a timestamp. As a concrete example, when a user clicks the "Check Stock" button in an inventory management system, the operation details "Check Stock" and the timestamp "YYYY-MM-DD HH:MM:SS" are recorded. This log data is temporarily saved in local storage. The input is the user's operation, and the output is the generated operation log data.

[0119] Step 2:

[0120] The terminal reads operation log data from local storage at regular intervals (for example, every hour) and sends it to the server. HTTP or HTTPS is used as the transmission protocol. The input is the operation log data from local storage, and the output is a transmission completion notification to the server.

[0121] Step 3:

[0122] The server saves the received operation log data in a database (for example, MySQL or PostgreSQL). Before saving, the data is formatted based on the database schema. Specifically, the log data is broken down into fields (operation details, timestamp, etc.) and stored. The input is the received operation log data, and the output is the formatted data saved in the database.

[0123] Step 4:

[0124] The server analyzes the stored operation log data. Log analysis software (such as Elasticsearch or Splunk) is used to visualize frequently occurring operations and patterns. For example, the number of times a specific operation was performed is tallied and displayed as a heat map. The input is database operation log data, and the output is visualized data of the analysis results.

[0125] Step 5:

[0126] The server detects abnormally frequent operations (anomalies) based on the analysis results. For example, if the "inventory check" operation is performed 50% more frequently than usual, it will recognize it as an anomaly. The input is the analysis result data, and the output is a report of the detected anomalies.

[0127] Step 6:

[0128] The server generates hypotheses for the detected anomalies using a generative AI model (e.g., GPT-3 or BERT). For example, it generates a hypothesis such as "The high frequency of inventory checks is due to improper inventory management." The input is the anomaly report, and the output is the generated hypothesis.

[0129] Step 7:

[0130] The server notifies the user of the generated hypotheses via email, dashboard alerts, or a dedicated mobile app. The input is the generated hypotheses, and the output is the completion of the notification to the user.

[0131] Step 8:

[0132] The user provides specific causes and additional information for the received hypothesis. For example, they provide detailed feedback such as "This is because the warehouse management system is outdated." The input is the hypothesis notification, and the output is the user's feedback.

[0133] Step 9:

[0134] The server generates business improvement proposals using a generative AI model based on user feedback. For example, it suggests "introducing a dashboard that displays inventory status in real time." The input is user feedback, and the output is the generated business improvement proposals.

[0135] Step 10:

[0136] The server proposes the generated business improvement proposal to the user. The proposal is made through display on a dashboard, email, or presentation at a meeting. The input is the generated business improvement proposal, and the output is the completed proposal to the user.

[0137] Step 11:

[0138] The user evaluates the proposed business improvement plan and decides whether to implement it. For example, the user may decide to "adopt the introduction of a dashboard." The input is the business improvement plan, and the output is the evaluation result and the decision to implement it.

[0139] Step 12:

[0140] The server monitors the usage status of the new business flow in real time. Specifically, it collects dashboard usage data and operation logs. The input is the usage data of the new business flow, and the output is a monitoring report.

[0141] Step 13:

[0142] The server verifies the effectiveness of the new workflow based on the monitoring results and evaluates it with specific numerical values, such as "Inventory check operations have decreased by 50%, and work efficiency has improved." The input is the monitoring data, and the output is an effectiveness verification report.

[0143] Step 14:

[0144] The server feeds back the effectiveness verification report to the user. It creates a report including specific numerical data and notifies the user. The input is the effectiveness verification report, and the output is the completion of feedback to the user.

[0145] (Application example 1)

[0146] 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."

[0147] Modern logistics centers require highly efficient and precise management. However, manual operation log recording and subsequent data analysis make it difficult to make real-time improvements, limiting the extent to which operational efficiency can be improved. Furthermore, the frequent occurrence of abnormal operations, the time and effort required to identify the causes, and the implementation of improvement proposals can lead to a decline in overall work efficiency.

[0148] 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.

[0149] In this invention, the server includes a means for using a smart device to record operation logs in real time, a means for providing feedback in real time, and a means for presenting specific improvement proposals to workers and determining whether or not to apply them, thereby enabling the rapid analysis and improvement of the work flow within the logistics center and the overall improvement of work efficiency.

[0150] An "operation log" is data that records a series of operations performed by a user.

[0151] "Server" refers to the central system that receives, stores, and analyzes operation logs.

[0152] "Business flow" refers to the series of steps and procedures that a business follows.

[0153] "Real-time feedback" refers to responses and suggestions for improvement that are provided immediately to the user's actions.

[0154] "Smart devices" refer to advanced electronic devices that record operational logs and provide feedback in real time.

[0155] "Abnormal operations" refer to frequent or inappropriate operations that deviate from normal business flow.

[0156] "Hypothesis" refers to a tentative explanation or speculation about the cause of the detected abnormal operation.

[0157] "User" refers to an individual or team that uses the system to carry out work.

[0158] "Improvement proposals" refer to proposals and action plans to improve the efficiency of business flows and operations.

[0159] "Monitoring" refers to the act of watching how new business processes are being used and measuring their effectiveness.

[0160] A "logistics center" refers to a location that manages the storage and delivery of goods.

[0161] The system of the present invention aims to improve the efficiency of operations within a logistics center. This system improves the workflow by recording operation logs, sending and saving them on a server, analyzing them, and presenting improvement proposals to the user.

[0162] Hardware and software configuration

[0163] Hardware:

[0164] 1. Smart devices: Used to record operation logs in real time. Smartphones and smart glasses are examples of such devices.

[0165] 2. Server: A central system that stores the received operation logs, analyzes them, and generates business improvement proposals.

[0166] software:

[0167] 1. Python: This is the main language used to implement the program in this system.

[0168] 2. Flask / Django: Web frameworks used for server-side API integration.

[0169] 3. requests: A library for making HTTP requests.

[0170] 4. Database: A system for storing operation logs and analysis results (e.g., MySQL, PostgreSQL).

[0171] Specific operation of the system

[0172] Recording and sending operation logs

[0173] The smart device terminal records each worker's operation in real time and periodically sends the data to the server. For example, operations such as "start picking" and "check inventory" are recorded.

[0174] Saving and analyzing operation logs

[0175] The server stores the received operation logs in a database and then performs data analysis to detect frequently performed operations and abnormal operations, i.e., operations that deviate from the normal business flow.

[0176] Hypothesis generation and feedback

[0177] The server generates a hypothesis based on the detected abnormal operation. For example, it may hypothesize that "the reason this operation is performed so frequently is due to uncertainty in inventory information." The hypothesis is then fed back to the user in real time. The user can then enter an answer based on the provided hypothesis and send the feedback to the server.

[0178] Proposing business improvement plans

[0179] The server generates specific business improvement proposals based on user feedback and presents them to the user. For example, the proposal might include "introducing a dashboard that displays inventory status in real time."

[0180] New workflow monitoring and effectiveness verification

[0181] After a new workflow is implemented, the server monitors its usage, verifies the extent to which the new workflow contributes to efficiency, and provides feedback to the user in the form of specific figures.

[0182] Specific examples

[0183] For example, if the "inventory check" operation is frequently performed in inventory management at a logistics center, the system records the operation in detail and sends the log to the server. The server analyzes the data, detects that the "inventory check" operation is abnormally frequent, and hypothesizes the cause. Based on user feedback, the server proposes a "dashboard that displays inventory status in real time." The new workflow is then adopted, its usage and effectiveness are monitored, and improvements in operational efficiency are confirmed.

[0184] Prompt Sentence Examples

[0185] "Design an application that records work logs at a logistics center and proposes improvement plans for efficiency. Please include a specific process flow, such as how to record operation logs, how to send and save the logs, how to analyze data, provide feedback, propose business improvement plans, and verify their effectiveness."

[0186] The above is a specific embodiment for carrying out the present invention.

[0187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0188] Step 1:

[0189] Recording of operation logs

[0190] The terminal uses a smart device (smartphone or smart glasses) to record each operation performed by the worker in detail. The input includes operations performed by the worker, such as "start picking" and "check inventory." A timestamp is assigned to each input operation, making it clear which operation was performed and when. Operation log data is generated as output.

[0191] Step 2:

[0192] Sending operation logs

[0193] The terminal sends the recorded operation log to the server at regular intervals (for example, every hour). The input is the operation log data recorded in step 1. The transmission method is an HTTP request. After transmission, the output is when the server receives the log data.

[0194] Step 3:

[0195] Saving operation logs

[0196] The operation log received by the server is saved in the database. The input is the operation log data received in step 2. An SQL query is used as the saving method. The output is that the operation log data is stored in the database.

[0197] Step 4:

[0198] Analysis of operation logs

[0199] The server analyzes the saved operation logs. The input is the operation log data stored in the database. The analysis methods include frequency analysis and pattern recognition to detect frequently performed operations and abnormal operations. The output is the analysis results, which include abnormal operation patterns and frequently performed operation data.

[0200] Step 5:

[0201] Hypothesis generation

[0202] The server generates hypotheses about abnormal operations based on the analysis results. The input is the analysis result data from step 4. Hypotheses are automatically generated using an AI model. The output is a hypothesis such as "Inventory check operations are being performed frequently due to problems with inventory management."

[0203] Step 6:

[0204] Feedback Notifications

[0205] The server notifies the user of the generated hypothesis. The input is the hypothesis generated in step 5. Notification methods include real-time display on a smart device or sending an alert. The output is the notification result to the user.

[0206] Step 7:

[0207] Collecting user responses

[0208] The user inputs a response to the feedback provided to the server. The input is additional data and comments from the user. The output is when the server receives the response data.

[0209] Step 8:

[0210] Generate business improvement proposals

[0211] The server generates business improvement proposals based on the user's responses. The input is the user response data received in step 7. Taking into account past log data and user feedback, specific improvement proposals are created using AI. The output is improvement proposals such as a "dashboard that displays inventory status in real time."

[0212] Step 9:

[0213] Proposing business improvement plans

[0214] The server presents the generated business improvement proposals to the user. The input is the business improvement proposals generated in step 8. Notification methods include displaying a dashboard on a smart device and sending implementation proposals. The output is the improvement proposals presented to the user.

[0215] Step 10:

[0216] New Workflow Monitoring

[0217] The server monitors the usage of the new business flow. The input is the implementation data of the new business flow. The log data is analyzed in real time to verify the frequency of use and effectiveness. The output is the effectiveness measurement data as a result of the monitoring.

[0218] Step 11:

[0219] Effectiveness verification

[0220] The server verifies the effectiveness of the new business flow. The input is the monitoring data obtained in step 10. The data is compared and analyzed to evaluate improvements in business efficiency and changes in operation frequency. The output is a concrete result of the verification of effectiveness, such as "business efficiency has improved by 50%."

[0221] Step 12:

[0222] Providing Feedback

[0223] The server feeds back the results of the effectiveness verification to the user. The input is the results of the effectiveness verification obtained in step 11. Feedback methods include periodic reports and real-time notifications. The output is the feedback results to the user.

[0224] 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.

[0225] The system of the present invention achieves more effective business improvement by combining an emotion engine that recognizes user emotions. In addition to recording and analyzing operation logs, this system also collects and analyzes user emotion data, which is used to generate and present business improvement proposals. The specific processing flow is explained below.

[0226] Recording and sending operation logs

[0227] The terminal records each operation performed by the user in detail. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and timestamp are recorded. In addition, the emotion engine analyzes the user's facial expressions and voice during the operation and records them as emotion data. The recorded operation log and emotion data are sent to the server at regular intervals (for example, every hour). This allows data to be collected in real time.

[0228] Saving and analyzing operation logs and emotion data

[0229] The server stores the received operation logs and emotion data in a database. The data to be stored includes user IDs, operation details, timestamps, and emotion data. The server analyzes the business flow based on this data and visualizes frequently occurring operations and specific patterns.

[0230] Anomaly Detection and Hypothesis Generation

[0231] The server uses the analysis results to detect operations that occur abnormally frequently as anomalies. For example, if the "check inventory" operation occurs abnormally frequently compared to other operations, it marks it as an anomaly. In addition, it uses emotion data provided by the emotion engine to analyze the user's emotional state at the time the anomaly occurred. For example, if anxiety or stress is high, this will also be included in the data.

[0232] The server generates hypotheses for anomalies, such as "frequent stock checks are due to poor inventory management and users feeling anxious," which allows for the emotional factors behind the problem to be taken into account.

[0233] User feedback and business improvement proposal generation

[0234] The server notifies the user of the generated hypothesis. For example, it presents the user with a question such as, "Please tell me why inventory check operations are occurring so frequently." The user responds by providing specific reasons and additional information. For example, the user might answer, "Inventory checks are necessary frequently to prevent product shortages."

[0235] The server generates business improvement proposals based on the user's feedback and emotions. For example, it suggests a "dashboard that displays inventory status in real time." It also adjusts the content and presentation method of the proposals by taking into account the emotional data. For example, if the user is prone to stress, it will devise a more appropriate wording for the proposals.

[0236] Proposing and monitoring business improvement proposals

[0237] The server presents the generated business improvement proposals to the user. If the user evaluates the proposals and decides to implement them, the server designs and implements the new business flow. For example, it introduces a real-time inventory status dashboard.

[0238] New workflow monitoring and effectiveness verification

[0239] After the proposed improvements are implemented, the server monitors the usage of the new workflow, for example, by monitoring how frequently the dashboard is used and how the user's emotional state changes when operating it.

[0240] The server verifies the effectiveness of the new workflow. For example, it evaluates whether the number of "inventory check" operations has decreased and whether users' emotional state has improved after the dashboard was introduced.

[0241] Final feedback and establishing the flow

[0242] The server then provides the final evaluation results as feedback to the user. For example, it might report, "By introducing the dashboard, inventory check operations have decreased by 50%, and user stress levels have also decreased." Based on the evaluation results, the user and server then formally establish the new business flow as a business process.

[0243] In this way, the system according to the present invention not only realizes the efficiency and streamlining of the workflow, but also realizes comprehensive business improvement that takes into consideration the emotional aspects of the user.

[0244] The processing flow will be explained below.

[0245] Step 1:

[0246] The device records user operations in real time. For example, when a user performs an "inventory check" operation, the device records the operation details and a timestamp.

[0247] Step 2:

[0248] The device analyzes the user's emotional state using an emotion engine. For example, it analyzes the user's facial expressions and voice, and generates emotion data such as anxiety, stress, and satisfaction.

[0249] Step 3:

[0250] The device sends operation logs and emotion data to the server at regular intervals (for example, every hour), allowing data to be collected and sent in real time.

[0251] Step 4:

[0252] The server stores the received operation log and emotion data in a database. The stored data includes the user ID, operation details, timestamp, and emotion data.

[0253] Step 5:

[0254] The server analyzes the operation logs and emotion data stored in the database. The purpose of the analysis is to understand the overall picture of the user's workflow and extract frequently occurring operations and specific emotion patterns.

[0255] Step 6:

[0256] Based on the analysis results, the server detects operations that are abnormally frequent as anomalies. For example, if the "inventory check" operation is abnormally frequent compared to other operations, it will mark it as an anomaly.

[0257] Step 7:

[0258] The server also references the user's emotional data when an anomaly occurs and generates a hypothesis. For example, it may hypothesize that "inventory checks are being conducted frequently because inventory management is not being properly performed and users are feeling anxious."

[0259] Step 8:

[0260] The server notifies the user of the generated hypothesis. For example, it displays a question to the user such as "Please tell me why inventory check operations are occurring so frequently."

[0261] Step 9:

[0262] The user responds to the server's question by providing specific reasons and additional information, such as "The reason we need to check inventory frequently is to prevent products from running out."

[0263] Step 10:

[0264] The server generates business improvement proposals based on user feedback and emotional data, such as a dashboard that displays inventory status in real time.

[0265] Step 11:

[0266] The server presents the generated business improvement proposals to the user, who evaluates them and decides whether to implement them.

[0267] Step 12:

[0268] If the user decides to adopt the proposed improvement, the server designs and implements the new workflow, for example, by introducing a real-time inventory status dashboard.

[0269] Step 13:

[0270] The server monitors the usage of the new workflow, specifically how frequently the dashboard is used and how the user's emotional state changes when operating it.

[0271] Step 14:

[0272] The server verifies the effectiveness of the new workflow, for example, evaluating whether the number of "inventory check" operations has decreased and whether the user's emotional state has improved after the dashboard was introduced.

[0273] Step 15:

[0274] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered users' stress levels."

[0275] Step 16:

[0276] Based on the evaluation results, the user and the server establish the new workflow as a formal business process. In this way, the present invention aims to improve the efficiency of the workflow and the user's emotional state.

[0277] Example 2

[0278] 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."

[0279] Conventional business improvement systems proposed improvement measures based on the analysis of operation logs, but did not take into account the user's emotional state. As a result, improvement measures were sometimes proposed that ignored psychological factors, and were unable to reduce the user's stress and anxiety. Furthermore, when verifying the effectiveness of new business flows after their implementation, emotional data was not taken into account in the evaluation. These problems need to be solved.

[0280] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for recording an operation log, means for transmitting the operation log to the server, means for saving the operation log, means for analyzing the saved operation log and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating business improvement proposals based on the user responses, means for presenting the business improvement proposals to the user, means for collecting and analyzing emotional data, means for sending the operation log including the emotional data to the server, means for analyzing the emotional data during operations and associating it with anomalies, means for adjusting the business improvement proposals taking the emotional data into consideration, means for monitoring the usage status and emotional state of the new workflow, means for verifying the effectiveness of the new workflow, and means for feeding back the verification results to the user. This makes it possible to propose business improvements that take the user's emotional state into consideration, and also enables comprehensive evaluation including emotional data when verifying the effectiveness of a new workflow after its introduction.

[0281] An "operation log" refers to historical information about operations performed by a user within the system, and specifically includes the operation details, user ID, timestamp, etc.

[0282] "Emotion data" refers to information about the user's psychological state analyzed from their facial expressions and voice using an emotion engine, and specifically refers to data that quantifies emotional states such as anxiety, stress, and joy.

[0283] "Server" refers to a computer system that operates on a network and receives, stores, analyzes, and provides feedback on data.

[0284] A "terminal" refers to a hardware device that a user operates, specifically an electronic device such as a computer or smartphone.

[0285] "Business flow" refers to a series of steps or procedures for carrying out a specific business operation.

[0286] "Analysis" refers to the process of processing collected data to detect specific patterns or anomalies.

[0287] An "anomaly" refers to an operation that occurs abnormally frequently and deviates from normal operating patterns.

[0288] A "hypothesis" refers to a prediction or theory that is made to estimate the cause of an anomaly.

[0289] "Feedback" refers to the evaluation results and suggestions that the system provides to the user.

[0290] "Monitoring" refers to the process of continuously monitoring the usage of the new workflow and the emotional state of the user.

[0291] "Improvement proposals" refer to specific proposals aimed at streamlining business processes and improving user experiences.

[0292] The system of the present invention collects and analyzes user operation logs and emotional data to help improve business operations, which not only improves operational efficiency but also reduces the psychological burden on users.

[0293] Hardware and Software Configuration

[0294] Hardware

[0295] Device: A device operated by a user. This can include desktop computers, laptops, smartphones, etc. These devices are equipped with cameras and microphones to capture facial and audio data from the user.

[0296] Server: A central system that collects, stores, and analyzes data. It is equipped with a high-performance database and analysis engine.

[0297] software

[0298] Emotion engine: Software that runs on the device and uses the camera and microphone to analyze the user's facial expressions and voice to generate emotion data.

[0299] Database management system: Runs on the server and stores and manages operation logs and emotion data.

[0300] Analysis engine: Software that runs on a server and visualizes business processes and detects anomalies based on collected data.

[0301] Generative AI model: Generates business improvement proposals based on user feedback.

[0302] Data processing and calculation

[0303] The device records the user's operation log in real time and uses an emotion engine to collect emotional data during the operation. For example, when a user performs an "inventory check" operation, the degree of "anxiety" or "stress" is recorded as emotional data along with the operation details.

[0304] The collected data is sent to a server at regular intervals. The server stores the received data in a database, and an analysis engine analyzes the business flow based on the stored data. This analysis makes it possible to visualize frequently occurring operations and specific patterns.

[0305] Based on the analysis results, the server detects abnormally frequent operations (anomalies). It also uses emotional data to analyze the user's emotional state at the time the anomaly occurred and evaluates whether the anomaly is due to psychological factors. For example, if the "inventory check" operation is performed frequently and the user feels high stress when doing so, it will be marked as an anomaly.

[0306] The server uses a generative AI model to generate a hypothesis about the anomaly and prompts the user to confirm the hypothesis, for example, "Please tell me why inventory check operations are occurring so frequently."

[0307] Based on user feedback, the server generates business improvement proposals. These proposals are chosen with appropriate content and expressions, taking into account emotional data. For example, when proposing a "dashboard that displays inventory status in real time," gentle expressions are used to avoid causing excessive stress to the user.

[0308] Examples of concrete examples and prompts

[0309] As a specific usage scenario, consider a case where a user uses an inventory management system and frequently performs "inventory check" operations. At this time, the emotion engine analyzes the user's facial expressions and voice to indicate that "anxiety" and "stress" are increasing.

[0310] The collected operation logs and emotion data are sent to a server, which stores them in a database and analyzes business flows and anomalies. The server detects an abnormally high number of "inventory check" operations and hypothesizes that "frequent inventory checks are occurring because inventory management is not being done properly and users are feeling anxious."

[0311] Based on this hypothesis, the generative AI model asks the user for feedback, displaying a prompt saying, "Please tell us why you are frequently checking inventory." The specific feedback received from the user is, "The reason why inventory checks are necessary so frequently is to prevent products from running out."

[0312] Based on this feedback, the server generates a proposal for a dashboard that displays inventory status in real time and presents it to the user in a way that is thoughtful and stress-free for the user.

[0313] As described above, the present invention is a system that utilizes operation logs and emotion data to propose business improvements and verify their effectiveness.

[0314] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0315] Step 1: Recording operational logs

[0316] The device records all operations performed by the user. When a user performs an operation such as "check inventory," the operation details, user ID, and timestamp are saved as a log.

[0317] Input: User action (e.g., clicking the "Check stock" button)

[0318] Data processing: Collection of operation details, user ID, and timestamp

[0319] Output: Operation log (e.g. "Check stock", user ID, timestamp)

[0320] Step 2: Collect and analyze emotion data

[0321] The device collects the user's facial expressions and voice data using a camera and microphone, and an emotion engine analyzes this data to generate emotion data.

[0322] Input: User's facial expressions and voice

[0323] Data processing: Analyze facial expressions and voice to determine emotional state (e.g., "anxiety" 80%, "stress" 60%)

[0324] Output: Emotion data (e.g., "anxiety" 80%, "stress" 60%)

[0325] Step 3: Sending data

[0326] The device sends operation logs and emotion data to the server at regular intervals.

[0327] Input: Operation log, emotion data

[0328] Data processing: Converting data into packets

[0329] Output: Send data to the server

[0330] Step 4: Save your data

[0331] The server stores the received data in a database, including the user ID, operation details, timestamp, and emotion data.

[0332] Input: Operation log, emotion data

[0333] Data processing: Insertion into database

[0334] Output: Update record in database

[0335] Step 5: Analyze the workflow

[0336] The server analyzes the business flow based on the stored data, for example, extracting and visualizing frequently occurring operations.

[0337] Input: Database operation log data

[0338] Data processing: Calculation and visualization of frequency distribution

[0339] Output: Visualized workflow (e.g. heat map)

[0340] Step 6: Anomaly detection

[0341] Based on the analysis results, the server detects abnormally frequent operations as anomalies.

[0342] Input: Workflow analysis results

[0343] Data processing: Detecting anomalies using statistical methods

[0344] Output: Anomaly list (e.g., "Stock Check" is abnormally high)

[0345] Step 7: Hypothesis generation

[0346] The server generates hypotheses for anomalies, such as "frequent inventory checks are occurring because users are feeling anxious" based on emotional data.

[0347] Input: Anomaly list, emotion data

[0348] Data processing: linking anomalies with emotional states, generating hypotheses

[0349] Output: Hypothesis (e.g., "The reason people check their inventory so frequently is because they have problems with inventory management and are feeling anxious")

[0350] Step 8: Get user feedback

[0351] The server notifies the user of the generated hypothesis and asks for feedback, for example by displaying a prompt such as "Please tell us why inventory check operations are occurring so frequently."

[0352] Input: Hypothesis

[0353] Data processing: Prompt sentence generation

[0354] Output: User notification (e.g. "Please tell me why inventory check operations are occurring so frequently")

[0355] Step 9: Generate business improvement proposals

[0356] The server generates business improvement proposals based on user feedback and emotional data, such as a dashboard that displays inventory status in real time.

[0357] Input: User feedback, emotion data

[0358] Data processing: Generating business improvement proposals that take into account feedback and emotional data

[0359] Output: Business improvement proposals (e.g., "Implementation of a real-time inventory dashboard")

[0360] Step 10: Propose improvements

[0361] The server presents the generated business improvement proposals to the user, for example, recommending the introduction of a dashboard that displays inventory status in real time.

[0362] Input: Business improvement proposal

[0363] Data processing: Message conversion of proposal content

[0364] Output: Suggestion notification to the user (e.g. "We recommend you install the real-time inventory dashboard")

[0365] Step 11: Monitoring the new workflow

[0366] After the proposed improvements are implemented, the server monitors the usage of the new workflow and the user's emotional state.

[0367] Input: New business flow usage log, emotion data

[0368] Data processing: Collection and analysis of usage and sentiment data

[0369] Output: New business flow evaluation report

[0370] Step 12: Verify the effect

[0371] The server verifies the effectiveness of the new workflow, for example, whether the number of "inventory check" operations has decreased after the dashboard was introduced, or whether the user's emotional state has improved.

[0372] Input: New Workflow Evaluation Report

[0373] Data processing: Before and after comparison, effect verification

[0374] Output: Verification results (e.g., "Inventory check operations decreased by 50%, stress levels decreased")

[0375] Step 13: Final feedback

[0376] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered user stress levels."

[0377] Input: Validation result

[0378] Data processing: feedback message generation

[0379] Output: Final report to the user

[0380] Step 14: Establishing the workflow

[0381] The user and server then formally establish the new business flow, the effectiveness of which has been confirmed based on the evaluation results, as a business process.

[0382] Input: Final report

[0383] Data processing: Setting up formal business flow

[0384] Output: Establishing a new workflow

[0385] In this way, specific input, data processing, and output are performed at each step, resulting in efficient business improvement and an improvement in the user's emotional state across the entire system.

[0386] (Application example 2)

[0387] 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."

[0388] Improving operational efficiency at logistics centers is an important issue for many companies. In particular, more effective operational improvements can be expected by considering the emotional aspects of workers in addition to their behavior. However, conventional systems have difficulty effectively utilizing data on worker emotions, resulting in only partial improvements to operational flow. Furthermore, when the cause of abnormal operations is due to emotions, there is also the issue of being unable to accurately identify the cause and propose improvement measures.

[0389] The identification process by the identification 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 recording an operation log, means for transmitting the operation log to the server, means for saving the operation log, means for analyzing the saved operation log and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating workflow improvement plans based on the user responses, means for presenting the workflow improvement plans to the user, means for monitoring the usage status of the new workflow, means for verifying the effectiveness of the new workflow, means for providing feedback on the verification results to the user, means for collecting user emotion data, means for analyzing the collected emotion data, means for using the emotion data to generate workflow improvement plans, and means for generating workflow improvement plans that take emotional factors into account based on the analysis results. This improves the efficiency of the workflow at the logistics center and enables comprehensive workflow improvement that also takes the emotions of workers into account.

[0390] An "operation log" is a detailed record of each operation a user performs within the system.

[0391] "Emotion data" refers to data relating to the user's emotional state, such as information analyzed from facial expressions and voice.

[0392] The "server" is a central computing device that collects and analyzes operation logs and emotion data, and generates and presents business improvement proposals.

[0393] "Visualization" is the visual presentation of data, making specific patterns and anomalies visible.

[0394] An "anomaly" refers to an abnormal operation or behavior that deviates from normal operating patterns.

[0395] A "hypothesis" is a possible explanation or theory as to why an anomaly occurs.

[0396] "Business improvement proposals" are specific proposals and measures to streamline or improve the current business flow.

[0397] "Feedback" refers to the user's reaction and evaluation of the analysis results and improvement proposals.

[0398] "Monitoring" is the activity of continuously observing the status of a system or process.

[0399] "Effectiveness verification" is the process of evaluating whether the business improvement plan that has been implemented is actually having the expected effect.

[0400] The "Logistics Center Business Improvement Assistant" system of the present invention uses smartphones or smart glasses to collect operation logs and emotional data of workers working in a logistics center, and analyzes the data on a server to improve business efficiency.

[0401] System Program

[0402] The terminal has the function of recording the worker's operation log and sending it to the server. Specifically, when a worker performs an operation such as "start picking," the operation details and timestamp are recorded. At the same time, the terminal's camera is used to capture the worker's facial expression, and an emotion engine analyzes the worker's emotional state (e.g., anxiety, stress) from the facial expression. This data is periodically sent to the server.

[0403] Hardware and software used

[0404] The hardware used is a smartphone or smart glasses (e.g., Google® Glass®). The camera built into these devices is used. The software used is an emotion recognition library (e.g., Emotion Recognition Library), a server-side data processing engine (e.g., an API built with Python or Flask), and a database (e.g., PostgreSQL).

[0405] Data processing and calculation

[0406] The server stores the received operation logs and emotion data in a database. The stored data includes user IDs, operation details, timestamps, and emotion data. The server analyzes this data and uses it to visualize business processes. For example, it identifies frequently occurring operations and specific patterns and displays them as graphs and charts.

[0407] Hypothesis generation and business improvement proposals

[0408] The server detects abnormally frequent operations (anomalies) from the analysis results and generates a hypothesis based on them. For example, it may hypothesize that "inventory checks are being performed frequently because inventory management is not being performed properly." This hypothesis is notified to the user, and specific reasons and additional information are collected. The server then generates business improvement proposals based on the user's answers and emotion data and presents them to the user.

[0409] Monitoring and effectiveness verification

[0410] After the proposed business improvement is implemented, the server monitors the usage of the new business flow. For example, it monitors how frequently a dashboard displaying real-time inventory status is used and how the user's emotional state changes when operating it. To verify the effectiveness of the new business flow, it also evaluates improvements in work efficiency and changes in the user's stress level.

[0411] Examples and prompts

[0412] For example, when a worker is picking items, the smart glasses recognize their movements and facial expressions and record them as emotion data. An example of a prompt for emotion analysis is as follows:

[0413] "Analyzing emotions from facial photos of workers taken with a smartphone camera"

[0414] In this way, the logistics center business improvement assistant system of the present invention streamlines the business flow of a logistics center and realizes comprehensive business improvement that also takes into account the emotional aspects of workers.

[0415] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0416] Step 1:

[0417] Operation log and emotional data recording

[0418] The terminal records the worker's operation log and emotional data. Specifically, when a worker performs an operation such as "start picking" using a smartphone or smart glasses, the operation details and timestamp are recorded. At the same time, the terminal's camera captures the worker's facial expression, and an emotion engine analyzes the facial expression to determine emotional data (e.g., anxiety, stress). The input is the worker's operation details and facial image data, and the output is the operation log and emotional data.

[0419] Step 2:

[0420] Sending data

[0421] The device sends the recorded operation log and emotion data to the server at regular intervals. Specifically, the process of sending this data to the server is performed using an HTTP request. The input is the operation log and emotion data, and the output is the data transfer to the server.

[0422] Step 3:

[0423] Data storage

[0424] The operation log and emotion data received by the server are stored in a database. Specifically, data including the user ID, operation content, timestamp, and emotion data is inserted into a database (e.g., PostgreSQL). The input is the operation log and emotion data sent to the server, and the output is storage in the database.

[0425] Step 4:

[0426] Data analysis

[0427] The server analyzes the stored operation logs and emotion data to visualize the business flow. Specifically, it retrieves data from the database and generates graphs and charts to visualize frequently occurring operations and specific operation patterns. The input is the operation logs and emotion data in the database, and the output is a graph or chart of the visualized business flow.

[0428] Step 5:

[0429] Anomaly Detection

[0430] The server detects operations that occur abnormally frequently as anomalies. Specifically, it detects anomalies using statistical methods based on the frequency distribution of standard operations. The input is analyzed operation log data, and the output is operation data tagged as anomalies.

[0431] Step 6:

[0432] Hypothesis generation

[0433] The server generates hypotheses based on anomalies. For example, it might create a hypothesis such as, "Frequent inventory checks are due to inappropriate inventory management, which makes workers feel anxious." The input is operation data and emotion data tagged as anomalies, and the output is the generated hypothesis.

[0434] Step 7:

[0435] User notification and feedback collection

[0436] The server notifies the user of the generated hypothesis and collects feedback. Specifically, it presents the user with the question, "Please tell us why inventory check operations are occurring so frequently," and collects the user's answer. The input is the hypothesis and the user's answer, and the output is the user's feedback.

[0437] Step 8:

[0438] Generate business improvement proposals

[0439] The server generates business improvement proposals based on user feedback and emotional data. Specifically, it proposes improvement proposals such as "introducing a dashboard that displays inventory status in real time." The input is user feedback and emotional data, and the output is the generated business improvement proposals.

[0440] Step 9:

[0441] Proposing business improvement plans

[0442] The server presents the generated business improvement proposals to the user. Specifically, it presents detailed information such as the dashboard design and how to use it. The input is the business improvement proposals, and the output is the improvement proposals presented to the user.

[0443] Step 10:

[0444] Monitoring new business processes

[0445] After the business improvement proposal is implemented, the server monitors the usage of the new business flow. Specifically, it monitors the frequency of dashboard use and changes in the user's emotional state. The input is the usage data and emotional data of the new business flow, and the output is the monitoring results.

[0446] Step 11:

[0447] Effectiveness verification

[0448] The server verifies the effectiveness of the new business flow. Specifically, it evaluates items such as "has the number of inventory check operations decreased?" and "has the user's stress level decreased?" The input is the monitoring results, and the output is an evaluation of the verified effectiveness.

[0449] Step 12:

[0450] Final Feedback

[0451] The server then feeds back the final evaluation results to the user. Specifically, it reports that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered users' stress levels." The input is the evaluation result of the effect, and the output is feedback to the user.

[0452] 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.

[0453] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0454] 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.

[0455] [Second embodiment]

[0456] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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."

[0468] The system according to the present invention realizes efficient business operations by analyzing and improving business flow. This system includes a terminal that records operation logs, a server that stores and analyzes the operation logs, and a means for providing feedback to users, and is implemented as follows:

[0469] Recording and sending operation logs

[0470] The terminal records each operation performed by the user in detail. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and timestamp are recorded. The recorded operation log is periodically sent to the server. The transmission is performed, for example, every hour, enabling real-time data collection.

[0471] Saving and analyzing operation logs

[0472] The server stores the received operation logs in a database. Based on the stored operation logs, the server analyzes the business flow. Specifically, it analyzes the operation logs and visualizes frequently occurring operations and patterns. Based on the analysis results, the server detects abnormally frequent operations as anomalies.

[0473] Hypothesis generation and user feedback

[0474] The server automatically generates hypotheses for detected anomalies. For example, it may hypothesize that "frequent inventory checks are caused by improper inventory management." The generated hypotheses are fed back to the user. The user can then provide specific reasons and additional information to improve the accuracy of the hypotheses.

[0475] Generate and present business improvement proposals

[0476] The server generates business improvement proposals based on user feedback. For example, it proposes a "dashboard that displays inventory status in real time." These improvement proposals are presented to the user, who evaluates and decides on them. If the user decides to adopt the improvement proposal, a new business flow is designed based on its contents.

[0477] New workflow monitoring and effectiveness verification

[0478] After the proposed improvements are implemented, the server monitors the usage of the new workflow. Specifically, it monitors the frequency and effectiveness of real-time use of the inventory status dashboard. As a result of the monitoring, it verifies whether or not work efficiency has improved, and provides feedback on the results to the user. For example, it reports specific figures such as, "By introducing the dashboard, the number of inventory check operations has decreased by 50%, improving work efficiency."

[0479] Specific examples

[0480] For example, consider a case where "inventory check" operations are frequently performed in a company's inventory management system. When this system is implemented, the terminal records these operations in detail and sends the log to the server. The server analyzes the data, detects that "inventory check" operations are occurring abnormally frequently, and generates hypotheses about the cause. Based on user feedback, the server proposes a dashboard that displays inventory status in real time. If the user evaluates this and decides to implement it, the dashboard will be used as a new business flow. Finally, the server monitors its effectiveness, and if improvements are confirmed, it will be established as a formal business process.

[0481] In this way, the system according to the present invention realizes efficient and rational business flow, and reduces the workload of the user.

[0482] The processing flow will be explained below.

[0483] Step 1:

[0484] The terminal records user operations in real time. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and a timestamp are recorded.

[0485] Step 2:

[0486] The terminal sends the recorded operation log to the server at regular intervals (for example, every hour), allowing data to be collected in real time.

[0487] Step 3:

[0488] The server stores the received operation logs in a database. The data to be stored includes the user ID, operation details, timestamp, etc.

[0489] Step 4:

[0490] The server periodically analyzes the operation logs stored in the database. The main purpose of the analysis is to grasp the overall picture of each business flow and extract frequently occurring operations and specific patterns.

[0491] Step 5:

[0492] Based on the analysis results, the server detects operations that occur abnormally frequently as anomalies. For example, if the "inventory check" operation occurs abnormally frequently compared to other operations, it will mark it as an anomaly.

[0493] Step 6:

[0494] The server generates hypotheses for detected anomalies, for example, "Inventory checks are occurring frequently because inventory management is not being properly performed."

[0495] Step 7:

[0496] The server notifies the user of the generated hypotheses, for example by presenting the user with a question such as "Please tell me why inventory check operations are occurring so frequently."

[0497] Step 8:

[0498] The user responds to the server's question by providing specific reasons and additional information, such as, "The reason we need to check inventory frequently is to prevent products from running out."

[0499] Step 9:

[0500] The server generates business improvement proposals based on user feedback, such as a "dashboard that displays inventory status in real time."

[0501] Step 10:

[0502] The server presents the generated business improvement proposals to the user, who evaluates them and decides whether to implement them.

[0503] Step 11:

[0504] If the user decides to adopt the proposed improvement, the server designs and implements the new workflow, for example, by introducing a real-time inventory status dashboard.

[0505] Step 12:

[0506] The server monitors the usage of the new workflow, for example, how often the dashboard is used.

[0507] Step 13:

[0508] The server verifies the effectiveness of the new workflow, for example, evaluating whether the "inventory check" operation has decreased since the dashboard was introduced.

[0509] Step 14:

[0510] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the number of inventory check operations has decreased by 50% since the introduction of the dashboard."

[0511] Step 15:

[0512] The user and server then formally establish the new business flow, the effectiveness of which has been confirmed based on the evaluation results, as a business process.

[0513] Example 1

[0514] 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."

[0515] In current business management systems, operation logs are recorded and analyzed separately, without any coordination, making it difficult to grasp the overall picture of business flows. Even when abnormal operations or patterns are detected, the causes and improvement plans are often generated manually, making efficient business improvement difficult. Furthermore, there is a lack of means to properly verify the effects of new business flows after they are introduced, making it difficult to ensure the effectiveness of improvements. There is a need for a system that can solve these issues and efficiently and automatically visualize and improve business flows.

[0516] 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.

[0517] In this invention, the server includes means for saving operation logs, means for analyzing the saved operation logs and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating business improvement plans based on the user responses, means for presenting the business improvement plans to the user, means for monitoring the usage status of the new workflow, means for verifying the effectiveness of the new workflow, and means for providing feedback to the user on the effectiveness of the workflow in concrete numerical values. This makes it possible to grasp the overall picture of the workflow, efficiently and automatically generate business improvement plans, and introduce effective workflows and verify their effectiveness.

[0518] An "operation log" is data that records the content of each operation performed by a user and the time at which it was performed.

[0519] A "server" is a central computer device that receives, stores, analyzes, and processes data sent from terminals, and improves business processes.

[0520] "Business flow" refers to a series of procedures that show the specific flow and process of business.

[0521] An "abnormally frequent operation" refers to an operation that is performed significantly more frequently than in the normal workflow, and is an operation that may be a sign of problems with the efficiency or quality of work.

[0522] A "hypothesis" is a guideline for speculating on possible causes or backgrounds based on detected abnormal operations.

[0523] An "improvement proposal" is a specific proposal for changes to make the current business flow more efficient or rational.

[0524] "Monitoring" is the activity of observing in real time how new business processes and improvement proposals are actually being implemented.

[0525] "Feedback" refers to the provision of information to encourage continuous business improvement by communicating monitoring and analysis results to users.

[0526] "Real-time" refers to a situation in which data is collected and processed immediately, and feedback and responses based on that data are provided without delay.

[0527] The system of the present invention realizes efficient business operations by analyzing and improving business flows. This system includes a terminal that records operation logs, a server that stores and analyzes the operation logs, and a means for providing feedback to users, and is specifically implemented as follows.

[0528] Recording and sending operation logs

[0529] The terminal records each operation performed by the user in detail. When a user performs an "inventory check" operation in the inventory management system, the operation content and timestamp are recorded. This operation log is temporarily stored in local storage or temporary memory. The operation log is then periodically (for example, every hour) sent to the server. The transmission is performed using the HTTP or HTTPS protocol. This makes it possible to collect data in real time.

[0530] Saving and analyzing operation logs

[0531] The server stores the received operation logs in a database (for example, MySQL or PostgreSQL). It then formats the data appropriately according to the database schema. Based on the stored operation logs, the server analyzes the business flow. Specifically, it uses log analysis software (for example, Elasticsearch or Splunk) to visualize frequently occurring operations and patterns. Based on the analysis results, it detects abnormally frequent operations as anomalies.

[0532] Hypothesis generation and user feedback

[0533] The server automatically generates hypotheses for detected anomalies. For example, it may hypothesize that "frequent inventory checks are caused by improper inventory management." A generative AI model (such as GPT-3 or BERT) is used to generate hypotheses. The generated hypotheses are notified to the user via email, dashboard alerts, or a dedicated mobile app. The user receives the notification and can provide specific causes or additional information to improve the accuracy of the hypothesis.

[0534] Generate and present business improvement proposals

[0535] The server generates business improvement proposals based on user feedback. Prompt statements such as "How to reduce inventory check operations" are input into the generative AI model, which then generates ideas for a "dashboard that displays inventory status in real time." These business improvement proposals are then proposed to the user. The proposals can be displayed on the dashboard, sent via email, or presented at a meeting. The user reviews and evaluates the proposals, and if a decision is made to adopt them, a new business flow is specifically designed.

[0536] New workflow monitoring and effectiveness verification

[0537] The server monitors the usage of the new business flow in real time. Specifically, it collects the frequency of dashboard use and operation logs, and also collects feedback from users. The server verifies the effectiveness of the new business flow based on the collected data and generates a report with specific figures, such as "By introducing the dashboard, inventory check operations have decreased by 50%, and business efficiency has improved." The results are fed back to the user, helping to improve business operations.

[0538] Prompt Sentence Examples

[0539] 1. "Please explain a specific example of recording and analyzing operation logs in an inventory management system."

[0540] 2. "Please tell me the detailed flow of the system, including the hypothesis generation and feedback process for improving business processes."

[0541] 3. Please explain the specific steps for generating and evaluating business improvement proposals based on user feedback.

[0542] In this way, the system according to the present invention realizes efficient and rational business flow, and reduces the workload of the user.

[0543] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0544] Step 1:

[0545] The terminal captures each operation performed by the user and generates log data that includes the operation details and a timestamp. As a concrete example, when a user clicks the "Check Stock" button in an inventory management system, the operation details "Check Stock" and the timestamp "YYYY-MM-DD HH:MM:SS" are recorded. This log data is temporarily saved in local storage. The input is the user's operation, and the output is the generated operation log data.

[0546] Step 2:

[0547] The terminal reads operation log data from local storage at regular intervals (for example, every hour) and sends it to the server. HTTP or HTTPS is used as the transmission protocol. The input is the operation log data from local storage, and the output is a transmission completion notification to the server.

[0548] Step 3:

[0549] The server saves the received operation log data in a database (for example, MySQL or PostgreSQL). Before saving, the data is formatted based on the database schema. Specifically, the log data is broken down into fields (operation details, timestamp, etc.) and stored. The input is the received operation log data, and the output is the formatted data saved in the database.

[0550] Step 4:

[0551] The server analyzes the stored operation log data. Log analysis software (such as Elasticsearch or Splunk) is used to visualize frequently occurring operations and patterns. For example, the number of times a specific operation was performed is tallied and displayed as a heat map. The input is database operation log data, and the output is visualized data of the analysis results.

[0552] Step 5:

[0553] The server detects abnormally frequent operations (anomalies) based on the analysis results. For example, if the "inventory check" operation is performed 50% more frequently than usual, it will recognize it as an anomaly. The input is the analysis result data, and the output is a report of the detected anomalies.

[0554] Step 6:

[0555] The server generates hypotheses for the detected anomalies using a generative AI model (e.g., GPT-3 or BERT). For example, it generates a hypothesis such as "The high frequency of inventory checks is due to improper inventory management." The input is the anomaly report, and the output is the generated hypothesis.

[0556] Step 7:

[0557] The server notifies the user of the generated hypotheses via email, dashboard alerts, or a dedicated mobile app. The input is the generated hypotheses, and the output is the completion of the notification to the user.

[0558] Step 8:

[0559] The user provides specific causes and additional information for the received hypothesis. For example, they provide detailed feedback such as "This is because the warehouse management system is outdated." The input is the hypothesis notification, and the output is the user's feedback.

[0560] Step 9:

[0561] The server generates business improvement proposals using a generative AI model based on user feedback. For example, it suggests "introducing a dashboard that displays inventory status in real time." The input is user feedback, and the output is the generated business improvement proposals.

[0562] Step 10:

[0563] The server proposes the generated business improvement proposal to the user. The proposal is made through display on a dashboard, email, or presentation at a meeting. The input is the generated business improvement proposal, and the output is the completed proposal to the user.

[0564] Step 11:

[0565] The user evaluates the proposed business improvement plan and decides whether to implement it. For example, the user may decide to "adopt the introduction of a dashboard." The input is the business improvement plan, and the output is the evaluation result and the decision to implement it.

[0566] Step 12:

[0567] The server monitors the usage status of the new business flow in real time. Specifically, it collects dashboard usage data and operation logs. The input is the usage data of the new business flow, and the output is a monitoring report.

[0568] Step 13:

[0569] The server verifies the effectiveness of the new workflow based on the monitoring results and evaluates it with specific numerical values, such as "Inventory check operations have decreased by 50%, and work efficiency has improved." The input is the monitoring data, and the output is an effectiveness verification report.

[0570] Step 14:

[0571] The server feeds back the effectiveness verification report to the user. It creates a report including specific numerical data and notifies the user. The input is the effectiveness verification report, and the output is the completion of feedback to the user.

[0572] (Application example 1)

[0573] 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."

[0574] Modern logistics centers require highly efficient and precise management. However, manual operation log recording and subsequent data analysis make it difficult to make real-time improvements, limiting the extent to which operational efficiency can be improved. Furthermore, the frequent occurrence of abnormal operations, the time and effort required to identify the causes, and the implementation of improvement proposals can lead to a decline in overall work efficiency.

[0575] 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.

[0576] In this invention, the server includes a means for using a smart device to record operation logs in real time, a means for providing feedback in real time, and a means for presenting specific improvement proposals to workers and determining whether or not to apply them, thereby enabling the rapid analysis and improvement of the work flow within the logistics center and the overall improvement of work efficiency.

[0577] An "operation log" is data that records a series of operations performed by a user.

[0578] "Server" refers to the central system that receives, stores, and analyzes operation logs.

[0579] "Business flow" refers to the series of steps and procedures that a business follows.

[0580] "Real-time feedback" refers to responses and suggestions for improvement that are provided immediately to the user's actions.

[0581] "Smart devices" refer to advanced electronic devices that record operational logs and provide feedback in real time.

[0582] "Abnormal operations" refer to frequent or inappropriate operations that deviate from normal business flow.

[0583] "Hypothesis" refers to a tentative explanation or speculation about the cause of the detected abnormal operation.

[0584] "User" refers to an individual or team that uses the system to carry out work.

[0585] "Improvement proposals" refer to proposals and action plans to improve the efficiency of business flows and operations.

[0586] "Monitoring" refers to the act of watching how new business processes are being used and measuring their effectiveness.

[0587] A "logistics center" refers to a location that manages the storage and delivery of goods.

[0588] The system of the present invention aims to improve the efficiency of operations within a logistics center. This system improves the workflow by recording operation logs, sending and saving them on a server, analyzing them, and presenting improvement proposals to the user.

[0589] Hardware and software configuration

[0590] Hardware:

[0591] 1. Smart devices: Used to record operation logs in real time. Smartphones and smart glasses are examples of such devices.

[0592] 2. Server: A central system that stores the received operation logs, analyzes them, and generates business improvement proposals.

[0593] software:

[0594] 1. Python: This is the main language used to implement the program in this system.

[0595] 2. Flask / Django: Web frameworks used for server-side API integration.

[0596] 3. requests: A library for making HTTP requests.

[0597] 4. Database: A system for storing operation logs and analysis results (e.g., MySQL, PostgreSQL).

[0598] Specific operation of the system

[0599] Recording and sending operation logs

[0600] The smart device terminal records each worker's operation in real time and periodically sends the data to the server. For example, operations such as "start picking" and "check inventory" are recorded.

[0601] Saving and analyzing operation logs

[0602] The server stores the received operation logs in a database and then performs data analysis to detect frequently performed operations and abnormal operations, i.e., operations that deviate from the normal business flow.

[0603] Hypothesis generation and feedback

[0604] The server generates a hypothesis based on the detected abnormal operation. For example, it may hypothesize that "the reason this operation is performed so frequently is due to uncertainty in inventory information." The hypothesis is then fed back to the user in real time. The user can then enter an answer based on the provided hypothesis and send the feedback to the server.

[0605] Proposing business improvement plans

[0606] The server generates specific business improvement proposals based on user feedback and presents them to the user. For example, the proposal might include "introducing a dashboard that displays inventory status in real time."

[0607] New workflow monitoring and effectiveness verification

[0608] After a new workflow is implemented, the server monitors its usage, verifies the extent to which the new workflow contributes to efficiency, and provides feedback to the user in the form of specific figures.

[0609] Specific examples

[0610] For example, if the "inventory check" operation is frequently performed in inventory management at a logistics center, the system records the operation in detail and sends the log to the server. The server analyzes the data, detects that the "inventory check" operation is abnormally frequent, and hypothesizes the cause. Based on user feedback, the server proposes a "dashboard that displays inventory status in real time." The new workflow is then adopted, its usage and effectiveness are monitored, and improvements in operational efficiency are confirmed.

[0611] Prompt Sentence Examples

[0612] "Design an application that records work logs at a logistics center and proposes improvement plans for efficiency. Please include a specific process flow, such as how to record operation logs, how to send and save the logs, how to analyze data, provide feedback, propose business improvement plans, and verify their effectiveness."

[0613] The above is a specific embodiment for carrying out the present invention.

[0614] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0615] Step 1:

[0616] Recording of operation logs

[0617] The terminal uses a smart device (smartphone or smart glasses) to record each operation performed by the worker in detail. The input includes operations performed by the worker, such as "start picking" and "check inventory." A timestamp is assigned to each input operation, making it clear which operation was performed and when. Operation log data is generated as output.

[0618] Step 2:

[0619] Sending operation logs

[0620] The terminal sends the recorded operation log to the server at regular intervals (for example, every hour). The input is the operation log data recorded in step 1. The transmission method is an HTTP request. After transmission, the output is when the server receives the log data.

[0621] Step 3:

[0622] Saving operation logs

[0623] The operation log received by the server is saved in the database. The input is the operation log data received in step 2. An SQL query is used as the saving method. The output is that the operation log data is stored in the database.

[0624] Step 4:

[0625] Analysis of operation logs

[0626] The server analyzes the saved operation logs. The input is the operation log data stored in the database. The analysis methods include frequency analysis and pattern recognition to detect frequently performed operations and abnormal operations. The output is the analysis results, which include abnormal operation patterns and frequently performed operation data.

[0627] Step 5:

[0628] Hypothesis generation

[0629] The server generates hypotheses about abnormal operations based on the analysis results. The input is the analysis result data from step 4. Hypotheses are automatically generated using an AI model. The output is a hypothesis such as "Inventory check operations are being performed frequently due to problems with inventory management."

[0630] Step 6:

[0631] Feedback Notifications

[0632] The server notifies the user of the generated hypothesis. The input is the hypothesis generated in step 5. Notification methods include real-time display on a smart device or sending an alert. The output is the notification result to the user.

[0633] Step 7:

[0634] Collecting user responses

[0635] The user inputs a response to the feedback provided to the server. The input is additional data and comments from the user. The output is when the server receives the response data.

[0636] Step 8:

[0637] Generate business improvement proposals

[0638] The server generates business improvement proposals based on the user's responses. The input is the user response data received in step 7. Taking into account past log data and user feedback, specific improvement proposals are created using AI. The output is improvement proposals such as a "dashboard that displays inventory status in real time."

[0639] Step 9:

[0640] Proposing business improvement plans

[0641] The server presents the generated business improvement proposals to the user. The input is the business improvement proposals generated in step 8. Notification methods include displaying a dashboard on a smart device and sending implementation proposals. The output is the improvement proposals presented to the user.

[0642] Step 10:

[0643] New Workflow Monitoring

[0644] The server monitors the usage of the new business flow. The input is the implementation data of the new business flow. The log data is analyzed in real time to verify the frequency of use and effectiveness. The output is the effectiveness measurement data as a result of the monitoring.

[0645] Step 11:

[0646] Effectiveness verification

[0647] The server verifies the effectiveness of the new business flow. The input is the monitoring data obtained in step 10. The data is compared and analyzed to evaluate improvements in business efficiency and changes in operation frequency. The output is a concrete result of the verification of effectiveness, such as "business efficiency has improved by 50%."

[0648] Step 12:

[0649] Providing Feedback

[0650] The server feeds back the results of the effectiveness verification to the user. The input is the results of the effectiveness verification obtained in step 11. Feedback methods include periodic reports and real-time notifications. The output is the feedback results to the user.

[0651] 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.

[0652] The system of the present invention achieves more effective business improvement by combining an emotion engine that recognizes user emotions. In addition to recording and analyzing operation logs, this system also collects and analyzes user emotion data, which is used to generate and present business improvement proposals. The specific processing flow is explained below.

[0653] Recording and sending operation logs

[0654] The terminal records each operation performed by the user in detail. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and timestamp are recorded. In addition, the emotion engine analyzes the user's facial expressions and voice during the operation and records them as emotion data. The recorded operation log and emotion data are sent to the server at regular intervals (for example, every hour). This allows data to be collected in real time.

[0655] Saving and analyzing operation logs and emotion data

[0656] The server stores the received operation logs and emotion data in a database. The data to be stored includes user IDs, operation details, timestamps, and emotion data. The server analyzes the business flow based on this data and visualizes frequently occurring operations and specific patterns.

[0657] Anomaly Detection and Hypothesis Generation

[0658] The server uses the analysis results to detect operations that occur abnormally frequently as anomalies. For example, if the "check inventory" operation occurs abnormally frequently compared to other operations, it marks it as an anomaly. In addition, it uses emotion data provided by the emotion engine to analyze the user's emotional state at the time the anomaly occurred. For example, if anxiety or stress is high, this will also be included in the data.

[0659] The server generates hypotheses for anomalies, such as "frequent stock checks are due to poor inventory management and users feeling anxious," which allows for the emotional factors behind the problem to be taken into account.

[0660] User feedback and business improvement proposal generation

[0661] The server notifies the user of the generated hypothesis. For example, it presents the user with a question such as, "Please tell me why inventory check operations are occurring so frequently." The user responds by providing specific reasons and additional information. For example, the user might answer, "Inventory checks are necessary frequently to prevent product shortages."

[0662] The server generates business improvement proposals based on the user's feedback and emotions. For example, it suggests a "dashboard that displays inventory status in real time." It also adjusts the content and presentation method of the proposals by taking into account the emotional data. For example, if the user is prone to stress, it will devise a more appropriate wording for the proposals.

[0663] Proposing and monitoring business improvement proposals

[0664] The server presents the generated business improvement proposals to the user. If the user evaluates the proposals and decides to implement them, the server designs and implements the new business flow. For example, it introduces a real-time inventory status dashboard.

[0665] New workflow monitoring and effectiveness verification

[0666] After the proposed improvements are implemented, the server monitors the usage of the new workflow, for example, by monitoring how frequently the dashboard is used and how the user's emotional state changes when operating it.

[0667] The server verifies the effectiveness of the new workflow. For example, it evaluates whether the number of "inventory check" operations has decreased and whether users' emotional state has improved after the dashboard was introduced.

[0668] Final feedback and establishing the flow

[0669] The server then provides the final evaluation results as feedback to the user. For example, it might report, "By introducing the dashboard, inventory check operations have decreased by 50%, and user stress levels have also decreased." Based on the evaluation results, the user and server then formally establish the new business flow as a business process.

[0670] In this way, the system according to the present invention not only realizes the efficiency and streamlining of the workflow, but also realizes comprehensive business improvement that takes into consideration the emotional aspects of the user.

[0671] The processing flow will be explained below.

[0672] Step 1:

[0673] The device records user operations in real time. For example, when a user performs an "inventory check" operation, the device records the operation details and a timestamp.

[0674] Step 2:

[0675] The device analyzes the user's emotional state using an emotion engine. For example, it analyzes the user's facial expressions and voice, and generates emotion data such as anxiety, stress, and satisfaction.

[0676] Step 3:

[0677] The device sends operation logs and emotion data to the server at regular intervals (for example, every hour), allowing data to be collected and sent in real time.

[0678] Step 4:

[0679] The server stores the received operation log and emotion data in a database. The stored data includes the user ID, operation details, timestamp, and emotion data.

[0680] Step 5:

[0681] The server analyzes the operation logs and emotion data stored in the database. The purpose of the analysis is to understand the overall picture of the user's workflow and extract frequently occurring operations and specific emotion patterns.

[0682] Step 6:

[0683] Based on the analysis results, the server detects operations that are abnormally frequent as anomalies. For example, if the "inventory check" operation is abnormally frequent compared to other operations, it will mark it as an anomaly.

[0684] Step 7:

[0685] The server also references the user's emotional data when an anomaly occurs and generates a hypothesis. For example, it may hypothesize that "inventory checks are being conducted frequently because inventory management is not being properly performed and users are feeling anxious."

[0686] Step 8:

[0687] The server notifies the user of the generated hypothesis. For example, it displays a question to the user such as "Please tell me why inventory check operations are occurring so frequently."

[0688] Step 9:

[0689] The user responds to the server's question by providing specific reasons and additional information, such as "The reason we need to check inventory frequently is to prevent products from running out."

[0690] Step 10:

[0691] The server generates business improvement proposals based on user feedback and emotional data, such as a dashboard that displays inventory status in real time.

[0692] Step 11:

[0693] The server presents the generated business improvement proposals to the user, who evaluates them and decides whether to implement them.

[0694] Step 12:

[0695] If the user decides to adopt the proposed improvement, the server designs and implements the new workflow, for example, by introducing a real-time inventory status dashboard.

[0696] Step 13:

[0697] The server monitors the usage of the new workflow, specifically how frequently the dashboard is used and how the user's emotional state changes when operating it.

[0698] Step 14:

[0699] The server verifies the effectiveness of the new workflow, for example, evaluating whether the number of "inventory check" operations has decreased and whether the user's emotional state has improved after the dashboard was introduced.

[0700] Step 15:

[0701] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered users' stress levels."

[0702] Step 16:

[0703] Based on the evaluation results, the user and the server establish the new workflow as a formal business process. In this way, the present invention aims to improve the efficiency of the workflow and the user's emotional state.

[0704] Example 2

[0705] 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."

[0706] Conventional business improvement systems proposed improvement measures based on the analysis of operation logs, but did not take into account the user's emotional state. As a result, improvement measures were sometimes proposed that ignored psychological factors, and were unable to reduce the user's stress and anxiety. Furthermore, when verifying the effectiveness of new business flows after their implementation, emotional data was not taken into account in the evaluation. These problems need to be solved.

[0707] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for recording an operation log, means for transmitting the operation log to the server, means for saving the operation log, means for analyzing the saved operation log and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating business improvement proposals based on the user responses, means for presenting the business improvement proposals to the user, means for collecting and analyzing emotional data, means for sending the operation log including the emotional data to the server, means for analyzing the emotional data during operations and associating it with anomalies, means for adjusting the business improvement proposals taking the emotional data into consideration, means for monitoring the usage status and emotional state of the new workflow, means for verifying the effectiveness of the new workflow, and means for feeding back the verification results to the user. This makes it possible to propose business improvements that take the user's emotional state into consideration, and also enables comprehensive evaluation including emotional data when verifying the effectiveness of a new workflow after its introduction.

[0708] An "operation log" refers to historical information about operations performed by a user within the system, and specifically includes the operation details, user ID, timestamp, etc.

[0709] "Emotion data" refers to information about the user's psychological state analyzed from their facial expressions and voice using an emotion engine, and specifically refers to data that quantifies emotional states such as anxiety, stress, and joy.

[0710] "Server" refers to a computer system that operates on a network and receives, stores, analyzes, and provides feedback on data.

[0711] A "terminal" refers to a hardware device that a user operates, specifically an electronic device such as a computer or smartphone.

[0712] "Business flow" refers to a series of steps or procedures for carrying out a specific business operation.

[0713] "Analysis" refers to the process of processing collected data to detect specific patterns or anomalies.

[0714] An "anomaly" refers to an operation that occurs abnormally frequently and deviates from normal operating patterns.

[0715] A "hypothesis" refers to a prediction or theory that is made to estimate the cause of an anomaly.

[0716] "Feedback" refers to the evaluation results and suggestions that the system provides to the user.

[0717] "Monitoring" refers to the process of continuously monitoring the usage of the new workflow and the emotional state of the user.

[0718] "Improvement proposals" refer to specific proposals aimed at streamlining business processes and improving user experiences.

[0719] The system of the present invention collects and analyzes user operation logs and emotional data to help improve business operations, which not only improves operational efficiency but also reduces the psychological burden on users.

[0720] Hardware and Software Configuration

[0721] Hardware

[0722] Device: A device operated by a user. This can include desktop computers, laptops, smartphones, etc. These devices are equipped with cameras and microphones to capture facial and audio data from the user.

[0723] Server: A central system that collects, stores, and analyzes data. It is equipped with a high-performance database and analysis engine.

[0724] software

[0725] Emotion engine: Software that runs on the device and uses the camera and microphone to analyze the user's facial expressions and voice to generate emotion data.

[0726] Database management system: Runs on the server and stores and manages operation logs and emotion data.

[0727] Analysis engine: Software that runs on a server and visualizes business processes and detects anomalies based on collected data.

[0728] Generative AI model: Generates business improvement proposals based on user feedback.

[0729] Data processing and calculation

[0730] The device records the user's operation log in real time and uses an emotion engine to collect emotional data during the operation. For example, when a user performs an "inventory check" operation, the degree of "anxiety" or "stress" is recorded as emotional data along with the operation details.

[0731] The collected data is sent to a server at regular intervals. The server stores the received data in a database, and an analysis engine analyzes the business flow based on the stored data. This analysis makes it possible to visualize frequently occurring operations and specific patterns.

[0732] Based on the analysis results, the server detects abnormally frequent operations (anomalies). It also uses emotional data to analyze the user's emotional state at the time the anomaly occurred and evaluates whether the anomaly is due to psychological factors. For example, if the "inventory check" operation is performed frequently and the user feels high stress when doing so, it will be marked as an anomaly.

[0733] The server uses a generative AI model to generate a hypothesis about the anomaly and prompts the user to confirm the hypothesis, for example, "Please tell me why inventory check operations are occurring so frequently."

[0734] Based on user feedback, the server generates business improvement proposals. These proposals are chosen with appropriate content and expressions, taking into account emotional data. For example, when proposing a "dashboard that displays inventory status in real time," gentle expressions are used to avoid causing excessive stress to the user.

[0735] Examples of concrete examples and prompts

[0736] As a specific usage scenario, consider a case where a user uses an inventory management system and frequently performs "inventory check" operations. At this time, the emotion engine analyzes the user's facial expressions and voice to indicate that "anxiety" and "stress" are increasing.

[0737] The collected operation logs and emotion data are sent to a server, which stores them in a database and analyzes business flows and anomalies. The server detects an abnormally high number of "inventory check" operations and hypothesizes that "frequent inventory checks are occurring because inventory management is not being done properly and users are feeling anxious."

[0738] Based on this hypothesis, the generative AI model asks the user for feedback, displaying a prompt saying, "Please tell us why you are frequently checking inventory." The specific feedback received from the user is, "The reason why inventory checks are necessary so frequently is to prevent products from running out."

[0739] Based on this feedback, the server generates a proposal for a dashboard that displays inventory status in real time and presents it to the user in a way that is thoughtful and stress-free for the user.

[0740] As described above, the present invention is a system that utilizes operation logs and emotion data to propose business improvements and verify their effectiveness.

[0741] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0742] Step 1: Recording operational logs

[0743] The device records all operations performed by the user. When a user performs an operation such as "check inventory," the operation details, user ID, and timestamp are saved as a log.

[0744] Input: User action (e.g., clicking the "Check stock" button)

[0745] Data processing: Collection of operation details, user ID, and timestamp

[0746] Output: Operation log (e.g. "Check stock", user ID, timestamp)

[0747] Step 2: Collect and analyze emotion data

[0748] The device collects the user's facial expressions and voice data using a camera and microphone, and an emotion engine analyzes this data to generate emotion data.

[0749] Input: User's facial expressions and voice

[0750] Data processing: Analyze facial expressions and voice to determine emotional state (e.g., "anxiety" 80%, "stress" 60%)

[0751] Output: Emotion data (e.g., "anxiety" 80%, "stress" 60%)

[0752] Step 3: Sending data

[0753] The device sends operation logs and emotion data to the server at regular intervals.

[0754] Input: Operation log, emotion data

[0755] Data processing: Converting data into packets

[0756] Output: Send data to the server

[0757] Step 4: Save your data

[0758] The server stores the received data in a database, including the user ID, operation details, timestamp, and emotion data.

[0759] Input: Operation log, emotion data

[0760] Data processing: Insertion into database

[0761] Output: Update record in database

[0762] Step 5: Analyze the workflow

[0763] The server analyzes the business flow based on the stored data, for example, extracting and visualizing frequently occurring operations.

[0764] Input: Database operation log data

[0765] Data processing: Calculation and visualization of frequency distribution

[0766] Output: Visualized workflow (e.g. heat map)

[0767] Step 6: Anomaly detection

[0768] Based on the analysis results, the server detects abnormally frequent operations as anomalies.

[0769] Input: Workflow analysis results

[0770] Data processing: Detecting anomalies using statistical methods

[0771] Output: Anomaly list (e.g., "Stock Check" is abnormally high)

[0772] Step 7: Hypothesis generation

[0773] The server generates hypotheses for anomalies, such as "frequent inventory checks are occurring because users are feeling anxious" based on emotional data.

[0774] Input: Anomaly list, emotion data

[0775] Data processing: linking anomalies with emotional states, generating hypotheses

[0776] Output: Hypothesis (e.g., "The reason people check their inventory so frequently is because they have problems with inventory management and are feeling anxious")

[0777] Step 8: Get user feedback

[0778] The server notifies the user of the generated hypothesis and asks for feedback, for example by displaying a prompt such as "Please tell us why inventory check operations are occurring so frequently."

[0779] Input: Hypothesis

[0780] Data processing: Prompt sentence generation

[0781] Output: User notification (e.g. "Please tell me why inventory check operations are occurring so frequently")

[0782] Step 9: Generate business improvement proposals

[0783] The server generates business improvement proposals based on user feedback and emotional data, such as a dashboard that displays inventory status in real time.

[0784] Input: User feedback, emotion data

[0785] Data processing: Generating business improvement proposals that take into account feedback and emotional data

[0786] Output: Business improvement proposals (e.g., "Implementation of a real-time inventory dashboard")

[0787] Step 10: Propose improvements

[0788] The server presents the generated business improvement proposals to the user, for example, recommending the introduction of a dashboard that displays inventory status in real time.

[0789] Input: Business improvement proposal

[0790] Data processing: Message conversion of proposal content

[0791] Output: Suggestion notification to the user (e.g. "We recommend you install the real-time inventory dashboard")

[0792] Step 11: Monitoring the new workflow

[0793] After the proposed improvements are implemented, the server monitors the usage of the new workflow and the user's emotional state.

[0794] Input: New business flow usage log, emotion data

[0795] Data processing: Collection and analysis of usage and sentiment data

[0796] Output: New business flow evaluation report

[0797] Step 12: Verify the effect

[0798] The server verifies the effectiveness of the new workflow, for example, whether the number of "inventory check" operations has decreased after the dashboard was introduced, or whether the user's emotional state has improved.

[0799] Input: New Workflow Evaluation Report

[0800] Data processing: Before and after comparison, effect verification

[0801] Output: Verification results (e.g., "Inventory check operations decreased by 50%, stress levels decreased")

[0802] Step 13: Final feedback

[0803] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered user stress levels."

[0804] Input: Validation result

[0805] Data processing: feedback message generation

[0806] Output: Final report to the user

[0807] Step 14: Establishing the workflow

[0808] The user and server then formally establish the new business flow, the effectiveness of which has been confirmed based on the evaluation results, as a business process.

[0809] Input: Final report

[0810] Data processing: Setting up formal business flow

[0811] Output: Establishing a new workflow

[0812] In this way, specific input, data processing, and output are performed at each step, resulting in efficient business improvement and an improvement in the user's emotional state across the entire system.

[0813] (Application example 2)

[0814] 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."

[0815] Improving operational efficiency at logistics centers is an important issue for many companies. In particular, more effective operational improvements can be expected by considering the emotional aspects of workers in addition to their behavior. However, conventional systems have difficulty effectively utilizing data on worker emotions, resulting in only partial improvements to operational flow. Furthermore, when the cause of abnormal operations is due to emotions, there is also the issue of being unable to accurately identify the cause and propose improvement measures.

[0816] The identification process by the identification 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 recording an operation log, means for transmitting the operation log to the server, means for saving the operation log, means for analyzing the saved operation log and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating workflow improvement plans based on the user responses, means for presenting the workflow improvement plans to the user, means for monitoring the usage status of the new workflow, means for verifying the effectiveness of the new workflow, means for providing feedback on the verification results to the user, means for collecting user emotion data, means for analyzing the collected emotion data, means for using the emotion data to generate workflow improvement plans, and means for generating workflow improvement plans that take emotional factors into account based on the analysis results. This improves the efficiency of the workflow at the logistics center and enables comprehensive workflow improvement that also takes the emotions of workers into account.

[0817] An "operation log" is a detailed record of each operation a user performs within the system.

[0818] "Emotion data" refers to data relating to the user's emotional state, such as information analyzed from facial expressions and voice.

[0819] The "server" is a central computing device that collects and analyzes operation logs and emotion data, and generates and presents business improvement proposals.

[0820] "Visualization" is the visual presentation of data, making specific patterns and anomalies visible.

[0821] An "anomaly" refers to an abnormal operation or behavior that deviates from normal operating patterns.

[0822] A "hypothesis" is a possible explanation or theory as to why an anomaly occurs.

[0823] "Business improvement proposals" are specific proposals and measures to streamline or improve the current business flow.

[0824] "Feedback" refers to the user's reaction and evaluation of the analysis results and improvement proposals.

[0825] "Monitoring" is the activity of continuously observing the status of a system or process.

[0826] "Effectiveness verification" is the process of evaluating whether the business improvement plan that has been implemented is actually having the expected effect.

[0827] The "Logistics Center Business Improvement Assistant" system of the present invention uses smartphones or smart glasses to collect operation logs and emotional data of workers working in a logistics center, and analyzes the data on a server to improve business efficiency.

[0828] System Program

[0829] The terminal has the function of recording the worker's operation log and sending it to the server. Specifically, when a worker performs an operation such as "start picking," the operation details and timestamp are recorded. At the same time, the terminal's camera is used to capture the worker's facial expression, and an emotion engine analyzes the worker's emotional state (e.g., anxiety, stress) from the facial expression. This data is periodically sent to the server.

[0830] Hardware and software used

[0831] The hardware used is a smartphone or smart glasses (e.g., Google Glass), and the camera built into these devices is used. The software used is an emotion recognition library (e.g., Emotion Recognition Library), a server-side data processing engine (e.g., an API built with Python or Flask), and a database (e.g., PostgreSQL).

[0832] Data processing and calculation

[0833] The server stores the received operation logs and emotion data in a database. The stored data includes user IDs, operation details, timestamps, and emotion data. The server analyzes this data and uses it to visualize business processes. For example, it identifies frequently occurring operations and specific patterns and displays them as graphs and charts.

[0834] Hypothesis generation and business improvement proposals

[0835] The server detects abnormally frequent operations (anomalies) from the analysis results and generates a hypothesis based on them. For example, it may hypothesize that "inventory checks are being performed frequently because inventory management is not being performed properly." This hypothesis is notified to the user, and specific reasons and additional information are collected. The server then generates business improvement proposals based on the user's answers and emotion data and presents them to the user.

[0836] Monitoring and effectiveness verification

[0837] After the proposed business improvement is implemented, the server monitors the usage of the new business flow. For example, it monitors how frequently a dashboard displaying real-time inventory status is used and how the user's emotional state changes when operating it. To verify the effectiveness of the new business flow, it also evaluates improvements in work efficiency and changes in the user's stress level.

[0838] Examples and prompts

[0839] For example, when a worker is picking items, the smart glasses recognize their movements and facial expressions and record them as emotion data. An example of a prompt for emotion analysis is as follows:

[0840] "Analyzing emotions from facial photos of workers taken with a smartphone camera"

[0841] In this way, the logistics center business improvement assistant system of the present invention streamlines the business flow of a logistics center and realizes comprehensive business improvement that also takes into account the emotional aspects of workers.

[0842] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0843] Step 1:

[0844] Operation log and emotional data recording

[0845] The terminal records the worker's operation log and emotional data. Specifically, when a worker performs an operation such as "start picking" using a smartphone or smart glasses, the operation details and timestamp are recorded. At the same time, the terminal's camera captures the worker's facial expression, and an emotion engine analyzes the facial expression to determine emotional data (e.g., anxiety, stress). The input is the worker's operation details and facial image data, and the output is the operation log and emotional data.

[0846] Step 2:

[0847] Sending data

[0848] The device sends the recorded operation log and emotion data to the server at regular intervals. Specifically, the process of sending this data to the server is performed using an HTTP request. The input is the operation log and emotion data, and the output is the data transfer to the server.

[0849] Step 3:

[0850] Data storage

[0851] The operation log and emotion data received by the server are stored in a database. Specifically, data including the user ID, operation content, timestamp, and emotion data is inserted into a database (e.g., PostgreSQL). The input is the operation log and emotion data sent to the server, and the output is storage in the database.

[0852] Step 4:

[0853] Data analysis

[0854] The server analyzes the stored operation logs and emotion data to visualize the business flow. Specifically, it retrieves data from the database and generates graphs and charts to visualize frequently occurring operations and specific operation patterns. The input is the operation logs and emotion data in the database, and the output is a graph or chart of the visualized business flow.

[0855] Step 5:

[0856] Anomaly Detection

[0857] The server detects operations that occur abnormally frequently as anomalies. Specifically, it detects anomalies using statistical methods based on the frequency distribution of standard operations. The input is analyzed operation log data, and the output is operation data tagged as anomalies.

[0858] Step 6:

[0859] Hypothesis generation

[0860] The server generates hypotheses based on anomalies. For example, it might create a hypothesis such as, "Frequent inventory checks are due to inappropriate inventory management, which makes workers feel anxious." The input is operation data and emotion data tagged as anomalies, and the output is the generated hypothesis.

[0861] Step 7:

[0862] User notification and feedback collection

[0863] The server notifies the user of the generated hypothesis and collects feedback. Specifically, it presents the user with the question, "Please tell us why inventory check operations are occurring so frequently," and collects the user's answer. The input is the hypothesis and the user's answer, and the output is the user's feedback.

[0864] Step 8:

[0865] Generate business improvement proposals

[0866] The server generates business improvement proposals based on user feedback and emotional data. Specifically, it proposes improvement proposals such as "introducing a dashboard that displays inventory status in real time." The input is user feedback and emotional data, and the output is the generated business improvement proposals.

[0867] Step 9:

[0868] Proposing business improvement plans

[0869] The server presents the generated business improvement proposals to the user. Specifically, it presents detailed information such as the dashboard design and how to use it. The input is the business improvement proposals, and the output is the improvement proposals presented to the user.

[0870] Step 10:

[0871] Monitoring new business processes

[0872] After the business improvement proposal is implemented, the server monitors the usage of the new business flow. Specifically, it monitors the frequency of dashboard use and changes in the user's emotional state. The input is the usage data and emotional data of the new business flow, and the output is the monitoring results.

[0873] Step 11:

[0874] Effectiveness verification

[0875] The server verifies the effectiveness of the new business flow. Specifically, it evaluates items such as "has the number of inventory check operations decreased?" and "has the user's stress level decreased?" The input is the monitoring results, and the output is an evaluation of the verified effectiveness.

[0876] Step 12:

[0877] Final Feedback

[0878] The server then feeds back the final evaluation results to the user. Specifically, it reports that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered users' stress levels." The input is the evaluation result of the effect, and the output is feedback to the user.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] [Third embodiment]

[0883] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0884] 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.

[0885] 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).

[0886] 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.

[0887] 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.

[0888] 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).

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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."

[0895] The system according to the present invention realizes efficient business operations by analyzing and improving business flow. This system includes a terminal that records operation logs, a server that stores and analyzes the operation logs, and a means for providing feedback to users, and is implemented as follows:

[0896] Recording and sending operation logs

[0897] The terminal records each operation performed by the user in detail. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and timestamp are recorded. The recorded operation log is periodically sent to the server. The transmission is performed, for example, every hour, enabling real-time data collection.

[0898] Saving and analyzing operation logs

[0899] The server stores the received operation logs in a database. Based on the stored operation logs, the server analyzes the business flow. Specifically, it analyzes the operation logs and visualizes frequently occurring operations and patterns. Based on the analysis results, the server detects abnormally frequent operations as anomalies.

[0900] Hypothesis generation and user feedback

[0901] The server automatically generates hypotheses for detected anomalies. For example, it may hypothesize that "frequent inventory checks are caused by improper inventory management." The generated hypotheses are fed back to the user. The user can then provide specific reasons and additional information to improve the accuracy of the hypotheses.

[0902] Generate and present business improvement proposals

[0903] The server generates business improvement proposals based on user feedback. For example, it proposes a "dashboard that displays inventory status in real time." These improvement proposals are presented to the user, who evaluates and decides on them. If the user decides to adopt the improvement proposal, a new business flow is designed based on its contents.

[0904] New workflow monitoring and effectiveness verification

[0905] After the proposed improvements are implemented, the server monitors the usage of the new workflow. Specifically, it monitors the frequency and effectiveness of real-time use of the inventory status dashboard. As a result of the monitoring, it verifies whether or not work efficiency has improved, and provides feedback on the results to the user. For example, it reports specific figures such as, "By introducing the dashboard, the number of inventory check operations has decreased by 50%, improving work efficiency."

[0906] Specific examples

[0907] For example, consider a case where "inventory check" operations are frequently performed in a company's inventory management system. When this system is implemented, the terminal records these operations in detail and sends the log to the server. The server analyzes the data, detects that "inventory check" operations are occurring abnormally frequently, and generates hypotheses about the cause. Based on user feedback, the server proposes a dashboard that displays inventory status in real time. If the user evaluates this and decides to implement it, the dashboard will be used as a new business flow. Finally, the server monitors its effectiveness, and if improvements are confirmed, it will be established as a formal business process.

[0908] In this way, the system according to the present invention realizes efficient and rational business flow, and reduces the workload of the user.

[0909] The processing flow will be explained below.

[0910] Step 1:

[0911] The terminal records user operations in real time. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and a timestamp are recorded.

[0912] Step 2:

[0913] The terminal sends the recorded operation log to the server at regular intervals (for example, every hour), allowing data to be collected in real time.

[0914] Step 3:

[0915] The server stores the received operation logs in a database. The data to be stored includes the user ID, operation details, timestamp, etc.

[0916] Step 4:

[0917] The server periodically analyzes the operation logs stored in the database. The main purpose of the analysis is to grasp the overall picture of each business flow and extract frequently occurring operations and specific patterns.

[0918] Step 5:

[0919] Based on the analysis results, the server detects operations that occur abnormally frequently as anomalies. For example, if the "inventory check" operation occurs abnormally frequently compared to other operations, it will mark it as an anomaly.

[0920] Step 6:

[0921] The server generates hypotheses for detected anomalies, for example, "Inventory checks are occurring frequently because inventory management is not being properly performed."

[0922] Step 7:

[0923] The server notifies the user of the generated hypotheses, for example by presenting the user with a question such as "Please tell me why inventory check operations are occurring so frequently."

[0924] Step 8:

[0925] The user responds to the server's question by providing specific reasons and additional information, such as, "The reason we need to check inventory frequently is to prevent products from running out."

[0926] Step 9:

[0927] The server generates business improvement proposals based on user feedback, such as a "dashboard that displays inventory status in real time."

[0928] Step 10:

[0929] The server presents the generated business improvement proposals to the user, who evaluates them and decides whether to implement them.

[0930] Step 11:

[0931] If the user decides to adopt the proposed improvement, the server designs and implements the new workflow, for example, by introducing a real-time inventory status dashboard.

[0932] Step 12:

[0933] The server monitors the usage of the new workflow, for example, how often the dashboard is used.

[0934] Step 13:

[0935] The server verifies the effectiveness of the new workflow, for example, evaluating whether the "inventory check" operation has decreased since the dashboard was introduced.

[0936] Step 14:

[0937] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the number of inventory check operations has decreased by 50% since the introduction of the dashboard."

[0938] Step 15:

[0939] The user and server then formally establish the new business flow, the effectiveness of which has been confirmed based on the evaluation results, as a business process.

[0940] Example 1

[0941] 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."

[0942] In current business management systems, operation logs are recorded and analyzed separately, without any coordination, making it difficult to grasp the overall picture of business flows. Even when abnormal operations or patterns are detected, the causes and improvement plans are often generated manually, making efficient business improvement difficult. Furthermore, there is a lack of means to properly verify the effects of new business flows after they are introduced, making it difficult to ensure the effectiveness of improvements. There is a need for a system that can solve these issues and efficiently and automatically visualize and improve business flows.

[0943] 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.

[0944] In this invention, the server includes means for saving operation logs, means for analyzing the saved operation logs and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating business improvement plans based on the user responses, means for presenting the business improvement plans to the user, means for monitoring the usage status of the new workflow, means for verifying the effectiveness of the new workflow, and means for providing feedback to the user on the effectiveness of the workflow in concrete numerical values. This makes it possible to grasp the overall picture of the workflow, efficiently and automatically generate business improvement plans, and introduce effective workflows and verify their effectiveness.

[0945] An "operation log" is data that records the content of each operation performed by a user and the time at which it was performed.

[0946] A "server" is a central computer device that receives, stores, analyzes, and processes data sent from terminals, and improves business processes.

[0947] "Business flow" refers to a series of procedures that show the specific flow and process of business.

[0948] An "abnormally frequent operation" refers to an operation that is performed significantly more frequently than in the normal workflow, and is an operation that may be a sign of problems with the efficiency or quality of work.

[0949] A "hypothesis" is a guideline for speculating on possible causes or backgrounds based on detected abnormal operations.

[0950] An "improvement proposal" is a specific proposal for changes to make the current business flow more efficient or rational.

[0951] "Monitoring" is the activity of observing in real time how new business processes and improvement proposals are actually being implemented.

[0952] "Feedback" refers to the provision of information to encourage continuous business improvement by communicating monitoring and analysis results to users.

[0953] "Real-time" refers to a situation in which data is collected and processed immediately, and feedback and responses based on that data are provided without delay.

[0954] The system of the present invention realizes efficient business operations by analyzing and improving business flows. This system includes a terminal that records operation logs, a server that stores and analyzes the operation logs, and a means for providing feedback to users, and is specifically implemented as follows.

[0955] Recording and sending operation logs

[0956] The terminal records each operation performed by the user in detail. When a user performs an "inventory check" operation in the inventory management system, the operation content and timestamp are recorded. This operation log is temporarily stored in local storage or temporary memory. The operation log is then periodically (for example, every hour) sent to the server. The transmission is performed using the HTTP or HTTPS protocol. This makes it possible to collect data in real time.

[0957] Saving and analyzing operation logs

[0958] The server stores the received operation logs in a database (for example, MySQL or PostgreSQL). It then formats the data appropriately according to the database schema. Based on the stored operation logs, the server analyzes the business flow. Specifically, it uses log analysis software (for example, Elasticsearch or Splunk) to visualize frequently occurring operations and patterns. Based on the analysis results, it detects abnormally frequent operations as anomalies.

[0959] Hypothesis generation and user feedback

[0960] The server automatically generates hypotheses for detected anomalies. For example, it may hypothesize that "frequent inventory checks are caused by improper inventory management." A generative AI model (such as GPT-3 or BERT) is used to generate hypotheses. The generated hypotheses are notified to the user via email, dashboard alerts, or a dedicated mobile app. The user receives the notification and can provide specific causes or additional information to improve the accuracy of the hypothesis.

[0961] Generate and present business improvement proposals

[0962] The server generates business improvement proposals based on user feedback. Prompt statements such as "How to reduce inventory check operations" are input into the generative AI model, which then generates ideas for a "dashboard that displays inventory status in real time." These business improvement proposals are then proposed to the user. The proposals can be displayed on the dashboard, sent via email, or presented at a meeting. The user reviews and evaluates the proposals, and if a decision is made to adopt them, a new business flow is specifically designed.

[0963] New workflow monitoring and effectiveness verification

[0964] The server monitors the usage of the new business flow in real time. Specifically, it collects the frequency of dashboard use and operation logs, and also collects feedback from users. The server verifies the effectiveness of the new business flow based on the collected data and generates a report with specific figures, such as "By introducing the dashboard, inventory check operations have decreased by 50%, and business efficiency has improved." The results are fed back to the user, helping to improve business operations.

[0965] Prompt Sentence Examples

[0966] 1. "Please explain a specific example of recording and analyzing operation logs in an inventory management system."

[0967] 2. "Please tell me the detailed flow of the system, including the hypothesis generation and feedback process for improving business processes."

[0968] 3. Please explain the specific steps for generating and evaluating business improvement proposals based on user feedback.

[0969] In this way, the system according to the present invention realizes efficient and rational business flow, and reduces the workload of the user.

[0970] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0971] Step 1:

[0972] The terminal captures each operation performed by the user and generates log data that includes the operation details and a timestamp. As a concrete example, when a user clicks the "Check Stock" button in an inventory management system, the operation details "Check Stock" and the timestamp "YYYY-MM-DD HH:MM:SS" are recorded. This log data is temporarily saved in local storage. The input is the user's operation, and the output is the generated operation log data.

[0973] Step 2:

[0974] The terminal reads operation log data from local storage at regular intervals (for example, every hour) and sends it to the server. HTTP or HTTPS is used as the transmission protocol. The input is the operation log data from local storage, and the output is a transmission completion notification to the server.

[0975] Step 3:

[0976] The server saves the received operation log data in a database (for example, MySQL or PostgreSQL). Before saving, the data is formatted based on the database schema. Specifically, the log data is broken down into fields (operation details, timestamp, etc.) and stored. The input is the received operation log data, and the output is the formatted data saved in the database.

[0977] Step 4:

[0978] The server analyzes the stored operation log data. Log analysis software (such as Elasticsearch or Splunk) is used to visualize frequently occurring operations and patterns. For example, the number of times a specific operation was performed is tallied and displayed as a heat map. The input is database operation log data, and the output is visualized data of the analysis results.

[0979] Step 5:

[0980] The server detects abnormally frequent operations (anomalies) based on the analysis results. For example, if the "inventory check" operation is performed 50% more frequently than usual, it will recognize it as an anomaly. The input is the analysis result data, and the output is a report of the detected anomalies.

[0981] Step 6:

[0982] The server generates hypotheses for the detected anomalies using a generative AI model (e.g., GPT-3 or BERT). For example, it generates a hypothesis such as "The high frequency of inventory checks is due to improper inventory management." The input is the anomaly report, and the output is the generated hypothesis.

[0983] Step 7:

[0984] The server notifies the user of the generated hypotheses via email, dashboard alerts, or a dedicated mobile app. The input is the generated hypotheses, and the output is the completion of the notification to the user.

[0985] Step 8:

[0986] The user provides specific causes and additional information for the received hypothesis. For example, they provide detailed feedback such as "This is because the warehouse management system is outdated." The input is the hypothesis notification, and the output is the user's feedback.

[0987] Step 9:

[0988] The server generates business improvement proposals using a generative AI model based on user feedback. For example, it suggests "introducing a dashboard that displays inventory status in real time." The input is user feedback, and the output is the generated business improvement proposals.

[0989] Step 10:

[0990] The server proposes the generated business improvement proposal to the user. The proposal is made through display on a dashboard, email, or presentation at a meeting. The input is the generated business improvement proposal, and the output is the completed proposal to the user.

[0991] Step 11:

[0992] The user evaluates the proposed business improvement plan and decides whether to implement it. For example, the user may decide to "adopt the introduction of a dashboard." The input is the business improvement plan, and the output is the evaluation result and the decision to implement it.

[0993] Step 12:

[0994] The server monitors the usage status of the new business flow in real time. Specifically, it collects dashboard usage data and operation logs. The input is the usage data of the new business flow, and the output is a monitoring report.

[0995] Step 13:

[0996] The server verifies the effectiveness of the new workflow based on the monitoring results and evaluates it with specific numerical values, such as "Inventory check operations have decreased by 50%, and work efficiency has improved." The input is the monitoring data, and the output is an effectiveness verification report.

[0997] Step 14:

[0998] The server feeds back the effectiveness verification report to the user. It creates a report including specific numerical data and notifies the user. The input is the effectiveness verification report, and the output is the completion of feedback to the user.

[0999] (Application example 1)

[1000] 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."

[1001] Modern logistics centers require highly efficient and precise management. However, manual operation log recording and subsequent data analysis make it difficult to make real-time improvements, limiting the extent to which operational efficiency can be improved. Furthermore, the frequent occurrence of abnormal operations, the time and effort required to identify the causes, and the implementation of improvement proposals can lead to a decline in overall work efficiency.

[1002] 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.

[1003] In this invention, the server includes a means for using a smart device to record operation logs in real time, a means for providing feedback in real time, and a means for presenting specific improvement proposals to workers and determining whether or not to apply them, thereby enabling the rapid analysis and improvement of the work flow within the logistics center and the overall improvement of work efficiency.

[1004] An "operation log" is data that records a series of operations performed by a user.

[1005] "Server" refers to the central system that receives, stores, and analyzes operation logs.

[1006] "Business flow" refers to the series of steps and procedures that a business follows.

[1007] "Real-time feedback" refers to responses and suggestions for improvement that are provided immediately to the user's actions.

[1008] "Smart devices" refer to advanced electronic devices that record operational logs and provide feedback in real time.

[1009] "Abnormal operations" refer to frequent or inappropriate operations that deviate from normal business flow.

[1010] "Hypothesis" refers to a tentative explanation or speculation about the cause of the detected abnormal operation.

[1011] "User" refers to an individual or team that uses the system to carry out work.

[1012] "Improvement proposals" refer to proposals and action plans to improve the efficiency of business flows and operations.

[1013] "Monitoring" refers to the act of watching how new business processes are being used and measuring their effectiveness.

[1014] A "logistics center" refers to a location that manages the storage and delivery of goods.

[1015] The system of the present invention aims to improve the efficiency of operations within a logistics center. This system improves the workflow by recording operation logs, sending and saving them on a server, analyzing them, and presenting improvement proposals to the user.

[1016] Hardware and software configuration

[1017] Hardware:

[1018] 1. Smart devices: Used to record operation logs in real time. Smartphones and smart glasses are examples of such devices.

[1019] 2. Server: A central system that stores the received operation logs, analyzes them, and generates business improvement proposals.

[1020] software:

[1021] 1. Python: This is the main language used to implement the program in this system.

[1022] 2. Flask / Django: Web frameworks used for server-side API integration.

[1023] 3. requests: A library for making HTTP requests.

[1024] 4. Database: A system for storing operation logs and analysis results (e.g., MySQL, PostgreSQL).

[1025] Specific operation of the system

[1026] Recording and sending operation logs

[1027] The smart device terminal records each worker's operation in real time and periodically sends the data to the server. For example, operations such as "start picking" and "check inventory" are recorded.

[1028] Saving and analyzing operation logs

[1029] The server stores the received operation logs in a database and then performs data analysis to detect frequently performed operations and abnormal operations, i.e., operations that deviate from the normal business flow.

[1030] Hypothesis generation and feedback

[1031] The server generates a hypothesis based on the detected abnormal operation. For example, it may hypothesize that "the reason this operation is performed so frequently is due to uncertainty in inventory information." The hypothesis is then fed back to the user in real time. The user can then enter an answer based on the provided hypothesis and send the feedback to the server.

[1032] Proposing business improvement plans

[1033] The server generates specific business improvement proposals based on user feedback and presents them to the user. For example, the proposal might include "introducing a dashboard that displays inventory status in real time."

[1034] New workflow monitoring and effectiveness verification

[1035] After a new workflow is implemented, the server monitors its usage, verifies the extent to which the new workflow contributes to efficiency, and provides feedback to the user in the form of specific figures.

[1036] Specific examples

[1037] For example, if the "inventory check" operation is frequently performed in inventory management at a logistics center, the system records the operation in detail and sends the log to the server. The server analyzes the data, detects that the "inventory check" operation is abnormally frequent, and hypothesizes the cause. Based on user feedback, the server proposes a "dashboard that displays inventory status in real time." The new workflow is then adopted, its usage and effectiveness are monitored, and improvements in operational efficiency are confirmed.

[1038] Prompt Sentence Examples

[1039] "Design an application that records work logs at a logistics center and proposes improvement plans for efficiency. Please include a specific process flow, such as how to record operation logs, how to send and save the logs, how to analyze data, provide feedback, propose business improvement plans, and verify their effectiveness."

[1040] The above is a specific embodiment for carrying out the present invention.

[1041] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1042] Step 1:

[1043] Recording of operation logs

[1044] The terminal uses a smart device (smartphone or smart glasses) to record each operation performed by the worker in detail. The input includes operations performed by the worker, such as "start picking" and "check inventory." A timestamp is assigned to each input operation, making it clear which operation was performed and when. Operation log data is generated as output.

[1045] Step 2:

[1046] Sending operation logs

[1047] The terminal sends the recorded operation log to the server at regular intervals (for example, every hour). The input is the operation log data recorded in step 1. The transmission method is an HTTP request. After transmission, the output is when the server receives the log data.

[1048] Step 3:

[1049] Saving operation logs

[1050] The operation log received by the server is saved in the database. The input is the operation log data received in step 2. An SQL query is used as the saving method. The output is that the operation log data is stored in the database.

[1051] Step 4:

[1052] Analysis of operation logs

[1053] The server analyzes the saved operation logs. The input is the operation log data stored in the database. The analysis methods include frequency analysis and pattern recognition to detect frequently performed operations and abnormal operations. The output is the analysis results, which include abnormal operation patterns and frequently performed operation data.

[1054] Step 5:

[1055] Hypothesis generation

[1056] The server generates hypotheses about abnormal operations based on the analysis results. The input is the analysis result data from step 4. Hypotheses are automatically generated using an AI model. The output is a hypothesis such as "Inventory check operations are being performed frequently due to problems with inventory management."

[1057] Step 6:

[1058] Feedback Notifications

[1059] The server notifies the user of the generated hypothesis. The input is the hypothesis generated in step 5. Notification methods include real-time display on a smart device or sending an alert. The output is the notification result to the user.

[1060] Step 7:

[1061] Collecting user responses

[1062] The user inputs a response to the feedback provided to the server. The input is additional data and comments from the user. The output is when the server receives the response data.

[1063] Step 8:

[1064] Generate business improvement proposals

[1065] The server generates business improvement proposals based on the user's responses. The input is the user response data received in step 7. Taking into account past log data and user feedback, specific improvement proposals are created using AI. The output is improvement proposals such as a "dashboard that displays inventory status in real time."

[1066] Step 9:

[1067] Proposing business improvement plans

[1068] The server presents the generated business improvement proposals to the user. The input is the business improvement proposals generated in step 8. Notification methods include displaying a dashboard on a smart device and sending implementation proposals. The output is the improvement proposals presented to the user.

[1069] Step 10:

[1070] New Workflow Monitoring

[1071] The server monitors the usage of the new business flow. The input is the implementation data of the new business flow. The log data is analyzed in real time to verify the frequency of use and effectiveness. The output is the effectiveness measurement data as a result of the monitoring.

[1072] Step 11:

[1073] Effectiveness verification

[1074] The server verifies the effectiveness of the new business flow. The input is the monitoring data obtained in step 10. The data is compared and analyzed to evaluate improvements in business efficiency and changes in operation frequency. The output is a concrete result of the verification of effectiveness, such as "business efficiency has improved by 50%."

[1075] Step 12:

[1076] Providing Feedback

[1077] The server feeds back the results of the effectiveness verification to the user. The input is the results of the effectiveness verification obtained in step 11. Feedback methods include periodic reports and real-time notifications. The output is the feedback results to the user.

[1078] 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.

[1079] The system of the present invention achieves more effective business improvement by combining an emotion engine that recognizes user emotions. In addition to recording and analyzing operation logs, this system also collects and analyzes user emotion data, which is used to generate and present business improvement proposals. The specific processing flow is explained below.

[1080] Recording and sending operation logs

[1081] The terminal records each operation performed by the user in detail. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and timestamp are recorded. In addition, the emotion engine analyzes the user's facial expressions and voice during the operation and records them as emotion data. The recorded operation log and emotion data are sent to the server at regular intervals (for example, every hour). This allows data to be collected in real time.

[1082] Saving and analyzing operation logs and emotion data

[1083] The server stores the received operation logs and emotion data in a database. The data to be stored includes user IDs, operation details, timestamps, and emotion data. The server analyzes the business flow based on this data and visualizes frequently occurring operations and specific patterns.

[1084] Anomaly Detection and Hypothesis Generation

[1085] The server uses the analysis results to detect operations that occur abnormally frequently as anomalies. For example, if the "check inventory" operation occurs abnormally frequently compared to other operations, it marks it as an anomaly. In addition, it uses emotion data provided by the emotion engine to analyze the user's emotional state at the time the anomaly occurred. For example, if anxiety or stress is high, this will also be included in the data.

[1086] The server generates hypotheses for anomalies, such as "frequent stock checks are due to poor inventory management and users feeling anxious," which allows for the emotional factors behind the problem to be taken into account.

[1087] User feedback and business improvement proposal generation

[1088] The server notifies the user of the generated hypothesis. For example, it presents the user with a question such as, "Please tell me why inventory check operations are occurring so frequently." The user responds by providing specific reasons and additional information. For example, the user might answer, "Inventory checks are necessary frequently to prevent product shortages."

[1089] The server generates business improvement proposals based on the user's feedback and emotions. For example, it suggests a "dashboard that displays inventory status in real time." It also adjusts the content and presentation method of the proposals by taking into account the emotional data. For example, if the user is prone to stress, it will devise a more appropriate wording for the proposals.

[1090] Proposing and monitoring business improvement proposals

[1091] The server presents the generated business improvement proposals to the user. If the user evaluates the proposals and decides to implement them, the server designs and implements the new business flow. For example, it introduces a real-time inventory status dashboard.

[1092] New workflow monitoring and effectiveness verification

[1093] After the proposed improvements are implemented, the server monitors the usage of the new workflow, for example, by monitoring how frequently the dashboard is used and how the user's emotional state changes when operating it.

[1094] The server verifies the effectiveness of the new workflow. For example, it evaluates whether the number of "inventory check" operations has decreased and whether users' emotional state has improved after the dashboard was introduced.

[1095] Final feedback and establishing the flow

[1096] The server then provides the final evaluation results as feedback to the user. For example, it might report, "By introducing the dashboard, inventory check operations have decreased by 50%, and user stress levels have also decreased." Based on the evaluation results, the user and server then formally establish the new business flow as a business process.

[1097] In this way, the system according to the present invention not only realizes the efficiency and streamlining of the workflow, but also realizes comprehensive business improvement that takes into consideration the emotional aspects of the user.

[1098] The processing flow will be explained below.

[1099] Step 1:

[1100] The device records user operations in real time. For example, when a user performs an "inventory check" operation, the device records the operation details and a timestamp.

[1101] Step 2:

[1102] The device analyzes the user's emotional state using an emotion engine. For example, it analyzes the user's facial expressions and voice, and generates emotion data such as anxiety, stress, and satisfaction.

[1103] Step 3:

[1104] The device sends operation logs and emotion data to the server at regular intervals (for example, every hour), allowing data to be collected and sent in real time.

[1105] Step 4:

[1106] The server stores the received operation log and emotion data in a database. The stored data includes the user ID, operation details, timestamp, and emotion data.

[1107] Step 5:

[1108] The server analyzes the operation logs and emotion data stored in the database. The purpose of the analysis is to understand the overall picture of the user's workflow and extract frequently occurring operations and specific emotion patterns.

[1109] Step 6:

[1110] Based on the analysis results, the server detects operations that are abnormally frequent as anomalies. For example, if the "inventory check" operation is abnormally frequent compared to other operations, it will mark it as an anomaly.

[1111] Step 7:

[1112] The server also references the user's emotional data when an anomaly occurs and generates a hypothesis. For example, it may hypothesize that "inventory checks are being conducted frequently because inventory management is not being properly performed and users are feeling anxious."

[1113] Step 8:

[1114] The server notifies the user of the generated hypothesis. For example, it displays a question to the user such as "Please tell me why inventory check operations are occurring so frequently."

[1115] Step 9:

[1116] The user responds to the server's question by providing specific reasons and additional information, such as "The reason we need to check inventory frequently is to prevent products from running out."

[1117] Step 10:

[1118] The server generates business improvement proposals based on user feedback and emotional data, such as a dashboard that displays inventory status in real time.

[1119] Step 11:

[1120] The server presents the generated business improvement proposals to the user, who evaluates them and decides whether to implement them.

[1121] Step 12:

[1122] If the user decides to adopt the proposed improvement, the server designs and implements the new workflow, for example, by introducing a real-time inventory status dashboard.

[1123] Step 13:

[1124] The server monitors the usage of the new workflow, specifically how frequently the dashboard is used and how the user's emotional state changes when operating it.

[1125] Step 14:

[1126] The server verifies the effectiveness of the new workflow, for example, evaluating whether the number of "inventory check" operations has decreased and whether the user's emotional state has improved after the dashboard was introduced.

[1127] Step 15:

[1128] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered users' stress levels."

[1129] Step 16:

[1130] Based on the evaluation results, the user and the server establish the new workflow as a formal business process. In this way, the present invention aims to improve the efficiency of the workflow and the user's emotional state.

[1131] Example 2

[1132] 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."

[1133] Conventional business improvement systems proposed improvement measures based on the analysis of operation logs, but did not take into account the user's emotional state. As a result, improvement measures were sometimes proposed that ignored psychological factors, and were unable to reduce the user's stress and anxiety. Furthermore, when verifying the effectiveness of new business flows after their implementation, emotional data was not taken into account in the evaluation. These problems need to be solved.

[1134] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for recording an operation log, means for transmitting the operation log to the server, means for saving the operation log, means for analyzing the saved operation log and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating business improvement proposals based on the user responses, means for presenting the business improvement proposals to the user, means for collecting and analyzing emotional data, means for sending the operation log including the emotional data to the server, means for analyzing the emotional data during operations and associating it with anomalies, means for adjusting the business improvement proposals taking the emotional data into consideration, means for monitoring the usage status and emotional state of the new workflow, means for verifying the effectiveness of the new workflow, and means for feeding back the verification results to the user. This makes it possible to propose business improvements that take the user's emotional state into consideration, and also enables comprehensive evaluation including emotional data when verifying the effectiveness of a new workflow after its introduction.

[1135] An "operation log" refers to historical information about operations performed by a user within the system, and specifically includes the operation details, user ID, timestamp, etc.

[1136] "Emotion data" refers to information about the user's psychological state analyzed from their facial expressions and voice using an emotion engine, and specifically refers to data that quantifies emotional states such as anxiety, stress, and joy.

[1137] "Server" refers to a computer system that operates on a network and receives, stores, analyzes, and provides feedback on data.

[1138] A "terminal" refers to a hardware device that a user operates, specifically an electronic device such as a computer or smartphone.

[1139] "Business flow" refers to a series of steps or procedures for carrying out a specific business operation.

[1140] "Analysis" refers to the process of processing collected data to detect specific patterns or anomalies.

[1141] An "anomaly" refers to an operation that occurs abnormally frequently and deviates from normal operating patterns.

[1142] A "hypothesis" refers to a prediction or theory that is made to estimate the cause of an anomaly.

[1143] "Feedback" refers to the evaluation results and suggestions that the system provides to the user.

[1144] "Monitoring" refers to the process of continuously monitoring the usage of the new workflow and the emotional state of the user.

[1145] "Improvement proposals" refer to specific proposals aimed at streamlining business processes and improving user experiences.

[1146] The system of the present invention collects and analyzes user operation logs and emotional data to help improve business operations, which not only improves operational efficiency but also reduces the psychological burden on users.

[1147] Hardware and Software Configuration

[1148] Hardware

[1149] Device: A device operated by a user. This can include desktop computers, laptops, smartphones, etc. These devices are equipped with cameras and microphones to capture facial and audio data from the user.

[1150] Server: A central system that collects, stores, and analyzes data. It is equipped with a high-performance database and analysis engine.

[1151] software

[1152] Emotion engine: Software that runs on the device and uses the camera and microphone to analyze the user's facial expressions and voice to generate emotion data.

[1153] Database management system: Runs on the server and stores and manages operation logs and emotion data.

[1154] Analysis engine: Software that runs on a server and visualizes business processes and detects anomalies based on collected data.

[1155] Generative AI model: Generates business improvement proposals based on user feedback.

[1156] Data processing and calculation

[1157] The device records the user's operation log in real time and uses an emotion engine to collect emotional data during the operation. For example, when a user performs an "inventory check" operation, the degree of "anxiety" or "stress" is recorded as emotional data along with the operation details.

[1158] The collected data is sent to a server at regular intervals. The server stores the received data in a database, and an analysis engine analyzes the business flow based on the stored data. This analysis makes it possible to visualize frequently occurring operations and specific patterns.

[1159] Based on the analysis results, the server detects abnormally frequent operations (anomalies). It also uses emotional data to analyze the user's emotional state at the time the anomaly occurred and evaluates whether the anomaly is due to psychological factors. For example, if the "inventory check" operation is performed frequently and the user feels high stress when doing so, it will be marked as an anomaly.

[1160] The server uses a generative AI model to generate a hypothesis about the anomaly and prompts the user to confirm the hypothesis, for example, "Please tell me why inventory check operations are occurring so frequently."

[1161] Based on user feedback, the server generates business improvement proposals. These proposals are chosen with appropriate content and expressions, taking into account emotional data. For example, when proposing a "dashboard that displays inventory status in real time," gentle expressions are used to avoid causing excessive stress to the user.

[1162] Examples of concrete examples and prompts

[1163] As a specific usage scenario, consider a case where a user uses an inventory management system and frequently performs "inventory check" operations. At this time, the emotion engine analyzes the user's facial expressions and voice to indicate that "anxiety" and "stress" are increasing.

[1164] The collected operation logs and emotion data are sent to a server, which stores them in a database and analyzes business flows and anomalies. The server detects an abnormally high number of "inventory check" operations and hypothesizes that "frequent inventory checks are occurring because inventory management is not being done properly and users are feeling anxious."

[1165] Based on this hypothesis, the generative AI model asks the user for feedback, displaying a prompt saying, "Please tell us why you are frequently checking inventory." The specific feedback received from the user is, "The reason why inventory checks are necessary so frequently is to prevent products from running out."

[1166] Based on this feedback, the server generates a proposal for a dashboard that displays inventory status in real time and presents it to the user in a way that is thoughtful and stress-free for the user.

[1167] As described above, the present invention is a system that utilizes operation logs and emotion data to propose business improvements and verify their effectiveness.

[1168] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1169] Step 1: Recording operational logs

[1170] The device records all operations performed by the user. When a user performs an operation such as "check inventory," the operation details, user ID, and timestamp are saved as a log.

[1171] Input: User action (e.g., clicking the "Check stock" button)

[1172] Data processing: Collection of operation details, user ID, and timestamp

[1173] Output: Operation log (e.g. "Check stock", user ID, timestamp)

[1174] Step 2: Collect and analyze emotion data

[1175] The device collects the user's facial expressions and voice data using a camera and microphone, and an emotion engine analyzes this data to generate emotion data.

[1176] Input: User's facial expressions and voice

[1177] Data processing: Analyze facial expressions and voice to determine emotional state (e.g., "anxiety" 80%, "stress" 60%)

[1178] Output: Emotion data (e.g., "anxiety" 80%, "stress" 60%)

[1179] Step 3: Sending data

[1180] The device sends operation logs and emotion data to the server at regular intervals.

[1181] Input: Operation log, emotion data

[1182] Data processing: Converting data into packets

[1183] Output: Send data to the server

[1184] Step 4: Save your data

[1185] The server stores the received data in a database, including the user ID, operation details, timestamp, and emotion data.

[1186] Input: Operation log, emotion data

[1187] Data processing: Insertion into database

[1188] Output: Update record in database

[1189] Step 5: Analyze the workflow

[1190] The server analyzes the business flow based on the stored data, for example, extracting and visualizing frequently occurring operations.

[1191] Input: Database operation log data

[1192] Data processing: Calculation and visualization of frequency distribution

[1193] Output: Visualized workflow (e.g. heat map)

[1194] Step 6: Anomaly detection

[1195] Based on the analysis results, the server detects abnormally frequent operations as anomalies.

[1196] Input: Workflow analysis results

[1197] Data processing: Detecting anomalies using statistical methods

[1198] Output: Anomaly list (e.g., "Stock Check" is abnormally high)

[1199] Step 7: Hypothesis generation

[1200] The server generates hypotheses for anomalies, such as "frequent inventory checks are occurring because users are feeling anxious" based on emotional data.

[1201] Input: Anomaly list, emotion data

[1202] Data processing: linking anomalies with emotional states, generating hypotheses

[1203] Output: Hypothesis (e.g., "The reason people check their inventory so frequently is because they have problems with inventory management and are feeling anxious")

[1204] Step 8: Get user feedback

[1205] The server notifies the user of the generated hypothesis and asks for feedback, for example by displaying a prompt such as "Please tell us why inventory check operations are occurring so frequently."

[1206] Input: Hypothesis

[1207] Data processing: Prompt sentence generation

[1208] Output: User notification (e.g. "Please tell me why inventory check operations are occurring so frequently")

[1209] Step 9: Generate business improvement proposals

[1210] The server generates business improvement proposals based on user feedback and emotional data, such as a dashboard that displays inventory status in real time.

[1211] Input: User feedback, emotion data

[1212] Data processing: Generating business improvement proposals that take into account feedback and emotional data

[1213] Output: Business improvement proposals (e.g., "Implementation of a real-time inventory dashboard")

[1214] Step 10: Propose improvements

[1215] The server presents the generated business improvement proposals to the user, for example, recommending the introduction of a dashboard that displays inventory status in real time.

[1216] Input: Business improvement proposal

[1217] Data processing: Message conversion of proposal content

[1218] Output: Suggestion notification to the user (e.g. "We recommend you install the real-time inventory dashboard")

[1219] Step 11: Monitoring the new workflow

[1220] After the proposed improvements are implemented, the server monitors the usage of the new workflow and the user's emotional state.

[1221] Input: New business flow usage log, emotion data

[1222] Data processing: Collection and analysis of usage and sentiment data

[1223] Output: New business flow evaluation report

[1224] Step 12: Verify the effect

[1225] The server verifies the effectiveness of the new workflow, for example, whether the number of "inventory check" operations has decreased after the dashboard was introduced, or whether the user's emotional state has improved.

[1226] Input: New Workflow Evaluation Report

[1227] Data processing: Before and after comparison, effect verification

[1228] Output: Verification results (e.g., "Inventory check operations decreased by 50%, stress levels decreased")

[1229] Step 13: Final feedback

[1230] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered user stress levels."

[1231] Input: Validation result

[1232] Data processing: feedback message generation

[1233] Output: Final report to the user

[1234] Step 14: Establishing the workflow

[1235] The user and server then formally establish the new business flow, the effectiveness of which has been confirmed based on the evaluation results, as a business process.

[1236] Input: Final report

[1237] Data processing: Setting up formal business flow

[1238] Output: Establishing a new workflow

[1239] In this way, specific input, data processing, and output are performed at each step, resulting in efficient business improvement and an improvement in the user's emotional state across the entire system.

[1240] (Application example 2)

[1241] 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."

[1242] Improving operational efficiency at logistics centers is an important issue for many companies. In particular, more effective operational improvements can be expected by considering the emotional aspects of workers in addition to their behavior. However, conventional systems have difficulty effectively utilizing data on worker emotions, resulting in only partial improvements to operational flow. Furthermore, when the cause of abnormal operations is due to emotions, there is also the issue of being unable to accurately identify the cause and propose improvement measures.

[1243] The identification process by the identification 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 recording an operation log, means for transmitting the operation log to the server, means for saving the operation log, means for analyzing the saved operation log and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating workflow improvement plans based on the user responses, means for presenting the workflow improvement plans to the user, means for monitoring the usage status of the new workflow, means for verifying the effectiveness of the new workflow, means for providing feedback on the verification results to the user, means for collecting user emotion data, means for analyzing the collected emotion data, means for using the emotion data to generate workflow improvement plans, and means for generating workflow improvement plans that take emotional factors into account based on the analysis results. This improves the efficiency of the workflow at the logistics center and enables comprehensive workflow improvement that also takes the emotions of workers into account.

[1244] An "operation log" is a detailed record of each operation a user performs within the system.

[1245] "Emotion data" refers to data relating to the user's emotional state, such as information analyzed from facial expressions and voice.

[1246] The "server" is a central computing device that collects and analyzes operation logs and emotion data, and generates and presents business improvement proposals.

[1247] "Visualization" is the visual presentation of data, making specific patterns and anomalies visible.

[1248] An "anomaly" refers to an abnormal operation or behavior that deviates from normal operating patterns.

[1249] A "hypothesis" is a possible explanation or theory as to why an anomaly occurs.

[1250] "Business improvement proposals" are specific proposals and measures to streamline or improve the current business flow.

[1251] "Feedback" refers to the user's reaction and evaluation of the analysis results and improvement proposals.

[1252] "Monitoring" is the activity of continuously observing the status of a system or process.

[1253] "Effectiveness verification" is the process of evaluating whether the business improvement plan that has been implemented is actually having the expected effect.

[1254] The "Logistics Center Business Improvement Assistant" system of the present invention uses smartphones or smart glasses to collect operation logs and emotional data of workers working in a logistics center, and analyzes the data on a server to improve business efficiency.

[1255] System Program

[1256] The terminal has the function of recording the worker's operation log and sending it to the server. Specifically, when a worker performs an operation such as "start picking," the operation details and timestamp are recorded. At the same time, the terminal's camera is used to capture the worker's facial expression, and an emotion engine analyzes the worker's emotional state (e.g., anxiety, stress) from the facial expression. This data is periodically sent to the server.

[1257] Hardware and software used

[1258] The hardware used is a smartphone or smart glasses (e.g., Google Glass), and the camera built into these devices is used. The software used is an emotion recognition library (e.g., Emotion Recognition Library), a server-side data processing engine (e.g., an API built with Python or Flask), and a database (e.g., PostgreSQL).

[1259] Data processing and calculation

[1260] The server stores the received operation logs and emotion data in a database. The stored data includes user IDs, operation details, timestamps, and emotion data. The server analyzes this data and uses it to visualize business processes. For example, it identifies frequently occurring operations and specific patterns and displays them as graphs and charts.

[1261] Hypothesis generation and business improvement proposals

[1262] The server detects abnormally frequent operations (anomalies) from the analysis results and generates a hypothesis based on them. For example, it may hypothesize that "inventory checks are being performed frequently because inventory management is not being performed properly." This hypothesis is notified to the user, and specific reasons and additional information are collected. The server then generates business improvement proposals based on the user's answers and emotion data and presents them to the user.

[1263] Monitoring and effectiveness verification

[1264] After the proposed business improvement is implemented, the server monitors the usage of the new business flow. For example, it monitors how frequently a dashboard displaying real-time inventory status is used and how the user's emotional state changes when operating it. To verify the effectiveness of the new business flow, it also evaluates improvements in work efficiency and changes in the user's stress level.

[1265] Examples and prompts

[1266] For example, when a worker is picking items, the smart glasses recognize their movements and facial expressions and record them as emotion data. An example of a prompt for emotion analysis is as follows:

[1267] "Analyzing emotions from facial photos of workers taken with a smartphone camera"

[1268] In this way, the logistics center business improvement assistant system of the present invention streamlines the business flow of a logistics center and realizes comprehensive business improvement that also takes into account the emotional aspects of workers.

[1269] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1270] Step 1:

[1271] Operation log and emotional data recording

[1272] The terminal records the worker's operation log and emotional data. Specifically, when a worker performs an operation such as "start picking" using a smartphone or smart glasses, the operation details and timestamp are recorded. At the same time, the terminal's camera captures the worker's facial expression, and an emotion engine analyzes the facial expression to determine emotional data (e.g., anxiety, stress). The input is the worker's operation details and facial image data, and the output is the operation log and emotional data.

[1273] Step 2:

[1274] Sending data

[1275] The device sends the recorded operation log and emotion data to the server at regular intervals. Specifically, the process of sending this data to the server is performed using an HTTP request. The input is the operation log and emotion data, and the output is the data transfer to the server.

[1276] Step 3:

[1277] Data storage

[1278] The operation log and emotion data received by the server are stored in a database. Specifically, data including the user ID, operation content, timestamp, and emotion data is inserted into a database (e.g., PostgreSQL). The input is the operation log and emotion data sent to the server, and the output is storage in the database.

[1279] Step 4:

[1280] Data analysis

[1281] The server analyzes the stored operation logs and emotion data to visualize the business flow. Specifically, it retrieves data from the database and generates graphs and charts to visualize frequently occurring operations and specific operation patterns. The input is the operation logs and emotion data in the database, and the output is a graph or chart of the visualized business flow.

[1282] Step 5:

[1283] Anomaly Detection

[1284] The server detects operations that occur abnormally frequently as anomalies. Specifically, it detects anomalies using statistical methods based on the frequency distribution of standard operations. The input is analyzed operation log data, and the output is operation data tagged as anomalies.

[1285] Step 6:

[1286] Hypothesis generation

[1287] The server generates hypotheses based on anomalies. For example, it might create a hypothesis such as, "Frequent inventory checks are due to inappropriate inventory management, which makes workers feel anxious." The input is operation data and emotion data tagged as anomalies, and the output is the generated hypothesis.

[1288] Step 7:

[1289] User notification and feedback collection

[1290] The server notifies the user of the generated hypothesis and collects feedback. Specifically, it presents the user with the question, "Please tell us why inventory check operations are occurring so frequently," and collects the user's answer. The input is the hypothesis and the user's answer, and the output is the user's feedback.

[1291] Step 8:

[1292] Generate business improvement proposals

[1293] The server generates business improvement proposals based on user feedback and emotional data. Specifically, it proposes improvement proposals such as "introducing a dashboard that displays inventory status in real time." The input is user feedback and emotional data, and the output is the generated business improvement proposals.

[1294] Step 9:

[1295] Proposing business improvement plans

[1296] The server presents the generated business improvement proposals to the user. Specifically, it presents detailed information such as the dashboard design and how to use it. The input is the business improvement proposals, and the output is the improvement proposals presented to the user.

[1297] Step 10:

[1298] Monitoring new business processes

[1299] After the business improvement proposal is implemented, the server monitors the usage of the new business flow. Specifically, it monitors the frequency of dashboard use and changes in the user's emotional state. The input is the usage data and emotional data of the new business flow, and the output is the monitoring results.

[1300] Step 11:

[1301] Effectiveness verification

[1302] The server verifies the effectiveness of the new business flow. Specifically, it evaluates items such as "has the number of inventory check operations decreased?" and "has the user's stress level decreased?" The input is the monitoring results, and the output is an evaluation of the verified effectiveness.

[1303] Step 12:

[1304] Final Feedback

[1305] The server then feeds back the final evaluation results to the user. Specifically, it reports that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered users' stress levels." The input is the evaluation result of the effect, and the output is feedback to the user.

[1306] 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.

[1307] 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.

[1308] 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.

[1309] [Fourth embodiment]

[1310] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1311] 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.

[1312] 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).

[1313] 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.

[1314] 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.

[1315] 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).

[1316] 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.

[1317] 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.

[1318] 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.

[1319] 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.

[1320] 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.

[1321] 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.

[1322] 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."

[1323] The system according to the present invention realizes efficient business operations by analyzing and improving business flow. This system includes a terminal that records operation logs, a server that stores and analyzes the operation logs, and a means for providing feedback to users, and is implemented as follows:

[1324] Recording and sending operation logs

[1325] The terminal records each operation performed by the user in detail. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and timestamp are recorded. The recorded operation log is periodically sent to the server. The transmission is performed, for example, every hour, enabling real-time data collection.

[1326] Saving and analyzing operation logs

[1327] The server stores the received operation logs in a database. Based on the stored operation logs, the server analyzes the business flow. Specifically, it analyzes the operation logs and visualizes frequently occurring operations and patterns. Based on the analysis results, the server detects abnormally frequent operations as anomalies.

[1328] Hypothesis generation and user feedback

[1329] The server automatically generates hypotheses for detected anomalies. For example, it may hypothesize that "frequent inventory checks are caused by improper inventory management." The generated hypotheses are fed back to the user. The user can then provide specific reasons and additional information to improve the accuracy of the hypotheses.

[1330] Generate and present business improvement proposals

[1331] The server generates business improvement proposals based on user feedback. For example, it proposes a "dashboard that displays inventory status in real time." These improvement proposals are presented to the user, who evaluates and decides on them. If the user decides to adopt the improvement proposal, a new business flow is designed based on its contents.

[1332] New workflow monitoring and effectiveness verification

[1333] After the proposed improvements are implemented, the server monitors the usage of the new workflow. Specifically, it monitors the frequency and effectiveness of real-time use of the inventory status dashboard. As a result of the monitoring, it verifies whether or not work efficiency has improved, and provides feedback on the results to the user. For example, it reports specific figures such as, "By introducing the dashboard, the number of inventory check operations has decreased by 50%, improving work efficiency."

[1334] Specific examples

[1335] For example, consider a case where "inventory check" operations are frequently performed in a company's inventory management system. When this system is implemented, the terminal records these operations in detail and sends the log to the server. The server analyzes the data, detects that "inventory check" operations are occurring abnormally frequently, and generates hypotheses about the cause. Based on user feedback, the server proposes a dashboard that displays inventory status in real time. If the user evaluates this and decides to implement it, the dashboard will be used as a new business flow. Finally, the server monitors its effectiveness, and if improvements are confirmed, it will be established as a formal business process.

[1336] In this way, the system according to the present invention realizes efficient and rational business flow, and reduces the workload of the user.

[1337] The processing flow will be explained below.

[1338] Step 1:

[1339] The terminal records user operations in real time. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and a timestamp are recorded.

[1340] Step 2:

[1341] The terminal sends the recorded operation log to the server at regular intervals (for example, every hour), allowing data to be collected in real time.

[1342] Step 3:

[1343] The server stores the received operation logs in a database. The data to be stored includes the user ID, operation details, timestamp, etc.

[1344] Step 4:

[1345] The server periodically analyzes the operation logs stored in the database. The main purpose of the analysis is to grasp the overall picture of each business flow and extract frequently occurring operations and specific patterns.

[1346] Step 5:

[1347] Based on the analysis results, the server detects operations that occur abnormally frequently as anomalies. For example, if the "inventory check" operation occurs abnormally frequently compared to other operations, it will mark it as an anomaly.

[1348] Step 6:

[1349] The server generates hypotheses for detected anomalies, for example, "Inventory checks are occurring frequently because inventory management is not being properly performed."

[1350] Step 7:

[1351] The server notifies the user of the generated hypotheses, for example by presenting the user with a question such as "Please tell me why inventory check operations are occurring so frequently."

[1352] Step 8:

[1353] The user responds to the server's question by providing specific reasons and additional information, such as, "The reason we need to check inventory frequently is to prevent products from running out."

[1354] Step 9:

[1355] The server generates business improvement proposals based on user feedback, such as a "dashboard that displays inventory status in real time."

[1356] Step 10:

[1357] The server presents the generated business improvement proposals to the user, who evaluates them and decides whether to implement them.

[1358] Step 11:

[1359] If the user decides to adopt the proposed improvement, the server designs and implements the new workflow, for example, by introducing a real-time inventory status dashboard.

[1360] Step 12:

[1361] The server monitors the usage of the new workflow, for example, how often the dashboard is used.

[1362] Step 13:

[1363] The server verifies the effectiveness of the new workflow, for example, evaluating whether the "inventory check" operation has decreased since the dashboard was introduced.

[1364] Step 14:

[1365] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the number of inventory check operations has decreased by 50% since the introduction of the dashboard."

[1366] Step 15:

[1367] The user and server then formally establish the new business flow, the effectiveness of which has been confirmed based on the evaluation results, as a business process.

[1368] Example 1

[1369] 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."

[1370] In current business management systems, operation logs are recorded and analyzed separately, without any coordination, making it difficult to grasp the overall picture of business flows. Even when abnormal operations or patterns are detected, the causes and improvement plans are often generated manually, making efficient business improvement difficult. Furthermore, there is a lack of means to properly verify the effects of new business flows after they are introduced, making it difficult to ensure the effectiveness of improvements. There is a need for a system that can solve these issues and efficiently and automatically visualize and improve business flows.

[1371] 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.

[1372] In this invention, the server includes means for saving operation logs, means for analyzing the saved operation logs and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating business improvement plans based on the user responses, means for presenting the business improvement plans to the user, means for monitoring the usage status of the new workflow, means for verifying the effectiveness of the new workflow, and means for providing feedback to the user on the effectiveness of the workflow in concrete numerical values. This makes it possible to grasp the overall picture of the workflow, efficiently and automatically generate business improvement plans, and introduce effective workflows and verify their effectiveness.

[1373] An "operation log" is data that records the content of each operation performed by a user and the time at which it was performed.

[1374] A "server" is a central computer device that receives, stores, analyzes, and processes data sent from terminals, and improves business processes.

[1375] "Business flow" refers to a series of procedures that show the specific flow and process of business.

[1376] An "abnormally frequent operation" refers to an operation that is performed significantly more frequently than in the normal workflow, and is an operation that may be a sign of problems with the efficiency or quality of work.

[1377] A "hypothesis" is a guideline for speculating on possible causes or backgrounds based on detected abnormal operations.

[1378] An "improvement proposal" is a specific proposal for changes to make the current business flow more efficient or rational.

[1379] "Monitoring" is the activity of observing in real time how new business processes and improvement proposals are actually being implemented.

[1380] "Feedback" refers to the provision of information to encourage continuous business improvement by communicating monitoring and analysis results to users.

[1381] "Real-time" refers to a situation in which data is collected and processed immediately, and feedback and responses based on that data are provided without delay.

[1382] The system of the present invention realizes efficient business operations by analyzing and improving business flows. This system includes a terminal that records operation logs, a server that stores and analyzes the operation logs, and a means for providing feedback to users, and is specifically implemented as follows.

[1383] Recording and sending operation logs

[1384] The terminal records each operation performed by the user in detail. When a user performs an "inventory check" operation in the inventory management system, the operation content and timestamp are recorded. This operation log is temporarily stored in local storage or temporary memory. The operation log is then periodically (for example, every hour) sent to the server. The transmission is performed using the HTTP or HTTPS protocol. This makes it possible to collect data in real time.

[1385] Saving and analyzing operation logs

[1386] The server stores the received operation logs in a database (for example, MySQL or PostgreSQL). It then formats the data appropriately according to the database schema. Based on the stored operation logs, the server analyzes the business flow. Specifically, it uses log analysis software (for example, Elasticsearch or Splunk) to visualize frequently occurring operations and patterns. Based on the analysis results, it detects abnormally frequent operations as anomalies.

[1387] Hypothesis generation and user feedback

[1388] The server automatically generates hypotheses for detected anomalies. For example, it may hypothesize that "frequent inventory checks are caused by improper inventory management." A generative AI model (such as GPT-3 or BERT) is used to generate hypotheses. The generated hypotheses are notified to the user via email, dashboard alerts, or a dedicated mobile app. The user receives the notification and can provide specific causes or additional information to improve the accuracy of the hypothesis.

[1389] Generate and present business improvement proposals

[1390] The server generates business improvement proposals based on user feedback. Prompt statements such as "How to reduce inventory check operations" are input into the generative AI model, which then generates ideas for a "dashboard that displays inventory status in real time." These business improvement proposals are then proposed to the user. The proposals can be displayed on the dashboard, sent via email, or presented at a meeting. The user reviews and evaluates the proposals, and if a decision is made to adopt them, a new business flow is specifically designed.

[1391] New workflow monitoring and effectiveness verification

[1392] The server monitors the usage of the new business flow in real time. Specifically, it collects the frequency of dashboard use and operation logs, and also collects feedback from users. The server verifies the effectiveness of the new business flow based on the collected data and generates a report with specific figures, such as "By introducing the dashboard, inventory check operations have decreased by 50%, and business efficiency has improved." The results are fed back to the user, helping to improve business operations.

[1393] Prompt Sentence Examples

[1394] 1. "Please explain a specific example of recording and analyzing operation logs in an inventory management system."

[1395] 2. "Please tell me the detailed flow of the system, including the hypothesis generation and feedback process for improving business processes."

[1396] 3. Please explain the specific steps for generating and evaluating business improvement proposals based on user feedback.

[1397] In this way, the system according to the present invention realizes efficient and rational business flow, and reduces the workload of the user.

[1398] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1399] Step 1:

[1400] The terminal captures each operation performed by the user and generates log data that includes the operation details and a timestamp. As a concrete example, when a user clicks the "Check Stock" button in an inventory management system, the operation details "Check Stock" and the timestamp "YYYY-MM-DD HH:MM:SS" are recorded. This log data is temporarily saved in local storage. The input is the user's operation, and the output is the generated operation log data.

[1401] Step 2:

[1402] The terminal reads operation log data from local storage at regular intervals (for example, every hour) and sends it to the server. HTTP or HTTPS is used as the transmission protocol. The input is the operation log data from local storage, and the output is a transmission completion notification to the server.

[1403] Step 3:

[1404] The server saves the received operation log data in a database (for example, MySQL or PostgreSQL). Before saving, the data is formatted based on the database schema. Specifically, the log data is broken down into fields (operation details, timestamp, etc.) and stored. The input is the received operation log data, and the output is the formatted data saved in the database.

[1405] Step 4:

[1406] The server analyzes the stored operation log data. Log analysis software (such as Elasticsearch or Splunk) is used to visualize frequently occurring operations and patterns. For example, the number of times a specific operation was performed is tallied and displayed as a heat map. The input is database operation log data, and the output is visualized data of the analysis results.

[1407] Step 5:

[1408] The server detects abnormally frequent operations (anomalies) based on the analysis results. For example, if the "inventory check" operation is performed 50% more frequently than usual, it will recognize it as an anomaly. The input is the analysis result data, and the output is a report of the detected anomalies.

[1409] Step 6:

[1410] The server generates hypotheses for the detected anomalies using a generative AI model (e.g., GPT-3 or BERT). For example, it generates a hypothesis such as "The high frequency of inventory checks is due to improper inventory management." The input is the anomaly report, and the output is the generated hypothesis.

[1411] Step 7:

[1412] The server notifies the user of the generated hypotheses via email, dashboard alerts, or a dedicated mobile app. The input is the generated hypotheses, and the output is the completion of the notification to the user.

[1413] Step 8:

[1414] The user provides specific causes and additional information for the received hypothesis. For example, they provide detailed feedback such as "This is because the warehouse management system is outdated." The input is the hypothesis notification, and the output is the user's feedback.

[1415] Step 9:

[1416] The server generates business improvement proposals using a generative AI model based on user feedback. For example, it suggests "introducing a dashboard that displays inventory status in real time." The input is user feedback, and the output is the generated business improvement proposals.

[1417] Step 10:

[1418] The server proposes the generated business improvement proposal to the user. The proposal is made through display on a dashboard, email, or presentation at a meeting. The input is the generated business improvement proposal, and the output is the completed proposal to the user.

[1419] Step 11:

[1420] The user evaluates the proposed business improvement plan and decides whether to implement it. For example, the user may decide to "adopt the introduction of a dashboard." The input is the business improvement plan, and the output is the evaluation result and the decision to implement it.

[1421] Step 12:

[1422] The server monitors the usage status of the new business flow in real time. Specifically, it collects dashboard usage data and operation logs. The input is the usage data of the new business flow, and the output is a monitoring report.

[1423] Step 13:

[1424] The server verifies the effectiveness of the new workflow based on the monitoring results and evaluates it with specific numerical values, such as "Inventory check operations have decreased by 50%, and work efficiency has improved." The input is the monitoring data, and the output is an effectiveness verification report.

[1425] Step 14:

[1426] The server feeds back the effectiveness verification report to the user. It creates a report including specific numerical data and notifies the user. The input is the effectiveness verification report, and the output is the completion of feedback to the user.

[1427] (Application example 1)

[1428] 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."

[1429] Modern logistics centers require highly efficient and precise management. However, manual operation log recording and subsequent data analysis make it difficult to make real-time improvements, limiting the extent to which operational efficiency can be improved. Furthermore, the frequent occurrence of abnormal operations, the time and effort required to identify the causes, and the implementation of improvement proposals can lead to a decline in overall work efficiency.

[1430] 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.

[1431] In this invention, the server includes a means for using a smart device to record operation logs in real time, a means for providing feedback in real time, and a means for presenting specific improvement proposals to workers and determining whether or not to apply them, thereby enabling the rapid analysis and improvement of the work flow within the logistics center and the overall improvement of work efficiency.

[1432] An "operation log" is data that records a series of operations performed by a user.

[1433] "Server" refers to the central system that receives, stores, and analyzes operation logs.

[1434] "Business flow" refers to the series of steps and procedures that a business follows.

[1435] "Real-time feedback" refers to responses and suggestions for improvement that are provided immediately to the user's actions.

[1436] "Smart devices" refer to advanced electronic devices that record operational logs and provide feedback in real time.

[1437] "Abnormal operations" refer to frequent or inappropriate operations that deviate from normal business flow.

[1438] "Hypothesis" refers to a tentative explanation or speculation about the cause of the detected abnormal operation.

[1439] "User" refers to an individual or team that uses the system to carry out work.

[1440] "Improvement proposals" refer to proposals and action plans to improve the efficiency of business flows and operations.

[1441] "Monitoring" refers to the act of watching how new business processes are being used and measuring their effectiveness.

[1442] A "logistics center" refers to a location that manages the storage and delivery of goods.

[1443] The system of the present invention aims to improve the efficiency of operations within a logistics center. This system improves the workflow by recording operation logs, sending and saving them on a server, analyzing them, and presenting improvement proposals to the user.

[1444] Hardware and software configuration

[1445] Hardware:

[1446] 1. Smart devices: Used to record operation logs in real time. Smartphones and smart glasses are examples of such devices.

[1447] 2. Server: A central system that stores the received operation logs, analyzes them, and generates business improvement proposals.

[1448] software:

[1449] 1. Python: This is the main language used to implement the program in this system.

[1450] 2. Flask / Django: Web frameworks used for server-side API integration.

[1451] 3. requests: A library for making HTTP requests.

[1452] 4. Database: A system for storing operation logs and analysis results (e.g., MySQL, PostgreSQL).

[1453] Specific operation of the system

[1454] Recording and sending operation logs

[1455] The smart device terminal records each worker's operation in real time and periodically sends the data to the server. For example, operations such as "start picking" and "check inventory" are recorded.

[1456] Saving and analyzing operation logs

[1457] The server stores the received operation logs in a database and then performs data analysis to detect frequently performed operations and abnormal operations, i.e., operations that deviate from the normal business flow.

[1458] Hypothesis generation and feedback

[1459] The server generates a hypothesis based on the detected abnormal operation. For example, it may hypothesize that "the reason this operation is performed so frequently is due to uncertainty in inventory information." The hypothesis is then fed back to the user in real time. The user can then enter an answer based on the provided hypothesis and send the feedback to the server.

[1460] Proposing business improvement plans

[1461] The server generates specific business improvement proposals based on user feedback and presents them to the user. For example, the proposal might include "introducing a dashboard that displays inventory status in real time."

[1462] New workflow monitoring and effectiveness verification

[1463] After a new workflow is implemented, the server monitors its usage, verifies the extent to which the new workflow contributes to efficiency, and provides feedback to the user in the form of specific figures.

[1464] Specific examples

[1465] For example, if the "inventory check" operation is frequently performed in inventory management at a logistics center, the system records the operation in detail and sends the log to the server. The server analyzes the data, detects that the "inventory check" operation is abnormally frequent, and hypothesizes the cause. Based on user feedback, the server proposes a "dashboard that displays inventory status in real time." The new workflow is then adopted, its usage and effectiveness are monitored, and improvements in operational efficiency are confirmed.

[1466] Prompt Sentence Examples

[1467] "Design an application that records work logs at a logistics center and proposes improvement plans for efficiency. Please include a specific process flow, such as how to record operation logs, how to send and save the logs, how to analyze data, provide feedback, propose business improvement plans, and verify their effectiveness."

[1468] The above is a specific embodiment for carrying out the present invention.

[1469] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1470] Step 1:

[1471] Recording of operation logs

[1472] The terminal uses a smart device (smartphone or smart glasses) to record each operation performed by the worker in detail. The input includes operations performed by the worker, such as "start picking" and "check inventory." A timestamp is assigned to each input operation, making it clear which operation was performed and when. Operation log data is generated as output.

[1473] Step 2:

[1474] Sending operation logs

[1475] The terminal sends the recorded operation log to the server at regular intervals (for example, every hour). The input is the operation log data recorded in step 1. The transmission method is an HTTP request. After transmission, the output is when the server receives the log data.

[1476] Step 3:

[1477] Saving operation logs

[1478] The operation log received by the server is saved in the database. The input is the operation log data received in step 2. An SQL query is used as the saving method. The output is that the operation log data is stored in the database.

[1479] Step 4:

[1480] Analysis of operation logs

[1481] The server analyzes the saved operation logs. The input is the operation log data stored in the database. The analysis methods include frequency analysis and pattern recognition to detect frequently performed operations and abnormal operations. The output is the analysis results, which include abnormal operation patterns and frequently performed operation data.

[1482] Step 5:

[1483] Hypothesis generation

[1484] The server generates hypotheses about abnormal operations based on the analysis results. The input is the analysis result data from step 4. Hypotheses are automatically generated using an AI model. The output is a hypothesis such as "Inventory check operations are being performed frequently due to problems with inventory management."

[1485] Step 6:

[1486] Feedback Notifications

[1487] The server notifies the user of the generated hypothesis. The input is the hypothesis generated in step 5. Notification methods include real-time display on a smart device or sending an alert. The output is the notification result to the user.

[1488] Step 7:

[1489] Collecting user responses

[1490] The user inputs a response to the feedback provided to the server. The input is additional data and comments from the user. The output is when the server receives the response data.

[1491] Step 8:

[1492] Generate business improvement proposals

[1493] The server generates business improvement proposals based on the user's responses. The input is the user response data received in step 7. Taking into account past log data and user feedback, specific improvement proposals are created using AI. The output is improvement proposals such as a "dashboard that displays inventory status in real time."

[1494] Step 9:

[1495] Proposing business improvement plans

[1496] The server presents the generated business improvement proposals to the user. The input is the business improvement proposals generated in step 8. Notification methods include displaying a dashboard on a smart device and sending implementation proposals. The output is the improvement proposals presented to the user.

[1497] Step 10:

[1498] New Workflow Monitoring

[1499] The server monitors the usage of the new business flow. The input is the implementation data of the new business flow. The log data is analyzed in real time to verify the frequency of use and effectiveness. The output is the effectiveness measurement data as a result of the monitoring.

[1500] Step 11:

[1501] Effectiveness verification

[1502] The server verifies the effectiveness of the new business flow. The input is the monitoring data obtained in step 10. The data is compared and analyzed to evaluate improvements in business efficiency and changes in operation frequency. The output is a concrete result of the verification of effectiveness, such as "business efficiency has improved by 50%."

[1503] Step 12:

[1504] Providing Feedback

[1505] The server feeds back the results of the effectiveness verification to the user. The input is the results of the effectiveness verification obtained in step 11. Feedback methods include periodic reports and real-time notifications. The output is the feedback results to the user.

[1506] 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.

[1507] The system of the present invention achieves more effective business improvement by combining an emotion engine that recognizes user emotions. In addition to recording and analyzing operation logs, this system also collects and analyzes user emotion data, which is used to generate and present business improvement proposals. The specific processing flow is explained below.

[1508] Recording and sending operation logs

[1509] The terminal records each operation performed by the user in detail. For example, when a user performs an "inventory check" operation in an inventory management system, the operation details and timestamp are recorded. In addition, the emotion engine analyzes the user's facial expressions and voice during the operation and records them as emotion data. The recorded operation log and emotion data are sent to the server at regular intervals (for example, every hour). This allows data to be collected in real time.

[1510] Saving and analyzing operation logs and emotion data

[1511] The server stores the received operation logs and emotion data in a database. The data to be stored includes user IDs, operation details, timestamps, and emotion data. The server analyzes the business flow based on this data and visualizes frequently occurring operations and specific patterns.

[1512] Anomaly Detection and Hypothesis Generation

[1513] The server uses the analysis results to detect operations that occur abnormally frequently as anomalies. For example, if the "check inventory" operation occurs abnormally frequently compared to other operations, it marks it as an anomaly. In addition, it uses emotion data provided by the emotion engine to analyze the user's emotional state at the time the anomaly occurred. For example, if anxiety or stress is high, this will also be included in the data.

[1514] The server generates hypotheses for anomalies, such as "frequent stock checks are due to poor inventory management and users feeling anxious," which allows for the emotional factors behind the problem to be taken into account.

[1515] User feedback and business improvement proposal generation

[1516] The server notifies the user of the generated hypothesis. For example, it presents the user with a question such as, "Please tell me why inventory check operations are occurring so frequently." The user responds by providing specific reasons and additional information. For example, the user might answer, "Inventory checks are necessary frequently to prevent product shortages."

[1517] The server generates business improvement proposals based on the user's feedback and emotions. For example, it suggests a "dashboard that displays inventory status in real time." It also adjusts the content and presentation method of the proposals by taking into account the emotional data. For example, if the user is prone to stress, it will devise a more appropriate wording for the proposals.

[1518] Proposing and monitoring business improvement proposals

[1519] The server presents the generated business improvement proposals to the user. If the user evaluates the proposals and decides to implement them, the server designs and implements the new business flow. For example, it introduces a real-time inventory status dashboard.

[1520] New workflow monitoring and effectiveness verification

[1521] After the proposed improvements are implemented, the server monitors the usage of the new workflow, for example, by monitoring how frequently the dashboard is used and how the user's emotional state changes when operating it.

[1522] The server verifies the effectiveness of the new workflow. For example, it evaluates whether the number of "inventory check" operations has decreased and whether users' emotional state has improved after the dashboard was introduced.

[1523] Final feedback and establishing the flow

[1524] The server then provides the final evaluation results as feedback to the user. For example, it might report, "By introducing the dashboard, inventory check operations have decreased by 50%, and user stress levels have also decreased." Based on the evaluation results, the user and server then formally establish the new business flow as a business process.

[1525] In this way, the system according to the present invention not only realizes the efficiency and streamlining of the workflow, but also realizes comprehensive business improvement that takes into consideration the emotional aspects of the user.

[1526] The processing flow will be explained below.

[1527] Step 1:

[1528] The device records user operations in real time. For example, when a user performs an "inventory check" operation, the device records the operation details and a timestamp.

[1529] Step 2:

[1530] The device analyzes the user's emotional state using an emotion engine. For example, it analyzes the user's facial expressions and voice, and generates emotion data such as anxiety, stress, and satisfaction.

[1531] Step 3:

[1532] The device sends operation logs and emotion data to the server at regular intervals (for example, every hour), allowing data to be collected and sent in real time.

[1533] Step 4:

[1534] The server stores the received operation log and emotion data in a database. The stored data includes the user ID, operation details, timestamp, and emotion data.

[1535] Step 5:

[1536] The server analyzes the operation logs and emotion data stored in the database. The purpose of the analysis is to understand the overall picture of the user's workflow and extract frequently occurring operations and specific emotion patterns.

[1537] Step 6:

[1538] Based on the analysis results, the server detects operations that are abnormally frequent as anomalies. For example, if the "inventory check" operation is abnormally frequent compared to other operations, it will mark it as an anomaly.

[1539] Step 7:

[1540] The server also references the user's emotional data when an anomaly occurs and generates a hypothesis. For example, it may hypothesize that "inventory checks are being conducted frequently because inventory management is not being properly performed and users are feeling anxious."

[1541] Step 8:

[1542] The server notifies the user of the generated hypothesis. For example, it displays a question to the user such as "Please tell me why inventory check operations are occurring so frequently."

[1543] Step 9:

[1544] The user responds to the server's question by providing specific reasons and additional information, such as "The reason we need to check inventory frequently is to prevent products from running out."

[1545] Step 10:

[1546] The server generates business improvement proposals based on user feedback and emotional data, such as a dashboard that displays inventory status in real time.

[1547] Step 11:

[1548] The server presents the generated business improvement proposals to the user, who evaluates them and decides whether to implement them.

[1549] Step 12:

[1550] If the user decides to adopt the proposed improvement, the server designs and implements the new workflow, for example, by introducing a real-time inventory status dashboard.

[1551] Step 13:

[1552] The server monitors the usage of the new workflow, specifically how frequently the dashboard is used and how the user's emotional state changes when operating it.

[1553] Step 14:

[1554] The server verifies the effectiveness of the new workflow, for example, evaluating whether the number of "inventory check" operations has decreased and whether the user's emotional state has improved after the dashboard was introduced.

[1555] Step 15:

[1556] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered users' stress levels."

[1557] Step 16:

[1558] Based on the evaluation results, the user and the server establish the new workflow as a formal business process. In this way, the present invention aims to improve the efficiency of the workflow and the user's emotional state.

[1559] Example 2

[1560] 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."

[1561] Conventional business improvement systems proposed improvement measures based on the analysis of operation logs, but did not take into account the user's emotional state. As a result, improvement measures were sometimes proposed that ignored psychological factors, and were unable to reduce the user's stress and anxiety. Furthermore, when verifying the effectiveness of new business flows after their implementation, emotional data was not taken into account in the evaluation. These problems need to be solved.

[1562] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for recording an operation log, means for transmitting the operation log to the server, means for saving the operation log, means for analyzing the saved operation log and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating business improvement proposals based on the user responses, means for presenting the business improvement proposals to the user, means for collecting and analyzing emotional data, means for sending the operation log including the emotional data to the server, means for analyzing the emotional data during operations and associating it with anomalies, means for adjusting the business improvement proposals taking the emotional data into consideration, means for monitoring the usage status and emotional state of the new workflow, means for verifying the effectiveness of the new workflow, and means for feeding back the verification results to the user. This makes it possible to propose business improvements that take the user's emotional state into consideration, and also enables comprehensive evaluation including emotional data when verifying the effectiveness of a new workflow after its introduction.

[1563] An "operation log" refers to historical information about operations performed by a user within the system, and specifically includes the operation details, user ID, timestamp, etc.

[1564] "Emotion data" refers to information about the user's psychological state analyzed from their facial expressions and voice using an emotion engine, and specifically refers to data that quantifies emotional states such as anxiety, stress, and joy.

[1565] "Server" refers to a computer system that operates on a network and receives, stores, analyzes, and provides feedback on data.

[1566] A "terminal" refers to a hardware device that a user operates, specifically an electronic device such as a computer or smartphone.

[1567] "Business flow" refers to a series of steps or procedures for carrying out a specific business operation.

[1568] "Analysis" refers to the process of processing collected data to detect specific patterns or anomalies.

[1569] An "anomaly" refers to an operation that occurs abnormally frequently and deviates from normal operating patterns.

[1570] A "hypothesis" refers to a prediction or theory that is made to estimate the cause of an anomaly.

[1571] "Feedback" refers to the evaluation results and suggestions that the system provides to the user.

[1572] "Monitoring" refers to the process of continuously monitoring the usage of the new workflow and the emotional state of the user.

[1573] "Improvement proposals" refer to specific proposals aimed at streamlining business processes and improving user experiences.

[1574] The system of the present invention collects and analyzes user operation logs and emotional data to help improve business operations, which not only improves operational efficiency but also reduces the psychological burden on users.

[1575] Hardware and Software Configuration

[1576] Hardware

[1577] Device: A device operated by a user. This can include desktop computers, laptops, smartphones, etc. These devices are equipped with cameras and microphones to capture facial and audio data from the user.

[1578] Server: A central system that collects, stores, and analyzes data. It is equipped with a high-performance database and analysis engine.

[1579] software

[1580] Emotion engine: Software that runs on the device and uses the camera and microphone to analyze the user's facial expressions and voice to generate emotion data.

[1581] Database management system: Runs on the server and stores and manages operation logs and emotion data.

[1582] Analysis engine: Software that runs on a server and visualizes business processes and detects anomalies based on collected data.

[1583] Generative AI model: Generates business improvement proposals based on user feedback.

[1584] Data processing and calculation

[1585] The device records the user's operation log in real time and uses an emotion engine to collect emotional data during the operation. For example, when a user performs an "inventory check" operation, the degree of "anxiety" or "stress" is recorded as emotional data along with the operation details.

[1586] The collected data is sent to a server at regular intervals. The server stores the received data in a database, and an analysis engine analyzes the business flow based on the stored data. This analysis makes it possible to visualize frequently occurring operations and specific patterns.

[1587] Based on the analysis results, the server detects abnormally frequent operations (anomalies). It also uses emotional data to analyze the user's emotional state at the time the anomaly occurred and evaluates whether the anomaly is due to psychological factors. For example, if the "inventory check" operation is performed frequently and the user feels high stress when doing so, it will be marked as an anomaly.

[1588] The server uses a generative AI model to generate a hypothesis about the anomaly and prompts the user to confirm the hypothesis, for example, "Please tell me why inventory check operations are occurring so frequently."

[1589] Based on user feedback, the server generates business improvement proposals. These proposals are chosen with appropriate content and expressions, taking into account emotional data. For example, when proposing a "dashboard that displays inventory status in real time," gentle expressions are used to avoid causing excessive stress to the user.

[1590] Examples of concrete examples and prompts

[1591] As a specific usage scenario, consider a case where a user uses an inventory management system and frequently performs "inventory check" operations. At this time, the emotion engine analyzes the user's facial expressions and voice to indicate that "anxiety" and "stress" are increasing.

[1592] The collected operation logs and emotion data are sent to a server, which stores them in a database and analyzes business flows and anomalies. The server detects an abnormally high number of "inventory check" operations and hypothesizes that "frequent inventory checks are occurring because inventory management is not being done properly and users are feeling anxious."

[1593] Based on this hypothesis, the generative AI model asks the user for feedback, displaying a prompt saying, "Please tell us why you are frequently checking inventory." The specific feedback received from the user is, "The reason why inventory checks are necessary so frequently is to prevent products from running out."

[1594] Based on this feedback, the server generates a proposal for a dashboard that displays inventory status in real time and presents it to the user in a way that is thoughtful and stress-free for the user.

[1595] As described above, the present invention is a system that utilizes operation logs and emotion data to propose business improvements and verify their effectiveness.

[1596] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1597] Step 1: Recording operational logs

[1598] The device records all operations performed by the user. When a user performs an operation such as "check inventory," the operation details, user ID, and timestamp are saved as a log.

[1599] Input: User action (e.g., clicking the "Check stock" button)

[1600] Data processing: Collection of operation details, user ID, and timestamp

[1601] Output: Operation log (e.g. "Check stock", user ID, timestamp)

[1602] Step 2: Collect and analyze emotion data

[1603] The device collects the user's facial expressions and voice data using a camera and microphone, and an emotion engine analyzes this data to generate emotion data.

[1604] Input: User's facial expressions and voice

[1605] Data processing: Analyze facial expressions and voice to determine emotional state (e.g., "anxiety" 80%, "stress" 60%)

[1606] Output: Emotion data (e.g., "anxiety" 80%, "stress" 60%)

[1607] Step 3: Sending data

[1608] The device sends operation logs and emotion data to the server at regular intervals.

[1609] Input: Operation log, emotion data

[1610] Data processing: Converting data into packets

[1611] Output: Send data to the server

[1612] Step 4: Save your data

[1613] The server stores the received data in a database, including the user ID, operation details, timestamp, and emotion data.

[1614] Input: Operation log, emotion data

[1615] Data processing: Insertion into database

[1616] Output: Update record in database

[1617] Step 5: Analyze the workflow

[1618] The server analyzes the business flow based on the stored data, for example, extracting and visualizing frequently occurring operations.

[1619] Input: Database operation log data

[1620] Data processing: Calculation and visualization of frequency distribution

[1621] Output: Visualized workflow (e.g. heat map)

[1622] Step 6: Anomaly detection

[1623] Based on the analysis results, the server detects abnormally frequent operations as anomalies.

[1624] Input: Workflow analysis results

[1625] Data processing: Detecting anomalies using statistical methods

[1626] Output: Anomaly list (e.g., "Stock Check" is abnormally high)

[1627] Step 7: Hypothesis generation

[1628] The server generates hypotheses for anomalies, such as "frequent inventory checks are occurring because users are feeling anxious" based on emotional data.

[1629] Input: Anomaly list, emotion data

[1630] Data processing: linking anomalies with emotional states, generating hypotheses

[1631] Output: Hypothesis (e.g., "The reason people check their inventory so frequently is because they have problems with inventory management and are feeling anxious")

[1632] Step 8: Get user feedback

[1633] The server notifies the user of the generated hypothesis and asks for feedback, for example by displaying a prompt such as "Please tell us why inventory check operations are occurring so frequently."

[1634] Input: Hypothesis

[1635] Data processing: Prompt sentence generation

[1636] Output: User notification (e.g. "Please tell me why inventory check operations are occurring so frequently")

[1637] Step 9: Generate business improvement proposals

[1638] The server generates business improvement proposals based on user feedback and emotional data, such as a dashboard that displays inventory status in real time.

[1639] Input: User feedback, emotion data

[1640] Data processing: Generating business improvement proposals that take into account feedback and emotional data

[1641] Output: Business improvement proposals (e.g., "Implementation of a real-time inventory dashboard")

[1642] Step 10: Propose improvements

[1643] The server presents the generated business improvement proposals to the user, for example, recommending the introduction of a dashboard that displays inventory status in real time.

[1644] Input: Business improvement proposal

[1645] Data processing: Message conversion of proposal content

[1646] Output: Suggestion notification to the user (e.g. "We recommend you install the real-time inventory dashboard")

[1647] Step 11: Monitoring the new workflow

[1648] After the proposed improvements are implemented, the server monitors the usage of the new workflow and the user's emotional state.

[1649] Input: New business flow usage log, emotion data

[1650] Data processing: Collection and analysis of usage and sentiment data

[1651] Output: New business flow evaluation report

[1652] Step 12: Verify the effect

[1653] The server verifies the effectiveness of the new workflow, for example, whether the number of "inventory check" operations has decreased after the dashboard was introduced, or whether the user's emotional state has improved.

[1654] Input: New Workflow Evaluation Report

[1655] Data processing: Before and after comparison, effect verification

[1656] Output: Verification results (e.g., "Inventory check operations decreased by 50%, stress levels decreased")

[1657] Step 13: Final feedback

[1658] The server then provides the final evaluation results as feedback to the user, for example, reporting that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered user stress levels."

[1659] Input: Validation result

[1660] Data processing: feedback message generation

[1661] Output: Final report to the user

[1662] Step 14: Establishing the workflow

[1663] The user and server then formally establish the new business flow, the effectiveness of which has been confirmed based on the evaluation results, as a business process.

[1664] Input: Final report

[1665] Data processing: Setting up formal business flow

[1666] Output: Establishing a new workflow

[1667] In this way, specific input, data processing, and output are performed at each step, resulting in efficient business improvement and an improvement in the user's emotional state across the entire system.

[1668] (Application example 2)

[1669] 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."

[1670] Improving operational efficiency at logistics centers is an important issue for many companies. In particular, more effective operational improvements can be expected by considering the emotional aspects of workers in addition to their behavior. However, conventional systems have difficulty effectively utilizing data on worker emotions, resulting in only partial improvements to operational flow. Furthermore, when the cause of abnormal operations is due to emotions, there is also the issue of being unable to accurately identify the cause and propose improvement measures.

[1671] The identification process by the identification 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 recording an operation log, means for transmitting the operation log to the server, means for saving the operation log, means for analyzing the saved operation log and visualizing the workflow, means for detecting abnormally frequent operations, means for generating hypotheses about abnormal operations, means for notifying the user of the hypotheses, means for collecting user responses, means for generating workflow improvement plans based on the user responses, means for presenting the workflow improvement plans to the user, means for monitoring the usage status of the new workflow, means for verifying the effectiveness of the new workflow, means for providing feedback on the verification results to the user, means for collecting user emotion data, means for analyzing the collected emotion data, means for using the emotion data to generate workflow improvement plans, and means for generating workflow improvement plans that take emotional factors into account based on the analysis results. This improves the efficiency of the workflow at the logistics center and enables comprehensive workflow improvement that also takes the emotions of workers into account.

[1672] An "operation log" is a detailed record of each operation a user performs within the system.

[1673] "Emotion data" refers to data relating to the user's emotional state, such as information analyzed from facial expressions and voice.

[1674] The "server" is a central computing device that collects and analyzes operation logs and emotion data, and generates and presents business improvement proposals.

[1675] "Visualization" is the visual presentation of data, making specific patterns and anomalies visible.

[1676] An "anomaly" refers to an abnormal operation or behavior that deviates from normal operating patterns.

[1677] A "hypothesis" is a possible explanation or theory as to why an anomaly occurs.

[1678] "Business improvement proposals" are specific proposals and measures to streamline or improve the current business flow.

[1679] "Feedback" refers to the user's reaction and evaluation of the analysis results and improvement proposals.

[1680] "Monitoring" is the activity of continuously observing the status of a system or process.

[1681] "Effectiveness verification" is the process of evaluating whether the business improvement plan that has been implemented is actually having the expected effect.

[1682] The "Logistics Center Business Improvement Assistant" system of the present invention uses smartphones or smart glasses to collect operation logs and emotional data of workers working in a logistics center, and analyzes the data on a server to improve business efficiency.

[1683] System Program

[1684] The terminal has the function of recording the worker's operation log and sending it to the server. Specifically, when a worker performs an operation such as "start picking," the operation details and timestamp are recorded. At the same time, the terminal's camera is used to capture the worker's facial expression, and an emotion engine analyzes the worker's emotional state (e.g., anxiety, stress) from the facial expression. This data is periodically sent to the server.

[1685] Hardware and software used

[1686] The hardware used is a smartphone or smart glasses (e.g., Google Glass), and the camera built into these devices is used. The software used is an emotion recognition library (e.g., Emotion Recognition Library), a server-side data processing engine (e.g., an API built with Python or Flask), and a database (e.g., PostgreSQL).

[1687] Data processing and calculation

[1688] The server stores the received operation logs and emotion data in a database. The stored data includes user IDs, operation details, timestamps, and emotion data. The server analyzes this data and uses it to visualize business processes. For example, it identifies frequently occurring operations and specific patterns and displays them as graphs and charts.

[1689] Hypothesis generation and business improvement proposals

[1690] The server detects abnormally frequent operations (anomalies) from the analysis results and generates a hypothesis based on them. For example, it may hypothesize that "inventory checks are being performed frequently because inventory management is not being performed properly." This hypothesis is notified to the user, and specific reasons and additional information are collected. The server then generates business improvement proposals based on the user's answers and emotion data and presents them to the user.

[1691] Monitoring and effectiveness verification

[1692] After the proposed business improvement is implemented, the server monitors the usage of the new business flow. For example, it monitors how frequently a dashboard displaying real-time inventory status is used and how the user's emotional state changes when operating it. To verify the effectiveness of the new business flow, it also evaluates improvements in work efficiency and changes in the user's stress level.

[1693] Examples and prompts

[1694] For example, when a worker is picking items, the smart glasses recognize their movements and facial expressions and record them as emotion data. An example of a prompt for emotion analysis is as follows:

[1695] "Analyzing emotions from facial photos of workers taken with a smartphone camera"

[1696] In this way, the logistics center business improvement assistant system of the present invention streamlines the business flow of a logistics center and realizes comprehensive business improvement that also takes into account the emotional aspects of workers.

[1697] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1698] Step 1:

[1699] Operation log and emotional data recording

[1700] The terminal records the worker's operation log and emotional data. Specifically, when a worker performs an operation such as "start picking" using a smartphone or smart glasses, the operation details and timestamp are recorded. At the same time, the terminal's camera captures the worker's facial expression, and an emotion engine analyzes the facial expression to determine emotional data (e.g., anxiety, stress). The input is the worker's operation details and facial image data, and the output is the operation log and emotional data.

[1701] Step 2:

[1702] Sending data

[1703] The device sends the recorded operation log and emotion data to the server at regular intervals. Specifically, the process of sending this data to the server is performed using an HTTP request. The input is the operation log and emotion data, and the output is the data transfer to the server.

[1704] Step 3:

[1705] Data storage

[1706] The operation log and emotion data received by the server are stored in a database. Specifically, data including the user ID, operation content, timestamp, and emotion data is inserted into a database (e.g., PostgreSQL). The input is the operation log and emotion data sent to the server, and the output is storage in the database.

[1707] Step 4:

[1708] Data analysis

[1709] The server analyzes the stored operation logs and emotion data to visualize the business flow. Specifically, it retrieves data from the database and generates graphs and charts to visualize frequently occurring operations and specific operation patterns. The input is the operation logs and emotion data in the database, and the output is a graph or chart of the visualized business flow.

[1710] Step 5:

[1711] Anomaly Detection

[1712] The server detects operations that occur abnormally frequently as anomalies. Specifically, it detects anomalies using statistical methods based on the frequency distribution of standard operations. The input is analyzed operation log data, and the output is operation data tagged as anomalies.

[1713] Step 6:

[1714] Hypothesis generation

[1715] The server generates hypotheses based on anomalies. For example, it might create a hypothesis such as, "Frequent inventory checks are due to inappropriate inventory management, which makes workers feel anxious." The input is operation data and emotion data tagged as anomalies, and the output is the generated hypothesis.

[1716] Step 7:

[1717] User notification and feedback collection

[1718] The server notifies the user of the generated hypothesis and collects feedback. Specifically, it presents the user with the question, "Please tell us why inventory check operations are occurring so frequently," and collects the user's answer. The input is the hypothesis and the user's answer, and the output is the user's feedback.

[1719] Step 8:

[1720] Generate business improvement proposals

[1721] The server generates business improvement proposals based on user feedback and emotional data. Specifically, it proposes improvement proposals such as "introducing a dashboard that displays inventory status in real time." The input is user feedback and emotional data, and the output is the generated business improvement proposals.

[1722] Step 9:

[1723] Proposing business improvement plans

[1724] The server presents the generated business improvement proposals to the user. Specifically, it presents detailed information such as the dashboard design and how to use it. The input is the business improvement proposals, and the output is the improvement proposals presented to the user.

[1725] Step 10:

[1726] Monitoring new business processes

[1727] After the business improvement proposal is implemented, the server monitors the usage of the new business flow. Specifically, it monitors the frequency of dashboard use and changes in the user's emotional state. The input is the usage data and emotional data of the new business flow, and the output is the monitoring results.

[1728] Step 11:

[1729] Effectiveness verification

[1730] The server verifies the effectiveness of the new business flow. Specifically, it evaluates items such as "has the number of inventory check operations decreased?" and "has the user's stress level decreased?" The input is the monitoring results, and the output is an evaluation of the verified effectiveness.

[1731] Step 12:

[1732] Final Feedback

[1733] The server then feeds back the final evaluation results to the user. Specifically, it reports that "the introduction of the dashboard has reduced inventory check operations by 50% and lowered users' stress levels." The input is the evaluation result of the effect, and the output is feedback to the user.

[1734] 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.

[1735] 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.

[1736] 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.

[1737] 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.

[1738] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1739] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1740] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1741] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1742] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1743] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values,...

Claims

1. a means for recording an operation log; A means for transmitting the operation log to a server; A means for storing an operation log; A means of analyzing saved operation logs and visualizing business flows; means for detecting abnormally frequent operations; a means for generating hypotheses about abnormal operations; a means for informing a user of the hypothesis; a means for collecting user responses; A means for generating business improvement proposals based on the user's answers; A means for presenting business improvement proposals to users; A means of monitoring the use of the new workflow; A means of verifying the effectiveness of new business processes, A means for feeding back the verification results to the user; A system including:

2. The system according to claim 1 , further comprising means for allowing a user to evaluate the business improvement plan and decide whether or not to implement it.

3. The system according to claim 1 , further comprising means for extracting operations that may be suggestions for business improvement from the analyzed data.

Images