system

Abstract

Provide a system. The system analyzes work efficiency from PC operation logs and provides advice to users, a means for reading log data; A means of analyzing the read log data and calculating work efficiency, A means for generating advice based on the calculated work efficiency; means for storing the results including the generated advice; A system including:

Description

[Technical Field]

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

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

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

[0004] In today's work environment, users perform a wide variety of tasks on their PCs, which can result in reduced work efficiency. To improve efficiency, it is important to clearly understand which activities users spend their time on, and which are productive and which are unproductive. However, current technology lacks a method for providing appropriate analysis and feedback to achieve this. In particular, there is a lack of a system that can effectively and accurately analyze users' PC operation logs and provide specific advice based on the results. [Means for solving the problem]

[0005] To solve this problem, the present invention provides a system that analyzes work efficiency from a PC operation log and provides advice to the user. This system includes a means for reading log data, a means for analyzing the read log data and calculating work efficiency, and a means for generating advice based on the calculated work efficiency. Furthermore, by including a means for saving the results including the generated advice, the system allows the user to obtain specific guidelines for understanding and improving their own work efficiency. This allows the user to review their own work habits and improve their efficiency.

[0006] "Log data" refers to data that records a user's activities on a PC, and specifically includes the activity content, start time, end time, etc.

[0007] "Analysis" is the process of processing log data, evaluating user activity, and calculating work efficiency.

[0008] "Work efficiency" indicates the ratio of productive activity time to total activity time in a certain period, and is an index for evaluating the work efficiency of a user.

[0009] "Advice" refers to guidelines or suggestions provided to the user based on the analysis results, with the aim of improving the user's work efficiency.

[0010] A "means" refers to a method, device, or process used to achieve a particular purpose. [Brief explanation of the drawings]

[0011] [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 illustrating 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

[0012] 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.

[0013] First, the terms used in the following description will be explained.

[0014] 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).

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] This invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. This system reads and analyzes the user's operation log data, calculates efficiency based on the results, and provides specific advice to the user.

[0033] System Overview

[0034] The system includes the following main components:

[0035] 1. Log data reading method:

[0036] The server reads the user's operation log file from the specified path.

[0037] This log file records the type of activity (e.g., "working," "browsing") and its start and end times.

[0038] 2. Log data analysis methods:

[0039] The server analyzes the log data and calculates the time taken for each activity.

[0040] Work efficiency is calculated by adding up the time spent on productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time.

[0041] 3. Advice Generation Methods:

[0042] The server generates advice to be provided to the user based on the calculated work efficiency.

[0043] Depending on the level of efficiency, create a message that includes specific areas for improvement or maintenance.

[0044] 4. Result storage means:

[0045] The server will save the generated advice and efficiency results to the specified file.

[0046] The user can refer to the results later.

[0047] Specific examples

[0048] Below is a concrete example of how this system calculates work efficiency and generates advice based on the user's operation log data.

[0049] 1. Example of log data

[0050] A user's activity log contains the following data:

[0051] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0052] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0053] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[0054] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0055] 2. Log data analysis

[0056] The server parses each entry and calculates the duration of each activity from the start and end times.

[0057] The server sums the duration of productive activities ("working," "meeting," "coding") and calculates the percentage of total activity time.

[0058] For example, in the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[0059] 3. Generating Advice

[0060] The server generates advice to provide to the user based on the calculated efficiency.

[0061] For example, if efficiency is 75% or higher, the advice generated is "Excellent! Your work efficiency is high. Keep it up!"

[0062] 4. Saving the results

[0063] The server stores the calculated efficiency and generated advice in a JSON format file.

[0064] Users can refer to this file later to check their own work efficiency and identify areas for improvement.

[0065] As described above, this system aims to improve users' work efficiency by efficiently analyzing their PC operation logs and providing specific advice.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The server specifies the log file path and reads the log data. Specifically, the server opens the specified file (e.g., user_log.json) and reads the JSON-formatted data from the file. The read data is stored in memory as an operation log.

[0069] Step 2:

[0070] The server analyzes the read log data one by one. The server scans the entries in the log data in a loop and obtains the activity, start time, and end time of each entry.

[0071] Step 3:

[0072] The server calculates the duration of the activity using the start and end times of each log entry. It calculates the difference between the start and end times and converts it to seconds.

[0073] Step 4:

[0074] The server classifies the duration of each activity. For productive activities (e.g., "working," "meeting," "coding"), the duration is counted as productive time, while other activities only count towards the total activity time.

[0075] Step 5:

[0076] After the server has finished parsing all the log entries, it calculates work efficiency based on the productive time and total active time. Efficiency is calculated by dividing the productive time by the total active time and converting the result into a percentage.

[0077] Step 6:

[0078] The server generates advice based on the calculated work efficiency, selecting appropriate messages for when the efficiency is 75% or more, 50% or more, or less than 50%, and creating advice sentences containing specific guidelines to provide to the user.

[0079] Step 7:

[0080] The server saves the generated advice and performance results, converts them into a JSON format file, and writes it to the specified file path.

[0081] Step 8:

[0082] Users can refer to the saved result files as needed, check the results, understand their own work efficiency, and find areas for improvement.

[0083] Example 1

[0084] 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."

[0085] In today's work environment, it is important to accurately evaluate the efficiency of PC-based work and provide appropriate advice. However, conventional methods often involve analyzing operation log data and calculating work efficiency manually, which is time-consuming and inaccurate. Furthermore, advice given to users is often vague and does not contribute to improving work efficiency.

[0086] 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.

[0087] In this invention, the server includes means for reading user operation information from a specified path, means for analyzing the read operation information and calculating the duration of each activity, means for adding up productive activity time based on the analyzed information and calculating work efficiency, means for generating advice based on the calculated work efficiency, and means for saving the results including the generated advice as data. This makes it possible to accurately evaluate the user's work efficiency and quickly provide specific and useful advice.

[0088] A "user operation log" is data showing the history of operations performed by a user on a PC, and includes the activity content, start time, and end time.

[0089] "Work efficiency" is the ratio of productive activity time to total activity time calculated based on the user's log.

[0090] The "specified path" refers to a path in the file system that indicates the location where the operation log file is saved.

[0091] "Duration" refers to the time elapsed from the start time to the end time of each activity.

[0092] "Productive activities" refer to work that is directly related to a user's job and creates value (e.g., work, meetings, coding, etc.).

[0093] "Advice" refers to specific suggestions or instructions for the user to improve their work efficiency based on the calculated work efficiency.

[0094] "Data" refers to information indicating the calculation results and generated advice that is saved in a file or other format.

[0095] "Analyzing" refers to the process of interpreting the read operation log data and calculating the start time, end time, and duration of each activity.

[0096] "Calculating" is the process of using analyzed data to determine a specific numerical value (e.g., operational efficiency).

[0097] "Saving" refers to keeping the generated results and advice in a file format or other format so that they can be referenced later.

[0098] The present invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. This system reads and analyzes the user's operation log data, calculates work efficiency based on the results, and provides specific advice to the user. Specific embodiments of the present invention are described below.

[0099] System Overview

[0100] The system includes the following main components:

[0101] 1. Log data reading method

[0102] The server reads the user operation information from the specified path using the open function and json module from the Python standard library.

[0103] 2. Log data analysis methods

[0104] The server analyzes the operation information it reads and uses the datetime module to calculate the duration of each activity. The analyzed information is stored in dictionary format.

[0105] 3. Efficiency calculation method

[0106] Based on the analyzed information, the server totals the productive activity time and calculates the work efficiency relative to the total activity time.

[0107] 4. Advice Generation Method

[0108] The server generates specific advice to provide to the user based on the calculated business efficiency, and creates a message according to the efficiency.

[0109] 5. Result storage means

[0110] The server saves the generated advice and calculation results in a JSON format file, which the user can then refer to later.

[0111] Specific examples

[0112] Below is a concrete example of how this system calculates business efficiency and generates advice based on user operation log data.

[0113] 1. Example of log data

[0114] A user's activity log contains the following data:

[0115] [

[0116] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[0117] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[0118] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"},

[0119] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0120] ]

[0121] 2. Log data analysis

[0122] The server parses each entry and calculates the duration of each activity from its start and end times. For example, if the start time of "working" is 2023-10-01T09:00:00 and the end time is 2023-10-01T12:00:00, the duration is 3 hours.

[0123] 3. Efficiency Calculation

[0124] The server adds up the duration of productive activities (e.g., "working," "meeting," "coding") and calculates the percentage of that time relative to the total activity time. In the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[0125] 4. Generating Advice

[0126] The server generates advice to provide to the user based on the calculated efficiency. For example, if the efficiency is 75% or higher, the advice generated is "Excellent! Your work efficiency is high. Keep it up!"

[0127] 5. Saving the results

[0128] The server saves the calculation results and generated advice in a JSON-formatted file, which users can refer to later to check their own work efficiency and identify areas for improvement.

[0129] Examples of prompt statements

[0130] Below are some example prompts to input to a generative AI model:

[0131] Analyze user operation log data, calculate operational efficiency, and generate advice. Operation log data is as follows:

[0132] [

[0133] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[0134] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[0135] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"},

[0136] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0137] ]

[0138] The expected output is in the following format:

[0139] {

[0140] "efficiency":<efficiency_value> ,

[0141] "advice": "<advice_message> "

[0142] }

[0143] The above is one embodiment of the present invention. The purpose of the present invention is to improve the work efficiency of users by efficiently analyzing their PC operation logs and providing specific advice.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1:

[0146] The server reads the user operation log from the specified path.

[0147] Input: Path to the operation log file (e.g. "C: / logs / user_log.txt")

[0148] Output: List format of operation log data

[0149] Specific operation: The server uses the open function to open the log file and uses the json module to read the contents in list format, which stores the operation log data in memory.

[0150] Step 2:

[0151] The server analyzes the operation log data it has read and calculates the duration of each activity.

[0152] Input: Operation log data (e.g., [{"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},...])

[0153] Output: Analysis data including the duration of each activity

[0154] What it does: The server uses the datetime module to calculate the duration of each activity by comparing the start and end times. The duration is converted from a total number of seconds, and the parsed result is stored in a list.

[0155] Step 3:

[0156] Based on the analyzed information, the server totals the productive activity time and calculates the work efficiency relative to the total activity time.

[0157] Input: Parsed operation log data (e.g., [{"activity": "working", "duration": 3}, ...])

[0158] Output: Calculated operational efficiency (e.g., 93.33%)

[0159] Specific operation: The server extracts only specific productive activities (e.g., "working," "meeting," "coding") and sums up their duration. It then sums up the total activity time and calculates work efficiency from the ratio.

[0160] Step 4:

[0161] The server generates advice to be provided to the user based on the calculated business efficiency.

[0162] Input: Calculated operational efficiency (e.g., 93.33%)

[0163] Output: The generated advisory message (e.g., "Excellent! Your work efficiency is high. Keep it up!")

[0164] Specific behavior: The server generates different advice messages according to the work efficiency value. For example, if the efficiency is 75% or higher, the message "Excellent! Your work efficiency is high. Keep it up!" will be generated.

[0165] Step 5:

[0166] The server saves the generated advice and calculation results in a JSON format file.

[0167] Input: Generated advice message and calculation result (e.g., {"efficiency": 93.33, "advice": "Excellent! Your work efficiency is high. Keep it up!"})

[0168] Output: Saved JSON format file (e.g. "C: / logs / user_efficiency_result.json")

[0169] Specific operation: The server uses the json module to convert the advice and calculation results into JSON format and writes them to a file using the open function, so that the user can view the results later.

[0170] By following the steps above, the system can efficiently analyze the user's operation log and quickly provide specific advice.

[0171] (Application example 1)

[0172] 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."

[0173] Modern factories and production lines require efficient analysis of machine and robot operation logs to improve production efficiency and optimize maintenance. However, conventional methods have faced challenges, such as the time-consuming nature of analyzing operation logs and the difficulty of providing efficient maintenance advice. Additionally, there has been a lack of easy ways to acquire and display data outside the factory. This can easily lead to reduced productivity and delays in maintenance.

[0174] 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.

[0175] In this invention, the server

[0176] a means for reading log data;

[0177] A means of analyzing the read log data and calculating work efficiency,

[0178] A means for generating advice based on the calculated work efficiency;

[0179] means for storing the results including the generated advice;

[0180] A means for reading and analyzing the operation log of a factory machine and calculating production efficiency and error occurrence frequency;

[0181] a means for generating maintenance advice based on the calculated production efficiency and error occurrence frequency;

[0182] A means to obtain and display analysis results and advice via smartphone;

[0183] This makes it possible to efficiently analyze the operation logs of factory machines and easily provide advice on improving production efficiency and performing optimal maintenance. In addition, data can be acquired and displayed via smartphone, making it easy to check the situation even when away from the site, enabling quick response.

[0184] A "PC operation log" is data that records the history of all user operations performed on a personal computer.

[0185] "Work efficiency" is an indicator that refers to the ratio of productive to unproductive activities within a given period of time.

[0186] "Means for reading log data" refers to a device or program that has the function of retrieving operation logs and machine logs from a specified storage location.

[0187] The "means for analyzing log data and calculating work efficiency" refers to a device or program for analyzing the contents of the acquired operation log and calculating work efficiency and production efficiency.

[0188] The "means for generating advice based on calculated work efficiency" refers to a device or program that provides the user with points to improve or maintain based on the calculated efficiency.

[0189] The "means for saving the results including the generated advice" is a device or program that saves the generated advice and analysis results in a designated storage location.

[0190] "Factory machine operation logs" are data that record the operation history of machines and robots operating within a factory.

[0191] "Production efficiency" is an efficiency index calculated from the operating and downtime of machines and robots in factories and manufacturing sites, as well as the frequency of errors.

[0192] "Error frequency" is an indicator that refers to the number of times a machine or robot makes an error within a certain period of time.

[0193] The "means for generating maintenance advice" refers to a device or program that provides users with advice on maintenance timing and improvements based on production efficiency and error frequency.

[0194] "Means for obtaining and displaying analysis results and advice via a smartphone" refers to a device or program that obtains and displays analysis results and advice on a smartphone.

[0195] This invention is a system that analyzes PC operation logs and factory machine operation logs, analyzes work efficiency and production efficiency, and provides advice to users. This system reads and analyzes the operation logs, calculates efficiency based on the results, and provides specific advice to users.

[0196] System configuration

[0197] The system includes the following main components:

[0198] 1. Log data reading method

[0199] Log data is read from a server or smartphone. This data includes PC operation logs and factory machine operation logs.

[0200] For example, it has the function of obtaining operation log files from factory machines via Wi-Fi.

[0201] 2. Log data analysis methods

[0202] Analyze log data and calculate work efficiency and production efficiency.

[0203] Specifically, the type of activity (operation, stop, error, etc.) in the log data and the start and end times of each activity are obtained, and their duration is calculated.

[0204] Production efficiency is calculated by comparing the total operating time of factory machines with the time they are down.

[0205] 3. A means of generating advice based on calculated efficiencies

[0206] Based on the calculated efficiency, advice is generated to be provided to the user.

[0207] For example, if production efficiency is declining, specific improvement advice such as "Please carry out regular maintenance" is generated.

[0208] 4. A means of saving the results, including the generated advice

[0209] The generated advice and analysis results are saved to a specified file or cloud storage.

[0210] This allows users to refer to the analysis results later and carry out appropriate maintenance and business improvements.

[0211] 5. A means to obtain and display analysis results and advice via smartphone

[0212] It has the function of obtaining and displaying analysis results and advice on a smartphone.

[0213] Users can use their smartphones to easily check data even outside the factory and take any necessary action quickly.

[0214] Processing flow

[0215] The specific processing flow of this system is as follows:

[0216] 1. Reading the log data

[0217] The server reads the operation log file from the specified path or cloud storage. For example, the operation log generated by a factory machine contains the following data:

[0218] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0219] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0220] 2. Log data analysis

[0221] Analyze the log data and calculate the duration of each activity. For example, analyze that "running" activity is 3 hours and "stopped" activity is 30 minutes.

[0222] 3. Efficiency Calculation

[0223] Calculate production efficiency based on operating time and downtime. For example, in the above log data, the operating time is 3 hours and the total activity time is 3.5 hours, so the efficiency is approximately 85.71%.

[0224] 4. Generating and Saving Advice

[0225] Based on the calculated efficiency, advice is generated, such as a message saying, "Production efficiency is declining. Please inspect and replace the following parts."

[0226] The generated advice and analysis results are saved in JSON format.

[0227] 5. Display on smartphones

[0228] Display analysis results and advice on your smartphone, allowing users to take action quickly. Use the following prompt as an example:

[0229] Analyze the following log data, calculate the production efficiency and the number of errors, and if the production efficiency is less than 80%, provide appropriate maintenance advice.

[0230] Log Data:

[0231] [

[0232] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[0233] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[0234] {"activity": "running", "start_time": "2023-10-01T12:30:00", "end_time": "2023-10-01T14:00:00"},

[0235] {"activity": "error", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T14:15:00"},

[0236] {"activity": "running", "start_time": "2023-10-01T14:15:00", "end_time": "2023-10-01T17:00:00"}

[0237] ]

[0238] As described above, the system of the present invention aims to support efficient business improvement and maintenance through analysis of operation logs, thereby improving the efficiency of users' factory operations and work.

[0239] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0240] Step 1:

[0241] Loading log data

[0242] The server reads operation log files from the specified storage location or cloud storage. Specifically, the server receives the file path or storage URL as input and retrieves JSON-formatted log data from that location. As an example, the operation log file "robot_log.json" of a factory machine is read via Wi-Fi. The read data includes the type of each activity (e.g., "running," "stopped," "error") as well as the start and end times.

[0243] Step 2:

[0244] Analyzing log data

[0245] The server analyzes the loaded operation log data. In this process, it analyzes each activity entry and calculates the duration of each activity based on the start and end times. Specifically, the server receives the start and end times as input, calculates the difference between them, and outputs the duration. For example, it analyzes that "running" activity lasted 3 hours from 09:00 to 12:00, and "stopped" activity lasted 30 minutes from 12:00 to 12:30.

[0246] Step 3:

[0247] Efficiency calculations

[0248] The server calculates efficiency based on the analysis data. Specifically, the server adds up the duration of each activity and calculates the ratio of productive to unproductive activities. The input is the duration of each activity, and the output is the efficiency percentage. For example, if the working time is 3 hours and the total activity time is 3.5 hours, the efficiency is calculated to be approximately 85.71%.

[0249] Step 4:

[0250] Generating Advice

[0251] The server generates advice to provide to the user based on the calculated efficiency. Here, the server receives the efficiency percentage as input and generates a message according to that value. The output is an advice message. For example, if the efficiency is less than 80%, the advice generated is "Production efficiency is declining. Please inspect and replace the following parts."

[0252] Step 5:

[0253] Saving the results

[0254] The server saves the generated advice and analysis results to a specified file or cloud storage. Specifically, the server receives analysis results and advice messages as input and saves them in a JSON format file. The output is the saved file.

[0255] Step 6:

[0256] Display on smartphone

[0257] The device (smartphone) retrieves and displays the analysis results and advice from the cloud storage or server. Specifically, the smartphone receives the cloud storage URL or API endpoint as input and displays the data from that location. The output is the analysis results and advice messages displayed on the smartphone screen. As an example, let's perform an analysis using the following prompt:

[0258] Analyze the following log data, calculate the production efficiency and the number of errors, and if the production efficiency is less than 80%, provide appropriate maintenance advice.

[0259] Log Data:

[0260] [

[0261] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[0262] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[0263] {"activity": "running", "start_time": "2023-10-01T12:30:00", "end_time": "2023-10-01T14:00:00"},

[0264] {"activity": "error", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T14:15:00"},

[0265] {"activity": "running", "start_time": "2023-10-01T14:15:00", "end_time": "2023-10-01T17:00:00"}

[0266] ]

[0267] 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.

[0268] This invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide more appropriate advice that takes into account the user's mental state.

[0269] System Overview

[0270] The system includes the following main components:

[0271] 1. Log data reading method:

[0272] The server reads the user's operation log file from the specified path.

[0273] This log file records the type of activity, as well as the start and end times of each activity.

[0274] 2. Log data analysis methods:

[0275] The server analyzes the log data and calculates the time taken for each activity.

[0276] Work efficiency is calculated by adding up the time spent on productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time.

[0277] 3. Emotion recognition means (emotion engine):

[0278] The server recognizes the user's emotions through facial expressions, voice, keystrokes, etc.

[0279] The recognized emotion data is recorded together with the operation log data and is used during analysis.

[0280] 4. Advice Generation Methods:

[0281] The server generates advice to be provided to the user based on the calculated work efficiency and the recognized emotion.

[0282] Depending on the level of efficiency and the user's emotional state, a message containing specific improvements or points to maintain is created.

[0283] 5. Result storage means:

[0284] The server will save the generated advice and efficiency results to the specified file.

[0285] The user can refer to the results later.

[0286] Specific examples

[0287] Below is a concrete example of how this system calculates work efficiency and generates advice based on the user's operation log data and emotion data.

[0288] 1. Example of log data

[0289] A user's activity log contains the following data:

[0290] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0291] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0292] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[0293] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0294] 2. Example of Emotion Data

[0295] During the same period, the emotion engine recognized the following emotions:

[0296] {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[0297] {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[0298] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[0299] 3. Log data analysis

[0300] The server parses each entry and calculates the duration of each activity from the start and end times.

[0301] The duration of productive activities ("working," "meeting," "coding") is summed and calculated as a percentage of total activity time.

[0302] For example, in the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[0303] 4. Emotion Data Analysis

[0304] The server analyzes the emotion data obtained from the emotion engine to identify the user's emotional state.

[0305] In the above example, the user is recognized as feeling "happy" at 09:30, "neutral" at 12:15, and "stressed" at 15:00.

[0306] 5. Generating Advice

[0307] The server generates advice to provide to the user based on the calculated efficiency and the perceived emotion.

[0308] For example, if your efficiency is 93.33% and you are feeling "stressed" in the afternoon, the following advice will be generated: "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or managing your tasks differently to reduce stress."

[0309] 6. Saving the results

[0310] The server stores the calculated efficiency, generated advice, and emotion data in a JSON format file.

[0311] Users can refer to this file later to check their own work efficiency and emotional state and find appropriate improvements.

[0312] As described above, this system aims to improve users' work efficiency by efficiently analyzing their PC operation logs and emotional data and providing specific advice.

[0313] The processing flow will be explained below.

[0314] Step 1:

[0315] The server specifies the log file path and reads the log data. Specifically, the server opens the specified file (e.g., user_log.json) and reads the JSON-formatted data from the file. The read data is stored in memory as an operation log.

[0316] Step 2:

[0317] The server collects emotion data using an emotion engine, analyzing the user's camera footage, voice input, keystrokes, etc., and generates emotion data including the type of emotion and a timestamp.

[0318] Step 3:

[0319] The server analyzes the operation log data it has read one by one. The server scans the entries in the log data in a loop and obtains the activity, start time, and end time for each entry.

[0320] Step 4:

[0321] The server calculates the duration of the activity using the start and end times of each log entry. It calculates the difference between the start and end times and converts it to seconds.

[0322] Step 5:

[0323] The server classifies the duration of each activity. For productive activities (e.g., "working," "meeting," "coding"), the duration is counted as productive time, while other activities only count towards the total activity time.

[0324] Step 6:

[0325] After the server has finished parsing all the log entries, it calculates work efficiency based on the productive time and total active time. Efficiency is calculated by dividing the productive time by the total active time and converting the result into a percentage.

[0326] Step 7:

[0327] The server analyzes the collected emotional data, assessing the user's emotional state during a specific time period and determining which emotions were most prevalent.

[0328] Step 8:

[0329] The server generates advice based on the calculated work efficiency and analyzed emotional data. Depending on the degree of efficiency and the user's emotional state, it creates a message containing specific points to improve or maintain.

[0330] Step 9:

[0331] The server saves the generated advice, work efficiency, and emotion data, converts this data into a JSON format file, and writes it to the specified file path.

[0332] Step 10:

[0333] Users can refer to the saved result file as needed, check the results, understand their own work efficiency and emotional state, and find appropriate improvement measures.

[0334] Example 2

[0335] 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."

[0336] Conventional work efficiency analysis systems are limited to analyzing only the user's operation log data and are unable to provide advice that takes into account the user's emotional state. This makes it difficult to present appropriate countermeasures for performance declines and increased stress caused by the user's mental state. Therefore, there is a need to provide a system that can analyze the user's operation log data and emotional data in an integrated manner and provide more personalized advice.

[0337] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0338] In this invention, the server includes means for reading log data, means for analyzing the read log data and calculating work efficiency, means for collecting emotion data using an emotion engine that recognizes the user's emotions, means for generating advice based on the recognized emotion data and the calculated work efficiency, and means for saving the results including the generated advice. This makes it possible to comprehensively analyze the user's operation log and emotion data and provide more appropriate advice that takes the user's mental state into consideration.

[0339] "Log data" refers to records of a user's PC operations, and includes information such as the activity content, start time, and end time.

[0340] "Analysis" refers to the process of calculating specific indicators (e.g., work efficiency) based on log data and sentiment data.

[0341] "Work efficiency" indicates the ratio of the user's productive activity time divided by the total activity time, and is a numerical representation of the user's work efficiency.

[0342] An "emotion engine" refers to a system or algorithm that recognizes emotions from input data such as a user's facial expressions, voice, and keystrokes, and outputs the results as data.

[0343] "Emotion data" is data that includes the user's emotional state (e.g., happy, neutral, stressed, etc.) recognized by the emotion engine.

[0344] The "advice generation means" is a means for generating specific suggestions and improvements for the user as messages based on the analyzed work efficiency and the recognized emotion data.

[0345] The "means for saving results" refers to a means for saving the generated advice and analysis results in a file, database, etc., so that they can be referenced later.

[0346] This invention is a system that analyzes PC operation log data and emotion data, evaluates the user's work efficiency based on the data, and provides specific advice. As an embodiment of the invention, the operations of the server, terminal, and user will be mainly described below.

[0347] Server Operation

[0348] The server reads the user's PC operation log data from the specified path. Specifically, it uses Python's open function and json module to read the log data, which records the type of activity, start time, and end time of each activity. It also uses the datetime module to analyze the operation log data and calculate the time taken for each activity.

[0349] The server then uses an emotion engine, OpenCV, Google® Cloud Speech-to-Text API, and proprietary algorithms to collect emotion data from the user's facial expressions, voice, and keystrokes. The collected emotion data is recorded along with the operation log data and used for analysis.

[0350] The server generates advice by inputting a prompt into the generative AI model based on the calculated work efficiency and the recognized emotion data. An example of a prompt is, "The user's work efficiency is 93.33%, and a state of stress was recognized in the afternoon. Please generate appropriate advice based on this information." The generated advice is saved in a file in JSON format for later reference.

[0351] Device behavior

[0352] A module for recording operation log data is installed on the user's device. This module captures user operations in real time and records the activity content, start time, and end time. It is also possible to use an emotion engine on the device to recognize the user's emotions in real time. For example, emotion data can be collected by facial expression recognition using a camera or voice analysis using a microphone.

[0353] User Actions

[0354] Users operate their PCs as usual and perform tasks using specific software. Operation log data captured during these tasks is sent to the server periodically or at a set time. The user can then check the generated advice on their device and adjust their work methods based on specific areas for improvement or maintenance.

[0355] Specific examples

[0356] For example, if a user works on a PC all day and the operation log data contains the following data:

[0357] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0358] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0359] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[0360] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0361] Suppose the sentiment data collected during the same period is as follows:

[0362] {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[0363] {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[0364] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[0365] The server analyzes the log data and emotion data and inputs prompt sentences, such as the following, into the generative AI model:

[0366] "The user's work efficiency was 93.33% and a stressful state was detected in the afternoon. Please generate appropriate advice based on this information."

[0367] As a result, the generative AI model offers advice like this:

[0368] "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or your tasks differently to reduce managing stress."

[0369] The above is an embodiment of the present invention, which allows a user to voluntarily obtain specific advice for improving work efficiency based on their own PC operation log data and emotion data.

[0370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0371] Step 1: Loading the log data

[0372] The server reads the user's operation log file from the specified path. The input is the path to the log file, and the output is a JSON-formatted object of the read log data. Specifically, the log data is read from the file using Python's open function and the json module. For example, the processing is as follows: log_data = json.load(open('path / to / logfile.json')).

[0373] Step 2: Analyze the log data

[0374] The server analyzes the operation log data and calculates the time taken for each activity. The input is a JSON object of the log data, and the output is the duration of each activity and the total productive activity time. Specifically, it uses the datetime module to calculate the difference between the start time and the end time. For example, it processes as follows:

[0375] Input: "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"

[0376] Output: Duration of activity (3 hours)

[0377] Step 3: Collecting and Recognizing Emotional Data

[0378] The server uses an emotion engine to collect emotion data from the user's facial expressions, voice, and keystrokes. The input is real-time data from devices connected to the emotion engine, and the output is a dataset of recognized emotions. Specifically, facial recognition is performed using OpenCV, voice emotion recognition is performed using the Google Cloud Speech-to-Text API, and emotion is inferred based on keystroke patterns. For example, voice data is collected and the API is called to recognize emotions.

[0379] Step 4: Generating Advice

[0380] The server generates advice to provide to the user based on the calculated work efficiency and the recognized emotion data. The input is the calculated work efficiency and emotion data, and the output is the generated advice message. Specifically, the prompt sentence "The user's work efficiency is 93.33%, and a state of stress was recognized in the afternoon. Please generate appropriate advice based on this information" is input to the generative AI model, and the generated text is obtained.

[0381] Step 5: Save the results

[0382] The server saves the generated advice and analysis results to the specified file. The input is the dataset of the generated advice and analysis results, and the output is the saved JSON format file. Specifically, the json.dump function is used to write the result data to a file. For example, it is processed as follows: with open('path / to / resultfile.json', 'w') as result_file:

[0383] These are the processing steps of this system, which makes it possible to comprehensively analyze the user's PC operation log data and emotional data and provide appropriate advice.

[0384] (Application example 2)

[0385] 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."

[0386] Conventional work efficiency analysis systems were able to calculate efficiency based on a user's operation log, but it was difficult to provide appropriate advice that took the user's emotional state into consideration. Furthermore, while some systems were able to aggregate efficiency data and emotional data, they were unable to provide real-time advice based on that data. The present invention aims to provide a system that can provide more appropriate and practical advice in real time by analyzing not only a user's work efficiency but also their emotional state.

[0387] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0388] In this invention, the server includes means for reading log data, means for analyzing the read log data and emotion data to calculate work efficiency and the user's emotional state, means for generating advice based on the calculated work efficiency and the recognized emotion, means for providing the generated advice in real time, and means for saving results including the generated advice, thereby making it possible to generate specific advice from the user's operation log and emotion data and provide it in real time.

[0389] A "PC operation log" is data that includes a record of operations performed by a user on a PC, and includes the type of operation, start time, end time, and so on.

[0390] "Emotion data" refers to data that includes the user's emotional state as recognized through facial expressions, voice, keystrokes, and the like.

[0391] "Work efficiency" is an index of efficiency calculated based on the ratio of the time spent on a user's productive activities to the total activity time.

[0392] "Advice" is a message containing specific points to improve or maintain that are provided to the user based on the analyzed work efficiency and emotional state.

[0393] The "means for reading log data" is a device or program that has the function of reading the PC operation log from a specified path.

[0394] The "analyzing means" is a device or program that analyzes the duration of each activity and the user's emotional state based on the read log data and emotional data, and calculates work efficiency.

[0395] The "means for generating advice" is a device or program for creating an advice message to be provided to the user based on the analyzed work efficiency and the user's emotional state.

[0396] The "means for providing in real time" is a device or program for instantly presenting the generated advice to the user.

[0397] The "means for storing results" refers to a device or program for recording the generated advice and calculated work efficiency results so that they can be referenced later.

[0398] This invention is a system that analyzes work efficiency from PC operation logs and emotional data and provides advice to users.

[0399] First, the server reads the PC's operation log from the specified path. This log data records the type of activity, start time, and end time of each activity. Next, the server analyzes the read log data and calculates the time spent on each activity. It calculates work efficiency by adding up the time spent on productive activities (such as "working," "meeting," and "coding") and comparing this with the total activity time.

[0400] Meanwhile, the server also analyzes emotional data. Emotional data is recognized through the user's facial expressions, voice, keystrokes, etc. A camera and microphone are used for this recognition, and the emotional state is analyzed using a machine learning model such as TENSORFLOW (registered trademark). The recognized emotional data is recorded together with the operation log data and used for analysis.

[0401] The server then generates advice to provide to the user based on the calculated work efficiency and the recognized emotions. Specifically, it uses a generative AI model to automatically generate optimal advice from the analysis results. This advice may include a message such as, "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or managing your tasks differently to reduce stress," depending on the efficiency level and the user's emotional state.

[0402] The generated advice is displayed on the terminal in real time, allowing the user to immediately receive this advice and obtain specific instructions for improving their work. In addition, the server stores the generated advice and calculated work efficiency results for the user to refer to later.

[0403] For example, a user's activity log might contain the following data:

[0404] - {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0405] - {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0406] - {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[0407] - {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0408] Also, suppose the emotion engine recognizes the following emotions:

[0409] - {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[0410] - {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[0411] - {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[0412] Based on this data, the server calculates work efficiency and generates the following advice for the user:

[0413] "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or your tasks differently to reduce managing stress."

[0414] Below are some example prompts to input to a generative AI model:

[0415] "Based on the log data and emotion data below, please calculate work efficiency and generate advice.

[0416] Log Data:

[0417] {"activity": "assembling", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0418] {"activity": "inspecting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T17:00:00"}

[0419] Emotional Data:

[0420] {"time": "2023-10-01T10:30:00", "emotion": "happy"}

[0421] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[0422] Calculate work efficiency and generate advice based on emotional data.”

[0423] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0424] Step 1:

[0425] The server reads the PC's operation log data from the specified path. This operation log contains the type of activity, start time, and end time for each activity. The input is the path to the operation log data file, and the output is the raw operation log data. Specifically, the server reads the file and stores the data in memory.

[0426] Step 2:

[0427] The server analyzes the loaded operation log data and calculates the duration of each activity. During the analysis, it finds the difference between the start and end times of each log entry and records this for each activity. The input is the raw operation log data, and the output is the calculated duration data for each activity. Specifically, it calculates the difference between timestamps and processes the data.

[0428] Step 3:

[0429] The server calculates work efficiency by summing the duration of productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time. The input is the calculated duration data and activity classification information, and the output is the work efficiency percentage. Specifically, it tallies the activity time belonging to each category and calculates the ratio.

[0430] Step 4:

[0431] The server recognizes emotions based on the user's facial and voice data acquired from the camera and microphone. This recognition is performed using a machine learning model such as TensorFlow. The input is facial and voice data, and the output is recognized emotion data. Specifically, the server preprocesses the captured data, inputs it into the machine learning model, and obtains the results.

[0432] Step 5:

[0433] The server generates advice to provide to the user based on the analyzed work efficiency and recognized emotional data. A generative AI model is used to generate this advice. The input is the work efficiency rate and emotional data, and the output is an advice message. Specifically, the server inputs appropriate advice words based on the efficiency and emotional profile into the generative AI model as a prompt, and obtains the response.

[0434] Step 6:

[0435] The server displays the generated advice on the terminal in real time. Possible display methods include a pop-up on the screen or a voice notification. The input is the advice message, and the output is a notification to the user. Specific operations include sending messages to the notification system and controlling the display.

[0436] Step 7:

[0437] The server records the generated advice and calculated performance results and saves them for future reference. The input is advice messages and performance data, and the output is a saved log file. Specific operations include writing to a database or file system.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] [Second embodiment]

[0442] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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).

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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."

[0454] This invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. This system reads and analyzes the user's operation log data, calculates efficiency based on the results, and provides specific advice to the user.

[0455] System Overview

[0456] The system includes the following main components:

[0457] 1. Log data reading method:

[0458] The server reads the user's operation log file from the specified path.

[0459] This log file records the type of activity (e.g., "working," "browsing") and its start and end times.

[0460] 2. Log data analysis methods:

[0461] The server analyzes the log data and calculates the time taken for each activity.

[0462] Work efficiency is calculated by adding up the time spent on productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time.

[0463] 3. Advice Generation Methods:

[0464] The server generates advice to be provided to the user based on the calculated work efficiency.

[0465] Depending on the level of efficiency, create a message that includes specific areas for improvement or maintenance.

[0466] 4. Result storage means:

[0467] The server will save the generated advice and efficiency results to the specified file.

[0468] The user can refer to the results later.

[0469] Specific examples

[0470] Below is a concrete example of how this system calculates work efficiency and generates advice based on the user's operation log data.

[0471] 1. Example of log data

[0472] A user's activity log contains the following data:

[0473] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0474] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0475] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[0476] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0477] 2. Log data analysis

[0478] The server parses each entry and calculates the duration of each activity from the start and end times.

[0479] The server sums the duration of productive activities ("working," "meeting," "coding") and calculates the percentage of total activity time.

[0480] For example, in the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[0481] 3. Generating Advice

[0482] The server generates advice to provide to the user based on the calculated efficiency.

[0483] For example, if efficiency is 75% or higher, the advice generated is "Excellent! Your work efficiency is high. Keep it up!"

[0484] 4. Saving the results

[0485] The server stores the calculated efficiency and generated advice in a JSON format file.

[0486] Users can refer to this file later to check their own work efficiency and identify areas for improvement.

[0487] As described above, this system aims to improve users' work efficiency by efficiently analyzing their PC operation logs and providing specific advice.

[0488] The processing flow will be explained below.

[0489] Step 1:

[0490] The server specifies the log file path and reads the log data. Specifically, the server opens the specified file (e.g., user_log.json) and reads the JSON-formatted data from the file. The read data is stored in memory as an operation log.

[0491] Step 2:

[0492] The server analyzes the read log data one by one. The server scans the entries in the log data in a loop and obtains the activity, start time, and end time of each entry.

[0493] Step 3:

[0494] The server calculates the duration of the activity using the start and end times of each log entry. It calculates the difference between the start and end times and converts it to seconds.

[0495] Step 4:

[0496] The server classifies the duration of each activity. For productive activities (e.g., "working," "meeting," "coding"), the duration is counted as productive time, while other activities only count towards the total activity time.

[0497] Step 5:

[0498] After the server has finished parsing all the log entries, it calculates work efficiency based on the productive time and total active time. Efficiency is calculated by dividing the productive time by the total active time and converting the result into a percentage.

[0499] Step 6:

[0500] The server generates advice based on the calculated work efficiency, selecting appropriate messages for when the efficiency is 75% or more, 50% or more, or less than 50%, and creating advice sentences containing specific guidelines to provide to the user.

[0501] Step 7:

[0502] The server saves the generated advice and performance results, converts them into a JSON format file, and writes it to the specified file path.

[0503] Step 8:

[0504] Users can refer to the saved result files as needed, check the results, understand their own work efficiency, and find areas for improvement.

[0505] Example 1

[0506] 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."

[0507] In today's work environment, it is important to accurately evaluate the efficiency of PC-based work and provide appropriate advice. However, conventional methods often involve analyzing operation log data and calculating work efficiency manually, which is time-consuming and inaccurate. Furthermore, advice given to users is often vague and does not contribute to improving work efficiency.

[0508] 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.

[0509] In this invention, the server includes means for reading user operation information from a specified path, means for analyzing the read operation information and calculating the duration of each activity, means for adding up productive activity time based on the analyzed information and calculating work efficiency, means for generating advice based on the calculated work efficiency, and means for saving the results including the generated advice as data. This makes it possible to accurately evaluate the user's work efficiency and quickly provide specific and useful advice.

[0510] A "user operation log" is data showing the history of operations performed by a user on a PC, and includes the activity content, start time, and end time.

[0511] "Work efficiency" is the ratio of productive activity time to total activity time calculated based on the user's log.

[0512] The "specified path" refers to a path in the file system that indicates the location where the operation log file is saved.

[0513] "Duration" refers to the time elapsed from the start time to the end time of each activity.

[0514] "Productive activities" refer to work that is directly related to a user's job and creates value (e.g., work, meetings, coding, etc.).

[0515] "Advice" refers to specific suggestions or instructions for the user to improve their work efficiency based on the calculated work efficiency.

[0516] "Data" refers to information indicating the calculation results and generated advice that is saved in a file or other format.

[0517] "Analyzing" refers to the process of interpreting the read operation log data and calculating the start time, end time, and duration of each activity.

[0518] "Calculating" is the process of using analyzed data to determine a specific numerical value (e.g., operational efficiency).

[0519] "Saving" refers to keeping the generated results and advice in a file format or other format so that they can be referenced later.

[0520] The present invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. This system reads and analyzes the user's operation log data, calculates work efficiency based on the results, and provides specific advice to the user. Specific embodiments of the present invention are described below.

[0521] System Overview

[0522] The system includes the following main components:

[0523] 1. Log data reading method

[0524] The server reads the user operation information from the specified path using the open function and json module from the Python standard library.

[0525] 2. Log data analysis methods

[0526] The server analyzes the operation information it reads and uses the datetime module to calculate the duration of each activity. The analyzed information is stored in dictionary format.

[0527] 3. Efficiency calculation method

[0528] Based on the analyzed information, the server totals the productive activity time and calculates the work efficiency relative to the total activity time.

[0529] 4. Advice Generation Method

[0530] The server generates specific advice to provide to the user based on the calculated business efficiency, and creates a message according to the efficiency.

[0531] 5. Result storage means

[0532] The server saves the generated advice and calculation results in a JSON format file, which the user can then refer to later.

[0533] Specific examples

[0534] Below is a concrete example of how this system calculates business efficiency and generates advice based on user operation log data.

[0535] 1. Example of log data

[0536] A user's activity log contains the following data:

[0537] [

[0538] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[0539] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[0540] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"},

[0541] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0542] ]

[0543] 2. Log data analysis

[0544] The server parses each entry and calculates the duration of each activity from its start and end times. For example, if the start time of "working" is 2023-10-01T09:00:00 and the end time is 2023-10-01T12:00:00, the duration is 3 hours.

[0545] 3. Efficiency Calculation

[0546] The server adds up the duration of productive activities (e.g., "working," "meeting," "coding") and calculates the percentage of that time relative to the total activity time. In the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[0547] 4. Generating Advice

[0548] The server generates advice to provide to the user based on the calculated efficiency. For example, if the efficiency is 75% or higher, the advice generated is "Excellent! Your work efficiency is high. Keep it up!"

[0549] 5. Saving the results

[0550] The server saves the calculation results and generated advice in a JSON-formatted file, which users can refer to later to check their own work efficiency and identify areas for improvement.

[0551] Examples of prompt statements

[0552] Below are some example prompts to input to a generative AI model:

[0553] Analyze user operation log data, calculate operational efficiency, and generate advice. Operation log data is as follows:

[0554] [

[0555] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[0556] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[0557] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"},

[0558] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0559] ]

[0560] The expected output is in the following format:

[0561] {

[0562] "efficiency":<efficiency_value> ,

[0563] "advice": "<advice_message> "

[0564] }

[0565] The above is one embodiment of the present invention. The purpose of the present invention is to improve the work efficiency of users by efficiently analyzing their PC operation logs and providing specific advice.

[0566] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0567] Step 1:

[0568] The server reads the user operation log from the specified path.

[0569] Input: Path to the operation log file (e.g. "C: / logs / user_log.txt")

[0570] Output: List format of operation log data

[0571] Specific operation: The server uses the open function to open the log file and uses the json module to read the contents in list format, which stores the operation log data in memory.

[0572] Step 2:

[0573] The server analyzes the operation log data it has read and calculates the duration of each activity.

[0574] Input: Operation log data (e.g., [{"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},...])

[0575] Output: Analysis data including the duration of each activity

[0576] What it does: The server uses the datetime module to calculate the duration of each activity by comparing the start and end times. The duration is converted from a total number of seconds, and the parsed result is stored in a list.

[0577] Step 3:

[0578] Based on the analyzed information, the server totals the productive activity time and calculates the work efficiency relative to the total activity time.

[0579] Input: Parsed operation log data (e.g., [{"activity": "working", "duration": 3}, ...])

[0580] Output: Calculated operational efficiency (e.g., 93.33%)

[0581] Specific operation: The server extracts only specific productive activities (e.g., "working," "meeting," "coding") and sums up their duration. It then sums up the total activity time and calculates work efficiency from the ratio.

[0582] Step 4:

[0583] The server generates advice to be provided to the user based on the calculated business efficiency.

[0584] Input: Calculated operational efficiency (e.g., 93.33%)

[0585] Output: The generated advisory message (e.g., "Excellent! Your work efficiency is high. Keep it up!")

[0586] Specific behavior: The server generates different advice messages according to the work efficiency value. For example, if the efficiency is 75% or higher, the message "Excellent! Your work efficiency is high. Keep it up!" will be generated.

[0587] Step 5:

[0588] The server saves the generated advice and calculation results in a JSON format file.

[0589] Input: Generated advice message and calculation result (e.g., {"efficiency": 93.33, "advice": "Excellent! Your work efficiency is high. Keep it up!"})

[0590] Output: Saved JSON format file (e.g. "C: / logs / user_efficiency_result.json")

[0591] Specific operation: The server uses the json module to convert the advice and calculation results into JSON format and writes them to a file using the open function, so that the user can view the results later.

[0592] By following the steps above, the system can efficiently analyze the user's operation log and quickly provide specific advice.

[0593] (Application example 1)

[0594] 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."

[0595] Modern factories and production lines require efficient analysis of machine and robot operation logs to improve production efficiency and optimize maintenance. However, conventional methods have faced challenges, such as the time-consuming nature of analyzing operation logs and the difficulty of providing efficient maintenance advice. Additionally, there has been a lack of easy ways to acquire and display data outside the factory. This can easily lead to reduced productivity and delays in maintenance.

[0596] 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.

[0597] In this invention, the server

[0598] a means for reading log data;

[0599] A means of analyzing the read log data and calculating work efficiency,

[0600] A means for generating advice based on the calculated work efficiency;

[0601] means for storing the results including the generated advice;

[0602] A means for reading and analyzing the operation log of a factory machine and calculating production efficiency and error occurrence frequency;

[0603] a means for generating maintenance advice based on the calculated production efficiency and error occurrence frequency;

[0604] A means to obtain and display analysis results and advice via smartphone;

[0605] This makes it possible to efficiently analyze the operation logs of factory machines and easily provide advice on improving production efficiency and performing optimal maintenance. In addition, data can be acquired and displayed via smartphone, making it easy to check the situation even when away from the site, enabling quick response.

[0606] A "PC operation log" is data that records the history of all user operations performed on a personal computer.

[0607] "Work efficiency" is an indicator that refers to the ratio of productive to unproductive activities within a given period of time.

[0608] "Means for reading log data" refers to a device or program that has the function of retrieving operation logs and machine logs from a specified storage location.

[0609] The "means for analyzing log data and calculating work efficiency" refers to a device or program for analyzing the contents of the acquired operation log and calculating work efficiency and production efficiency.

[0610] The "means for generating advice based on calculated work efficiency" refers to a device or program that provides the user with points to improve or maintain based on the calculated efficiency.

[0611] The "means for saving the results including the generated advice" is a device or program that saves the generated advice and analysis results in a designated storage location.

[0612] "Factory machine operation logs" are data that record the operation history of machines and robots operating within a factory.

[0613] "Production efficiency" is an efficiency index calculated from the operating and downtime of machines and robots in factories and manufacturing sites, as well as the frequency of errors.

[0614] "Error frequency" is an indicator that refers to the number of times a machine or robot makes an error within a certain period of time.

[0615] The "means for generating maintenance advice" refers to a device or program that provides users with advice on maintenance timing and improvements based on production efficiency and error frequency.

[0616] "Means for obtaining and displaying analysis results and advice via a smartphone" refers to a device or program that obtains and displays analysis results and advice on a smartphone.

[0617] This invention is a system that analyzes PC operation logs and factory machine operation logs, analyzes work efficiency and production efficiency, and provides advice to users. This system reads and analyzes the operation logs, calculates efficiency based on the results, and provides specific advice to users.

[0618] System configuration

[0619] The system includes the following main components:

[0620] 1. Log data reading method

[0621] Log data is read from a server or smartphone. This data includes PC operation logs and factory machine operation logs.

[0622] For example, it has the function of obtaining operation log files from factory machines via Wi-Fi.

[0623] 2. Log data analysis methods

[0624] Analyze log data and calculate work efficiency and production efficiency.

[0625] Specifically, the type of activity (operation, stop, error, etc.) in the log data and the start and end times of each activity are obtained, and their duration is calculated.

[0626] Production efficiency is calculated by comparing the total operating time of factory machines with the time they are down.

[0627] 3. A means of generating advice based on calculated efficiencies

[0628] Based on the calculated efficiency, advice is generated to be provided to the user.

[0629] For example, if production efficiency is declining, specific improvement advice such as "Please carry out regular maintenance" is generated.

[0630] 4. A means of saving the results, including the generated advice

[0631] The generated advice and analysis results are saved to a specified file or cloud storage.

[0632] This allows users to refer to the analysis results later and carry out appropriate maintenance and business improvements.

[0633] 5. A means to obtain and display analysis results and advice via smartphone

[0634] It has the function of obtaining and displaying analysis results and advice on a smartphone.

[0635] Users can use their smartphones to easily check data even outside the factory and take any necessary action quickly.

[0636] Processing flow

[0637] The specific processing flow of this system is as follows:

[0638] 1. Reading the log data

[0639] The server reads the operation log file from the specified path or cloud storage. For example, the operation log generated by a factory machine contains the following data:

[0640] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0641] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0642] 2. Log data analysis

[0643] Analyze the log data and calculate the duration of each activity. For example, analyze that "running" activity is 3 hours and "stopped" activity is 30 minutes.

[0644] 3. Efficiency Calculation

[0645] Calculate production efficiency based on operating time and downtime. For example, in the above log data, the operating time is 3 hours and the total activity time is 3.5 hours, so the efficiency is approximately 85.71%.

[0646] 4. Generating and Saving Advice

[0647] Based on the calculated efficiency, advice is generated, such as a message saying, "Production efficiency is declining. Please inspect and replace the following parts."

[0648] The generated advice and analysis results are saved in JSON format.

[0649] 5. Display on smartphones

[0650] Display analysis results and advice on your smartphone, allowing users to take action quickly. Use the following prompt as an example:

[0651] Analyze the following log data, calculate the production efficiency and the number of errors, and if the production efficiency is less than 80%, provide appropriate maintenance advice.

[0652] Log Data:

[0653] [

[0654] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[0655] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[0656] {"activity": "running", "start_time": "2023-10-01T12:30:00", "end_time": "2023-10-01T14:00:00"},

[0657] {"activity": "error", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T14:15:00"},

[0658] {"activity": "running", "start_time": "2023-10-01T14:15:00", "end_time": "2023-10-01T17:00:00"}

[0659] ]

[0660] As described above, the system of the present invention aims to support efficient business improvement and maintenance through analysis of operation logs, thereby improving the efficiency of users' factory operations and work.

[0661] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0662] Step 1:

[0663] Loading log data

[0664] The server reads operation log files from the specified storage location or cloud storage. Specifically, the server receives the file path or storage URL as input and retrieves JSON-formatted log data from that location. As an example, the operation log file "robot_log.json" of a factory machine is read via Wi-Fi. The read data includes the type of each activity (e.g., "running," "stopped," "error") as well as the start and end times.

[0665] Step 2:

[0666] Analyzing log data

[0667] The server analyzes the loaded operation log data. In this process, it analyzes each activity entry and calculates the duration of each activity based on the start and end times. Specifically, the server receives the start and end times as input, calculates the difference between them, and outputs the duration. For example, it analyzes that "running" activity lasted 3 hours from 09:00 to 12:00, and "stopped" activity lasted 30 minutes from 12:00 to 12:30.

[0668] Step 3:

[0669] Efficiency calculations

[0670] The server calculates efficiency based on the analysis data. Specifically, the server adds up the duration of each activity and calculates the ratio of productive to unproductive activities. The input is the duration of each activity, and the output is the efficiency percentage. For example, if the working time is 3 hours and the total activity time is 3.5 hours, the efficiency is calculated to be approximately 85.71%.

[0671] Step 4:

[0672] Generating Advice

[0673] The server generates advice to provide to the user based on the calculated efficiency. Here, the server receives the efficiency percentage as input and generates a message according to that value. The output is an advice message. For example, if the efficiency is less than 80%, the advice generated is "Production efficiency is declining. Please inspect and replace the following parts."

[0674] Step 5:

[0675] Saving the results

[0676] The server saves the generated advice and analysis results to a specified file or cloud storage. Specifically, the server receives analysis results and advice messages as input and saves them in a JSON format file. The output is the saved file.

[0677] Step 6:

[0678] Display on smartphone

[0679] The device (smartphone) retrieves and displays the analysis results and advice from the cloud storage or server. Specifically, the smartphone receives the cloud storage URL or API endpoint as input and displays the data from that location. The output is the analysis results and advice messages displayed on the smartphone screen. As an example, let's perform an analysis using the following prompt:

[0680] Analyze the following log data, calculate the production efficiency and the number of errors, and if the production efficiency is less than 80%, provide appropriate maintenance advice.

[0681] Log Data:

[0682] [

[0683] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[0684] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[0685] {"activity": "running", "start_time": "2023-10-01T12:30:00", "end_time": "2023-10-01T14:00:00"},

[0686] {"activity": "error", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T14:15:00"},

[0687] {"activity": "running", "start_time": "2023-10-01T14:15:00", "end_time": "2023-10-01T17:00:00"}

[0688] ]

[0689] 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.

[0690] This invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide more appropriate advice that takes into account the user's mental state.

[0691] System Overview

[0692] The system includes the following main components:

[0693] 1. Log data reading method:

[0694] The server reads the user's operation log file from the specified path.

[0695] This log file records the type of activity, as well as the start and end times of each activity.

[0696] 2. Log data analysis methods:

[0697] The server analyzes the log data and calculates the time taken for each activity.

[0698] Work efficiency is calculated by adding up the time spent on productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time.

[0699] 3. Emotion recognition means (emotion engine):

[0700] The server recognizes the user's emotions through facial expressions, voice, keystrokes, etc.

[0701] The recognized emotion data is recorded together with the operation log data and is used during analysis.

[0702] 4. Advice Generation Methods:

[0703] The server generates advice to be provided to the user based on the calculated work efficiency and the recognized emotion.

[0704] Depending on the level of efficiency and the user's emotional state, a message containing specific improvements or points to maintain is created.

[0705] 5. Result storage means:

[0706] The server will save the generated advice and efficiency results to the specified file.

[0707] The user can refer to the results later.

[0708] Specific examples

[0709] Below is a concrete example of how this system calculates work efficiency and generates advice based on the user's operation log data and emotion data.

[0710] 1. Example of log data

[0711] A user's activity log contains the following data:

[0712] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0713] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0714] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[0715] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0716] 2. Example of Emotion Data

[0717] During the same period, the emotion engine recognized the following emotions:

[0718] {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[0719] {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[0720] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[0721] 3. Log data analysis

[0722] The server parses each entry and calculates the duration of each activity from the start and end times.

[0723] The duration of productive activities ("working," "meeting," "coding") is summed and calculated as a percentage of total activity time.

[0724] For example, in the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[0725] 4. Emotion Data Analysis

[0726] The server analyzes the emotion data obtained from the emotion engine to identify the user's emotional state.

[0727] In the above example, the user is recognized as feeling "happy" at 09:30, "neutral" at 12:15, and "stressed" at 15:00.

[0728] 5. Generating Advice

[0729] The server generates advice to provide to the user based on the calculated efficiency and the perceived emotion.

[0730] For example, if your efficiency is 93.33% and you are feeling "stressed" in the afternoon, the following advice will be generated: "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or managing your tasks differently to reduce stress."

[0731] 6. Saving the results

[0732] The server stores the calculated efficiency, generated advice, and emotion data in a JSON format file.

[0733] Users can refer to this file later to check their own work efficiency and emotional state and find appropriate improvements.

[0734] As described above, this system aims to improve users' work efficiency by efficiently analyzing their PC operation logs and emotional data and providing specific advice.

[0735] The processing flow will be explained below.

[0736] Step 1:

[0737] The server specifies the log file path and reads the log data. Specifically, the server opens the specified file (e.g., user_log.json) and reads the JSON-formatted data from the file. The read data is stored in memory as an operation log.

[0738] Step 2:

[0739] The server collects emotion data using an emotion engine, analyzing the user's camera footage, voice input, keystrokes, etc., and generates emotion data including the type of emotion and a timestamp.

[0740] Step 3:

[0741] The server analyzes the operation log data it has read one by one. The server scans the entries in the log data in a loop and obtains the activity, start time, and end time for each entry.

[0742] Step 4:

[0743] The server calculates the duration of the activity using the start and end times of each log entry. It calculates the difference between the start and end times and converts it to seconds.

[0744] Step 5:

[0745] The server classifies the duration of each activity. For productive activities (e.g., "working," "meeting," "coding"), the duration is counted as productive time, while other activities only count towards the total activity time.

[0746] Step 6:

[0747] After the server has finished parsing all the log entries, it calculates work efficiency based on the productive time and total active time. Efficiency is calculated by dividing the productive time by the total active time and converting the result into a percentage.

[0748] Step 7:

[0749] The server analyzes the collected emotional data, assessing the user's emotional state during a specific time period and determining which emotions were most prevalent.

[0750] Step 8:

[0751] The server generates advice based on the calculated work efficiency and analyzed emotional data. Depending on the degree of efficiency and the user's emotional state, it creates a message containing specific points to improve or maintain.

[0752] Step 9:

[0753] The server saves the generated advice, work efficiency, and emotion data, converts this data into a JSON format file, and writes it to the specified file path.

[0754] Step 10:

[0755] Users can refer to the saved result file as needed, check the results, understand their own work efficiency and emotional state, and find appropriate improvement measures.

[0756] Example 2

[0757] 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."

[0758] Conventional work efficiency analysis systems are limited to analyzing only the user's operation log data and are unable to provide advice that takes into account the user's emotional state. This makes it difficult to present appropriate countermeasures for performance declines and increased stress caused by the user's mental state. Therefore, there is a need to provide a system that can analyze the user's operation log data and emotional data in an integrated manner and provide more personalized advice.

[0759] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0760] In this invention, the server includes means for reading log data, means for analyzing the read log data and calculating work efficiency, means for collecting emotion data using an emotion engine that recognizes the user's emotions, means for generating advice based on the recognized emotion data and the calculated work efficiency, and means for saving the results including the generated advice. This makes it possible to comprehensively analyze the user's operation log and emotion data and provide more appropriate advice that takes the user's mental state into consideration.

[0761] "Log data" refers to records of a user's PC operations, and includes information such as the activity content, start time, and end time.

[0762] "Analysis" refers to the process of calculating specific indicators (e.g., work efficiency) based on log data and sentiment data.

[0763] "Work efficiency" indicates the ratio of the user's productive activity time divided by the total activity time, and is a numerical representation of the user's work efficiency.

[0764] An "emotion engine" refers to a system or algorithm that recognizes emotions from input data such as a user's facial expressions, voice, and keystrokes, and outputs the results as data.

[0765] "Emotion data" is data that includes the user's emotional state (e.g., happy, neutral, stressed, etc.) recognized by the emotion engine.

[0766] The "advice generation means" is a means for generating specific suggestions and improvements for the user as messages based on the analyzed work efficiency and the recognized emotion data.

[0767] The "means for saving results" refers to a means for saving the generated advice and analysis results in a file, database, etc., so that they can be referenced later.

[0768] This invention is a system that analyzes PC operation log data and emotion data, evaluates the user's work efficiency based on the data, and provides specific advice. As an embodiment of the invention, the operations of the server, terminal, and user will be mainly described below.

[0769] Server Operation

[0770] The server reads the user's PC operation log data from the specified path. Specifically, it uses Python's open function and json module to read the log data, which records the type of activity, start time, and end time of each activity. It also uses the datetime module to analyze the operation log data and calculate the time taken for each activity.

[0771] The server then uses an emotion engine, OpenCV, Google Cloud Speech-to-Text API, and proprietary algorithms to collect emotion data from the user's facial expressions, voice, and keystrokes. The collected emotion data is recorded along with operation log data and used for analysis.

[0772] The server generates advice by inputting a prompt into the generative AI model based on the calculated work efficiency and the recognized emotion data. An example of a prompt is, "The user's work efficiency is 93.33%, and a state of stress was recognized in the afternoon. Please generate appropriate advice based on this information." The generated advice is saved in a file in JSON format for later reference.

[0773] Device behavior

[0774] A module for recording operation log data is installed on the user's device. This module captures user operations in real time and records the activity content, start time, and end time. It is also possible to use an emotion engine on the device to recognize the user's emotions in real time. For example, emotion data can be collected by facial expression recognition using a camera or voice analysis using a microphone.

[0775] User Actions

[0776] Users operate their PCs as usual and perform tasks using specific software. Operation log data captured during these tasks is sent to the server periodically or at a set time. The user can then check the generated advice on their device and adjust their work methods based on specific areas for improvement or maintenance.

[0777] Specific examples

[0778] For example, if a user works on a PC all day and the operation log data contains the following data:

[0779] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0780] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0781] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[0782] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0783] Suppose the sentiment data collected during the same period is as follows:

[0784] {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[0785] {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[0786] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[0787] The server analyzes the log data and emotion data and inputs prompt sentences, such as the following, into the generative AI model:

[0788] "The user's work efficiency was 93.33% and a stressful state was detected in the afternoon. Please generate appropriate advice based on this information."

[0789] As a result, the generative AI model offers advice like this:

[0790] "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or your tasks differently to reduce managing stress."

[0791] The above is an embodiment of the present invention, which allows a user to voluntarily obtain specific advice for improving work efficiency based on their own PC operation log data and emotion data.

[0792] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0793] Step 1: Loading the log data

[0794] The server reads the user's operation log file from the specified path. The input is the path to the log file, and the output is a JSON-formatted object of the read log data. Specifically, the log data is read from the file using Python's open function and the json module. For example, the processing is as follows: log_data = json.load(open('path / to / logfile.json')).

[0795] Step 2: Analyze the log data

[0796] The server analyzes the operation log data and calculates the time taken for each activity. The input is a JSON object of the log data, and the output is the duration of each activity and the total productive activity time. Specifically, it uses the datetime module to calculate the difference between the start time and the end time. For example, it processes as follows:

[0797] Input: "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"

[0798] Output: Duration of activity (3 hours)

[0799] Step 3: Collecting and Recognizing Emotional Data

[0800] The server uses an emotion engine to collect emotion data from the user's facial expressions, voice, and keystrokes. The input is real-time data from devices connected to the emotion engine, and the output is a dataset of recognized emotions. Specifically, facial recognition is performed using OpenCV, voice emotion recognition is performed using the Google Cloud Speech-to-Text API, and emotion is inferred based on keystroke patterns. For example, voice data is collected and the API is called to recognize emotions.

[0801] Step 4: Generating Advice

[0802] The server generates advice to provide to the user based on the calculated work efficiency and the recognized emotion data. The input is the calculated work efficiency and emotion data, and the output is the generated advice message. Specifically, the prompt sentence "The user's work efficiency is 93.33%, and a state of stress was recognized in the afternoon. Please generate appropriate advice based on this information" is input to the generative AI model, and the generated text is obtained.

[0803] Step 5: Save the results

[0804] The server saves the generated advice and analysis results to the specified file. The input is the dataset of the generated advice and analysis results, and the output is the saved JSON format file. Specifically, the json.dump function is used to write the result data to a file. For example, it is processed as follows: with open('path / to / resultfile.json', 'w') as result_file:

[0805] These are the processing steps of this system, which makes it possible to comprehensively analyze the user's PC operation log data and emotional data and provide appropriate advice.

[0806] (Application example 2)

[0807] 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."

[0808] Conventional work efficiency analysis systems were able to calculate efficiency based on a user's operation log, but it was difficult to provide appropriate advice that took the user's emotional state into consideration. Furthermore, while some systems were able to aggregate efficiency data and emotional data, they were unable to provide real-time advice based on that data. The present invention aims to provide a system that can provide more appropriate and practical advice in real time by analyzing not only a user's work efficiency but also their emotional state.

[0809] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0810] In this invention, the server includes means for reading log data, means for analyzing the read log data and emotion data to calculate work efficiency and the user's emotional state, means for generating advice based on the calculated work efficiency and the recognized emotion, means for providing the generated advice in real time, and means for saving results including the generated advice, thereby making it possible to generate specific advice from the user's operation log and emotion data and provide it in real time.

[0811] A "PC operation log" is data that includes a record of operations performed by a user on a PC, and includes the type of operation, start time, end time, and so on.

[0812] "Emotion data" refers to data that includes the user's emotional state as recognized through facial expressions, voice, keystrokes, and the like.

[0813] "Work efficiency" is an index of efficiency calculated based on the ratio of the time spent on a user's productive activities to the total activity time.

[0814] "Advice" is a message containing specific points to improve or maintain that are provided to the user based on the analyzed work efficiency and emotional state.

[0815] The "means for reading log data" is a device or program that has the function of reading the PC operation log from a specified path.

[0816] The "analyzing means" is a device or program that analyzes the duration of each activity and the user's emotional state based on the read log data and emotional data, and calculates work efficiency.

[0817] The "means for generating advice" is a device or program for creating an advice message to be provided to the user based on the analyzed work efficiency and the user's emotional state.

[0818] The "means for providing in real time" is a device or program for instantly presenting the generated advice to the user.

[0819] The "means for storing results" refers to a device or program for recording the generated advice and calculated work efficiency results so that they can be referenced later.

[0820] This invention is a system that analyzes work efficiency from PC operation logs and emotional data and provides advice to users.

[0821] First, the server reads the PC's operation log from the specified path. This log data records the type of activity, start time, and end time of each activity. Next, the server analyzes the read log data and calculates the time spent on each activity. It calculates work efficiency by adding up the time spent on productive activities (such as "working," "meeting," and "coding") and comparing this with the total activity time.

[0822] Meanwhile, the server also analyzes emotional data. Emotional data is recognized through the user's facial expressions, voice, keystrokes, etc. This recognition is performed using a camera and microphone, and the emotional state is analyzed using a machine learning model such as TensorFlow. The recognized emotional data is recorded along with the operation log data and used for analysis.

[0823] The server then generates advice to provide to the user based on the calculated work efficiency and the recognized emotions. Specifically, it uses a generative AI model to automatically generate optimal advice from the analysis results. This advice may include a message such as, "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or managing your tasks differently to reduce stress," depending on the efficiency level and the user's emotional state.

[0824] The generated advice is displayed on the terminal in real time, allowing the user to immediately receive this advice and obtain specific instructions for improving their work. In addition, the server stores the generated advice and calculated work efficiency results for the user to refer to later.

[0825] For example, a user's activity log might contain the following data:

[0826] - {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0827] - {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0828] - {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[0829] - {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0830] Also, suppose the emotion engine recognizes the following emotions:

[0831] - {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[0832] - {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[0833] - {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[0834] Based on this data, the server calculates work efficiency and generates the following advice for the user:

[0835] "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or your tasks differently to reduce managing stress."

[0836] Below are some example prompts to input to a generative AI model:

[0837] "Based on the log data and emotion data below, please calculate work efficiency and generate advice.

[0838] Log Data:

[0839] {"activity": "assembling", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0840] {"activity": "inspecting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T17:00:00"}

[0841] Emotional Data:

[0842] {"time": "2023-10-01T10:30:00", "emotion": "happy"}

[0843] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[0844] Calculate work efficiency and generate advice based on emotional data.”

[0845] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0846] Step 1:

[0847] The server reads the PC's operation log data from the specified path. This operation log contains the type of activity, start time, and end time for each activity. The input is the path to the operation log data file, and the output is the raw operation log data. Specifically, the server reads the file and stores the data in memory.

[0848] Step 2:

[0849] The server analyzes the loaded operation log data and calculates the duration of each activity. During the analysis, it finds the difference between the start and end times of each log entry and records this for each activity. The input is the raw operation log data, and the output is the calculated duration data for each activity. Specifically, it calculates the difference between timestamps and processes the data.

[0850] Step 3:

[0851] The server calculates work efficiency by summing the duration of productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time. The input is the calculated duration data and activity classification information, and the output is the work efficiency percentage. Specifically, it tallies the activity time belonging to each category and calculates the ratio.

[0852] Step 4:

[0853] The server recognizes emotions based on the user's facial and voice data acquired from the camera and microphone. This recognition is performed using a machine learning model such as TensorFlow. The input is facial and voice data, and the output is recognized emotion data. Specifically, the server preprocesses the captured data, inputs it into the machine learning model, and obtains the results.

[0854] Step 5:

[0855] The server generates advice to provide to the user based on the analyzed work efficiency and recognized emotional data. A generative AI model is used to generate this advice. The input is the work efficiency rate and emotional data, and the output is an advice message. Specifically, the server inputs appropriate advice words based on the efficiency and emotional profile into the generative AI model as a prompt, and obtains the response.

[0856] Step 6:

[0857] The server displays the generated advice on the terminal in real time. Possible display methods include a pop-up on the screen or a voice notification. The input is the advice message, and the output is a notification to the user. Specific operations include sending messages to the notification system and controlling the display.

[0858] Step 7:

[0859] The server records the generated advice and calculated performance results and saves them for future reference. The input is advice messages and performance data, and the output is a saved log file. Specific operations include writing to a database or file system.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] [Third embodiment]

[0864] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0865] 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.

[0866] 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).

[0867] 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.

[0868] 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.

[0869] 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).

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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."

[0876] This invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. This system reads and analyzes the user's operation log data, calculates efficiency based on the results, and provides specific advice to the user.

[0877] System Overview

[0878] The system includes the following main components:

[0879] 1. Log data reading method:

[0880] The server reads the user's operation log file from the specified path.

[0881] This log file records the type of activity (e.g., "working," "browsing") and its start and end times.

[0882] 2. Log data analysis methods:

[0883] The server analyzes the log data and calculates the time taken for each activity.

[0884] Work efficiency is calculated by adding up the time spent on productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time.

[0885] 3. Advice Generation Methods:

[0886] The server generates advice to be provided to the user based on the calculated work efficiency.

[0887] Depending on the level of efficiency, create a message that includes specific areas for improvement or maintenance.

[0888] 4. Result storage means:

[0889] The server will save the generated advice and efficiency results to the specified file.

[0890] The user can refer to the results later.

[0891] Specific examples

[0892] Below is a concrete example of how this system calculates work efficiency and generates advice based on the user's operation log data.

[0893] 1. Example of log data

[0894] A user's activity log contains the following data:

[0895] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[0896] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[0897] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[0898] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0899] 2. Log data analysis

[0900] The server parses each entry and calculates the duration of each activity from the start and end times.

[0901] The server sums the duration of productive activities ("working," "meeting," "coding") and calculates the percentage of total activity time.

[0902] For example, in the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[0903] 3. Generating Advice

[0904] The server generates advice to provide to the user based on the calculated efficiency.

[0905] For example, if efficiency is 75% or higher, the advice generated is "Excellent! Your work efficiency is high. Keep it up!"

[0906] 4. Saving the results

[0907] The server stores the calculated efficiency and generated advice in a JSON format file.

[0908] Users can refer to this file later to check their own work efficiency and identify areas for improvement.

[0909] As described above, this system aims to improve users' work efficiency by efficiently analyzing their PC operation logs and providing specific advice.

[0910] The processing flow will be explained below.

[0911] Step 1:

[0912] The server specifies the log file path and reads the log data. Specifically, the server opens the specified file (e.g., user_log.json) and reads the JSON-formatted data from the file. The read data is stored in memory as an operation log.

[0913] Step 2:

[0914] The server analyzes the read log data one by one. The server scans the entries in the log data in a loop and obtains the activity, start time, and end time of each entry.

[0915] Step 3:

[0916] The server calculates the duration of the activity using the start and end times of each log entry. It calculates the difference between the start and end times and converts it to seconds.

[0917] Step 4:

[0918] The server classifies the duration of each activity. For productive activities (e.g., "working," "meeting," "coding"), the duration is counted as productive time, while other activities only count towards the total activity time.

[0919] Step 5:

[0920] After the server has finished parsing all the log entries, it calculates work efficiency based on the productive time and total active time. Efficiency is calculated by dividing the productive time by the total active time and converting the result into a percentage.

[0921] Step 6:

[0922] The server generates advice based on the calculated work efficiency, selecting appropriate messages for when the efficiency is 75% or more, 50% or more, or less than 50%, and creating advice sentences containing specific guidelines to provide to the user.

[0923] Step 7:

[0924] The server saves the generated advice and performance results, converts them into a JSON format file, and writes it to the specified file path.

[0925] Step 8:

[0926] Users can refer to the saved result files as needed, check the results, understand their own work efficiency, and find areas for improvement.

[0927] Example 1

[0928] 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."

[0929] In today's work environment, it is important to accurately evaluate the efficiency of PC-based work and provide appropriate advice. However, conventional methods often involve analyzing operation log data and calculating work efficiency manually, which is time-consuming and inaccurate. Furthermore, advice given to users is often vague and does not contribute to improving work efficiency.

[0930] 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.

[0931] In this invention, the server includes means for reading user operation information from a specified path, means for analyzing the read operation information and calculating the duration of each activity, means for adding up productive activity time based on the analyzed information and calculating work efficiency, means for generating advice based on the calculated work efficiency, and means for saving the results including the generated advice as data. This makes it possible to accurately evaluate the user's work efficiency and quickly provide specific and useful advice.

[0932] A "user operation log" is data showing the history of operations performed by a user on a PC, and includes the activity content, start time, and end time.

[0933] "Work efficiency" is the ratio of productive activity time to total activity time calculated based on the user's log.

[0934] The "specified path" refers to a path in the file system that indicates the location where the operation log file is saved.

[0935] "Duration" refers to the time elapsed from the start time to the end time of each activity.

[0936] "Productive activities" refer to work that is directly related to a user's job and creates value (e.g., work, meetings, coding, etc.).

[0937] "Advice" refers to specific suggestions or instructions for the user to improve their work efficiency based on the calculated work efficiency.

[0938] "Data" refers to information indicating the calculation results and generated advice that is saved in a file or other format.

[0939] "Analyzing" refers to the process of interpreting the read operation log data and calculating the start time, end time, and duration of each activity.

[0940] "Calculating" is the process of using analyzed data to determine a specific numerical value (e.g., operational efficiency).

[0941] "Saving" refers to keeping the generated results and advice in a file format or other format so that they can be referenced later.

[0942] The present invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. This system reads and analyzes the user's operation log data, calculates work efficiency based on the results, and provides specific advice to the user. Specific embodiments of the present invention are described below.

[0943] System Overview

[0944] The system includes the following main components:

[0945] 1. Log data reading method

[0946] The server reads the user operation information from the specified path using the open function and json module from the Python standard library.

[0947] 2. Log data analysis methods

[0948] The server analyzes the operation information it reads and uses the datetime module to calculate the duration of each activity. The analyzed information is stored in dictionary format.

[0949] 3. Efficiency calculation method

[0950] Based on the analyzed information, the server totals the productive activity time and calculates the work efficiency relative to the total activity time.

[0951] 4. Advice Generation Method

[0952] The server generates specific advice to provide to the user based on the calculated business efficiency, and creates a message according to the efficiency.

[0953] 5. Result storage means

[0954] The server saves the generated advice and calculation results in a JSON format file, which the user can then refer to later.

[0955] Specific examples

[0956] Below is a concrete example of how this system calculates business efficiency and generates advice based on user operation log data.

[0957] 1. Example of log data

[0958] A user's activity log contains the following data:

[0959] [

[0960] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[0961] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[0962] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"},

[0963] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0964] ]

[0965] 2. Log data analysis

[0966] The server parses each entry and calculates the duration of each activity from its start and end times. For example, if the start time of "working" is 2023-10-01T09:00:00 and the end time is 2023-10-01T12:00:00, the duration is 3 hours.

[0967] 3. Efficiency Calculation

[0968] The server adds up the duration of productive activities (e.g., "working," "meeting," "coding") and calculates the percentage of that time relative to the total activity time. In the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[0969] 4. Generating Advice

[0970] The server generates advice to provide to the user based on the calculated efficiency. For example, if the efficiency is 75% or higher, the advice generated is "Excellent! Your work efficiency is high. Keep it up!"

[0971] 5. Saving the results

[0972] The server saves the calculation results and generated advice in a JSON-formatted file, which users can refer to later to check their own work efficiency and identify areas for improvement.

[0973] Examples of prompt statements

[0974] Below are some example prompts to input to a generative AI model:

[0975] Analyze user operation log data, calculate operational efficiency, and generate advice. Operation log data is as follows:

[0976] [

[0977] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[0978] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[0979] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"},

[0980] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[0981] ]

[0982] The expected output is in the following format:

[0983] {

[0984] "efficiency":<efficiency_value> ,

[0985] "advice": "<advice_message> "

[0986] }

[0987] The above is one embodiment of the present invention. The purpose of the present invention is to improve the work efficiency of users by efficiently analyzing their PC operation logs and providing specific advice.

[0988] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0989] Step 1:

[0990] The server reads the user operation log from the specified path.

[0991] Input: Path to the operation log file (e.g. "C: / logs / user_log.txt")

[0992] Output: List format of operation log data

[0993] Specific operation: The server uses the open function to open the log file and uses the json module to read the contents in list format, which stores the operation log data in memory.

[0994] Step 2:

[0995] The server analyzes the operation log data it has read and calculates the duration of each activity.

[0996] Input: Operation log data (e.g., [{"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},...])

[0997] Output: Analysis data including the duration of each activity

[0998] What it does: The server uses the datetime module to calculate the duration of each activity by comparing the start and end times. The duration is converted from a total number of seconds, and the parsed result is stored in a list.

[0999] Step 3:

[1000] Based on the analyzed information, the server totals the productive activity time and calculates the work efficiency relative to the total activity time.

[1001] Input: Parsed operation log data (e.g., [{"activity": "working", "duration": 3}, ...])

[1002] Output: Calculated operational efficiency (e.g., 93.33%)

[1003] Specific operation: The server extracts only specific productive activities (e.g., "working," "meeting," "coding") and sums up their duration. It then sums up the total activity time and calculates work efficiency from the ratio.

[1004] Step 4:

[1005] The server generates advice to be provided to the user based on the calculated business efficiency.

[1006] Input: Calculated operational efficiency (e.g., 93.33%)

[1007] Output: The generated advisory message (e.g., "Excellent! Your work efficiency is high. Keep it up!")

[1008] Specific behavior: The server generates different advice messages according to the work efficiency value. For example, if the efficiency is 75% or higher, the message "Excellent! Your work efficiency is high. Keep it up!" will be generated.

[1009] Step 5:

[1010] The server saves the generated advice and calculation results in a JSON format file.

[1011] Input: Generated advice message and calculation result (e.g., {"efficiency": 93.33, "advice": "Excellent! Your work efficiency is high. Keep it up!"})

[1012] Output: Saved JSON format file (e.g. "C: / logs / user_efficiency_result.json")

[1013] Specific operation: The server uses the json module to convert the advice and calculation results into JSON format and writes them to a file using the open function, so that the user can view the results later.

[1014] By following the steps above, the system can efficiently analyze the user's operation log and quickly provide specific advice.

[1015] (Application example 1)

[1016] 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."

[1017] Modern factories and production lines require efficient analysis of machine and robot operation logs to improve production efficiency and optimize maintenance. However, conventional methods have faced challenges, such as the time-consuming nature of analyzing operation logs and the difficulty of providing efficient maintenance advice. Additionally, there has been a lack of easy ways to acquire and display data outside the factory. This can easily lead to reduced productivity and delays in maintenance.

[1018] 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.

[1019] In this invention, the server

[1020] a means for reading log data;

[1021] A means of analyzing the read log data and calculating work efficiency,

[1022] A means for generating advice based on the calculated work efficiency;

[1023] means for storing the results including the generated advice;

[1024] A means for reading and analyzing the operation log of a factory machine and calculating production efficiency and error occurrence frequency;

[1025] a means for generating maintenance advice based on the calculated production efficiency and error occurrence frequency;

[1026] A means to obtain and display analysis results and advice via smartphone;

[1027] This makes it possible to efficiently analyze the operation logs of factory machines and easily provide advice on improving production efficiency and performing optimal maintenance. In addition, data can be acquired and displayed via smartphone, making it easy to check the situation even when away from the site, enabling quick response.

[1028] A "PC operation log" is data that records the history of all user operations performed on a personal computer.

[1029] "Work efficiency" is an indicator that refers to the ratio of productive to unproductive activities within a given period of time.

[1030] "Means for reading log data" refers to a device or program that has the function of retrieving operation logs and machine logs from a specified storage location.

[1031] The "means for analyzing log data and calculating work efficiency" refers to a device or program for analyzing the contents of the acquired operation log and calculating work efficiency and production efficiency.

[1032] The "means for generating advice based on calculated work efficiency" refers to a device or program that provides the user with points to improve or maintain based on the calculated efficiency.

[1033] The "means for saving the results including the generated advice" is a device or program that saves the generated advice and analysis results in a designated storage location.

[1034] "Factory machine operation logs" are data that record the operation history of machines and robots operating within a factory.

[1035] "Production efficiency" is an efficiency index calculated from the operating and downtime of machines and robots in factories and manufacturing sites, as well as the frequency of errors.

[1036] "Error frequency" is an indicator that refers to the number of times a machine or robot makes an error within a certain period of time.

[1037] The "means for generating maintenance advice" refers to a device or program that provides users with advice on maintenance timing and improvements based on production efficiency and error frequency.

[1038] "Means for obtaining and displaying analysis results and advice via a smartphone" refers to a device or program that obtains and displays analysis results and advice on a smartphone.

[1039] This invention is a system that analyzes PC operation logs and factory machine operation logs, analyzes work efficiency and production efficiency, and provides advice to users. This system reads and analyzes the operation logs, calculates efficiency based on the results, and provides specific advice to users.

[1040] System configuration

[1041] The system includes the following main components:

[1042] 1. Log data reading method

[1043] Log data is read from a server or smartphone. This data includes PC operation logs and factory machine operation logs.

[1044] For example, it has the function of obtaining operation log files from factory machines via Wi-Fi.

[1045] 2. Log data analysis methods

[1046] Analyze log data and calculate work efficiency and production efficiency.

[1047] Specifically, the type of activity (operation, stop, error, etc.) in the log data and the start and end times of each activity are obtained, and their duration is calculated.

[1048] Production efficiency is calculated by comparing the total operating time of factory machines with the time they are down.

[1049] 3. A means of generating advice based on calculated efficiencies

[1050] Based on the calculated efficiency, advice is generated to be provided to the user.

[1051] For example, if production efficiency is declining, specific improvement advice such as "Please carry out regular maintenance" is generated.

[1052] 4. A means of saving the results, including the generated advice

[1053] The generated advice and analysis results are saved to a specified file or cloud storage.

[1054] This allows users to refer to the analysis results later and carry out appropriate maintenance and business improvements.

[1055] 5. A means to obtain and display analysis results and advice via smartphone

[1056] It has the function of obtaining and displaying analysis results and advice on a smartphone.

[1057] Users can use their smartphones to easily check data even outside the factory and take any necessary action quickly.

[1058] Processing flow

[1059] The specific processing flow of this system is as follows:

[1060] 1. Reading the log data

[1061] The server reads the operation log file from the specified path or cloud storage. For example, the operation log generated by a factory machine contains the following data:

[1062] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1063] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[1064] 2. Log data analysis

[1065] Analyze the log data and calculate the duration of each activity. For example, analyze that "running" activity is 3 hours and "stopped" activity is 30 minutes.

[1066] 3. Efficiency Calculation

[1067] Calculate production efficiency based on operating time and downtime. For example, in the above log data, the operating time is 3 hours and the total activity time is 3.5 hours, so the efficiency is approximately 85.71%.

[1068] 4. Generating and Saving Advice

[1069] Based on the calculated efficiency, advice is generated, such as a message saying, "Production efficiency is declining. Please inspect and replace the following parts."

[1070] The generated advice and analysis results are saved in JSON format.

[1071] 5. Display on smartphones

[1072] Display analysis results and advice on your smartphone, allowing users to take action quickly. Use the following prompt as an example:

[1073] Analyze the following log data, calculate the production efficiency and the number of errors, and if the production efficiency is less than 80%, provide appropriate maintenance advice.

[1074] Log Data:

[1075] [

[1076] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[1077] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[1078] {"activity": "running", "start_time": "2023-10-01T12:30:00", "end_time": "2023-10-01T14:00:00"},

[1079] {"activity": "error", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T14:15:00"},

[1080] {"activity": "running", "start_time": "2023-10-01T14:15:00", "end_time": "2023-10-01T17:00:00"}

[1081] ]

[1082] As described above, the system of the present invention aims to support efficient business improvement and maintenance through analysis of operation logs, thereby improving the efficiency of users' factory operations and work.

[1083] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1084] Step 1:

[1085] Loading log data

[1086] The server reads operation log files from the specified storage location or cloud storage. Specifically, the server receives the file path or storage URL as input and retrieves JSON-formatted log data from that location. As an example, the operation log file "robot_log.json" of a factory machine is read via Wi-Fi. The read data includes the type of each activity (e.g., "running," "stopped," "error") as well as the start and end times.

[1087] Step 2:

[1088] Analyzing log data

[1089] The server analyzes the loaded operation log data. In this process, it analyzes each activity entry and calculates the duration of each activity based on the start and end times. Specifically, the server receives the start and end times as input, calculates the difference between them, and outputs the duration. For example, it analyzes that "running" activity lasted 3 hours from 09:00 to 12:00, and "stopped" activity lasted 30 minutes from 12:00 to 12:30.

[1090] Step 3:

[1091] Efficiency calculations

[1092] The server calculates efficiency based on the analysis data. Specifically, the server adds up the duration of each activity and calculates the ratio of productive to unproductive activities. The input is the duration of each activity, and the output is the efficiency percentage. For example, if the working time is 3 hours and the total activity time is 3.5 hours, the efficiency is calculated to be approximately 85.71%.

[1093] Step 4:

[1094] Generating Advice

[1095] The server generates advice to provide to the user based on the calculated efficiency. Here, the server receives the efficiency percentage as input and generates a message according to that value. The output is an advice message. For example, if the efficiency is less than 80%, the advice generated is "Production efficiency is declining. Please inspect and replace the following parts."

[1096] Step 5:

[1097] Saving the results

[1098] The server saves the generated advice and analysis results to a specified file or cloud storage. Specifically, the server receives analysis results and advice messages as input and saves them in a JSON format file. The output is the saved file.

[1099] Step 6:

[1100] Display on smartphone

[1101] The device (smartphone) retrieves and displays the analysis results and advice from the cloud storage or server. Specifically, the smartphone receives the cloud storage URL or API endpoint as input and displays the data from that location. The output is the analysis results and advice messages displayed on the smartphone screen. As an example, let's perform an analysis using the following prompt:

[1102] Analyze the following log data, calculate the production efficiency and the number of errors, and if the production efficiency is less than 80%, provide appropriate maintenance advice.

[1103] Log Data:

[1104] [

[1105] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[1106] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[1107] {"activity": "running", "start_time": "2023-10-01T12:30:00", "end_time": "2023-10-01T14:00:00"},

[1108] {"activity": "error", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T14:15:00"},

[1109] {"activity": "running", "start_time": "2023-10-01T14:15:00", "end_time": "2023-10-01T17:00:00"}

[1110] ]

[1111] 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.

[1112] This invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide more appropriate advice that takes into account the user's mental state.

[1113] System Overview

[1114] The system includes the following main components:

[1115] 1. Log data reading method:

[1116] The server reads the user's operation log file from the specified path.

[1117] This log file records the type of activity, as well as the start and end times of each activity.

[1118] 2. Log data analysis methods:

[1119] The server analyzes the log data and calculates the time taken for each activity.

[1120] Work efficiency is calculated by adding up the time spent on productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time.

[1121] 3. Emotion recognition means (emotion engine):

[1122] The server recognizes the user's emotions through facial expressions, voice, keystrokes, etc.

[1123] The recognized emotion data is recorded together with the operation log data and is used during analysis.

[1124] 4. Advice Generation Methods:

[1125] The server generates advice to be provided to the user based on the calculated work efficiency and the recognized emotion.

[1126] Depending on the level of efficiency and the user's emotional state, a message containing specific improvements or points to maintain is created.

[1127] 5. Result storage means:

[1128] The server will save the generated advice and efficiency results to the specified file.

[1129] The user can refer to the results later.

[1130] Specific examples

[1131] Below is a concrete example of how this system calculates work efficiency and generates advice based on the user's operation log data and emotion data.

[1132] 1. Example of log data

[1133] A user's activity log contains the following data:

[1134] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1135] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[1136] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[1137] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[1138] 2. Example of Emotion Data

[1139] During the same period, the emotion engine recognized the following emotions:

[1140] {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[1141] {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[1142] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[1143] 3. Log data analysis

[1144] The server parses each entry and calculates the duration of each activity from the start and end times.

[1145] The duration of productive activities ("working," "meeting," "coding") is summed and calculated as a percentage of total activity time.

[1146] For example, in the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[1147] 4. Emotion Data Analysis

[1148] The server analyzes the emotion data obtained from the emotion engine to identify the user's emotional state.

[1149] In the above example, the user is recognized as feeling "happy" at 09:30, "neutral" at 12:15, and "stressed" at 15:00.

[1150] 5. Generating Advice

[1151] The server generates advice to provide to the user based on the calculated efficiency and the perceived emotion.

[1152] For example, if your efficiency is 93.33% and you are feeling "stressed" in the afternoon, the following advice will be generated: "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or managing your tasks differently to reduce stress."

[1153] 6. Saving the results

[1154] The server stores the calculated efficiency, generated advice, and emotion data in a JSON format file.

[1155] Users can refer to this file later to check their own work efficiency and emotional state and find appropriate improvements.

[1156] As described above, this system aims to improve users' work efficiency by efficiently analyzing their PC operation logs and emotional data and providing specific advice.

[1157] The processing flow will be explained below.

[1158] Step 1:

[1159] The server specifies the log file path and reads the log data. Specifically, the server opens the specified file (e.g., user_log.json) and reads the JSON-formatted data from the file. The read data is stored in memory as an operation log.

[1160] Step 2:

[1161] The server collects emotion data using an emotion engine, analyzing the user's camera footage, voice input, keystrokes, etc., and generates emotion data including the type of emotion and a timestamp.

[1162] Step 3:

[1163] The server analyzes the operation log data it has read one by one. The server scans the entries in the log data in a loop and obtains the activity, start time, and end time for each entry.

[1164] Step 4:

[1165] The server calculates the duration of the activity using the start and end times of each log entry. It calculates the difference between the start and end times and converts it to seconds.

[1166] Step 5:

[1167] The server classifies the duration of each activity. For productive activities (e.g., "working," "meeting," "coding"), the duration is counted as productive time, while other activities only count towards the total activity time.

[1168] Step 6:

[1169] After the server has finished parsing all the log entries, it calculates work efficiency based on the productive time and total active time. Efficiency is calculated by dividing the productive time by the total active time and converting the result into a percentage.

[1170] Step 7:

[1171] The server analyzes the collected emotional data, assessing the user's emotional state during a specific time period and determining which emotions were most prevalent.

[1172] Step 8:

[1173] The server generates advice based on the calculated work efficiency and analyzed emotional data. Depending on the degree of efficiency and the user's emotional state, it creates a message containing specific points to improve or maintain.

[1174] Step 9:

[1175] The server saves the generated advice, work efficiency, and emotion data, converts this data into a JSON format file, and writes it to the specified file path.

[1176] Step 10:

[1177] Users can refer to the saved result file as needed, check the results, understand their own work efficiency and emotional state, and find appropriate improvement measures.

[1178] Example 2

[1179] 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."

[1180] Conventional work efficiency analysis systems are limited to analyzing only the user's operation log data and are unable to provide advice that takes into account the user's emotional state. This makes it difficult to present appropriate countermeasures for performance declines and increased stress caused by the user's mental state. Therefore, there is a need to provide a system that can analyze the user's operation log data and emotional data in an integrated manner and provide more personalized advice.

[1181] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1182] In this invention, the server includes means for reading log data, means for analyzing the read log data and calculating work efficiency, means for collecting emotion data using an emotion engine that recognizes the user's emotions, means for generating advice based on the recognized emotion data and the calculated work efficiency, and means for saving the results including the generated advice. This makes it possible to comprehensively analyze the user's operation log and emotion data and provide more appropriate advice that takes the user's mental state into consideration.

[1183] "Log data" refers to records of a user's PC operations, and includes information such as the activity content, start time, and end time.

[1184] "Analysis" refers to the process of calculating specific indicators (e.g., work efficiency) based on log data and sentiment data.

[1185] "Work efficiency" indicates the ratio of the user's productive activity time divided by the total activity time, and is a numerical representation of the user's work efficiency.

[1186] An "emotion engine" refers to a system or algorithm that recognizes emotions from input data such as a user's facial expressions, voice, and keystrokes, and outputs the results as data.

[1187] "Emotion data" is data that includes the user's emotional state (e.g., happy, neutral, stressed, etc.) recognized by the emotion engine.

[1188] The "advice generation means" is a means for generating specific suggestions and improvements for the user as messages based on the analyzed work efficiency and the recognized emotion data.

[1189] The "means for saving results" refers to a means for saving the generated advice and analysis results in a file, database, etc., so that they can be referenced later.

[1190] This invention is a system that analyzes PC operation log data and emotion data, evaluates the user's work efficiency based on the data, and provides specific advice. As an embodiment of the invention, the operations of the server, terminal, and user will be mainly described below.

[1191] Server Operation

[1192] The server reads the user's PC operation log data from the specified path. Specifically, it uses Python's open function and json module to read the log data, which records the type of activity, start time, and end time of each activity. It also uses the datetime module to analyze the operation log data and calculate the time taken for each activity.

[1193] The server then uses an emotion engine, OpenCV, Google Cloud Speech-to-Text API, and proprietary algorithms to collect emotion data from the user's facial expressions, voice, and keystrokes. The collected emotion data is recorded along with operation log data and used for analysis.

[1194] The server generates advice by inputting a prompt into the generative AI model based on the calculated work efficiency and the recognized emotion data. An example of a prompt is, "The user's work efficiency is 93.33%, and a state of stress was recognized in the afternoon. Please generate appropriate advice based on this information." The generated advice is saved in a file in JSON format for later reference.

[1195] Device behavior

[1196] A module for recording operation log data is installed on the user's device. This module captures user operations in real time and records the activity content, start time, and end time. It is also possible to use an emotion engine on the device to recognize the user's emotions in real time. For example, emotion data can be collected by facial expression recognition using a camera or voice analysis using a microphone.

[1197] User Actions

[1198] Users operate their PCs as usual and perform tasks using specific software. Operation log data captured during these tasks is sent to the server periodically or at a set time. The user can then check the generated advice on their device and adjust their work methods based on specific areas for improvement or maintenance.

[1199] Specific examples

[1200] For example, if a user works on a PC all day and the operation log data contains the following data:

[1201] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1202] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[1203] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[1204] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[1205] Suppose the sentiment data collected during the same period is as follows:

[1206] {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[1207] {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[1208] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[1209] The server analyzes the log data and emotion data and inputs prompt sentences, such as the following, into the generative AI model:

[1210] "The user's work efficiency was 93.33% and a stressful state was detected in the afternoon. Please generate appropriate advice based on this information."

[1211] As a result, the generative AI model offers advice like this:

[1212] "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or your tasks differently to reduce managing stress."

[1213] The above is an embodiment of the present invention, which allows a user to voluntarily obtain specific advice for improving work efficiency based on their own PC operation log data and emotion data.

[1214] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1215] Step 1: Loading the log data

[1216] The server reads the user's operation log file from the specified path. The input is the path to the log file, and the output is a JSON-formatted object of the read log data. Specifically, the log data is read from the file using Python's open function and the json module. For example, the processing is as follows: log_data = json.load(open('path / to / logfile.json')).

[1217] Step 2: Analyze the log data

[1218] The server analyzes the operation log data and calculates the time taken for each activity. The input is a JSON object of the log data, and the output is the duration of each activity and the total productive activity time. Specifically, it uses the datetime module to calculate the difference between the start time and the end time. For example, it processes as follows:

[1219] Input: "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"

[1220] Output: Duration of activity (3 hours)

[1221] Step 3: Collecting and Recognizing Emotional Data

[1222] The server uses an emotion engine to collect emotion data from the user's facial expressions, voice, and keystrokes. The input is real-time data from devices connected to the emotion engine, and the output is a dataset of recognized emotions. Specifically, facial recognition is performed using OpenCV, voice emotion recognition is performed using the Google Cloud Speech-to-Text API, and emotion is inferred based on keystroke patterns. For example, voice data is collected and the API is called to recognize emotions.

[1223] Step 4: Generating Advice

[1224] The server generates advice to provide to the user based on the calculated work efficiency and the recognized emotion data. The input is the calculated work efficiency and emotion data, and the output is the generated advice message. Specifically, the prompt sentence "The user's work efficiency is 93.33%, and a state of stress was recognized in the afternoon. Please generate appropriate advice based on this information" is input to the generative AI model, and the generated text is obtained.

[1225] Step 5: Save the results

[1226] The server saves the generated advice and analysis results to the specified file. The input is the dataset of the generated advice and analysis results, and the output is the saved JSON format file. Specifically, the json.dump function is used to write the result data to a file. For example, it is processed as follows: with open('path / to / resultfile.json', 'w') as result_file:

[1227] These are the processing steps of this system, which makes it possible to comprehensively analyze the user's PC operation log data and emotional data and provide appropriate advice.

[1228] (Application example 2)

[1229] 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."

[1230] Conventional work efficiency analysis systems were able to calculate efficiency based on a user's operation log, but it was difficult to provide appropriate advice that took the user's emotional state into consideration. Furthermore, while some systems were able to aggregate efficiency data and emotional data, they were unable to provide real-time advice based on that data. The present invention aims to provide a system that can provide more appropriate and practical advice in real time by analyzing not only a user's work efficiency but also their emotional state.

[1231] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1232] In this invention, the server includes means for reading log data, means for analyzing the read log data and emotion data to calculate work efficiency and the user's emotional state, means for generating advice based on the calculated work efficiency and the recognized emotion, means for providing the generated advice in real time, and means for saving results including the generated advice, thereby making it possible to generate specific advice from the user's operation log and emotion data and provide it in real time.

[1233] A "PC operation log" is data that includes a record of operations performed by a user on a PC, and includes the type of operation, start time, end time, and so on.

[1234] "Emotion data" refers to data that includes the user's emotional state as recognized through facial expressions, voice, keystrokes, and the like.

[1235] "Work efficiency" is an index of efficiency calculated based on the ratio of the time spent on a user's productive activities to the total activity time.

[1236] "Advice" is a message containing specific points to improve or maintain that are provided to the user based on the analyzed work efficiency and emotional state.

[1237] The "means for reading log data" is a device or program that has the function of reading the PC operation log from a specified path.

[1238] The "analyzing means" is a device or program that analyzes the duration of each activity and the user's emotional state based on the read log data and emotional data, and calculates work efficiency.

[1239] The "means for generating advice" is a device or program for creating an advice message to be provided to the user based on the analyzed work efficiency and the user's emotional state.

[1240] The "means for providing in real time" is a device or program for instantly presenting the generated advice to the user.

[1241] The "means for storing results" refers to a device or program for recording the generated advice and calculated work efficiency results so that they can be referenced later.

[1242] This invention is a system that analyzes work efficiency from PC operation logs and emotional data and provides advice to users.

[1243] First, the server reads the PC's operation log from the specified path. This log data records the type of activity, start time, and end time of each activity. Next, the server analyzes the read log data and calculates the time spent on each activity. It calculates work efficiency by adding up the time spent on productive activities (such as "working," "meeting," and "coding") and comparing this with the total activity time.

[1244] Meanwhile, the server also analyzes emotional data. Emotional data is recognized through the user's facial expressions, voice, keystrokes, etc. This recognition is performed using a camera and microphone, and the emotional state is analyzed using a machine learning model such as TensorFlow. The recognized emotional data is recorded along with the operation log data and used for analysis.

[1245] The server then generates advice to provide to the user based on the calculated work efficiency and the recognized emotions. Specifically, it uses a generative AI model to automatically generate optimal advice from the analysis results. This advice may include a message such as, "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or managing your tasks differently to reduce stress," depending on the efficiency level and the user's emotional state.

[1246] The generated advice is displayed on the terminal in real time, allowing the user to immediately receive this advice and obtain specific instructions for improving their work. In addition, the server stores the generated advice and calculated work efficiency results for the user to refer to later.

[1247] For example, a user's activity log might contain the following data:

[1248] - {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1249] - {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[1250] - {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[1251] - {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[1252] Also, suppose the emotion engine recognizes the following emotions:

[1253] - {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[1254] - {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[1255] - {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[1256] Based on this data, the server calculates work efficiency and generates the following advice for the user:

[1257] "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or your tasks differently to reduce managing stress."

[1258] Below are some example prompts to input to a generative AI model:

[1259] "Based on the log data and emotion data below, please calculate work efficiency and generate advice.

[1260] Log Data:

[1261] {"activity": "assembling", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1262] {"activity": "inspecting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T17:00:00"}

[1263] Emotional Data:

[1264] {"time": "2023-10-01T10:30:00", "emotion": "happy"}

[1265] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[1266] Calculate work efficiency and generate advice based on emotional data.”

[1267] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1268] Step 1:

[1269] The server reads the PC's operation log data from the specified path. This operation log contains the type of activity, start time, and end time for each activity. The input is the path to the operation log data file, and the output is the raw operation log data. Specifically, the server reads the file and stores the data in memory.

[1270] Step 2:

[1271] The server analyzes the loaded operation log data and calculates the duration of each activity. During the analysis, it finds the difference between the start and end times of each log entry and records this for each activity. The input is the raw operation log data, and the output is the calculated duration data for each activity. Specifically, it calculates the difference between timestamps and processes the data.

[1272] Step 3:

[1273] The server calculates work efficiency by summing the duration of productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time. The input is the calculated duration data and activity classification information, and the output is the work efficiency percentage. Specifically, it tallies the activity time belonging to each category and calculates the ratio.

[1274] Step 4:

[1275] The server recognizes emotions based on the user's facial and voice data acquired from the camera and microphone. This recognition is performed using a machine learning model such as TensorFlow. The input is facial and voice data, and the output is recognized emotion data. Specifically, the server preprocesses the captured data, inputs it into the machine learning model, and obtains the results.

[1276] Step 5:

[1277] The server generates advice to provide to the user based on the analyzed work efficiency and recognized emotional data. A generative AI model is used to generate this advice. The input is the work efficiency rate and emotional data, and the output is an advice message. Specifically, the server inputs appropriate advice words based on the efficiency and emotional profile into the generative AI model as a prompt, and obtains the response.

[1278] Step 6:

[1279] The server displays the generated advice on the terminal in real time. Possible display methods include a pop-up on the screen or a voice notification. The input is the advice message, and the output is a notification to the user. Specific operations include sending messages to the notification system and controlling the display.

[1280] Step 7:

[1281] The server records the generated advice and calculated performance results and saves them for future reference. The input is advice messages and performance data, and the output is a saved log file. Specific operations include writing to a database or file system.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] [Fourth embodiment]

[1286] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1287] 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.

[1288] 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).

[1289] 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.

[1290] 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.

[1291] 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).

[1292] 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.

[1293] 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.

[1294] 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.

[1295] 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.

[1296] 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.

[1297] 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.

[1298] 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."

[1299] This invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. This system reads and analyzes the user's operation log data, calculates efficiency based on the results, and provides specific advice to the user.

[1300] System Overview

[1301] The system includes the following main components:

[1302] 1. Log data reading method:

[1303] The server reads the user's operation log file from the specified path.

[1304] This log file records the type of activity (e.g., "working," "browsing") and its start and end times.

[1305] 2. Log data analysis methods:

[1306] The server analyzes the log data and calculates the time taken for each activity.

[1307] Work efficiency is calculated by adding up the time spent on productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time.

[1308] 3. Advice Generation Methods:

[1309] The server generates advice to be provided to the user based on the calculated work efficiency.

[1310] Depending on the level of efficiency, create a message that includes specific areas for improvement or maintenance.

[1311] 4. Result storage means:

[1312] The server will save the generated advice and efficiency results to the specified file.

[1313] The user can refer to the results later.

[1314] Specific examples

[1315] Below is a concrete example of how this system calculates work efficiency and generates advice based on the user's operation log data.

[1316] 1. Example of log data

[1317] A user's activity log contains the following data:

[1318] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1319] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[1320] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[1321] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[1322] 2. Log data analysis

[1323] The server parses each entry and calculates the duration of each activity from the start and end times.

[1324] The server sums the duration of productive activities ("working," "meeting," "coding") and calculates the percentage of total activity time.

[1325] For example, in the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[1326] 3. Generating Advice

[1327] The server generates advice to provide to the user based on the calculated efficiency.

[1328] For example, if efficiency is 75% or higher, the advice generated is "Excellent! Your work efficiency is high. Keep it up!"

[1329] 4. Saving the results

[1330] The server stores the calculated efficiency and generated advice in a JSON format file.

[1331] Users can refer to this file later to check their own work efficiency and identify areas for improvement.

[1332] As described above, this system aims to improve users' work efficiency by efficiently analyzing their PC operation logs and providing specific advice.

[1333] The processing flow will be explained below.

[1334] Step 1:

[1335] The server specifies the log file path and reads the log data. Specifically, the server opens the specified file (e.g., user_log.json) and reads the JSON-formatted data from the file. The read data is stored in memory as an operation log.

[1336] Step 2:

[1337] The server analyzes the read log data one by one. The server scans the entries in the log data in a loop and obtains the activity, start time, and end time of each entry.

[1338] Step 3:

[1339] The server calculates the duration of the activity using the start and end times of each log entry. It calculates the difference between the start and end times and converts it to seconds.

[1340] Step 4:

[1341] The server classifies the duration of each activity. For productive activities (e.g., "working," "meeting," "coding"), the duration is counted as productive time, while other activities only count towards the total activity time.

[1342] Step 5:

[1343] After the server has finished parsing all the log entries, it calculates work efficiency based on the productive time and total active time. Efficiency is calculated by dividing the productive time by the total active time and converting the result into a percentage.

[1344] Step 6:

[1345] The server generates advice based on the calculated work efficiency, selecting appropriate messages for when the efficiency is 75% or more, 50% or more, or less than 50%, and creating advice sentences containing specific guidelines to provide to the user.

[1346] Step 7:

[1347] The server saves the generated advice and performance results, converts them into a JSON format file, and writes it to the specified file path.

[1348] Step 8:

[1349] Users can refer to the saved result files as needed, check the results, understand their own work efficiency, and find areas for improvement.

[1350] Example 1

[1351] 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."

[1352] In today's work environment, it is important to accurately evaluate the efficiency of PC-based work and provide appropriate advice. However, conventional methods often involve analyzing operation log data and calculating work efficiency manually, which is time-consuming and inaccurate. Furthermore, advice given to users is often vague and does not contribute to improving work efficiency.

[1353] 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.

[1354] In this invention, the server includes means for reading user operation information from a specified path, means for analyzing the read operation information and calculating the duration of each activity, means for adding up productive activity time based on the analyzed information and calculating work efficiency, means for generating advice based on the calculated work efficiency, and means for saving the results including the generated advice as data. This makes it possible to accurately evaluate the user's work efficiency and quickly provide specific and useful advice.

[1355] A "user operation log" is data showing the history of operations performed by a user on a PC, and includes the activity content, start time, and end time.

[1356] "Work efficiency" is the ratio of productive activity time to total activity time calculated based on the user's log.

[1357] The "specified path" refers to a path in the file system that indicates the location where the operation log file is saved.

[1358] "Duration" refers to the time elapsed from the start time to the end time of each activity.

[1359] "Productive activities" refer to work that is directly related to a user's job and creates value (e.g., work, meetings, coding, etc.).

[1360] "Advice" refers to specific suggestions or instructions for the user to improve their work efficiency based on the calculated work efficiency.

[1361] "Data" refers to information indicating the calculation results and generated advice that is saved in a file or other format.

[1362] "Analyzing" refers to the process of interpreting the read operation log data and calculating the start time, end time, and duration of each activity.

[1363] "Calculating" is the process of using analyzed data to determine a specific numerical value (e.g., operational efficiency).

[1364] "Saving" refers to keeping the generated results and advice in a file format or other format so that they can be referenced later.

[1365] The present invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. This system reads and analyzes the user's operation log data, calculates work efficiency based on the results, and provides specific advice to the user. Specific embodiments of the present invention are described below.

[1366] System Overview

[1367] The system includes the following main components:

[1368] 1. Log data reading method

[1369] The server reads the user operation information from the specified path using the open function and json module from the Python standard library.

[1370] 2. Log data analysis methods

[1371] The server analyzes the operation information it reads and uses the datetime module to calculate the duration of each activity. The analyzed information is stored in dictionary format.

[1372] 3. Efficiency calculation method

[1373] Based on the analyzed information, the server totals the productive activity time and calculates the work efficiency relative to the total activity time.

[1374] 4. Advice Generation Method

[1375] The server generates specific advice to provide to the user based on the calculated business efficiency, and creates a message according to the efficiency.

[1376] 5. Result storage means

[1377] The server saves the generated advice and calculation results in a JSON format file, which the user can then refer to later.

[1378] Specific examples

[1379] Below is a concrete example of how this system calculates business efficiency and generates advice based on user operation log data.

[1380] 1. Example of log data

[1381] A user's activity log contains the following data:

[1382] [

[1383] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[1384] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[1385] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"},

[1386] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[1387] ]

[1388] 2. Log data analysis

[1389] The server parses each entry and calculates the duration of each activity from its start and end times. For example, if the start time of "working" is 2023-10-01T09:00:00 and the end time is 2023-10-01T12:00:00, the duration is 3 hours.

[1390] 3. Efficiency Calculation

[1391] The server adds up the duration of productive activities (e.g., "working," "meeting," "coding") and calculates the percentage of that time relative to the total activity time. In the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[1392] 4. Generating Advice

[1393] The server generates advice to provide to the user based on the calculated efficiency. For example, if the efficiency is 75% or higher, the advice generated is "Excellent! Your work efficiency is high. Keep it up!"

[1394] 5. Saving the results

[1395] The server saves the calculation results and generated advice in a JSON-formatted file, which users can refer to later to check their own work efficiency and identify areas for improvement.

[1396] Examples of prompt statements

[1397] Below are some example prompts to input to a generative AI model:

[1398] Analyze user operation log data, calculate operational efficiency, and generate advice. Operation log data is as follows:

[1399] [

[1400] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[1401] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[1402] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"},

[1403] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[1404] ]

[1405] The expected output is in the following format:

[1406] {

[1407] "efficiency":<efficiency_value> ,

[1408] "advice": "<advice_message> "

[1409] }

[1410] The above is one embodiment of the present invention. The purpose of the present invention is to improve the work efficiency of users by efficiently analyzing their PC operation logs and providing specific advice.

[1411] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1412] Step 1:

[1413] The server reads the user operation log from the specified path.

[1414] Input: Path to the operation log file (e.g. "C: / logs / user_log.txt")

[1415] Output: List format of operation log data

[1416] Specific operation: The server uses the open function to open the log file and uses the json module to read the contents in list format, which stores the operation log data in memory.

[1417] Step 2:

[1418] The server analyzes the operation log data it has read and calculates the duration of each activity.

[1419] Input: Operation log data (e.g., [{"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},...])

[1420] Output: Analysis data including the duration of each activity

[1421] What it does: The server uses the datetime module to calculate the duration of each activity by comparing the start and end times. The duration is converted from a total number of seconds, and the parsed result is stored in a list.

[1422] Step 3:

[1423] Based on the analyzed information, the server totals the productive activity time and calculates the work efficiency relative to the total activity time.

[1424] Input: Parsed operation log data (e.g., [{"activity": "working", "duration": 3}, ...])

[1425] Output: Calculated operational efficiency (e.g., 93.33%)

[1426] Specific operation: The server extracts only specific productive activities (e.g., "working," "meeting," "coding") and sums up their duration. It then sums up the total activity time and calculates work efficiency from the ratio.

[1427] Step 4:

[1428] The server generates advice to be provided to the user based on the calculated business efficiency.

[1429] Input: Calculated operational efficiency (e.g., 93.33%)

[1430] Output: The generated advisory message (e.g., "Excellent! Your work efficiency is high. Keep it up!")

[1431] Specific behavior: The server generates different advice messages according to the work efficiency value. For example, if the efficiency is 75% or higher, the message "Excellent! Your work efficiency is high. Keep it up!" will be generated.

[1432] Step 5:

[1433] The server saves the generated advice and calculation results in a JSON format file.

[1434] Input: Generated advice message and calculation result (e.g., {"efficiency": 93.33, "advice": "Excellent! Your work efficiency is high. Keep it up!"})

[1435] Output: Saved JSON format file (e.g. "C: / logs / user_efficiency_result.json")

[1436] Specific operation: The server uses the json module to convert the advice and calculation results into JSON format and writes them to a file using the open function, so that the user can view the results later.

[1437] By following the steps above, the system can efficiently analyze the user's operation log and quickly provide specific advice.

[1438] (Application example 1)

[1439] 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."

[1440] Modern factories and production lines require efficient analysis of machine and robot operation logs to improve production efficiency and optimize maintenance. However, conventional methods have faced challenges, such as the time-consuming nature of analyzing operation logs and the difficulty of providing efficient maintenance advice. Additionally, there has been a lack of easy ways to acquire and display data outside the factory. This can easily lead to reduced productivity and delays in maintenance.

[1441] 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.

[1442] In this invention, the server

[1443] a means for reading log data;

[1444] A means of analyzing the read log data and calculating work efficiency,

[1445] A means for generating advice based on the calculated work efficiency;

[1446] means for storing the results including the generated advice;

[1447] A means for reading and analyzing the operation log of a factory machine and calculating production efficiency and error occurrence frequency;

[1448] a means for generating maintenance advice based on the calculated production efficiency and error occurrence frequency;

[1449] A means to obtain and display analysis results and advice via smartphone;

[1450] This makes it possible to efficiently analyze the operation logs of factory machines and easily provide advice on improving production efficiency and performing optimal maintenance. In addition, data can be acquired and displayed via smartphone, making it easy to check the situation even when away from the site, enabling quick response.

[1451] A "PC operation log" is data that records the history of all user operations performed on a personal computer.

[1452] "Work efficiency" is an indicator that refers to the ratio of productive to unproductive activities within a given period of time.

[1453] "Means for reading log data" refers to a device or program that has the function of retrieving operation logs and machine logs from a specified storage location.

[1454] The "means for analyzing log data and calculating work efficiency" refers to a device or program for analyzing the contents of the acquired operation log and calculating work efficiency and production efficiency.

[1455] The "means for generating advice based on calculated work efficiency" refers to a device or program that provides the user with points to improve or maintain based on the calculated efficiency.

[1456] The "means for saving the results including the generated advice" is a device or program that saves the generated advice and analysis results in a designated storage location.

[1457] "Factory machine operation logs" are data that record the operation history of machines and robots operating within a factory.

[1458] "Production efficiency" is an efficiency index calculated from the operating and downtime of machines and robots in factories and manufacturing sites, as well as the frequency of errors.

[1459] "Error frequency" is an indicator that refers to the number of times a machine or robot makes an error within a certain period of time.

[1460] The "means for generating maintenance advice" refers to a device or program that provides users with advice on maintenance timing and improvements based on production efficiency and error frequency.

[1461] "Means for obtaining and displaying analysis results and advice via a smartphone" refers to a device or program that obtains and displays analysis results and advice on a smartphone.

[1462] This invention is a system that analyzes PC operation logs and factory machine operation logs, analyzes work efficiency and production efficiency, and provides advice to users. This system reads and analyzes the operation logs, calculates efficiency based on the results, and provides specific advice to users.

[1463] System configuration

[1464] The system includes the following main components:

[1465] 1. Log data reading method

[1466] Log data is read from a server or smartphone. This data includes PC operation logs and factory machine operation logs.

[1467] For example, it has the function of obtaining operation log files from factory machines via Wi-Fi.

[1468] 2. Log data analysis methods

[1469] Analyze log data and calculate work efficiency and production efficiency.

[1470] Specifically, the type of activity (operation, stop, error, etc.) in the log data and the start and end times of each activity are obtained, and their duration is calculated.

[1471] Production efficiency is calculated by comparing the total operating time of factory machines with the time they are down.

[1472] 3. A means of generating advice based on calculated efficiencies

[1473] Based on the calculated efficiency, advice is generated to be provided to the user.

[1474] For example, if production efficiency is declining, specific improvement advice such as "Please carry out regular maintenance" is generated.

[1475] 4. A means of saving the results, including the generated advice

[1476] The generated advice and analysis results are saved to a specified file or cloud storage.

[1477] This allows users to refer to the analysis results later and carry out appropriate maintenance and business improvements.

[1478] 5. A means to obtain and display analysis results and advice via smartphone

[1479] It has the function of obtaining and displaying analysis results and advice on a smartphone.

[1480] Users can use their smartphones to easily check data even outside the factory and take any necessary action quickly.

[1481] Processing flow

[1482] The specific processing flow of this system is as follows:

[1483] 1. Reading the log data

[1484] The server reads the operation log file from the specified path or cloud storage. For example, the operation log generated by a factory machine contains the following data:

[1485] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1486] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[1487] 2. Log data analysis

[1488] Analyze the log data and calculate the duration of each activity. For example, analyze that "running" activity is 3 hours and "stopped" activity is 30 minutes.

[1489] 3. Efficiency Calculation

[1490] Calculate production efficiency based on operating time and downtime. For example, in the above log data, the operating time is 3 hours and the total activity time is 3.5 hours, so the efficiency is approximately 85.71%.

[1491] 4. Generating and Saving Advice

[1492] Based on the calculated efficiency, advice is generated, such as a message saying, "Production efficiency is declining. Please inspect and replace the following parts."

[1493] The generated advice and analysis results are saved in JSON format.

[1494] 5. Display on smartphones

[1495] Display analysis results and advice on your smartphone, allowing users to take action quickly. Use the following prompt as an example:

[1496] Analyze the following log data, calculate the production efficiency and the number of errors, and if the production efficiency is less than 80%, provide appropriate maintenance advice.

[1497] Log Data:

[1498] [

[1499] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[1500] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[1501] {"activity": "running", "start_time": "2023-10-01T12:30:00", "end_time": "2023-10-01T14:00:00"},

[1502] {"activity": "error", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T14:15:00"},

[1503] {"activity": "running", "start_time": "2023-10-01T14:15:00", "end_time": "2023-10-01T17:00:00"}

[1504] ]

[1505] As described above, the system of the present invention aims to support efficient business improvement and maintenance through analysis of operation logs, thereby improving the efficiency of users' factory operations and work.

[1506] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1507] Step 1:

[1508] Loading log data

[1509] The server reads operation log files from the specified storage location or cloud storage. Specifically, the server receives the file path or storage URL as input and retrieves JSON-formatted log data from that location. As an example, the operation log file "robot_log.json" of a factory machine is read via Wi-Fi. The read data includes the type of each activity (e.g., "running," "stopped," "error") as well as the start and end times.

[1510] Step 2:

[1511] Analyzing log data

[1512] The server analyzes the loaded operation log data. In this process, it analyzes each activity entry and calculates the duration of each activity based on the start and end times. Specifically, the server receives the start and end times as input, calculates the difference between them, and outputs the duration. For example, it analyzes that "running" activity lasted 3 hours from 09:00 to 12:00, and "stopped" activity lasted 30 minutes from 12:00 to 12:30.

[1513] Step 3:

[1514] Efficiency calculations

[1515] The server calculates efficiency based on the analysis data. Specifically, the server adds up the duration of each activity and calculates the ratio of productive to unproductive activities. The input is the duration of each activity, and the output is the efficiency percentage. For example, if the working time is 3 hours and the total activity time is 3.5 hours, the efficiency is calculated to be approximately 85.71%.

[1516] Step 4:

[1517] Generating Advice

[1518] The server generates advice to provide to the user based on the calculated efficiency. Here, the server receives the efficiency percentage as input and generates a message according to that value. The output is an advice message. For example, if the efficiency is less than 80%, the advice generated is "Production efficiency is declining. Please inspect and replace the following parts."

[1519] Step 5:

[1520] Saving the results

[1521] The server saves the generated advice and analysis results to a specified file or cloud storage. Specifically, the server receives analysis results and advice messages as input and saves them in a JSON format file. The output is the saved file.

[1522] Step 6:

[1523] Display on smartphone

[1524] The device (smartphone) retrieves and displays the analysis results and advice from the cloud storage or server. Specifically, the smartphone receives the cloud storage URL or API endpoint as input and displays the data from that location. The output is the analysis results and advice messages displayed on the smartphone screen. As an example, let's perform an analysis using the following prompt:

[1525] Analyze the following log data, calculate the production efficiency and the number of errors, and if the production efficiency is less than 80%, provide appropriate maintenance advice.

[1526] Log Data:

[1527] [

[1528] {"activity": "running", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"},

[1529] {"activity": "stopped", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"},

[1530] {"activity": "running", "start_time": "2023-10-01T12:30:00", "end_time": "2023-10-01T14:00:00"},

[1531] {"activity": "error", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T14:15:00"},

[1532] {"activity": "running", "start_time": "2023-10-01T14:15:00", "end_time": "2023-10-01T17:00:00"}

[1533] ]

[1534] 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.

[1535] This invention relates to a system that analyzes work efficiency from PC operation logs and provides advice to users. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide more appropriate advice that takes into account the user's mental state.

[1536] System Overview

[1537] The system includes the following main components:

[1538] 1. Log data reading method:

[1539] The server reads the user's operation log file from the specified path.

[1540] This log file records the type of activity, as well as the start and end times of each activity.

[1541] 2. Log data analysis methods:

[1542] The server analyzes the log data and calculates the time taken for each activity.

[1543] Work efficiency is calculated by adding up the time spent on productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time.

[1544] 3. Emotion recognition means (emotion engine):

[1545] The server recognizes the user's emotions through facial expressions, voice, keystrokes, etc.

[1546] The recognized emotion data is recorded together with the operation log data and is used during analysis.

[1547] 4. Advice Generation Methods:

[1548] The server generates advice to be provided to the user based on the calculated work efficiency and the recognized emotion.

[1549] Depending on the level of efficiency and the user's emotional state, a message containing specific improvements or points to maintain is created.

[1550] 5. Result storage means:

[1551] The server will save the generated advice and efficiency results to the specified file.

[1552] The user can refer to the results later.

[1553] Specific examples

[1554] Below is a concrete example of how this system calculates work efficiency and generates advice based on the user's operation log data and emotion data.

[1555] 1. Example of log data

[1556] A user's activity log contains the following data:

[1557] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1558] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[1559] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[1560] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[1561] 2. Example of Emotion Data

[1562] During the same period, the emotion engine recognized the following emotions:

[1563] {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[1564] {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[1565] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[1566] 3. Log data analysis

[1567] The server parses each entry and calculates the duration of each activity from the start and end times.

[1568] The duration of productive activities ("working," "meeting," "coding") is summed and calculated as a percentage of total activity time.

[1569] For example, in the case of the above log data, the productive time is 7 hours and the total activity time is 7.5 hours, so the work efficiency is approximately 93.33%.

[1570] 4. Emotion Data Analysis

[1571] The server analyzes the emotion data obtained from the emotion engine to identify the user's emotional state.

[1572] In the above example, the user is recognized as feeling "happy" at 09:30, "neutral" at 12:15, and "stressed" at 15:00.

[1573] 5. Generating Advice

[1574] The server generates advice to provide to the user based on the calculated efficiency and the perceived emotion.

[1575] For example, if your efficiency is 93.33% and you are feeling "stressed" in the afternoon, the following advice will be generated: "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or managing your tasks differently to reduce stress."

[1576] 6. Saving the results

[1577] The server stores the calculated efficiency, generated advice, and emotion data in a JSON format file.

[1578] Users can refer to this file later to check their own work efficiency and emotional state and find appropriate improvements.

[1579] As described above, this system aims to improve users' work efficiency by efficiently analyzing their PC operation logs and emotional data and providing specific advice.

[1580] The processing flow will be explained below.

[1581] Step 1:

[1582] The server specifies the log file path and reads the log data. Specifically, the server opens the specified file (e.g., user_log.json) and reads the JSON-formatted data from the file. The read data is stored in memory as an operation log.

[1583] Step 2:

[1584] The server collects emotion data using an emotion engine, analyzing the user's camera footage, voice input, keystrokes, etc., and generates emotion data including the type of emotion and a timestamp.

[1585] Step 3:

[1586] The server analyzes the operation log data it has read one by one. The server scans the entries in the log data in a loop and obtains the activity, start time, and end time for each entry.

[1587] Step 4:

[1588] The server calculates the duration of the activity using the start and end times of each log entry. It calculates the difference between the start and end times and converts it to seconds.

[1589] Step 5:

[1590] The server classifies the duration of each activity. For productive activities (e.g., "working," "meeting," "coding"), the duration is counted as productive time, while other activities only count towards the total activity time.

[1591] Step 6:

[1592] After the server has finished parsing all the log entries, it calculates work efficiency based on the productive time and total active time. Efficiency is calculated by dividing the productive time by the total active time and converting the result into a percentage.

[1593] Step 7:

[1594] The server analyzes the collected emotional data, assessing the user's emotional state during a specific time period and determining which emotions were most prevalent.

[1595] Step 8:

[1596] The server generates advice based on the calculated work efficiency and analyzed emotional data. Depending on the degree of efficiency and the user's emotional state, it creates a message containing specific points to improve or maintain.

[1597] Step 9:

[1598] The server saves the generated advice, work efficiency, and emotion data, converts this data into a JSON format file, and writes it to the specified file path.

[1599] Step 10:

[1600] Users can refer to the saved result file as needed, check the results, understand their own work efficiency and emotional state, and find appropriate improvement measures.

[1601] Example 2

[1602] 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."

[1603] Conventional work efficiency analysis systems are limited to analyzing only the user's operation log data and are unable to provide advice that takes into account the user's emotional state. This makes it difficult to present appropriate countermeasures for performance declines and increased stress caused by the user's mental state. Therefore, there is a need to provide a system that can analyze the user's operation log data and emotional data in an integrated manner and provide more personalized advice.

[1604] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1605] In this invention, the server includes means for reading log data, means for analyzing the read log data and calculating work efficiency, means for collecting emotion data using an emotion engine that recognizes the user's emotions, means for generating advice based on the recognized emotion data and the calculated work efficiency, and means for saving the results including the generated advice. This makes it possible to comprehensively analyze the user's operation log and emotion data and provide more appropriate advice that takes the user's mental state into consideration.

[1606] "Log data" refers to records of a user's PC operations, and includes information such as the activity content, start time, and end time.

[1607] "Analysis" refers to the process of calculating specific indicators (e.g., work efficiency) based on log data and sentiment data.

[1608] "Work efficiency" indicates the ratio of the user's productive activity time divided by the total activity time, and is a numerical representation of the user's work efficiency.

[1609] An "emotion engine" refers to a system or algorithm that recognizes emotions from input data such as a user's facial expressions, voice, and keystrokes, and outputs the results as data.

[1610] "Emotion data" is data that includes the user's emotional state (e.g., happy, neutral, stressed, etc.) recognized by the emotion engine.

[1611] The "advice generation means" is a means for generating specific suggestions and improvements for the user as messages based on the analyzed work efficiency and the recognized emotion data.

[1612] The "means for saving results" refers to a means for saving the generated advice and analysis results in a file, database, etc., so that they can be referenced later.

[1613] This invention is a system that analyzes PC operation log data and emotion data, evaluates the user's work efficiency based on the data, and provides specific advice. As an embodiment of the invention, the operations of the server, terminal, and user will be mainly described below.

[1614] Server Operation

[1615] The server reads the user's PC operation log data from the specified path. Specifically, it uses Python's open function and json module to read the log data, which records the type of activity, start time, and end time of each activity. It also uses the datetime module to analyze the operation log data and calculate the time taken for each activity.

[1616] The server then uses an emotion engine, OpenCV, Google Cloud Speech-to-Text API, and proprietary algorithms to collect emotion data from the user's facial expressions, voice, and keystrokes. The collected emotion data is recorded along with operation log data and used for analysis.

[1617] The server generates advice by inputting a prompt into the generative AI model based on the calculated work efficiency and the recognized emotion data. An example of a prompt is, "The user's work efficiency is 93.33%, and a state of stress was recognized in the afternoon. Please generate appropriate advice based on this information." The generated advice is saved in a file in JSON format for later reference.

[1618] Device behavior

[1619] A module for recording operation log data is installed on the user's device. This module captures user operations in real time and records the activity content, start time, and end time. It is also possible to use an emotion engine on the device to recognize the user's emotions in real time. For example, emotion data can be collected by facial expression recognition using a camera or voice analysis using a microphone.

[1620] User Actions

[1621] Users operate their PCs as usual and perform tasks using specific software. Operation log data captured during these tasks is sent to the server periodically or at a set time. The user can then check the generated advice on their device and adjust their work methods based on specific areas for improvement or maintenance.

[1622] Specific examples

[1623] For example, if a user works on a PC all day and the operation log data contains the following data:

[1624] {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1625] {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[1626] {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[1627] {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[1628] Suppose the sentiment data collected during the same period is as follows:

[1629] {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[1630] {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[1631] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[1632] The server analyzes the log data and emotion data and inputs prompt sentences, such as the following, into the generative AI model:

[1633] "The user's work efficiency was 93.33% and a stressful state was detected in the afternoon. Please generate appropriate advice based on this information."

[1634] As a result, the generative AI model offers advice like this:

[1635] "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or your tasks differently to reduce managing stress."

[1636] The above is an embodiment of the present invention, which allows a user to voluntarily obtain specific advice for improving work efficiency based on their own PC operation log data and emotion data.

[1637] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1638] Step 1: Loading the log data

[1639] The server reads the user's operation log file from the specified path. The input is the path to the log file, and the output is a JSON-formatted object of the read log data. Specifically, the log data is read from the file using Python's open function and the json module. For example, the processing is as follows: log_data = json.load(open('path / to / logfile.json')).

[1640] Step 2: Analyze the log data

[1641] The server analyzes the operation log data and calculates the time taken for each activity. The input is a JSON object of the log data, and the output is the duration of each activity and the total productive activity time. Specifically, it uses the datetime module to calculate the difference between the start time and the end time. For example, it processes as follows:

[1642] Input: "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"

[1643] Output: Duration of activity (3 hours)

[1644] Step 3: Collecting and Recognizing Emotional Data

[1645] The server uses an emotion engine to collect emotion data from the user's facial expressions, voice, and keystrokes. The input is real-time data from devices connected to the emotion engine, and the output is a dataset of recognized emotions. Specifically, facial recognition is performed using OpenCV, voice emotion recognition is performed using the Google Cloud Speech-to-Text API, and emotion is inferred based on keystroke patterns. For example, voice data is collected and the API is called to recognize emotions.

[1646] Step 4: Generating Advice

[1647] The server generates advice to provide to the user based on the calculated work efficiency and the recognized emotion data. The input is the calculated work efficiency and emotion data, and the output is the generated advice message. Specifically, the prompt sentence "The user's work efficiency is 93.33%, and a state of stress was recognized in the afternoon. Please generate appropriate advice based on this information" is input to the generative AI model, and the generated text is obtained.

[1648] Step 5: Save the results

[1649] The server saves the generated advice and analysis results to the specified file. The input is the dataset of the generated advice and analysis results, and the output is the saved JSON format file. Specifically, the json.dump function is used to write the result data to a file. For example, it is processed as follows: with open('path / to / resultfile.json', 'w') as result_file:

[1650] These are the processing steps of this system, which makes it possible to comprehensively analyze the user's PC operation log data and emotional data and provide appropriate advice.

[1651] (Application example 2)

[1652] 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."

[1653] Conventional work efficiency analysis systems were able to calculate efficiency based on a user's operation log, but it was difficult to provide appropriate advice that took the user's emotional state into consideration. Furthermore, while some systems were able to aggregate efficiency data and emotional data, they were unable to provide real-time advice based on that data. The present invention aims to provide a system that can provide more appropriate and practical advice in real time by analyzing not only a user's work efficiency but also their emotional state.

[1654] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1655] In this invention, the server includes means for reading log data, means for analyzing the read log data and emotion data to calculate work efficiency and the user's emotional state, means for generating advice based on the calculated work efficiency and the recognized emotion, means for providing the generated advice in real time, and means for saving results including the generated advice, thereby making it possible to generate specific advice from the user's operation log and emotion data and provide it in real time.

[1656] A "PC operation log" is data that includes a record of operations performed by a user on a PC, and includes the type of operation, start time, end time, and so on.

[1657] "Emotion data" refers to data that includes the user's emotional state as recognized through facial expressions, voice, keystrokes, and the like.

[1658] "Work efficiency" is an index of efficiency calculated based on the ratio of the time spent on a user's productive activities to the total activity time.

[1659] "Advice" is a message containing specific points to improve or maintain that are provided to the user based on the analyzed work efficiency and emotional state.

[1660] The "means for reading log data" is a device or program that has the function of reading the PC operation log from a specified path.

[1661] The "analyzing means" is a device or program that analyzes the duration of each activity and the user's emotional state based on the read log data and emotional data, and calculates work efficiency.

[1662] The "means for generating advice" is a device or program for creating an advice message to be provided to the user based on the analyzed work efficiency and the user's emotional state.

[1663] The "means for providing in real time" is a device or program for instantly presenting the generated advice to the user.

[1664] The "means for storing results" refers to a device or program for recording the generated advice and calculated work efficiency results so that they can be referenced later.

[1665] This invention is a system that analyzes work efficiency from PC operation logs and emotional data and provides advice to users.

[1666] First, the server reads the PC's operation log from the specified path. This log data records the type of activity, start time, and end time of each activity. Next, the server analyzes the read log data and calculates the time spent on each activity. It calculates work efficiency by adding up the time spent on productive activities (such as "working," "meeting," and "coding") and comparing this with the total activity time.

[1667] Meanwhile, the server also analyzes emotional data. Emotional data is recognized through the user's facial expressions, voice, keystrokes, etc. This recognition is performed using a camera and microphone, and the emotional state is analyzed using a machine learning model such as TensorFlow. The recognized emotional data is recorded along with the operation log data and used for analysis.

[1668] The server then generates advice to provide to the user based on the calculated work efficiency and the recognized emotions. Specifically, it uses a generative AI model to automatically generate optimal advice from the analysis results. This advice may include a message such as, "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or managing your tasks differently to reduce stress," depending on the efficiency level and the user's emotional state.

[1669] The generated advice is displayed on the terminal in real time, allowing the user to immediately receive this advice and obtain specific instructions for improving their work. In addition, the server stores the generated advice and calculated work efficiency results for the user to refer to later.

[1670] For example, a user's activity log might contain the following data:

[1671] - {"activity": "working", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1672] - {"activity": "browsing", "start_time": "2023-10-01T12:00:00", "end_time": "2023-10-01T12:30:00"}

[1673] - {"activity": "meeting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T14:00:00"}

[1674] - {"activity": "coding", "start_time": "2023-10-01T14:00:00", "end_time": "2023-10-01T17:00:00"}

[1675] Also, suppose the emotion engine recognizes the following emotions:

[1676] - {"time": "2023-10-01T09:30:00", "emotion": "happy"}

[1677] - {"time": "2023-10-01T12:15:00", "emotion": "neutral"}

[1678] - {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[1679] Based on this data, the server calculates work efficiency and generates the following advice for the user:

[1680] "Your work efficiency is high. However, you appeared stressed in the afternoon. Consider taking short breaks or your tasks differently to reduce managing stress."

[1681] Below are some example prompts to input to a generative AI model:

[1682] "Based on the log data and emotion data below, please calculate work efficiency and generate advice.

[1683] Log Data:

[1684] {"activity": "assembling", "start_time": "2023-10-01T09:00:00", "end_time": "2023-10-01T12:00:00"}

[1685] {"activity": "inspecting", "start_time": "2023-10-01T13:00:00", "end_time": "2023-10-01T17:00:00"}

[1686] Emotional Data:

[1687] {"time": "2023-10-01T10:30:00", "emotion": "happy"}

[1688] {"time": "2023-10-01T15:00:00", "emotion": "stressed"}

[1689] Calculate work efficiency and generate advice based on emotional data.”

[1690] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1691] Step 1:

[1692] The server reads the PC's operation log data from the specified path. This operation log contains the type of activity, start time, and end time for each activity. The input is the path to the operation log data file, and the output is the raw operation log data. Specifically, the server reads the file and stores the data in memory.

[1693] Step 2:

[1694] The server analyzes the loaded operation log data and calculates the duration of each activity. During the analysis, it finds the difference between the start and end times of each log entry and records this for each activity. The input is the raw operation log data, and the output is the calculated duration data for each activity. Specifically, it calculates the difference between timestamps and processes the data.

[1695] Step 3:

[1696] The server calculates work efficiency by summing the duration of productive activities (e.g., "working," "meeting," "coding") and comparing it with the total activity time. The input is the calculated duration data and activity classification information, and the output is the work efficiency percentage. Specifically, it tallies the activity time belonging to each category and calculates the ratio.

[1697] Step 4:

[1698] The server recognizes emotions based on the user's facial and voice data acquired from the camera and microphone. This recognition is performed using a machine learning model such as TensorFlow. The input is facial and voice data, and the output is recognized emotion data. Specifically, the server preprocesses the captured data, inputs it into the machine learning model, and obtains the results.

[1699] Step 5:

[1700] The server generates advice to provide to the user based on the analyzed work efficiency and recognized emotional data. A generative AI model is used to generate this advice. The input is the work efficiency rate and emotional data, and the output is an advice message. Specifically, the server inputs appropriate advice words based on the efficiency and emotional profile into the generative AI model as a prompt, and obtains the response.

[1701] Step 6:

[1702] The server displays the generated advice on the terminal in real time. Possible display methods include a pop-up on the screen or a voice notification. The input is the advice message, and the output is a notification to the user. Specific operations include sending messages to the notification system and controlling the display.

[1703] Step 7:

[1704] The server records the generated advice and calculated performance results and saves them for future reference. The input is advice messages and performance data, and the output is a saved log file. Specific operations include writing to a database or file system.

[1705] 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.

[1706] 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.

[1707] 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.

[1708] 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.

[1709] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes 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.

[1710] 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.

[1711] 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).

[1712] 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.

[1713] 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."

[1714] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1715] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1716] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1717] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1718] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1719] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1720] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1721] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1722] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1723] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1724] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1725] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1726] The following is further disclosed regarding the above embodiment.

[1727] (Claim 1)

[1728] A system that analyzes work efficiency from PC operation logs and provides advice to users,

[1729] a means for reading log data;

[1730] A means of analyzing the read log data and calculating work efficiency,

[1731] A means for generating advice based on the calculated work efficiency;

[1732] means for storing the results including the generated advice;

[1733] A system including:

[1734] (Claim 2)

[1735] 2. The system according to claim 1, further comprising means for analyzing the activity content, start time, and end time contained in the log data and calculating productive time and total activity time.

[1736] (Claim 3)

[1737] 10. The system of claim 1, further comprising means for generating different advice messages based on the calculated work efficiency.

[1738] "Example 1"

[1739] (Claim 1)

[1740] A system that analyzes work efficiency from a user's operation log and provides advice to the user,

[1741] A means for reading user operation information from a specified path;

[1742] means for analyzing the loaded operation information and calculating the duration of each activity;

[1743] A means of calculating work efficiency by adding up productive activity time based on the analyzed information;

[1744] means for generating advice based on the calculated operational efficiency;

[1745] means for storing the results including the generated advice as data;

[1746] A system including:

[1747] (Claim 2)

[1748] 2. The system according to claim 1, further comprising means for analyzing the content, start time, and end time of an activity contained in the operation information, and calculating productive activity time and total activity time.

[1749] (Claim 3)

[1750] 10. The system of claim 1, further comprising means for generating different advisory messages based on the calculated operational efficiency.

[1751] "Application Example 1"

[1752] (Claim 1)

[1753] A system that analyzes work efficiency from PC operation logs and provides advice to users,

[1754] a means for reading log data;

[1755] A means of analyzing the read log data and calculating work efficiency,

[1756] A means for generating advice based on the calculated work efficiency;

[1757] means for storing the results including the generated advice;

[1758] A means for reading and analyzing the operation log of a factory machine and calculating production efficiency and error occurrence frequency;

[1759] a means for generating maintenance advice based on the calculated production efficiency and error occurrence frequency;

[1760] A means to obtain and display analysis results and advice via smartphone;

[1761] A system including:

[1762] (Claim 2)

[1763] 2. The system according to claim 1, further comprising means for analyzing the activity content, start time, and end time contained in the log data and calculating productive time and total activity time.

[1764] (Claim 3)

[1765] 10. The system of claim 1, further comprising: means for generating different advice messages based on the calculated work efficiency; and means for generating different maintenance advice messages based on the calculated production efficiency.

[1766] "Example 2: Combining Emotion Engines"

[1767] (Claim 1)

[1768] A system that analyzes work efficiency from PC operation logs and provides advice to users,

[1769] a means for reading log data;

[1770] A means of analyzing the read log data and calculating work efficiency,

[1771] means for collecting emotion data using an emotion engine that recognizes the emotion of a user;

[1772] means for generating advice based on the recognized emotion data and the calculated work efficiency;

[1773] means for storing the results including the generated advice;

[1774] A system including:

[1775] (Claim 2)

[1776] 2. The system according to claim 1, further comprising means for analyzing the activity content, start time, and end time contained in the log data and calculating productive time and total activity time.

[1777] (Claim 3)

[1778] 10. The system of claim 1, further comprising means for generating different advice messages based on the calculated work efficiency and the perceived emotion.

[1779] "Application example 2 when combining emotion engines"

[1780] (Claim 1)

[1781] A system that analyzes work efficiency from PC operation logs and emotional data and provides advice to users,

[1782] a means for reading log data;

[1783] A means for analyzing the read log data and emotion data and calculating the work efficiency and the user's emotion state;

[1784] means for generating advice based on the calculated work efficiency and the perceived emotions;

[1785] a means for providing the generated advice in real time;

[1786] means for storing the results including the generated advice;

[1787] A system including:

[1788] (Claim 2)

[1789] 2. The system according to claim 1, further comprising means for analyzing the activity content, start time, and end time contained in the log data and calculating productive time and total activity time.

[1790] (Claim 3)

[1791] 10. The system of claim 1, further comprising means for generating different advice messages based on the calculated work efficiency and the perceived emotional state. [Explanation of symbols]

[1792] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A system that analyzes work efficiency from PC operation logs and provides advice to users, a means for reading log data; A means of analyzing the read log data and calculating work efficiency, A means for generating advice based on the calculated work efficiency; means for storing the results including the generated advice; A system including:

2. 2. The system according to claim 1, further comprising means for analyzing the activity details, start times, and end times contained in the log data, and calculating productive time and total activity time.

3. 2. The system of claim 1, further comprising means for generating different advice messages based on the calculated work efficiency.

Images