system

Abstract

Provide a system. A means for receiving initial data and processed data uploaded by a user; means for comparing the initial data with the processed data to identify the processing details of the data; means for automatically generating a data processing code based on the processing content; means for transmitting the generated processing code to a user; A system including:

Description

[Technical Field]

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

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

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

[0004] One of the major challenges faced by data scientists is the significant amount of time and effort required to properly process various data sets and convert them into a format suitable for analysis. In particular, manually creating data processing code is tedious, error-prone, and inefficient. Therefore, automation and streamlining of data processing work is necessary. This invention aims to solve this problem by providing a system that automatically generates the necessary data processing code based on the initial data and processed data provided by the user. [Means for solving the problem]

[0005] The data processing and automatic generation system according to the present invention includes the following means: First, a means for receiving initial data and processed data uploaded by a user; Second, a means for comparing the initial data with the processed data and identifying the data processing content; Third, a means for automatically generating a data processing code based on the identified processing content; and Third, a means for transmitting the generated processing code to the user. These means enable a user to quickly process data without having to manually create the code.

[0006] "User" means a person who uses the system to upload initial data and processed data and receives a data processing code.

[0007] "Upload" refers to the operation of a user sending data from their own terminal to the system.

[0008] "Initial data" refers to raw data provided to the system by the user.

[0009] "Processed data" refers to data that has been processed and indicates the final data format desired by the user.

[0010] "Receiving" refers to the action of the server acquiring and storing data sent by the user.

[0011] "Comparing" refers to the action of the server collating each piece of data to identify differences or changes between the initial data and the processed data.

[0012] "Identifying" refers to the act of the server analyzing the differences between the initial data and the processed data and clearly indicating what kind of data processing has been performed.

[0013] "Data processing content" refers to the specific operations and conversions performed to convert the initial data into processed data.

[0014] "Automatically generating" refers to the server programmatically creating code based on the processing of the data.

[0015] "Data processing code" is program code required to process data into a specific format.

[0016] "Send" refers to the action of sending the data processing code generated by the server to the user's terminal.

[0017] "Data conversion" is the process of changing data from one format to another.

[0018] "Filtering" is the process of selecting data based on specific conditions and extracting only the necessary parts.

[0019] "Aggregation" refers to collecting data and processing it numerically according to certain rules.

[0020] A "combination operation" refers to combining multiple data sets into one. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The following describes an embodiment of the present invention. This system automatically generates the necessary data processing code based on the initial data (before data) and processed data (after data) provided by the user.

[0043] Overall system overview

[0044] This system is mainly composed of three entities: a server, a terminal, and a user. The user uploads the initial data and processed data from their own terminal, and the server receives and processes the data, finally generating a data processing code and providing it to the user.

[0045] Entering data

[0046] The user prepares CSV files of the initial data and the processed data, and uploads them to the server from their terminal. For example, the following format of data is assumed:

[0047] Initial data (before data)

[0048] csv

[0049] Name, age, address

[0050] Taro Tanaka, 30, Tokyo

[0051] Hanako Yamada, 25, Osaka Prefecture

[0052] Post-processing data (after data)

[0053] csv

[0054] Name, Age, Address, Age Category

[0055] Taro Tanaka, 30, Tokyo, 30s

[0056] Hanako Yamada, 25, Osaka Prefecture, 20s

[0057] Receiving data

[0058] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage, preparing them for subsequent data processing.

[0059] Data comparison and analysis

[0060] The server compares the saved initial data with the processed data. Specifically, it checks the differences in fields (columns) between the initial data and the processed data, and identifies newly added fields and changed content.

[0061] For example, in the above example, the server identifies that a new field called "age category" has been added. Since the value of this field is generated based on "age," the server analyzes it and infers the distribution rule of the age category.

[0062] Generate data manipulation code

[0063] The server automatically generates a data manipulation code based on the specified data manipulation content. In this example, a code for generating the specified age category is automatically generated. The generated code is designed to be easy for users to use.

[0064] Code Contribution

[0065] The generated data processing code is sent from the server to the user's device. The user can run this code in their own development environment to convert the initial data into a format similar to the processed data. For example, the following Python code is provided to the user:

[0066] example

[0067] python

[0068] import pandas as pd

[0069] import numpy as np

[0070] def add_age_category(df):

[0071] conditions = [

[0072] (df['age'] >= 20) & (df['age'] < 30),

[0073] (df['age'] >= 30) & (df['age'] < 40),

[0074] ]

[0075] choices = ['20s', '30s']

[0076] df['Age Category'] = np.select(conditions, choices, default='Other')

[0077] return df

[0078] Usage example

[0079] df_before = pd.read_csv('before_data.csv')

[0080] df_after = add_age_category(df_before)

[0081] df_after.to_csv('after_data.csv', index=False)

[0082] In this way, this system automatically generates data processing code according to the user's needs, significantly reducing the amount of manual coding required, and enabling data scientists to more efficiently conduct data analysis.

[0083] The processing flow will be explained below.

[0084] Step 1: Enter your data

[0085] The user prepares the initial data (before_data.csv) and the processed data (after_data.csv) and uploads them to the system from the terminal.

[0086] csv

[0087] Initial Data

[0088] Name, age, address

[0089] Taro Tanaka, 30, Tokyo

[0090] Hanako Yamada, 25, Osaka Prefecture

[0091] csv

[0092] Processed data

[0093] Name, Age, Address, Age Category

[0094] Taro Tanaka, 30, Tokyo, 30s

[0095] Hanako Yamada, 25, Osaka Prefecture, 20s

[0096] Step 2: Receiving the data

[0097] The server receives the initial data and processed data uploaded by the user.

[0098] The server stores the received data in its internal storage and prepares it for processing.

[0099] Step 3: Loading Data

[0100] The server reads the initial data and processed data from the internal storage and converts them into an internal data frame format.

[0101] Step 4: Compare the data

[0102] The server compares the fields (columns) of the initial data and the processed data to identify new columns and changes.

[0103] In this example, we identify that a new column called "Age Category" has been added.

[0104] Step 5: Data content analysis

[0105] The server analyzes the content of the identified new column "age category."

[0106] Specifically, we analyze whether people are classified as "in their 20s" or "in their 30s" based on their age.

[0107] Step 6: Estimating the processing logic

[0108] The server estimates the logic for generating an "age category" based on age.

[0109] For example, the rule is estimated such that if the age is between 20 and 30, the person is in their 20s, and if the age is between 30 and 40, the person is in their 30s.

[0110] Step 7: Auto-generate code

[0111] The server automatically generates a data processing code based on the estimated processing logic.

[0112] The specific Python code is as follows:

[0113] python

[0114] import pandas as pd

[0115] import numpy as np

[0116] def add_age_category(df):

[0117] conditions = [

[0118] (df['age'] >= 20) & (df['age'] < 30),

[0119] (df['age'] >= 30) & (df['age'] < 40),

[0120] ]

[0121] choices = ['20s', '30s']

[0122] df['Age Category'] = np.select(conditions, choices, default='Other')

[0123] return df

[0124] Step 8: Submit your code

[0125] The server transmits the generated data processing code to the terminal.

[0126] The user executes the received code in their own development environment and converts the initial data into processed data.

[0127] This series of processes allows users to quickly convert data into a new format without having to manually write complex data processing code.

[0128] Example 1

[0129] 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."

[0130] Conventional data processing methods require manual coding, which is complicated for users without experience or skills. Furthermore, it requires a lot of time and effort, making it difficult to process data quickly and accurately. Therefore, there is a need for a system that can automatically generate data processing code based on the initial data and processed data provided by the user, and provide this code to significantly improve the efficiency of coding work.

[0131] 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.

[0132] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify field differences and data conversion rules, means for automatically generating a data conversion code based on the identified data conversion rules, and means for transmitting the generated data conversion code to the user, thereby significantly reducing the user's manual coding work and enabling quick and accurate data processing.

[0133] "User" refers to an individual or organization that uses the system to upload data and receive a processing code.

[0134] "Initial data" refers to data before processing that a user uploads to the system.

[0135] "Processed data" is data that a user uploads to the system after processing, and indicates how the initial data should be changed.

[0136] "Means for receiving" refers to the function by which the server receives the initial data and processed data uploaded by the user and stores them in its internal storage.

[0137] "Means for comparing and identifying field differences and data conversion rules" refers to the function by which the server compares the fields (columns) of the initial data and the processed data, and analyzes newly added fields and changed content.

[0138] "Data conversion code" is program code that is automatically generated based on the specified data conversion rules.

[0139] "Means for automatic generation" refers to the function of the server to programmatically generate data processing code based on data conversion rules.

[0140] "Means for transmitting" refers to the function of transmitting the generated data processing code from the server to the user's terminal.

[0141] This invention is a data processing system that automatically generates necessary data processing code based on the initial data and processed data provided by the user. This system is mainly composed of three entities: a server, a terminal, and a user.

[0142] The server is the central hardware that performs the main calculations and data analysis processes. The server receives and stores the initial data and processed data uploaded by users, analyzes the data, and generates data processing code.

[0143] The user is responsible for preparing the initial data and processed data and uploading them to the server. Specifically, the user uses their own device to send a CSV file to the server.

[0144] The terminal is a computer or mobile device that a user uses to upload data to the server. The terminal provides an interface for data upload and receives the generated data processing code from the server.

[0145] Entering and Receiving Data

[0146] The user creates the initial data and processed data as CSV files through the terminal. For example, the initial data is in the following format:

[0147] Initial data (before data)

[0148] csv

[0149] Name, age, address

[0150] Taro Tanaka, 30, Tokyo

[0151] Hanako Yamada, 25, Osaka Prefecture

[0152] The processed data has the following format:

[0153] Post-processing data (after data)

[0154] csv

[0155] Name, Age, Address, Age Category

[0156] Taro Tanaka, 30, Tokyo, 30s

[0157] Hanako Yamada, 25, Osaka Prefecture, 20s

[0158] The user uploads this data from the terminal to the server.

[0159] Receiving and storing data

[0160] The server receives the uploaded CSV file and saves it in its internal storage. The saved file is used for data analysis later.

[0161] Data comparison and analysis

[0162] The server compares the initial data with the processed data and identifies newly added fields and changes. Specifically, for example, it detects that the processed data contains a new field called "age category." The server analyzes that the value of this field is generated based on "age" and infers the rule.

[0163] Generate data manipulation code

[0164] The server automatically generates data processing code, such as Python code, based on the specified data conversion rules. This generated code is provided to users in a format that is easy to understand and use.

[0165] Code Contribution

[0166] The generated data processing code is sent from the server to the user's device, and the user can use this code to convert the initial data into the same format as the processed data.

[0167] Examples and prompts

[0168] As a concrete example, the following prompt sentence is input to the generative AI model:

[0169] Generate data processing code based on the initial data and processed data provided by the user. For example, the initial data and processed data are as follows:

[0170] Initial data:

[0171] Name, age, address

[0172] Taro Tanaka, 30, Tokyo

[0173] Hanako Yamada, 25, Osaka Prefecture

[0174] Processed data:

[0175] Name, Age, Address, Age Category

[0176] Taro Tanaka, 30, Tokyo, 30s

[0177] Hanako Yamada, 25, Osaka Prefecture, 20s

[0178] Based on this data, generate Python code to add age categories.

[0179] Using this prompt, the server can generate the appropriate data manipulation code.

[0180] As described above, the present invention automatically generates data processing code according to the user's needs, significantly reducing the amount of manual coding required, and as a result, data scientists can more efficiently conduct data analysis.

[0181] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0182] Step 1:

[0183] The user prepares the initial data and processed data in CSV file format. The user uploads these files to the server via their terminal. Specifically, the user accesses the system interface using the terminal's browser, opens the file selection dialog, selects the CSV file, and starts uploading to the server. The input is the CSV files of the initial data and processed data, and the output is sending the file to the server.

[0184] Step 2:

[0185] The server receives the CSV file uploaded by the user. The received file is saved in the server's internal storage. This action saves the CSV file in the specified directory (e.g., / data / uploads / ). The input is the CSV file uploaded in step 1, and the output is the file saved in the internal storage.

[0186] Step 3:

[0187] The server loads the saved initial data and processed data, compares them, and analyzes changes in the data. Specifically, the server uses the Pandas library to load the CSV file in DataFrame format and compares the columns of the initial data and processed data. For example, it identifies that a new column, "Age Category," has been added to the processed data. This analysis extracts the differences in the fields between the initial data and processed data. The input is the CSV file saved in Step 2, and the output is the identified data transformation rules.

[0188] Step 4:

[0189] The server automatically generates data processing code based on the specified data conversion rules. Specifically, the server inputs the following prompt sentence into the generating AI model:

[0190] Generate data processing code based on the initial data and processed data provided by the user. For example, the initial data and processed data are as follows:

[0191] Initial data:

[0192] Name, age, address

[0193] Taro Tanaka, 30, Tokyo

[0194] Hanako Yamada, 25, Osaka Prefecture

[0195] Processed data:

[0196] Name, Age, Address, Age Category

[0197] Taro Tanaka, 30, Tokyo, 30s

[0198] Hanako Yamada, 25, Osaka Prefecture, 20s

[0199] Based on this data, generate Python code to add age categories.

[0200] Based on the prompt, the AI ​​model generates data processing code. The input is the specified data transformation rule and the prompt, and the output is the generated data processing code.

[0201] Step 5:

[0202] The server sends the generated data processing code to the user's device. Specifically, the server saves the generated code in file format and provides the file to the user as a download link or sends it directly by email. The input is the generated data processing code, and the output is a code file provided in a form accessible to the user.

[0203] Step 6:

[0204] The user downloads the data processing code provided by the server and runs it in their own development environment. Specifically, the user runs the downloaded code and converts the initial data into a format similar to the processed data. The input is the data processing code sent from the server and a CSV file of the initial data, and the output is the processed data file (CSV format).

[0205] This process allows users to process data without much effort by using automatically generated code.

[0206] (Application example 1)

[0207] 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."

[0208] Conventional data processing systems require users to manually write complex code, which requires a huge amount of time and effort. Furthermore, high levels of automation are required in fields such as logistics centers, where real-time data analysis and immediate decision-making are required. However, much of the data requires processing, such as categorization based on specific attribute values, but there is a lack of automated methods for efficiently performing this process.

[0209] 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.

[0210] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify the processing details of the data, means for automatically generating a data processing code based on the processing details, means for transmitting the generated processing code to the user, means for categorizing the initial data and the processed data based on the original data, and means for adding a new field based on the information obtained by the categorization. This makes it possible to automatically generate the data processing code required by the user and efficiently categorize the data based on specific attribute values.

[0211] "Initial data" refers to data uploaded by a user before processing.

[0212] "Processed data" is data that indicates the state of the initial data after it has been processed.

[0213] "Data processing content" refers to the changes and operations that occur between the initial data and the processed data.

[0214] "Data processing code" is program code for performing data conversion, filtering, aggregation, and joining operations.

[0215] "Categorization" refers to the operation of grouping data based on specific attribute values ​​(e.g., age or delivery time).

[0216] A "field" is a column of data elements used in databases, spreadsheets, etc.

[0217] An embodiment of the present invention will be described below. This system uses smartphones in a logistics center to automate real-time data analysis and processing.

[0218] System Overview

[0219] This system automatically generates a data processing code based on the initial data and processed data uploaded by the user and provides it to the user. It mainly consists of a server, a terminal (smartphone), and the user.

[0220] Hardware and Software Use

[0221] The server is a computer with high-performance data processing capabilities that receives and stores data uploaded by users. The terminals are smartphones used by logistics center staff, which input initial data and processed data and check and use received data. The software uses a Python runtime environment (e.g., Pyodide), Pandas, and Numpy libraries.

[0222] Generate data manipulation code

[0223] The server first receives the initial data and processed data uploaded by the user and saves them in its internal storage. The server then compares the initial data with the processed data to identify the data processing details. In particular, by analyzing newly added fields and changed content, the server categorizes the data based on attribute values. For example, it categorizes delivery efficiency based on delivery time (fast, medium, slow).

[0224] Examples of data processing

[0225] Specifically, the initial data for delivery information includes a "delivery ID" and "delivery time," and the processed data includes a "delivery efficiency category." Based on this analysis, data processing code is generated to add a new field (delivery efficiency category) according to a specific attribute value (delivery time). This code is provided to the user and can be executed on their smartphone.

[0226] Prompt Sentence Examples

[0227] Users can input the following prompt sentence into the generative AI model to generate data processing code.

[0228] Initial data (shipping information)

[0229] Delivery ID, Delivery time (hours)

[0230] 12345, 1.5

[0231] 67890, 3.0

[0232] 54321, 6.5

[0233] Processed data (delivery efficiency category)

[0234] Delivery ID, Delivery time (hours), Delivery efficiency category

[0235] 12345, 1.5, high speed

[0236] 67890, 3.0, medium speed

[0237] 54321, 6.5, slow

[0238] Use this data to generate a Python script that categorizes the data based on delivery time.

[0239] In this way, the system automates data analysis and processing in logistics centers, significantly reducing the workload of staff, and enables instant categorization based on specific data attributes, enabling faster decision-making.

[0240] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0241] Step 1:

[0242] The user prepares the initial data and processed data and uploads them to the server in CSV file format using a smartphone (terminal). The input includes the initial data (e.g., delivery ID and delivery time) and processed data (e.g., delivery ID, delivery time, delivery efficiency category). The output is that the server receives and stores this data.

[0243] Step 2:

[0244] The server compares the uploaded initial data with the processed data. At this stage, it analyzes the structure of the data columns (fields) and changes in data values. Specifically, it identifies new fields (e.g., "Delivery Efficiency Category") and analyzes the rules by which the values ​​of those fields are generated. The input is the initial data and the processed data, and the output is the identified processing details.

[0245] Step 3:

[0246] The server automatically generates data processing code based on the specified processing details. This code is used to convert, filter, aggregate, and combine data. Specifically, it describes a process to add delivery efficiency categories such as "fast," "medium," and "slow" based on delivery time. The input is the processing details specified in the previous step, and the output is the generated data processing code.

[0247] Step 4:

[0248] The generated data processing code is sent from the server to the user's smartphone. By executing this code on the smartphone, the user can convert the initial data into a format similar to the processed data. The input is the generated data processing code, and the output is data processing code that can be executed on the smartphone.

[0249] Step 5:

[0250] The user executes the generated data processing code on their smartphone. This converts the initial data into a format similar to the processed data and adds a new field (delivery efficiency category). The input is the initial data and the data processing code, and the output is the processed data.

[0251] Step 6:

[0252] The generated processed data is saved again as a CSV file, which users can download and use. This enables data analysis and rapid decision-making at the logistics center. The input is the processed data, and the output is a downloadable CSV file.

[0253] 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.

[0254] The following describes an embodiment of the present invention. This system not only automatically generates the necessary data processing code based on the initial data (before data) and processed data (after data) provided by the user, but also has the ability to recognize the user's emotions and adjust the data processing accordingly.

[0255] Overall system overview

[0256] This system is mainly composed of a server, a terminal, a user, and an emotion engine. Users upload initial data and processed data from their own terminals, and the server receives and processes this data. Finally, it generates a data processing code and provides it to the user. During this process, the emotion engine recognizes the user's emotional state and adjusts the data processing content and code delivery method as necessary.

[0257] Entering data

[0258] The user prepares CSV files of the initial data and processed data, and uploads them to the server from their terminal. For example, the following format of data is assumed:

[0259] Initial data (before data)

[0260] csv

[0261] Name, age, address

[0262] Taro Tanaka, 30, Tokyo

[0263] Hanako Yamada, 25, Osaka Prefecture

[0264] Post-processing data (after data)

[0265] csv

[0266] Name, Age, Address, Age Category

[0267] Taro Tanaka, 30, Tokyo, 30s

[0268] Hanako Yamada, 25, Osaka Prefecture, 20s

[0269] Receiving data

[0270] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage, preparing them for subsequent data processing.

[0271] Loading data

[0272] The server reads the initial data and processed data from the internal storage and converts them into an internal data frame format.

[0273] Data comparison and analysis

[0274] The server compares the fields (columns) of the initial data and the processed data to identify new columns or changes. For example, in this example, it identifies that a new column called "Age Category" has been added. Since the values ​​of this field are generated based on "Age," the server analyzes this and infers the distribution rules for the age category.

[0275] Generate data manipulation code

[0276] The server automatically generates a data processing code based on the specified data processing content. In this example, a code for generating the specified age category is automatically generated.

[0277] Emotion engine processing

[0278] The emotion engine recognizes the user's emotional state and reflects it in the data processing work. For example, if the user is feeling stressed, the emotion engine will reduce the complexity of the generated data processing code or provide more detailed explanations. It will also change the way the code is presented (e.g., step-by-step guides) depending on the user's emotional state.

[0279] Code Contribution

[0280] The generated data processing code is sent from the server to the user's terminal. The user executes this code in their own development environment to convert the initial data into the same format as the processed data.

[0281] In this way, this system automatically generates data processing code based on user input, and furthermore, by recognizing the user's emotional state and adjusting the processing content, it significantly reduces the amount of manual coding work and allows users to perform data processing more comfortably. As a result, data scientists can conduct data analysis more efficiently and accurately.

[0282] The processing flow will be explained below.

[0283] Step 1: Enter your data

[0284] The user prepares the initial data (before_data.csv) and the processed data (after_data.csv) and uploads them to the system from the terminal.

[0285] csv

[0286] Initial Data

[0287] Name, age, address

[0288] Taro Tanaka, 30, Tokyo

[0289] Hanako Yamada, 25, Osaka Prefecture

[0290] csv

[0291] Processed data

[0292] Name, Age, Address, Age Category

[0293] Taro Tanaka, 30, Tokyo, 30s

[0294] Hanako Yamada, 25, Osaka Prefecture, 20s

[0295] Step 2: Receiving the data

[0296] The server receives the initial data and processed data uploaded by the user.

[0297] The server stores the received data in its internal storage.

[0298] Step 3: Loading Data

[0299] The server reads the initial data and processed data from the internal storage and converts them into a data frame format.

[0300] Step 4: Compare and analyze the data

[0301] The server compares the fields (columns) of the initial data and the processed data, and identifies any added, deleted, or changed fields.

[0302] In this example, we identify that a new column called "Age Category" has been added.

[0303] Step 5: Data content analysis

[0304] The server analyzes the values ​​of the newly identified column "age category" and infers how they were generated.

[0305] Analyze that "age category" is classified as "20s" or "30s" based on "age."

[0306] Step 6: Estimating the processing logic

[0307] The server estimates a generation group for "age category" based on age.

[0308] For example, if the age is between 20 and 30, it will be "20s," and if the age is between 30 and 40, it will be "30s."

[0309] Step 7: Emotion Engine Emotion Recognition

[0310] The emotion engine analyzes data from the user's camera and microphone to recognize the user's emotional state (e.g., stressed, relaxed).

[0311] Step 8: Emotional Adjustment

[0312] The emotion engine adjusts the difficulty and level of detail of the generated data manipulation code based on the recognized emotional state of the user.

[0313] For example, if the user is feeling stressed, the emotion engine adjusts the code to reduce complexity and provide concise code.

[0314] Also, if the user is relaxed, provide a standard chord.

[0315] Step 9: Generate data manipulation code

[0316] The server automatically generates a data processing code based on the estimated processing logic.

[0317] Step 10: Submit your code

[0318] The server transmits the generated data processing code to the terminal.

[0319] The user executes the received code in their own development environment to convert the initial data into a format similar to the processed data.

[0320] This process eliminates the need for users to manually write complex data processing code, and the emotion engine takes the user's emotional state into consideration, allowing data processing work to be carried out efficiently while maintaining user comfort.

[0321] Example 2

[0322] 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."

[0323] Conventional data processing systems require users to manually create data processing codes, which is inefficient and prone to errors. Furthermore, no system takes into account the user's emotional state, which can increase the stress of the work. Therefore, there was a need for a system that automatically generates data processing codes based on the initial data and processed data provided by the user, and also adjusts the work according to the user's emotional state.

[0324] 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.

[0325] In this invention, the server includes means for receiving initial data and processed data uploaded by the user, means for comparing the initial data with the processed data to identify the data processing details, means for automatically generating a data processing code based on the identified processing details, means for recognizing the user's emotional state and adjusting the data processing details and the code provision method according to that state, and means for transmitting the generated processing code to the user. This frees the user from manual coding work, enables efficient and accurate data processing, and allows the user to work in an emotionally sensitive environment.

[0326] "Initial data" refers to the original data provided by the user before any data processing.

[0327] "Processed data" refers to data that has been processed into a format or content desired by the user.

[0328] "Data processing code" is a program code required to generate processed data from initial data.

[0329] "Emotional state" refers to the user's psychological and emotional state, including stress, frustration, relaxation, and the like.

[0330] "Data column structure" refers to the arrangement and relationships of each field or column of data.

[0331] "Changes in data values" refers to differences in the values ​​of data points or fields that occur between the initial data and the processed data.

[0332] "Data transformation" is the process of changing the format of data from one form to another.

[0333] "Filtering" is the process of extracting only data that meets specific conditions.

[0334] "Aggregation" is the process of calculating statistics, totals, averages, etc. from a collection of data.

[0335] A "join operation" is the process of combining multiple data sets into one.

[0336] A "server" refers to a central computer system for processing data, and has the role of receiving requests from users, performing the necessary processing, and returning the results.

[0337] The following is a detailed description of an embodiment of the present invention. This system automatically generates the necessary data processing code based primarily on the initial data and processed data uploaded by the user. It also has the ability to recognize the user's emotional state and adjust the data processing content and code delivery method accordingly.

[0338] System configuration

[0339] This system consists of a server, a terminal, a user, and an emotion engine. The user uses the terminal to upload the initial data and processed data, and the server receives and processes this data. The server uses the emotion engine to recognize the user's emotional state and adjust the data processing content.

[0340] Hardware and Software Used

[0341] This system uses the following hardware and software:

[0342] Hardware:

[0343] Server: A high-performance computer system.

[0344] Terminal: A personal computer or mobile terminal through which a user enters data.

[0345] software:

[0346] Pandas: A Python data processing library.

[0347] Emotion engine: Software for recognizing the user's emotional state.

[0348] Database Management System (DBMS): Software for storing and managing data.

[0349] Specific examples of processing

[0350] The user prepares the following initial data and processed data. An example of CSV format is shown below:

[0351] Initial data (before data):

[0352] csv

[0353] Name, age, address

[0354] Taro Tanaka, 30, Tokyo

[0355] Hanako Yamada, 25, Osaka Prefecture

[0356] After processing data:

[0357] csv

[0358] Name, Age, Address, Age Category

[0359] Taro Tanaka, 30, Tokyo, 30s

[0360] Hanako Yamada, 25, Osaka Prefecture, 20s

[0361] The server receives this data and converts it into a data frame using Pandas. It then compares the initial data with the processed data to identify new columns or changes. In this example, it identifies that a new column called "Age Category" has been added. Because this column is generated based on "Age," the server infers the distribution rule for the age category.

[0362] Prompt Sentence Examples

[0363] For example, when a user requests data processing, the prompt text is as follows:

[0364] Write code using Pandas to add a new column based on the following initial data. The goal is to add age categories based on the age column.

[0365] Initial data:

[0366] Name, age, address

[0367] Taro Tanaka, 30, Tokyo

[0368] Hanako Yamada, 25, Osaka Prefecture

[0369] Example of processed data:

[0370] Name, Age, Address, Age Category

[0371] Taro Tanaka, 30, Tokyo, 30s

[0372] Hanako Yamada, 25, Osaka Prefecture, 20s

[0373] "

[0374] The emotion engine responds by reducing the complexity of the generated data processing code or by providing more detailed explanations when the user is stressed, and also by changing the way the code is presented (e.g., step-by-step guides) depending on the user's emotional state.

[0375] In this way, our system automatically generates data processing code based on user input and further adjusts the processing content based on the user's emotional state, significantly reducing the amount of manual coding work required and allowing users to perform data processing more comfortably. As a result, data scientists and other users can conduct data analysis more efficiently and accurately.

[0376] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0377] Step 1:

[0378] The user prepares the initial data and processed data.

[0379] Users prepare the initial data and processed data in CSV format on their own devices. These data are used as the basis for data processing.

[0380] Input: Initial data, processed data (CSV file)

[0381] Output: Prepared data file

[0382] Specific behavior: A user creates and edits a CSV file using Excel or a text editor.

[0383] Step 2:

[0384] The user uploads the initial data and processed data to the server.

[0385] Users use a dedicated web interface on their terminal to upload the initial data and processed data to the server.

[0386] Input: Prepared initial data and processed data

[0387] Output: Data file uploaded to the server

[0388] Specific behavior: A user opens a web browser, selects a file on the upload screen, and clicks the "Send" button.

[0389] Step 3:

[0390] The server receives and stores the uploaded data.

[0391] The server receives the CSV file sent by the user via an HTTP request, checks the integrity of the data, and then saves it in its internal storage.

[0392] Input: Data upload request from user

[0393] Output: Initial data and processed data stored in the server storage

[0394] Specific operation: The server checks the format of the data and saves the file in the specified directory.

[0395] Step 4:

[0396] The server reads the stored data and converts it into a data frame format.

[0397] The server reads the data from its internal storage and converts it into a dataframe format using a data processing library such as Pandas.

[0398] Input: Saved initial data and processed data

[0399] Output: Data converted to a data frame format

[0400] Specific operation: The server uses Pandas' read_csv function to read the CSV file and convert it into a data frame.

[0401] Step 5:

[0402] The server compares the initial data with the processed data and identifies the data processing details.

[0403] The server compares the columns of the initial data and the processed data, identifies new columns and changes, and identifies the data processing details.

[0404] Input: Initial data and processed data in data frame format

[0405] Output: Identified data manipulations (new columns and changes)

[0406] Specific operation: The server uses Pandas' merge function or DataFrame's comparison function to extract column differences and detect the generation rules for new columns.

[0407] Step 6:

[0408] The server automatically generates a data processing code based on the specified data processing content.

[0409] The server generates data processing code in the form of a Python script based on the analyzed data processing content.

[0410] Input: Identified data manipulation details

[0411] Output: Automatically generated data processing code

[0412] Specific operation: The server generates Python code based on the specified rules and describes the logic for data processing.

[0413] Step 7:

[0414] The emotion engine recognizes the user's emotional state and reflects it in the data processing process.

[0415] The emotion engine analyzes the user's emotional state (e.g., stress) and adjusts the complexity of the generated data processing code or provides detailed explanations.

[0416] Input: Data about the user's emotional state

[0417] Output: Adjusted data processing code

[0418] How it works: The emotion engine analyzes voice analysis, keyboard typing speed, etc., and adds explanations and comments to the code as needed.

[0419] Step 8:

[0420] The server transmits the generated data processing code to the user's terminal.

[0421] The server transmits the generated data processing code to the user's terminal so that the user can download it.

[0422] Input: Generated data processing code

[0423] Output: Data processing code provided to the user's device

[0424] What happens: The server sends the code file via an HTTP response and provides a link for the user to download it.

[0425] Step 9:

[0426] The user receives the code and runs it.

[0427] The user executes the received code in their own development environment and converts the initial data into a format similar to the processed data.

[0428] Input: Data processing code received from the server

[0429] Output: New data files generated by the executed data manipulation code.

[0430] Specific operation: The user runs the code in a development environment such as Python, and checks and saves the converted data.

[0431] Through the above steps, the system efficiently and accurately processes data based on the data provided by the user, supporting the user's work.

[0432] (Application example 2)

[0433] 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."

[0434] In situations where large amounts of data must be handled efficiently, such as on a production line, data processing and conversion tasks not only require time and effort, but are prone to errors. Furthermore, the emotional state of workers can have a significant impact on productivity and accuracy. However, no existing systems have been able to automatically generate data processing code that takes the user's emotional state into account. This creates the problem of users finding it difficult to understand and execute the code when they are stressed.

[0435] 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.

[0436] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify the data processing content, means for automatically generating a data processing code based on the processing content, means for recognizing the user's emotional state using an emotion recognition engine, means for adjusting the generated data processing code based on the emotional state, and means for transmitting the generated processing code to the user. This makes it possible to provide an adaptive data processing code according to the user's emotional state, thereby reducing user stress and improving data processing efficiency.

[0437] "Initial data" refers to data before processing that is first input or uploaded by a user.

[0438] "Processed data" refers to data obtained by performing a specific processing operation on the initial data.

[0439] "Data processing content" refers to the method and content of data conversion or processing, which is identified by comparing the initial data with the processed data.

[0440] The "data processing code" is a program code for executing data processing that is automatically generated based on the specified data processing content.

[0441] An "emotion recognition engine" is a function or system for recognizing a user's emotional state in real time.

[0442] "Emotional state" refers to the internal state that the user is feeling, such as stressed, relaxed, confused, etc.

[0443] This invention is a system that realizes automation of data processing on a manufacturing line and generates data processing codes taking into account the emotional state of staff. The following hardware and software are used to implement this invention.

[0444] Hardware and Software

[0445] 1. Hardware:

[0446] Server: Receives, stores, processes and transmits data.

[0447] Terminal: A device (PC, tablet, etc.) that a user uses to upload data.

[0448] Emotion recognition camera: A camera for recognizing the user's emotional state in real time.

[0449] Sensor: A sensor device that collects data from the production line.

[0450] 2. Software:

[0451] OS and server software: The basic software required to operate a server.

[0452] Data processing libraries: For example, use the Python Pandas library to work with data.

[0453] Emotion Recognition Software: Analyze the user's emotional state using the EmotionRecognition module.

[0454] Generative AI model to use: An AI model that understands the specific data manipulation requirements and generates code.

[0455] System configuration and operation

[0456] 1. Upload your data

[0457] Users use their devices to upload the initial data and processed data to the server. The data is often provided in CSV file format.

[0458] 2. Receipt and storage of data

[0459] The server receives the data uploaded by the user and saves it in the internal storage, then reads the data into the internal data frame format.

[0460] 3. Data Analysis and Code Generation

[0461] The server compares the initial data with the processed data, identifies new columns and changes, and automatically generates data processing code based on this. The Pandas library is used to perform detailed analysis of the column structure of the data frame and changes in data values.

[0462] 4. Emotion recognition

[0463] The emotion recognition camera captures the user's emotional state in real time, and the emotion recognition software (EmotionRecognition module) analyzes it to determine whether the user is feeling stressed or relaxed.

[0464] 5. Adjusting the code

[0465] Based on the emotion recognition results, the server adjusts the generated data processing code. For example, if the user is stressed, the code is simplified and detailed comments are added. On the other hand, if the user is relaxed, efficient and concise code is generated.

[0466] 6. Send the code

[0467] The adjusted data processing code is sent to the user's terminal, and the user can use this code to perform data processing.

[0468] Specific examples

[0469] For example, suppose production line data is provided as follows:

[0470] Initial data (before data)

[0471] csv

[0472] Product ID, Quality

[0473] 1001, 85

[0474] 1002, 92

[0475] Post-processing data (after data)

[0476] csv

[0477] Product ID, Quality, Quality Category

[0478] 1001, 85, Medium

[0479] 1002, 92, High

[0480] Prompt Sentence Examples

[0481] "Tell me how you can process data from the production line in real time and adjust the production process according to the emotions of your staff."

[0482] In this way, it is possible to provide details for specifically implementing the invention and to demonstrate how the user can operate the system effectively.

[0483] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0484] Step 1:

[0485] The user uses the terminal to prepare CSV files of the initial data (before data) and the processed data (after data), and uploads them to the server. Specifically, the user selects the CSV file from the file selection screen on the terminal and clicks the upload button.

[0486] Input: Initial data CSV file, processed data CSV file

[0487] Output: Data is sent to the server

[0488] Step 2:

[0489] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage. The received data is kept as a temporary file and prepared for the next processing.

[0490] Input: Initial data and processed data sent by the user

[0491] Output: Initial data and processed data stored in the server's internal storage

[0492] Step 3:

[0493] The server loads the initial data and processed data from the internal storage and converts them into an internal data frame using the Pandas library, which makes subsequent processing easier.

[0494] Input: CSV file stored in the server's internal storage

[0495] Output: Initial data and processed data in data frame format

[0496] Step 4:

[0497] The server compares the column structure and data values ​​of the initial data with those of the processed data to identify the data processing details. This analysis detects new columns and value changes and estimates the type of processing that has occurred.

[0498] Input: Initial data and processed data in data frame format

[0499] Output: Identification of processing details (e.g., detection of a new column "Quality Category")

[0500] Step 5:

[0501] The server automatically generates data processing code based on the specified processing details. The generated code is Python code, and includes code for deriving the "quality category," for example.

[0502] Input: Processing details identification result

[0503] Output: Data processing code (Python script)

[0504] Step 6:

[0505] The emotion recognition camera captures the user's emotional state, which is then analyzed by the EmotionRecognition module, and the analysis results are sent to the server as data indicating whether the user is stressed or relaxed.

[0506] Input: Video data from emotion recognition camera

[0507] Output: User's emotional state data

[0508] Step 7:

[0509] The server adjusts the data processing code based on the emotion recognition results: if the user is stressed, it adds detailed comments to the code and simplifies the process; if the user is relaxed, it creates a more efficient code structure.

[0510] Input: User's emotional state data, initial data processing code

[0511] Output: Adjusted data processing code

[0512] Step 8:

[0513] The adjusted data processing code is sent from the server to the user's terminal, and the user executes this code in their own development environment to convert the initial data into a format similar to the processed data.

[0514] Input: Adjusted data processing code

[0515] Output: Data manipulation code sent to the user's terminal

[0516] In this way, the entire system processes in a single flow, automating data processing and realizing adaptive data processing that takes into account the user's emotional state.

[0517] 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.

[0518] 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.

[0519] 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.

[0520] [Second embodiment]

[0521] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0522] 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.

[0523] 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).

[0524] 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.

[0525] 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.

[0526] 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).

[0527] 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.

[0528] 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.

[0529] 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.

[0530] 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.

[0531] 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.

[0532] 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."

[0533] The following describes an embodiment of the present invention. This system automatically generates the necessary data processing code based on the initial data (before data) and processed data (after data) provided by the user.

[0534] Overall system overview

[0535] This system is mainly composed of three entities: a server, a terminal, and a user. The user uploads the initial data and processed data from their own terminal, and the server receives and processes the data, finally generating a data processing code and providing it to the user.

[0536] Entering data

[0537] The user prepares CSV files of the initial data and the processed data, and uploads them to the server from their terminal. For example, the following format of data is assumed:

[0538] Initial data (before data)

[0539] csv

[0540] Name, age, address

[0541] Taro Tanaka, 30, Tokyo

[0542] Hanako Yamada, 25, Osaka Prefecture

[0543] Post-processing data (after data)

[0544] csv

[0545] Name, Age, Address, Age Category

[0546] Taro Tanaka, 30, Tokyo, 30s

[0547] Hanako Yamada, 25, Osaka Prefecture, 20s

[0548] Receiving data

[0549] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage, preparing them for subsequent data processing.

[0550] Data comparison and analysis

[0551] The server compares the saved initial data with the processed data. Specifically, it checks the differences in fields (columns) between the initial data and the processed data, and identifies newly added fields and changed content.

[0552] For example, in the above example, the server identifies that a new field called "age category" has been added. Since the value of this field is generated based on "age," the server analyzes it and infers the distribution rule of the age category.

[0553] Generate data manipulation code

[0554] The server automatically generates a data manipulation code based on the specified data manipulation content. In this example, a code for generating the specified age category is automatically generated. The generated code is designed to be easy for users to use.

[0555] Code Contribution

[0556] The generated data processing code is sent from the server to the user's device. The user can run this code in their own development environment to convert the initial data into a format similar to the processed data. For example, the following Python code is provided to the user:

[0557] example

[0558] python

[0559] import pandas as pd

[0560] import numpy as np

[0561] def add_age_category(df):

[0562] conditions = [

[0563] (df['age'] >= 20) & (df['age'] < 30),

[0564] (df['age'] >= 30) & (df['age'] < 40),

[0565] ]

[0566] choices = ['20s', '30s']

[0567] df['Age Category'] = np.select(conditions, choices, default='Other')

[0568] return df

[0569] Usage example

[0570] df_before = pd.read_csv('before_data.csv')

[0571] df_after = add_age_category(df_before)

[0572] df_after.to_csv('after_data.csv', index=False)

[0573] In this way, this system automatically generates data processing code according to the user's needs, significantly reducing the amount of manual coding required, and enabling data scientists to more efficiently conduct data analysis.

[0574] The processing flow will be explained below.

[0575] Step 1: Enter your data

[0576] The user prepares the initial data (before_data.csv) and the processed data (after_data.csv) and uploads them to the system from the terminal.

[0577] csv

[0578] Initial Data

[0579] Name, age, address

[0580] Taro Tanaka, 30, Tokyo

[0581] Hanako Yamada, 25, Osaka Prefecture

[0582] csv

[0583] Processed data

[0584] Name, Age, Address, Age Category

[0585] Taro Tanaka, 30, Tokyo, 30s

[0586] Hanako Yamada, 25, Osaka Prefecture, 20s

[0587] Step 2: Receiving the data

[0588] The server receives the initial data and processed data uploaded by the user.

[0589] The server stores the received data in its internal storage and prepares it for processing.

[0590] Step 3: Loading Data

[0591] The server reads the initial data and processed data from the internal storage and converts them into an internal data frame format.

[0592] Step 4: Compare the data

[0593] The server compares the fields (columns) of the initial data and the processed data to identify new columns and changes.

[0594] In this example, we identify that a new column called "Age Category" has been added.

[0595] Step 5: Data content analysis

[0596] The server analyzes the content of the identified new column "age category."

[0597] Specifically, we analyze whether people are classified as "in their 20s" or "in their 30s" based on their age.

[0598] Step 6: Estimating the processing logic

[0599] The server estimates the logic for generating an "age category" based on age.

[0600] For example, the rule is estimated such that if the age is between 20 and 30, the person is in their 20s, and if the age is between 30 and 40, the person is in their 30s.

[0601] Step 7: Auto-generate code

[0602] The server automatically generates a data processing code based on the estimated processing logic.

[0603] The specific Python code is as follows:

[0604] python

[0605] import pandas as pd

[0606] import numpy as np

[0607] def add_age_category(df):

[0608] conditions = [

[0609] (df['age'] >= 20) & (df['age'] < 30),

[0610] (df['age'] >= 30) & (df['age'] < 40),

[0611] ]

[0612] choices = ['20s', '30s']

[0613] df['Age Category'] = np.select(conditions, choices, default='Other')

[0614] return df

[0615] Step 8: Submit your code

[0616] The server transmits the generated data processing code to the terminal.

[0617] The user executes the received code in their own development environment and converts the initial data into processed data.

[0618] This series of processes allows users to quickly convert data into a new format without having to manually write complex data processing code.

[0619] Example 1

[0620] 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."

[0621] Conventional data processing methods require manual coding, which is complicated for users without experience or skills. Furthermore, it requires a lot of time and effort, making it difficult to process data quickly and accurately. Therefore, there is a need for a system that can automatically generate data processing code based on the initial data and processed data provided by the user, and provide this code to significantly improve the efficiency of coding work.

[0622] 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.

[0623] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify field differences and data conversion rules, means for automatically generating a data conversion code based on the identified data conversion rules, and means for transmitting the generated data conversion code to the user, thereby significantly reducing the user's manual coding work and enabling quick and accurate data processing.

[0624] "User" refers to an individual or organization that uses the system to upload data and receive a processing code.

[0625] "Initial data" refers to data before processing that a user uploads to the system.

[0626] "Processed data" is data that a user uploads to the system after processing, and indicates how the initial data should be changed.

[0627] "Means for receiving" refers to the function by which the server receives the initial data and processed data uploaded by the user and stores them in its internal storage.

[0628] "Means for comparing and identifying field differences and data conversion rules" refers to the function by which the server compares the fields (columns) of the initial data and the processed data, and analyzes newly added fields and changed content.

[0629] "Data conversion code" is program code that is automatically generated based on the specified data conversion rules.

[0630] "Means for automatic generation" refers to the function of the server to programmatically generate data processing code based on data conversion rules.

[0631] "Means for transmitting" refers to the function of transmitting the generated data processing code from the server to the user's terminal.

[0632] This invention is a data processing system that automatically generates necessary data processing code based on the initial data and processed data provided by the user. This system is mainly composed of three entities: a server, a terminal, and a user.

[0633] The server is the central hardware that performs the main calculations and data analysis processes. The server receives and stores the initial data and processed data uploaded by users, analyzes the data, and generates data processing code.

[0634] The user is responsible for preparing the initial data and processed data and uploading them to the server. Specifically, the user uses their own device to send a CSV file to the server.

[0635] The terminal is a computer or mobile device that a user uses to upload data to the server. The terminal provides an interface for data upload and receives the generated data processing code from the server.

[0636] Entering and Receiving Data

[0637] The user creates the initial data and processed data as CSV files through the terminal. For example, the initial data is in the following format:

[0638] Initial data (before data)

[0639] csv

[0640] Name, age, address

[0641] Taro Tanaka, 30, Tokyo

[0642] Hanako Yamada, 25, Osaka Prefecture

[0643] The processed data has the following format:

[0644] Post-processing data (after data)

[0645] csv

[0646] Name, Age, Address, Age Category

[0647] Taro Tanaka, 30, Tokyo, 30s

[0648] Hanako Yamada, 25, Osaka Prefecture, 20s

[0649] The user uploads this data from the terminal to the server.

[0650] Receiving and storing data

[0651] The server receives the uploaded CSV file and saves it in its internal storage. The saved file is used for data analysis later.

[0652] Data comparison and analysis

[0653] The server compares the initial data with the processed data and identifies newly added fields and changes. Specifically, for example, it detects that the processed data contains a new field called "age category." The server analyzes that the value of this field is generated based on "age" and infers the rule.

[0654] Generate data manipulation code

[0655] The server automatically generates data processing code, such as Python code, based on the specified data conversion rules. This generated code is provided to users in a format that is easy to understand and use.

[0656] Code Contribution

[0657] The generated data processing code is sent from the server to the user's device, and the user can use this code to convert the initial data into the same format as the processed data.

[0658] Examples and prompts

[0659] As a concrete example, the following prompt sentence is input to the generative AI model:

[0660] Generate data processing code based on the initial data and processed data provided by the user. For example, the initial data and processed data are as follows:

[0661] Initial data:

[0662] Name, age, address

[0663] Taro Tanaka, 30, Tokyo

[0664] Hanako Yamada, 25, Osaka Prefecture

[0665] Processed data:

[0666] Name, Age, Address, Age Category

[0667] Taro Tanaka, 30, Tokyo, 30s

[0668] Hanako Yamada, 25, Osaka Prefecture, 20s

[0669] Based on this data, generate Python code to add age categories.

[0670] Using this prompt, the server can generate the appropriate data manipulation code.

[0671] As described above, the present invention automatically generates data processing code according to the user's needs, significantly reducing the amount of manual coding required, and as a result, data scientists can more efficiently conduct data analysis.

[0672] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0673] Step 1:

[0674] The user prepares the initial data and processed data in CSV file format. The user uploads these files to the server via their terminal. Specifically, the user accesses the system interface using the terminal's browser, opens the file selection dialog, selects the CSV file, and starts uploading to the server. The input is the CSV files of the initial data and processed data, and the output is sending the file to the server.

[0675] Step 2:

[0676] The server receives the CSV file uploaded by the user. The received file is saved in the server's internal storage. This action saves the CSV file in the specified directory (e.g., / data / uploads / ). The input is the CSV file uploaded in step 1, and the output is the file saved in the internal storage.

[0677] Step 3:

[0678] The server loads the saved initial data and processed data, compares them, and analyzes changes in the data. Specifically, the server uses the Pandas library to load the CSV file in DataFrame format and compares the columns of the initial data and processed data. For example, it identifies that a new column, "Age Category," has been added to the processed data. This analysis extracts the differences in the fields between the initial data and processed data. The input is the CSV file saved in Step 2, and the output is the identified data transformation rules.

[0679] Step 4:

[0680] The server automatically generates data processing code based on the specified data conversion rules. Specifically, the server inputs the following prompt sentence into the generating AI model:

[0681] Generate data processing code based on the initial data and processed data provided by the user. For example, the initial data and processed data are as follows:

[0682] Initial data:

[0683] Name, age, address

[0684] Taro Tanaka, 30, Tokyo

[0685] Hanako Yamada, 25, Osaka Prefecture

[0686] Processed data:

[0687] Name, Age, Address, Age Category

[0688] Taro Tanaka, 30, Tokyo, 30s

[0689] Hanako Yamada, 25, Osaka Prefecture, 20s

[0690] Based on this data, generate Python code to add age categories.

[0691] Based on the prompt, the AI ​​model generates data processing code. The input is the specified data transformation rule and the prompt, and the output is the generated data processing code.

[0692] Step 5:

[0693] The server sends the generated data processing code to the user's device. Specifically, the server saves the generated code in file format and provides the file to the user as a download link or sends it directly by email. The input is the generated data processing code, and the output is a code file provided in a form accessible to the user.

[0694] Step 6:

[0695] The user downloads the data processing code provided by the server and runs it in their own development environment. Specifically, the user runs the downloaded code and converts the initial data into a format similar to the processed data. The input is the data processing code sent from the server and a CSV file of the initial data, and the output is the processed data file (CSV format).

[0696] This process allows users to process data without much effort by using automatically generated code.

[0697] (Application example 1)

[0698] 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."

[0699] Conventional data processing systems require users to manually write complex code, which requires a huge amount of time and effort. Furthermore, high levels of automation are required in fields such as logistics centers, where real-time data analysis and immediate decision-making are required. However, much of the data requires processing, such as categorization based on specific attribute values, but there is a lack of automated methods for efficiently performing this process.

[0700] 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.

[0701] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify the processing details of the data, means for automatically generating a data processing code based on the processing details, means for transmitting the generated processing code to the user, means for categorizing the initial data and the processed data based on the original data, and means for adding a new field based on the information obtained by the categorization. This makes it possible to automatically generate the data processing code required by the user and efficiently categorize the data based on specific attribute values.

[0702] "Initial data" refers to data uploaded by a user before processing.

[0703] "Processed data" is data that indicates the state of the initial data after it has been processed.

[0704] "Data processing content" refers to the changes and operations that occur between the initial data and the processed data.

[0705] "Data processing code" is program code for performing data conversion, filtering, aggregation, and joining operations.

[0706] "Categorization" refers to the operation of grouping data based on specific attribute values ​​(e.g., age or delivery time).

[0707] A "field" is a column of data elements used in databases, spreadsheets, etc.

[0708] An embodiment of the present invention will be described below. This system uses smartphones in a logistics center to automate real-time data analysis and processing.

[0709] System Overview

[0710] This system automatically generates a data processing code based on the initial data and processed data uploaded by the user and provides it to the user. It mainly consists of a server, a terminal (smartphone), and the user.

[0711] Hardware and Software Use

[0712] The server is a computer with high-performance data processing capabilities that receives and stores data uploaded by users. The terminals are smartphones used by logistics center staff, which input initial data and processed data and check and use received data. The software uses a Python runtime environment (e.g., Pyodide), Pandas, and Numpy libraries.

[0713] Generate data manipulation code

[0714] The server first receives the initial data and processed data uploaded by the user and saves them in its internal storage. The server then compares the initial data with the processed data to identify the data processing details. In particular, by analyzing newly added fields and changed content, the server categorizes the data based on attribute values. For example, it categorizes delivery efficiency based on delivery time (fast, medium, slow).

[0715] Examples of data processing

[0716] Specifically, the initial data for delivery information includes a "delivery ID" and "delivery time," and the processed data includes a "delivery efficiency category." Based on this analysis, data processing code is generated to add a new field (delivery efficiency category) according to a specific attribute value (delivery time). This code is provided to the user and can be executed on their smartphone.

[0717] Prompt Sentence Examples

[0718] Users can input the following prompt sentence into the generative AI model to generate data processing code.

[0719] Initial data (shipping information)

[0720] Delivery ID, Delivery time (hours)

[0721] 12345, 1.5

[0722] 67890, 3.0

[0723] 54321, 6.5

[0724] Processed data (delivery efficiency category)

[0725] Delivery ID, Delivery time (hours), Delivery efficiency category

[0726] 12345, 1.5, high speed

[0727] 67890, 3.0, medium speed

[0728] 54321, 6.5, slow

[0729] Use this data to generate a Python script that categorizes the data based on delivery time.

[0730] In this way, the system automates data analysis and processing in logistics centers, significantly reducing the workload of staff, and enables instant categorization based on specific data attributes, enabling faster decision-making.

[0731] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0732] Step 1:

[0733] The user prepares the initial data and processed data and uploads them to the server in CSV file format using a smartphone (terminal). The input includes the initial data (e.g., delivery ID and delivery time) and processed data (e.g., delivery ID, delivery time, delivery efficiency category). The output is that the server receives and stores this data.

[0734] Step 2:

[0735] The server compares the uploaded initial data with the processed data. At this stage, it analyzes the structure of the data columns (fields) and changes in data values. Specifically, it identifies new fields (e.g., "Delivery Efficiency Category") and analyzes the rules by which the values ​​of those fields are generated. The input is the initial data and the processed data, and the output is the identified processing details.

[0736] Step 3:

[0737] The server automatically generates data processing code based on the specified processing details. This code is used to convert, filter, aggregate, and combine data. Specifically, it describes a process to add delivery efficiency categories such as "fast," "medium," and "slow" based on delivery time. The input is the processing details specified in the previous step, and the output is the generated data processing code.

[0738] Step 4:

[0739] The generated data processing code is sent from the server to the user's smartphone. By executing this code on the smartphone, the user can convert the initial data into a format similar to the processed data. The input is the generated data processing code, and the output is data processing code that can be executed on the smartphone.

[0740] Step 5:

[0741] The user executes the generated data processing code on their smartphone. This converts the initial data into a format similar to the processed data and adds a new field (delivery efficiency category). The input is the initial data and the data processing code, and the output is the processed data.

[0742] Step 6:

[0743] The generated processed data is saved again as a CSV file, which users can download and use. This enables data analysis and rapid decision-making at the logistics center. The input is the processed data, and the output is a downloadable CSV file.

[0744] 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.

[0745] The following describes an embodiment of the present invention. This system not only automatically generates the necessary data processing code based on the initial data (before data) and processed data (after data) provided by the user, but also has the ability to recognize the user's emotions and adjust the data processing accordingly.

[0746] Overall system overview

[0747] This system is mainly composed of a server, a terminal, a user, and an emotion engine. Users upload initial data and processed data from their own terminals, and the server receives and processes this data. Finally, it generates a data processing code and provides it to the user. During this process, the emotion engine recognizes the user's emotional state and adjusts the data processing content and code delivery method as necessary.

[0748] Entering data

[0749] The user prepares CSV files of the initial data and processed data, and uploads them to the server from their terminal. For example, the following format of data is assumed:

[0750] Initial data (before data)

[0751] csv

[0752] Name, age, address

[0753] Taro Tanaka, 30, Tokyo

[0754] Hanako Yamada, 25, Osaka Prefecture

[0755] Post-processing data (after data)

[0756] csv

[0757] Name, Age, Address, Age Category

[0758] Taro Tanaka, 30, Tokyo, 30s

[0759] Hanako Yamada, 25, Osaka Prefecture, 20s

[0760] Receiving data

[0761] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage, preparing them for subsequent data processing.

[0762] Loading data

[0763] The server reads the initial data and processed data from the internal storage and converts them into an internal data frame format.

[0764] Data comparison and analysis

[0765] The server compares the fields (columns) of the initial data and the processed data to identify new columns or changes. For example, in this example, it identifies that a new column called "Age Category" has been added. Since the values ​​of this field are generated based on "Age," the server analyzes this and infers the distribution rules for the age category.

[0766] Generate data manipulation code

[0767] The server automatically generates a data processing code based on the specified data processing content. In this example, a code for generating the specified age category is automatically generated.

[0768] Emotion engine processing

[0769] The emotion engine recognizes the user's emotional state and reflects it in the data processing work. For example, if the user is feeling stressed, the emotion engine will reduce the complexity of the generated data processing code or provide more detailed explanations. It will also change the way the code is presented (e.g., step-by-step guides) depending on the user's emotional state.

[0770] Code Contribution

[0771] The generated data processing code is sent from the server to the user's terminal. The user executes this code in their own development environment to convert the initial data into the same format as the processed data.

[0772] In this way, this system automatically generates data processing code based on user input, and furthermore, by recognizing the user's emotional state and adjusting the processing content, it significantly reduces the amount of manual coding work and allows users to perform data processing more comfortably. As a result, data scientists can conduct data analysis more efficiently and accurately.

[0773] The processing flow will be explained below.

[0774] Step 1: Enter your data

[0775] The user prepares the initial data (before_data.csv) and the processed data (after_data.csv) and uploads them to the system from the terminal.

[0776] csv

[0777] Initial Data

[0778] Name, age, address

[0779] Taro Tanaka, 30, Tokyo

[0780] Hanako Yamada, 25, Osaka Prefecture

[0781] csv

[0782] Processed data

[0783] Name, Age, Address, Age Category

[0784] Taro Tanaka, 30, Tokyo, 30s

[0785] Hanako Yamada, 25, Osaka Prefecture, 20s

[0786] Step 2: Receiving the data

[0787] The server receives the initial data and processed data uploaded by the user.

[0788] The server stores the received data in its internal storage.

[0789] Step 3: Loading Data

[0790] The server reads the initial data and processed data from the internal storage and converts them into a data frame format.

[0791] Step 4: Compare and analyze the data

[0792] The server compares the fields (columns) of the initial data and the processed data, and identifies any added, deleted, or changed fields.

[0793] In this example, we identify that a new column called "Age Category" has been added.

[0794] Step 5: Data content analysis

[0795] The server analyzes the values ​​of the newly identified column "age category" and infers how they were generated.

[0796] Analyze that "age category" is classified as "20s" or "30s" based on "age."

[0797] Step 6: Estimating the processing logic

[0798] The server estimates a generation group for "age category" based on age.

[0799] For example, if the age is between 20 and 30, it will be "20s," and if the age is between 30 and 40, it will be "30s."

[0800] Step 7: Emotion Engine Emotion Recognition

[0801] The emotion engine analyzes data from the user's camera and microphone to recognize the user's emotional state (e.g., stressed, relaxed).

[0802] Step 8: Emotional Adjustment

[0803] The emotion engine adjusts the difficulty and level of detail of the generated data manipulation code based on the recognized emotional state of the user.

[0804] For example, if the user is feeling stressed, the emotion engine adjusts the code to reduce complexity and provide concise code.

[0805] Also, if the user is relaxed, provide a standard chord.

[0806] Step 9: Generate data manipulation code

[0807] The server automatically generates a data processing code based on the estimated processing logic.

[0808] Step 10: Submit your code

[0809] The server transmits the generated data processing code to the terminal.

[0810] The user executes the received code in their own development environment to convert the initial data into a format similar to the processed data.

[0811] This process eliminates the need for users to manually write complex data processing code, and the emotion engine takes the user's emotional state into consideration, allowing data processing work to be carried out efficiently while maintaining user comfort.

[0812] Example 2

[0813] 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."

[0814] Conventional data processing systems require users to manually create data processing codes, which is inefficient and prone to errors. Furthermore, no system takes into account the user's emotional state, which can increase the stress of the work. Therefore, there was a need for a system that automatically generates data processing codes based on the initial data and processed data provided by the user, and also adjusts the work according to the user's emotional state.

[0815] 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.

[0816] In this invention, the server includes means for receiving initial data and processed data uploaded by the user, means for comparing the initial data with the processed data to identify the data processing details, means for automatically generating a data processing code based on the identified processing details, means for recognizing the user's emotional state and adjusting the data processing details and the code provision method according to that state, and means for transmitting the generated processing code to the user. This frees the user from manual coding work, enables efficient and accurate data processing, and allows the user to work in an emotionally sensitive environment.

[0817] "Initial data" refers to the original data provided by the user before any data processing.

[0818] "Processed data" refers to data that has been processed into a format or content desired by the user.

[0819] "Data processing code" is a program code required to generate processed data from initial data.

[0820] "Emotional state" refers to the user's psychological and emotional state, including stress, frustration, relaxation, and the like.

[0821] "Data column structure" refers to the arrangement and relationships of each field or column of data.

[0822] "Changes in data values" refers to differences in the values ​​of data points or fields that occur between the initial data and the processed data.

[0823] "Data transformation" is the process of changing the format of data from one form to another.

[0824] "Filtering" is the process of extracting only data that meets specific conditions.

[0825] "Aggregation" is the process of calculating statistics, totals, averages, etc. from a collection of data.

[0826] A "join operation" is the process of combining multiple data sets into one.

[0827] A "server" refers to a central computer system for processing data, and has the role of receiving requests from users, performing the necessary processing, and returning the results.

[0828] The following is a detailed description of an embodiment of the present invention. This system automatically generates the necessary data processing code based primarily on the initial data and processed data uploaded by the user. It also has the ability to recognize the user's emotional state and adjust the data processing content and code delivery method accordingly.

[0829] System configuration

[0830] This system consists of a server, a terminal, a user, and an emotion engine. The user uses the terminal to upload the initial data and processed data, and the server receives and processes this data. The server uses the emotion engine to recognize the user's emotional state and adjust the data processing content.

[0831] Hardware and Software Used

[0832] This system uses the following hardware and software:

[0833] Hardware:

[0834] Server: A high-performance computer system.

[0835] Terminal: A personal computer or mobile terminal through which a user enters data.

[0836] software:

[0837] Pandas: A Python data processing library.

[0838] Emotion engine: Software for recognizing the user's emotional state.

[0839] Database Management System (DBMS): Software for storing and managing data.

[0840] Specific examples of processing

[0841] The user prepares the following initial data and processed data. An example of CSV format is shown below:

[0842] Initial data (before data):

[0843] csv

[0844] Name, age, address

[0845] Taro Tanaka, 30, Tokyo

[0846] Hanako Yamada, 25, Osaka Prefecture

[0847] After processing data:

[0848] csv

[0849] Name, Age, Address, Age Category

[0850] Taro Tanaka, 30, Tokyo, 30s

[0851] Hanako Yamada, 25, Osaka Prefecture, 20s

[0852] The server receives this data and converts it into a data frame using Pandas. It then compares the initial data with the processed data to identify new columns or changes. In this example, it identifies that a new column called "Age Category" has been added. Because this column is generated based on "Age," the server infers the distribution rule for the age category.

[0853] Prompt Sentence Examples

[0854] For example, when a user requests data processing, the prompt text is as follows:

[0855] Write code using Pandas to add a new column based on the following initial data. The goal is to add age categories based on the age column.

[0856] Initial data:

[0857] Name, age, address

[0858] Taro Tanaka, 30, Tokyo

[0859] Hanako Yamada, 25, Osaka Prefecture

[0860] Example of processed data:

[0861] Name, Age, Address, Age Category

[0862] Taro Tanaka, 30, Tokyo, 30s

[0863] Hanako Yamada, 25, Osaka Prefecture, 20s

[0864] "

[0865] The emotion engine responds by reducing the complexity of the generated data processing code or by providing more detailed explanations when the user is stressed, and also by changing the way the code is presented (e.g., step-by-step guides) depending on the user's emotional state.

[0866] In this way, our system automatically generates data processing code based on user input and further adjusts the processing content based on the user's emotional state, significantly reducing the amount of manual coding work required and allowing users to perform data processing more comfortably. As a result, data scientists and other users can conduct data analysis more efficiently and accurately.

[0867] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0868] Step 1:

[0869] The user prepares the initial data and processed data.

[0870] Users prepare the initial data and processed data in CSV format on their own devices. These data are used as the basis for data processing.

[0871] Input: Initial data, processed data (CSV file)

[0872] Output: Prepared data file

[0873] Specific behavior: A user creates and edits a CSV file using Excel or a text editor.

[0874] Step 2:

[0875] The user uploads the initial data and processed data to the server.

[0876] Users use a dedicated web interface on their terminal to upload the initial data and processed data to the server.

[0877] Input: Prepared initial data and processed data

[0878] Output: Data file uploaded to the server

[0879] Specific behavior: A user opens a web browser, selects a file on the upload screen, and clicks the "Send" button.

[0880] Step 3:

[0881] The server receives and stores the uploaded data.

[0882] The server receives the CSV file sent by the user via an HTTP request, checks the integrity of the data, and then saves it in its internal storage.

[0883] Input: Data upload request from user

[0884] Output: Initial data and processed data stored in the server storage

[0885] Specific operation: The server checks the format of the data and saves the file in the specified directory.

[0886] Step 4:

[0887] The server reads the stored data and converts it into a data frame format.

[0888] The server reads the data from its internal storage and converts it into a dataframe format using a data processing library such as Pandas.

[0889] Input: Saved initial data and processed data

[0890] Output: Data converted to a data frame format

[0891] Specific operation: The server uses Pandas' read_csv function to read the CSV file and convert it into a data frame.

[0892] Step 5:

[0893] The server compares the initial data with the processed data and identifies the data processing details.

[0894] The server compares the columns of the initial data and the processed data, identifies new columns and changes, and identifies the data processing details.

[0895] Input: Initial data and processed data in data frame format

[0896] Output: Identified data manipulations (new columns and changes)

[0897] Specific operation: The server uses Pandas' merge function or DataFrame's comparison function to extract column differences and detect the generation rules for new columns.

[0898] Step 6:

[0899] The server automatically generates a data processing code based on the specified data processing content.

[0900] The server generates data processing code in the form of a Python script based on the analyzed data processing content.

[0901] Input: Identified data manipulation details

[0902] Output: Automatically generated data processing code

[0903] Specific operation: The server generates Python code based on the specified rules and describes the logic for data processing.

[0904] Step 7:

[0905] The emotion engine recognizes the user's emotional state and reflects it in the data processing process.

[0906] The emotion engine analyzes the user's emotional state (e.g., stress) and adjusts the complexity of the generated data processing code or provides detailed explanations.

[0907] Input: Data about the user's emotional state

[0908] Output: Adjusted data processing code

[0909] How it works: The emotion engine analyzes voice analysis, keyboard typing speed, etc., and adds explanations and comments to the code as needed.

[0910] Step 8:

[0911] The server transmits the generated data processing code to the user's terminal.

[0912] The server transmits the generated data processing code to the user's terminal so that the user can download it.

[0913] Input: Generated data processing code

[0914] Output: Data processing code provided to the user's device

[0915] What happens: The server sends the code file via an HTTP response and provides a link for the user to download it.

[0916] Step 9:

[0917] The user receives the code and runs it.

[0918] The user executes the received code in their own development environment and converts the initial data into a format similar to the processed data.

[0919] Input: Data processing code received from the server

[0920] Output: New data files generated by the executed data manipulation code.

[0921] Specific operation: The user runs the code in a development environment such as Python, and checks and saves the converted data.

[0922] Through the above steps, the system efficiently and accurately processes data based on the data provided by the user, supporting the user's work.

[0923] (Application example 2)

[0924] 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."

[0925] In situations where large amounts of data must be handled efficiently, such as on a production line, data processing and conversion tasks not only require time and effort, but are prone to errors. Furthermore, the emotional state of workers can have a significant impact on productivity and accuracy. However, no existing systems have been able to automatically generate data processing code that takes the user's emotional state into account. This creates the problem of users finding it difficult to understand and execute the code when they are stressed.

[0926] 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.

[0927] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify the data processing content, means for automatically generating a data processing code based on the processing content, means for recognizing the user's emotional state using an emotion recognition engine, means for adjusting the generated data processing code based on the emotional state, and means for transmitting the generated processing code to the user. This makes it possible to provide an adaptive data processing code according to the user's emotional state, thereby reducing user stress and improving data processing efficiency.

[0928] "Initial data" refers to data before processing that is first input or uploaded by a user.

[0929] "Processed data" refers to data obtained by performing a specific processing operation on the initial data.

[0930] "Data processing content" refers to the method and content of data conversion or processing, which is identified by comparing the initial data with the processed data.

[0931] The "data processing code" is a program code for executing data processing that is automatically generated based on the specified data processing content.

[0932] An "emotion recognition engine" is a function or system for recognizing a user's emotional state in real time.

[0933] "Emotional state" refers to the internal state that the user is feeling, such as stressed, relaxed, confused, etc.

[0934] This invention is a system that realizes automation of data processing on a manufacturing line and generates data processing codes taking into account the emotional state of staff. The following hardware and software are used to implement this invention.

[0935] Hardware and Software

[0936] 1. Hardware:

[0937] Server: Receives, stores, processes and transmits data.

[0938] Terminal: A device (PC, tablet, etc.) that a user uses to upload data.

[0939] Emotion recognition camera: A camera for recognizing the user's emotional state in real time.

[0940] Sensor: A sensor device that collects data from the production line.

[0941] 2. Software:

[0942] OS and server software: The basic software required to operate a server.

[0943] Data processing libraries: For example, use the Python Pandas library to work with data.

[0944] Emotion Recognition Software: Analyze the user's emotional state using the EmotionRecognition module.

[0945] Generative AI model to use: An AI model that understands the specific data manipulation requirements and generates code.

[0946] System configuration and operation

[0947] 1. Upload your data

[0948] Users use their devices to upload the initial data and processed data to the server. The data is often provided in CSV file format.

[0949] 2. Receipt and storage of data

[0950] The server receives the data uploaded by the user and saves it in the internal storage, then reads the data into the internal data frame format.

[0951] 3. Data Analysis and Code Generation

[0952] The server compares the initial data with the processed data, identifies new columns and changes, and automatically generates data processing code based on this. The Pandas library is used to perform detailed analysis of the column structure of the data frame and changes in data values.

[0953] 4. Emotion recognition

[0954] The emotion recognition camera captures the user's emotional state in real time, and the emotion recognition software (EmotionRecognition module) analyzes it to determine whether the user is feeling stressed or relaxed.

[0955] 5. Adjusting the code

[0956] Based on the emotion recognition results, the server adjusts the generated data processing code. For example, if the user is stressed, the code is simplified and detailed comments are added. On the other hand, if the user is relaxed, efficient and concise code is generated.

[0957] 6. Send the code

[0958] The adjusted data processing code is sent to the user's terminal, and the user can use this code to perform data processing.

[0959] Specific examples

[0960] For example, suppose production line data is provided as follows:

[0961] Initial data (before data)

[0962] csv

[0963] Product ID, Quality

[0964] 1001, 85

[0965] 1002, 92

[0966] Post-processing data (after data)

[0967] csv

[0968] Product ID, Quality, Quality Category

[0969] 1001, 85, Medium

[0970] 1002, 92, High

[0971] Prompt Sentence Examples

[0972] "Tell me how you can process data from the production line in real time and adjust the production process according to the emotions of your staff."

[0973] In this way, it is possible to provide details for specifically implementing the invention and to demonstrate how the user can operate the system effectively.

[0974] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0975] Step 1:

[0976] The user uses the terminal to prepare CSV files of the initial data (before data) and the processed data (after data), and uploads them to the server. Specifically, the user selects the CSV file from the file selection screen on the terminal and clicks the upload button.

[0977] Input: Initial data CSV file, processed data CSV file

[0978] Output: Data is sent to the server

[0979] Step 2:

[0980] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage. The received data is kept as a temporary file and prepared for the next processing.

[0981] Input: Initial data and processed data sent by the user

[0982] Output: Initial data and processed data stored in the server's internal storage

[0983] Step 3:

[0984] The server loads the initial data and processed data from the internal storage and converts them into an internal data frame using the Pandas library, which makes subsequent processing easier.

[0985] Input: CSV file stored in the server's internal storage

[0986] Output: Initial data and processed data in data frame format

[0987] Step 4:

[0988] The server compares the column structure and data values ​​of the initial data with those of the processed data to identify the data processing details. This analysis detects new columns and value changes and estimates the type of processing that has occurred.

[0989] Input: Initial data and processed data in data frame format

[0990] Output: Identification of processing details (e.g., detection of a new column "Quality Category")

[0991] Step 5:

[0992] The server automatically generates data processing code based on the specified processing details. The generated code is Python code, and includes code for deriving the "quality category," for example.

[0993] Input: Processing details identification result

[0994] Output: Data processing code (Python script)

[0995] Step 6:

[0996] The emotion recognition camera captures the user's emotional state, which is then analyzed by the EmotionRecognition module, and the analysis results are sent to the server as data indicating whether the user is stressed or relaxed.

[0997] Input: Video data from emotion recognition camera

[0998] Output: User's emotional state data

[0999] Step 7:

[1000] The server adjusts the data processing code based on the emotion recognition results: if the user is stressed, it adds detailed comments to the code and simplifies the process; if the user is relaxed, it creates a more efficient code structure.

[1001] Input: User's emotional state data, initial data processing code

[1002] Output: Adjusted data processing code

[1003] Step 8:

[1004] The adjusted data processing code is sent from the server to the user's terminal, and the user executes this code in their own development environment to convert the initial data into a format similar to the processed data.

[1005] Input: Adjusted data processing code

[1006] Output: Data manipulation code sent to the user's terminal

[1007] In this way, the entire system processes in a single flow, automating data processing and realizing adaptive data processing that takes into account the user's emotional state.

[1008] 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.

[1009] 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.

[1010] 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.

[1011] [Third embodiment]

[1012] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1013] 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.

[1014] 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).

[1015] 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.

[1016] 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.

[1017] 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).

[1018] 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.

[1019] 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.

[1020] 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.

[1021] 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.

[1022] 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.

[1023] 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."

[1024] The following describes an embodiment of the present invention. This system automatically generates the necessary data processing code based on the initial data (before data) and processed data (after data) provided by the user.

[1025] Overall system overview

[1026] This system is mainly composed of three entities: a server, a terminal, and a user. The user uploads the initial data and processed data from their own terminal, and the server receives and processes the data, finally generating a data processing code and providing it to the user.

[1027] Entering data

[1028] The user prepares CSV files of the initial data and the processed data, and uploads them to the server from their terminal. For example, the following format of data is assumed:

[1029] Initial data (before data)

[1030] csv

[1031] Name, age, address

[1032] Taro Tanaka, 30, Tokyo

[1033] Hanako Yamada, 25, Osaka Prefecture

[1034] Post-processing data (after data)

[1035] csv

[1036] Name, Age, Address, Age Category

[1037] Taro Tanaka, 30, Tokyo, 30s

[1038] Hanako Yamada, 25, Osaka Prefecture, 20s

[1039] Receiving data

[1040] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage, preparing them for subsequent data processing.

[1041] Data comparison and analysis

[1042] The server compares the saved initial data with the processed data. Specifically, it checks the differences in fields (columns) between the initial data and the processed data, and identifies newly added fields and changed content.

[1043] For example, in the above example, the server identifies that a new field called "age category" has been added. Since the value of this field is generated based on "age," the server analyzes it and infers the distribution rule of the age category.

[1044] Generate data manipulation code

[1045] The server automatically generates a data manipulation code based on the specified data manipulation content. In this example, a code for generating the specified age category is automatically generated. The generated code is designed to be easy for users to use.

[1046] Code Contribution

[1047] The generated data processing code is sent from the server to the user's device. The user can run this code in their own development environment to convert the initial data into a format similar to the processed data. For example, the following Python code is provided to the user:

[1048] example

[1049] python

[1050] import pandas as pd

[1051] import numpy as np

[1052] def add_age_category(df):

[1053] conditions = [

[1054] (df['age'] >= 20) & (df['age'] < 30),

[1055] (df['age'] >= 30) & (df['age'] < 40),

[1056] ]

[1057] choices = ['20s', '30s']

[1058] df['Age Category'] = np.select(conditions, choices, default='Other')

[1059] return df

[1060] Usage example

[1061] df_before = pd.read_csv('before_data.csv')

[1062] df_after = add_age_category(df_before)

[1063] df_after.to_csv('after_data.csv', index=False)

[1064] In this way, this system automatically generates data processing code according to the user's needs, significantly reducing the amount of manual coding required, and enabling data scientists to more efficiently conduct data analysis.

[1065] The processing flow will be explained below.

[1066] Step 1: Enter your data

[1067] The user prepares the initial data (before_data.csv) and the processed data (after_data.csv) and uploads them to the system from the terminal.

[1068] csv

[1069] Initial Data

[1070] Name, age, address

[1071] Taro Tanaka, 30, Tokyo

[1072] Hanako Yamada, 25, Osaka Prefecture

[1073] csv

[1074] Processed data

[1075] Name, Age, Address, Age Category

[1076] Taro Tanaka, 30, Tokyo, 30s

[1077] Hanako Yamada, 25, Osaka Prefecture, 20s

[1078] Step 2: Receiving the data

[1079] The server receives the initial data and processed data uploaded by the user.

[1080] The server stores the received data in its internal storage and prepares it for processing.

[1081] Step 3: Loading Data

[1082] The server reads the initial data and processed data from the internal storage and converts them into an internal data frame format.

[1083] Step 4: Compare the data

[1084] The server compares the fields (columns) of the initial data and the processed data to identify new columns and changes.

[1085] In this example, we identify that a new column called "Age Category" has been added.

[1086] Step 5: Data content analysis

[1087] The server analyzes the content of the identified new column "age category."

[1088] Specifically, we analyze whether people are classified as "in their 20s" or "in their 30s" based on their age.

[1089] Step 6: Estimating the processing logic

[1090] The server estimates the logic for generating an "age category" based on age.

[1091] For example, the rule is estimated such that if the age is between 20 and 30, the person is in their 20s, and if the age is between 30 and 40, the person is in their 30s.

[1092] Step 7: Auto-generate code

[1093] The server automatically generates a data processing code based on the estimated processing logic.

[1094] The specific Python code is as follows:

[1095] python

[1096] import pandas as pd

[1097] import numpy as np

[1098] def add_age_category(df):

[1099] conditions = [

[1100] (df['age'] >= 20) & (df['age'] < 30),

[1101] (df['age'] >= 30) & (df['age'] < 40),

[1102] ]

[1103] choices = ['20s', '30s']

[1104] df['Age Category'] = np.select(conditions, choices, default='Other')

[1105] return df

[1106] Step 8: Submit your code

[1107] The server transmits the generated data processing code to the terminal.

[1108] The user executes the received code in their own development environment and converts the initial data into processed data.

[1109] This series of processes allows users to quickly convert data into a new format without having to manually write complex data processing code.

[1110] Example 1

[1111] 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."

[1112] Conventional data processing methods require manual coding, which is complicated for users without experience or skills. Furthermore, it requires a lot of time and effort, making it difficult to process data quickly and accurately. Therefore, there is a need for a system that can automatically generate data processing code based on the initial data and processed data provided by the user, and provide this code to significantly improve the efficiency of coding work.

[1113] 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.

[1114] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify field differences and data conversion rules, means for automatically generating a data conversion code based on the identified data conversion rules, and means for transmitting the generated data conversion code to the user, thereby significantly reducing the user's manual coding work and enabling quick and accurate data processing.

[1115] "User" refers to an individual or organization that uses the system to upload data and receive a processing code.

[1116] "Initial data" refers to data before processing that a user uploads to the system.

[1117] "Processed data" is data that a user uploads to the system after processing, and indicates how the initial data should be changed.

[1118] "Means for receiving" refers to the function by which the server receives the initial data and processed data uploaded by the user and stores them in its internal storage.

[1119] "Means for comparing and identifying field differences and data conversion rules" refers to the function by which the server compares the fields (columns) of the initial data and the processed data, and analyzes newly added fields and changed content.

[1120] "Data conversion code" is program code that is automatically generated based on the specified data conversion rules.

[1121] "Means for automatic generation" refers to the function of the server to programmatically generate data processing code based on data conversion rules.

[1122] "Means for transmitting" refers to the function of transmitting the generated data processing code from the server to the user's terminal.

[1123] This invention is a data processing system that automatically generates necessary data processing code based on the initial data and processed data provided by the user. This system is mainly composed of three entities: a server, a terminal, and a user.

[1124] The server is the central hardware that performs the main calculations and data analysis processes. The server receives and stores the initial data and processed data uploaded by users, analyzes the data, and generates data processing code.

[1125] The user is responsible for preparing the initial data and processed data and uploading them to the server. Specifically, the user uses their own device to send a CSV file to the server.

[1126] The terminal is a computer or mobile device that a user uses to upload data to the server. The terminal provides an interface for data upload and receives the generated data processing code from the server.

[1127] Entering and Receiving Data

[1128] The user creates the initial data and processed data as CSV files through the terminal. For example, the initial data is in the following format:

[1129] Initial data (before data)

[1130] csv

[1131] Name, age, address

[1132] Taro Tanaka, 30, Tokyo

[1133] Hanako Yamada, 25, Osaka Prefecture

[1134] The processed data has the following format:

[1135] Post-processing data (after data)

[1136] csv

[1137] Name, Age, Address, Age Category

[1138] Taro Tanaka, 30, Tokyo, 30s

[1139] Hanako Yamada, 25, Osaka Prefecture, 20s

[1140] The user uploads this data from the terminal to the server.

[1141] Receiving and storing data

[1142] The server receives the uploaded CSV file and saves it in its internal storage. The saved file is used for data analysis later.

[1143] Data comparison and analysis

[1144] The server compares the initial data with the processed data and identifies newly added fields and changes. Specifically, for example, it detects that the processed data contains a new field called "age category." The server analyzes that the value of this field is generated based on "age" and infers the rule.

[1145] Generate data manipulation code

[1146] The server automatically generates data processing code, such as Python code, based on the specified data conversion rules. This generated code is provided to users in a format that is easy to understand and use.

[1147] Code Contribution

[1148] The generated data processing code is sent from the server to the user's device, and the user can use this code to convert the initial data into the same format as the processed data.

[1149] Examples and prompts

[1150] As a concrete example, the following prompt sentence is input to the generative AI model:

[1151] Generate data processing code based on the initial data and processed data provided by the user. For example, the initial data and processed data are as follows:

[1152] Initial data:

[1153] Name, age, address

[1154] Taro Tanaka, 30, Tokyo

[1155] Hanako Yamada, 25, Osaka Prefecture

[1156] Processed data:

[1157] Name, Age, Address, Age Category

[1158] Taro Tanaka, 30, Tokyo, 30s

[1159] Hanako Yamada, 25, Osaka Prefecture, 20s

[1160] Based on this data, generate Python code to add age categories.

[1161] Using this prompt, the server can generate the appropriate data manipulation code.

[1162] As described above, the present invention automatically generates data processing code according to the user's needs, significantly reducing the amount of manual coding required, and as a result, data scientists can more efficiently conduct data analysis.

[1163] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1164] Step 1:

[1165] The user prepares the initial data and processed data in CSV file format. The user uploads these files to the server via their terminal. Specifically, the user accesses the system interface using the terminal's browser, opens the file selection dialog, selects the CSV file, and starts uploading to the server. The input is the CSV files of the initial data and processed data, and the output is sending the file to the server.

[1166] Step 2:

[1167] The server receives the CSV file uploaded by the user. The received file is saved in the server's internal storage. This action saves the CSV file in the specified directory (e.g., / data / uploads / ). The input is the CSV file uploaded in step 1, and the output is the file saved in the internal storage.

[1168] Step 3:

[1169] The server loads the saved initial data and processed data, compares them, and analyzes changes in the data. Specifically, the server uses the Pandas library to load the CSV file in DataFrame format and compares the columns of the initial data and processed data. For example, it identifies that a new column, "Age Category," has been added to the processed data. This analysis extracts the differences in the fields between the initial data and processed data. The input is the CSV file saved in Step 2, and the output is the identified data transformation rules.

[1170] Step 4:

[1171] The server automatically generates data processing code based on the specified data conversion rules. Specifically, the server inputs the following prompt sentence into the generating AI model:

[1172] Generate data processing code based on the initial data and processed data provided by the user. For example, the initial data and processed data are as follows:

[1173] Initial data:

[1174] Name, age, address

[1175] Taro Tanaka, 30, Tokyo

[1176] Hanako Yamada, 25, Osaka Prefecture

[1177] Processed data:

[1178] Name, Age, Address, Age Category

[1179] Taro Tanaka, 30, Tokyo, 30s

[1180] Hanako Yamada, 25, Osaka Prefecture, 20s

[1181] Based on this data, generate Python code to add age categories.

[1182] Based on the prompt, the AI ​​model generates data processing code. The input is the specified data transformation rule and the prompt, and the output is the generated data processing code.

[1183] Step 5:

[1184] The server sends the generated data processing code to the user's device. Specifically, the server saves the generated code in file format and provides the file to the user as a download link or sends it directly by email. The input is the generated data processing code, and the output is a code file provided in a form accessible to the user.

[1185] Step 6:

[1186] The user downloads the data processing code provided by the server and runs it in their own development environment. Specifically, the user runs the downloaded code and converts the initial data into a format similar to the processed data. The input is the data processing code sent from the server and a CSV file of the initial data, and the output is the processed data file (CSV format).

[1187] This process allows users to process data without much effort by using automatically generated code.

[1188] (Application example 1)

[1189] 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."

[1190] Conventional data processing systems require users to manually write complex code, which requires a huge amount of time and effort. Furthermore, high levels of automation are required in fields such as logistics centers, where real-time data analysis and immediate decision-making are required. However, much of the data requires processing, such as categorization based on specific attribute values, but there is a lack of automated methods for efficiently performing this process.

[1191] 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.

[1192] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify the processing details of the data, means for automatically generating a data processing code based on the processing details, means for transmitting the generated processing code to the user, means for categorizing the initial data and the processed data based on the original data, and means for adding a new field based on the information obtained by the categorization. This makes it possible to automatically generate the data processing code required by the user and efficiently categorize the data based on specific attribute values.

[1193] "Initial data" refers to data uploaded by a user before processing.

[1194] "Processed data" is data that indicates the state of the initial data after it has been processed.

[1195] "Data processing content" refers to the changes and operations that occur between the initial data and the processed data.

[1196] "Data processing code" is program code for performing data conversion, filtering, aggregation, and joining operations.

[1197] "Categorization" refers to the operation of grouping data based on specific attribute values ​​(e.g., age or delivery time).

[1198] A "field" is a column of data elements used in databases, spreadsheets, etc.

[1199] An embodiment of the present invention will be described below. This system uses smartphones in a logistics center to automate real-time data analysis and processing.

[1200] System Overview

[1201] This system automatically generates a data processing code based on the initial data and processed data uploaded by the user and provides it to the user. It mainly consists of a server, a terminal (smartphone), and the user.

[1202] Hardware and Software Use

[1203] The server is a computer with high-performance data processing capabilities that receives and stores data uploaded by users. The terminals are smartphones used by logistics center staff, which input initial data and processed data and check and use received data. The software uses a Python runtime environment (e.g., Pyodide), Pandas, and Numpy libraries.

[1204] Generate data manipulation code

[1205] The server first receives the initial data and processed data uploaded by the user and saves them in its internal storage. The server then compares the initial data with the processed data to identify the data processing details. In particular, by analyzing newly added fields and changed content, the server categorizes the data based on attribute values. For example, it categorizes delivery efficiency based on delivery time (fast, medium, slow).

[1206] Examples of data processing

[1207] Specifically, the initial data for delivery information includes a "delivery ID" and "delivery time," and the processed data includes a "delivery efficiency category." Based on this analysis, data processing code is generated to add a new field (delivery efficiency category) according to a specific attribute value (delivery time). This code is provided to the user and can be executed on their smartphone.

[1208] Prompt Sentence Examples

[1209] Users can input the following prompt sentence into the generative AI model to generate data processing code.

[1210] Initial data (shipping information)

[1211] Delivery ID, Delivery time (hours)

[1212] 12345, 1.5

[1213] 67890, 3.0

[1214] 54321, 6.5

[1215] Processed data (delivery efficiency category)

[1216] Delivery ID, Delivery time (hours), Delivery efficiency category

[1217] 12345, 1.5, high speed

[1218] 67890, 3.0, medium speed

[1219] 54321, 6.5, slow

[1220] Use this data to generate a Python script that categorizes the data based on delivery time.

[1221] In this way, the system automates data analysis and processing in logistics centers, significantly reducing the workload of staff, and enables instant categorization based on specific data attributes, enabling faster decision-making.

[1222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1223] Step 1:

[1224] The user prepares the initial data and processed data and uploads them to the server in CSV file format using a smartphone (terminal). The input includes the initial data (e.g., delivery ID and delivery time) and processed data (e.g., delivery ID, delivery time, delivery efficiency category). The output is that the server receives and stores this data.

[1225] Step 2:

[1226] The server compares the uploaded initial data with the processed data. At this stage, it analyzes the structure of the data columns (fields) and changes in data values. Specifically, it identifies new fields (e.g., "Delivery Efficiency Category") and analyzes the rules by which the values ​​of those fields are generated. The input is the initial data and the processed data, and the output is the identified processing details.

[1227] Step 3:

[1228] The server automatically generates data processing code based on the specified processing details. This code is used to convert, filter, aggregate, and combine data. Specifically, it describes a process to add delivery efficiency categories such as "fast," "medium," and "slow" based on delivery time. The input is the processing details specified in the previous step, and the output is the generated data processing code.

[1229] Step 4:

[1230] The generated data processing code is sent from the server to the user's smartphone. By executing this code on the smartphone, the user can convert the initial data into a format similar to the processed data. The input is the generated data processing code, and the output is data processing code that can be executed on the smartphone.

[1231] Step 5:

[1232] The user executes the generated data processing code on their smartphone. This converts the initial data into a format similar to the processed data and adds a new field (delivery efficiency category). The input is the initial data and the data processing code, and the output is the processed data.

[1233] Step 6:

[1234] The generated processed data is saved again as a CSV file, which users can download and use. This enables data analysis and rapid decision-making at the logistics center. The input is the processed data, and the output is a downloadable CSV file.

[1235] 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.

[1236] The following describes an embodiment of the present invention. This system not only automatically generates the necessary data processing code based on the initial data (before data) and processed data (after data) provided by the user, but also has the ability to recognize the user's emotions and adjust the data processing accordingly.

[1237] Overall system overview

[1238] This system is mainly composed of a server, a terminal, a user, and an emotion engine. Users upload initial data and processed data from their own terminals, and the server receives and processes this data. Finally, it generates a data processing code and provides it to the user. During this process, the emotion engine recognizes the user's emotional state and adjusts the data processing content and code delivery method as necessary.

[1239] Entering data

[1240] The user prepares CSV files of the initial data and processed data, and uploads them to the server from their terminal. For example, the following format of data is assumed:

[1241] Initial data (before data)

[1242] csv

[1243] Name, age, address

[1244] Taro Tanaka, 30, Tokyo

[1245] Hanako Yamada, 25, Osaka Prefecture

[1246] Post-processing data (after data)

[1247] csv

[1248] Name, Age, Address, Age Category

[1249] Taro Tanaka, 30, Tokyo, 30s

[1250] Hanako Yamada, 25, Osaka Prefecture, 20s

[1251] Receiving data

[1252] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage, preparing them for subsequent data processing.

[1253] Loading data

[1254] The server reads the initial data and processed data from the internal storage and converts them into an internal data frame format.

[1255] Data comparison and analysis

[1256] The server compares the fields (columns) of the initial data and the processed data to identify new columns or changes. For example, in this example, it identifies that a new column called "Age Category" has been added. Since the values ​​of this field are generated based on "Age," the server analyzes this and infers the distribution rules for the age category.

[1257] Generate data manipulation code

[1258] The server automatically generates a data processing code based on the specified data processing content. In this example, a code for generating the specified age category is automatically generated.

[1259] Emotion engine processing

[1260] The emotion engine recognizes the user's emotional state and reflects it in the data processing work. For example, if the user is feeling stressed, the emotion engine will reduce the complexity of the generated data processing code or provide more detailed explanations. It will also change the way the code is presented (e.g., step-by-step guides) depending on the user's emotional state.

[1261] Code Contribution

[1262] The generated data processing code is sent from the server to the user's terminal. The user executes this code in their own development environment to convert the initial data into the same format as the processed data.

[1263] In this way, this system automatically generates data processing code based on user input, and furthermore, by recognizing the user's emotional state and adjusting the processing content, it significantly reduces the amount of manual coding work and allows users to perform data processing more comfortably. As a result, data scientists can conduct data analysis more efficiently and accurately.

[1264] The processing flow will be explained below.

[1265] Step 1: Enter your data

[1266] The user prepares the initial data (before_data.csv) and the processed data (after_data.csv) and uploads them to the system from the terminal.

[1267] csv

[1268] Initial Data

[1269] Name, age, address

[1270] Taro Tanaka, 30, Tokyo

[1271] Hanako Yamada, 25, Osaka Prefecture

[1272] csv

[1273] Processed data

[1274] Name, Age, Address, Age Category

[1275] Taro Tanaka, 30, Tokyo, 30s

[1276] Hanako Yamada, 25, Osaka Prefecture, 20s

[1277] Step 2: Receiving the data

[1278] The server receives the initial data and processed data uploaded by the user.

[1279] The server stores the received data in its internal storage.

[1280] Step 3: Loading Data

[1281] The server reads the initial data and processed data from the internal storage and converts them into a data frame format.

[1282] Step 4: Compare and analyze the data

[1283] The server compares the fields (columns) of the initial data and the processed data, and identifies any added, deleted, or changed fields.

[1284] In this example, we identify that a new column called "Age Category" has been added.

[1285] Step 5: Data content analysis

[1286] The server analyzes the values ​​of the newly identified column "age category" and infers how they were generated.

[1287] Analyze that "age category" is classified as "20s" or "30s" based on "age."

[1288] Step 6: Estimating the processing logic

[1289] The server estimates a generation group for "age category" based on age.

[1290] For example, if the age is between 20 and 30, it will be "20s," and if the age is between 30 and 40, it will be "30s."

[1291] Step 7: Emotion Engine Emotion Recognition

[1292] The emotion engine analyzes data from the user's camera and microphone to recognize the user's emotional state (e.g., stressed, relaxed).

[1293] Step 8: Emotional Adjustment

[1294] The emotion engine adjusts the difficulty and level of detail of the generated data manipulation code based on the recognized emotional state of the user.

[1295] For example, if the user is feeling stressed, the emotion engine adjusts the code to reduce complexity and provide concise code.

[1296] Also, if the user is relaxed, provide a standard chord.

[1297] Step 9: Generate data manipulation code

[1298] The server automatically generates a data processing code based on the estimated processing logic.

[1299] Step 10: Submit your code

[1300] The server transmits the generated data processing code to the terminal.

[1301] The user executes the received code in their own development environment to convert the initial data into a format similar to the processed data.

[1302] This process eliminates the need for users to manually write complex data processing code, and the emotion engine takes the user's emotional state into consideration, allowing data processing work to be carried out efficiently while maintaining user comfort.

[1303] Example 2

[1304] 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."

[1305] Conventional data processing systems require users to manually create data processing codes, which is inefficient and prone to errors. Furthermore, no system takes into account the user's emotional state, which can increase the stress of the work. Therefore, there was a need for a system that automatically generates data processing codes based on the initial data and processed data provided by the user, and also adjusts the work according to the user's emotional state.

[1306] 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.

[1307] In this invention, the server includes means for receiving initial data and processed data uploaded by the user, means for comparing the initial data with the processed data to identify the data processing details, means for automatically generating a data processing code based on the identified processing details, means for recognizing the user's emotional state and adjusting the data processing details and the code provision method according to that state, and means for transmitting the generated processing code to the user. This frees the user from manual coding work, enables efficient and accurate data processing, and allows the user to work in an emotionally sensitive environment.

[1308] "Initial data" refers to the original data provided by the user before any data processing.

[1309] "Processed data" refers to data that has been processed into a format or content desired by the user.

[1310] "Data processing code" is a program code required to generate processed data from initial data.

[1311] "Emotional state" refers to the user's psychological and emotional state, including stress, frustration, relaxation, and the like.

[1312] "Data column structure" refers to the arrangement and relationships of each field or column of data.

[1313] "Changes in data values" refers to differences in the values ​​of data points or fields that occur between the initial data and the processed data.

[1314] "Data transformation" is the process of changing the format of data from one form to another.

[1315] "Filtering" is the process of extracting only data that meets specific conditions.

[1316] "Aggregation" is the process of calculating statistics, totals, averages, etc. from a collection of data.

[1317] A "join operation" is the process of combining multiple data sets into one.

[1318] A "server" refers to a central computer system for processing data, and has the role of receiving requests from users, performing the necessary processing, and returning the results.

[1319] The following is a detailed description of an embodiment of the present invention. This system automatically generates the necessary data processing code based primarily on the initial data and processed data uploaded by the user. It also has the ability to recognize the user's emotional state and adjust the data processing content and code delivery method accordingly.

[1320] System configuration

[1321] This system consists of a server, a terminal, a user, and an emotion engine. The user uses the terminal to upload the initial data and processed data, and the server receives and processes this data. The server uses the emotion engine to recognize the user's emotional state and adjust the data processing content.

[1322] Hardware and Software Used

[1323] This system uses the following hardware and software:

[1324] Hardware:

[1325] Server: A high-performance computer system.

[1326] Terminal: A personal computer or mobile terminal through which a user enters data.

[1327] software:

[1328] Pandas: A Python data processing library.

[1329] Emotion engine: Software for recognizing the user's emotional state.

[1330] Database Management System (DBMS): Software for storing and managing data.

[1331] Specific examples of processing

[1332] The user prepares the following initial data and processed data. An example of CSV format is shown below:

[1333] Initial data (before data):

[1334] csv

[1335] Name, age, address

[1336] Taro Tanaka, 30, Tokyo

[1337] Hanako Yamada, 25, Osaka Prefecture

[1338] After processing data:

[1339] csv

[1340] Name, Age, Address, Age Category

[1341] Taro Tanaka, 30, Tokyo, 30s

[1342] Hanako Yamada, 25, Osaka Prefecture, 20s

[1343] The server receives this data and converts it into a data frame using Pandas. It then compares the initial data with the processed data to identify new columns or changes. In this example, it identifies that a new column called "Age Category" has been added. Because this column is generated based on "Age," the server infers the distribution rule for the age category.

[1344] Prompt Sentence Examples

[1345] For example, when a user requests data processing, the prompt text is as follows:

[1346] Write code using Pandas to add a new column based on the following initial data. The goal is to add age categories based on the age column.

[1347] Initial data:

[1348] Name, age, address

[1349] Taro Tanaka, 30, Tokyo

[1350] Hanako Yamada, 25, Osaka Prefecture

[1351] Example of processed data:

[1352] Name, Age, Address, Age Category

[1353] Taro Tanaka, 30, Tokyo, 30s

[1354] Hanako Yamada, 25, Osaka Prefecture, 20s

[1355] "

[1356] The emotion engine responds by reducing the complexity of the generated data processing code or by providing more detailed explanations when the user is stressed, and also by changing the way the code is presented (e.g., step-by-step guides) depending on the user's emotional state.

[1357] In this way, our system automatically generates data processing code based on user input and further adjusts the processing content based on the user's emotional state, significantly reducing the amount of manual coding work required and allowing users to perform data processing more comfortably. As a result, data scientists and other users can conduct data analysis more efficiently and accurately.

[1358] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1359] Step 1:

[1360] The user prepares the initial data and processed data.

[1361] Users prepare the initial data and processed data in CSV format on their own devices. These data are used as the basis for data processing.

[1362] Input: Initial data, processed data (CSV file)

[1363] Output: Prepared data file

[1364] Specific behavior: A user creates and edits a CSV file using Excel or a text editor.

[1365] Step 2:

[1366] The user uploads the initial data and processed data to the server.

[1367] Users use a dedicated web interface on their terminal to upload the initial data and processed data to the server.

[1368] Input: Prepared initial data and processed data

[1369] Output: Data file uploaded to the server

[1370] Specific behavior: A user opens a web browser, selects a file on the upload screen, and clicks the "Send" button.

[1371] Step 3:

[1372] The server receives and stores the uploaded data.

[1373] The server receives the CSV file sent by the user via an HTTP request, checks the integrity of the data, and then saves it in its internal storage.

[1374] Input: Data upload request from user

[1375] Output: Initial data and processed data stored in the server storage

[1376] Specific operation: The server checks the format of the data and saves the file in the specified directory.

[1377] Step 4:

[1378] The server reads the stored data and converts it into a data frame format.

[1379] The server reads the data from its internal storage and converts it into a dataframe format using a data processing library such as Pandas.

[1380] Input: Saved initial data and processed data

[1381] Output: Data converted to a data frame format

[1382] Specific operation: The server uses Pandas' read_csv function to read the CSV file and convert it into a data frame.

[1383] Step 5:

[1384] The server compares the initial data with the processed data and identifies the data processing details.

[1385] The server compares the columns of the initial data and the processed data, identifies new columns and changes, and identifies the data processing details.

[1386] Input: Initial data and processed data in data frame format

[1387] Output: Identified data manipulations (new columns and changes)

[1388] Specific operation: The server uses Pandas' merge function or DataFrame's comparison function to extract column differences and detect the generation rules for new columns.

[1389] Step 6:

[1390] The server automatically generates a data processing code based on the specified data processing content.

[1391] The server generates data processing code in the form of a Python script based on the analyzed data processing content.

[1392] Input: Identified data manipulation details

[1393] Output: Automatically generated data processing code

[1394] Specific operation: The server generates Python code based on the specified rules and describes the logic for data processing.

[1395] Step 7:

[1396] The emotion engine recognizes the user's emotional state and reflects it in the data processing process.

[1397] The emotion engine analyzes the user's emotional state (e.g., stress) and adjusts the complexity of the generated data processing code or provides detailed explanations.

[1398] Input: Data about the user's emotional state

[1399] Output: Adjusted data processing code

[1400] How it works: The emotion engine analyzes voice analysis, keyboard typing speed, etc., and adds explanations and comments to the code as needed.

[1401] Step 8:

[1402] The server transmits the generated data processing code to the user's terminal.

[1403] The server transmits the generated data processing code to the user's terminal so that the user can download it.

[1404] Input: Generated data processing code

[1405] Output: Data processing code provided to the user's device

[1406] What happens: The server sends the code file via an HTTP response and provides a link for the user to download it.

[1407] Step 9:

[1408] The user receives the code and runs it.

[1409] The user executes the received code in their own development environment and converts the initial data into a format similar to the processed data.

[1410] Input: Data processing code received from the server

[1411] Output: New data files generated by the executed data manipulation code.

[1412] Specific operation: The user runs the code in a development environment such as Python, and checks and saves the converted data.

[1413] Through the above steps, the system efficiently and accurately processes data based on the data provided by the user, supporting the user's work.

[1414] (Application example 2)

[1415] 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."

[1416] In situations where large amounts of data must be handled efficiently, such as on a production line, data processing and conversion tasks not only require time and effort, but are prone to errors. Furthermore, the emotional state of workers can have a significant impact on productivity and accuracy. However, no existing systems have been able to automatically generate data processing code that takes the user's emotional state into account. This creates the problem of users finding it difficult to understand and execute the code when they are stressed.

[1417] 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.

[1418] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify the data processing content, means for automatically generating a data processing code based on the processing content, means for recognizing the user's emotional state using an emotion recognition engine, means for adjusting the generated data processing code based on the emotional state, and means for transmitting the generated processing code to the user. This makes it possible to provide an adaptive data processing code according to the user's emotional state, thereby reducing user stress and improving data processing efficiency.

[1419] "Initial data" refers to data before processing that is first input or uploaded by a user.

[1420] "Processed data" refers to data obtained by performing a specific processing operation on the initial data.

[1421] "Data processing content" refers to the method and content of data conversion or processing, which is identified by comparing the initial data with the processed data.

[1422] The "data processing code" is a program code for executing data processing that is automatically generated based on the specified data processing content.

[1423] An "emotion recognition engine" is a function or system for recognizing a user's emotional state in real time.

[1424] "Emotional state" refers to the internal state that the user is feeling, such as stressed, relaxed, confused, etc.

[1425] This invention is a system that realizes automation of data processing on a manufacturing line and generates data processing codes taking into account the emotional state of staff. The following hardware and software are used to implement this invention.

[1426] Hardware and Software

[1427] 1. Hardware:

[1428] Server: Receives, stores, processes and transmits data.

[1429] Terminal: A device (PC, tablet, etc.) that a user uses to upload data.

[1430] Emotion recognition camera: A camera for recognizing the user's emotional state in real time.

[1431] Sensor: A sensor device that collects data from the production line.

[1432] 2. Software:

[1433] OS and server software: The basic software required to operate a server.

[1434] Data processing libraries: For example, use the Python Pandas library to work with data.

[1435] Emotion Recognition Software: Analyze the user's emotional state using the EmotionRecognition module.

[1436] Generative AI model to use: An AI model that understands the specific data manipulation requirements and generates code.

[1437] System configuration and operation

[1438] 1. Upload your data

[1439] Users use their devices to upload the initial data and processed data to the server. The data is often provided in CSV file format.

[1440] 2. Receipt and storage of data

[1441] The server receives the data uploaded by the user and saves it in the internal storage, then reads the data into the internal data frame format.

[1442] 3. Data Analysis and Code Generation

[1443] The server compares the initial data with the processed data, identifies new columns and changes, and automatically generates data processing code based on this. The Pandas library is used to perform detailed analysis of the column structure of the data frame and changes in data values.

[1444] 4. Emotion recognition

[1445] The emotion recognition camera captures the user's emotional state in real time, and the emotion recognition software (EmotionRecognition module) analyzes it to determine whether the user is feeling stressed or relaxed.

[1446] 5. Adjusting the code

[1447] Based on the emotion recognition results, the server adjusts the generated data processing code. For example, if the user is stressed, the code is simplified and detailed comments are added. On the other hand, if the user is relaxed, efficient and concise code is generated.

[1448] 6. Send the code

[1449] The adjusted data processing code is sent to the user's terminal, and the user can use this code to perform data processing.

[1450] Specific examples

[1451] For example, suppose production line data is provided as follows:

[1452] Initial data (before data)

[1453] csv

[1454] Product ID, Quality

[1455] 1001, 85

[1456] 1002, 92

[1457] Post-processing data (after data)

[1458] csv

[1459] Product ID, Quality, Quality Category

[1460] 1001, 85, Medium

[1461] 1002, 92, High

[1462] Prompt Sentence Examples

[1463] "Tell me how you can process data from the production line in real time and adjust the production process according to the emotions of your staff."

[1464] In this way, it is possible to provide details for specifically implementing the invention and to demonstrate how the user can operate the system effectively.

[1465] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1466] Step 1:

[1467] The user uses the terminal to prepare CSV files of the initial data (before data) and the processed data (after data), and uploads them to the server. Specifically, the user selects the CSV file from the file selection screen on the terminal and clicks the upload button.

[1468] Input: Initial data CSV file, processed data CSV file

[1469] Output: Data is sent to the server

[1470] Step 2:

[1471] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage. The received data is kept as a temporary file and prepared for the next processing.

[1472] Input: Initial data and processed data sent by the user

[1473] Output: Initial data and processed data stored in the server's internal storage

[1474] Step 3:

[1475] The server loads the initial data and processed data from the internal storage and converts them into an internal data frame using the Pandas library, which makes subsequent processing easier.

[1476] Input: CSV file stored in the server's internal storage

[1477] Output: Initial data and processed data in data frame format

[1478] Step 4:

[1479] The server compares the column structure and data values ​​of the initial data with those of the processed data to identify the data processing details. This analysis detects new columns and value changes and estimates the type of processing that has occurred.

[1480] Input: Initial data and processed data in data frame format

[1481] Output: Identification of processing details (e.g., detection of a new column "Quality Category")

[1482] Step 5:

[1483] The server automatically generates data processing code based on the specified processing details. The generated code is Python code, and includes code for deriving the "quality category," for example.

[1484] Input: Processing details identification result

[1485] Output: Data processing code (Python script)

[1486] Step 6:

[1487] The emotion recognition camera captures the user's emotional state, which is then analyzed by the EmotionRecognition module, and the analysis results are sent to the server as data indicating whether the user is stressed or relaxed.

[1488] Input: Video data from emotion recognition camera

[1489] Output: User's emotional state data

[1490] Step 7:

[1491] The server adjusts the data processing code based on the emotion recognition results: if the user is stressed, it adds detailed comments to the code and simplifies the process; if the user is relaxed, it creates a more efficient code structure.

[1492] Input: User's emotional state data, initial data processing code

[1493] Output: Adjusted data processing code

[1494] Step 8:

[1495] The adjusted data processing code is sent from the server to the user's terminal, and the user executes this code in their own development environment to convert the initial data into a format similar to the processed data.

[1496] Input: Adjusted data processing code

[1497] Output: Data manipulation code sent to the user's terminal

[1498] In this way, the entire system processes in a single flow, automating data processing and realizing adaptive data processing that takes into account the user's emotional state.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] [Fourth embodiment]

[1503] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1504] 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.

[1505] 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).

[1506] 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.

[1507] 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.

[1508] 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).

[1509] 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.

[1510] 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.

[1511] 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.

[1512] 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.

[1513] 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.

[1514] 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.

[1515] 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."

[1516] The following describes an embodiment of the present invention. This system automatically generates the necessary data processing code based on the initial data (before data) and processed data (after data) provided by the user.

[1517] Overall system overview

[1518] This system is mainly composed of three entities: a server, a terminal, and a user. The user uploads the initial data and processed data from their own terminal, and the server receives and processes the data, finally generating a data processing code and providing it to the user.

[1519] Entering data

[1520] The user prepares CSV files of the initial data and the processed data, and uploads them to the server from their terminal. For example, the following format of data is assumed:

[1521] Initial data (before data)

[1522] csv

[1523] Name, age, address

[1524] Taro Tanaka, 30, Tokyo

[1525] Hanako Yamada, 25, Osaka Prefecture

[1526] Post-processing data (after data)

[1527] csv

[1528] Name, Age, Address, Age Category

[1529] Taro Tanaka, 30, Tokyo, 30s

[1530] Hanako Yamada, 25, Osaka Prefecture, 20s

[1531] Receiving data

[1532] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage, preparing them for subsequent data processing.

[1533] Data comparison and analysis

[1534] The server compares the saved initial data with the processed data. Specifically, it checks the differences in fields (columns) between the initial data and the processed data, and identifies newly added fields and changed content.

[1535] For example, in the above example, the server identifies that a new field called "age category" has been added. Since the value of this field is generated based on "age," the server analyzes it and infers the distribution rule of the age category.

[1536] Generate data manipulation code

[1537] The server automatically generates a data manipulation code based on the specified data manipulation content. In this example, a code for generating the specified age category is automatically generated. The generated code is designed to be easy for users to use.

[1538] Code Contribution

[1539] The generated data processing code is sent from the server to the user's device. The user can run this code in their own development environment to convert the initial data into a format similar to the processed data. For example, the following Python code is provided to the user:

[1540] example

[1541] python

[1542] import pandas as pd

[1543] import numpy as np

[1544] def add_age_category(df):

[1545] conditions = [

[1546] (df['age'] >= 20) & (df['age'] < 30),

[1547] (df['age'] >= 30) & (df['age'] < 40),

[1548] ]

[1549] choices = ['20s', '30s']

[1550] df['Age Category'] = np.select(conditions, choices, default='Other')

[1551] return df

[1552] Usage example

[1553] df_before = pd.read_csv('before_data.csv')

[1554] df_after = add_age_category(df_before)

[1555] df_after.to_csv('after_data.csv', index=False)

[1556] In this way, this system automatically generates data processing code according to the user's needs, significantly reducing the amount of manual coding required, and enabling data scientists to more efficiently conduct data analysis.

[1557] The processing flow will be explained below.

[1558] Step 1: Enter your data

[1559] The user prepares the initial data (before_data.csv) and the processed data (after_data.csv) and uploads them to the system from the terminal.

[1560] csv

[1561] Initial Data

[1562] Name, age, address

[1563] Taro Tanaka, 30, Tokyo

[1564] Hanako Yamada, 25, Osaka Prefecture

[1565] csv

[1566] Processed data

[1567] Name, Age, Address, Age Category

[1568] Taro Tanaka, 30, Tokyo, 30s

[1569] Hanako Yamada, 25, Osaka Prefecture, 20s

[1570] Step 2: Receiving the data

[1571] The server receives the initial data and processed data uploaded by the user.

[1572] The server stores the received data in its internal storage and prepares it for processing.

[1573] Step 3: Loading Data

[1574] The server reads the initial data and processed data from the internal storage and converts them into an internal data frame format.

[1575] Step 4: Compare the data

[1576] The server compares the fields (columns) of the initial data and the processed data to identify new columns and changes.

[1577] In this example, we identify that a new column called "Age Category" has been added.

[1578] Step 5: Data content analysis

[1579] The server analyzes the content of the identified new column "age category."

[1580] Specifically, we analyze whether people are classified as "in their 20s" or "in their 30s" based on their age.

[1581] Step 6: Estimating the processing logic

[1582] The server estimates the logic for generating an "age category" based on age.

[1583] For example, the rule is estimated such that if the age is between 20 and 30, the person is in their 20s, and if the age is between 30 and 40, the person is in their 30s.

[1584] Step 7: Auto-generate code

[1585] The server automatically generates a data processing code based on the estimated processing logic.

[1586] The specific Python code is as follows:

[1587] python

[1588] import pandas as pd

[1589] import numpy as np

[1590] def add_age_category(df):

[1591] conditions = [

[1592] (df['age'] >= 20) & (df['age'] < 30),

[1593] (df['age'] >= 30) & (df['age'] < 40),

[1594] ]

[1595] choices = ['20s', '30s']

[1596] df['Age Category'] = np.select(conditions, choices, default='Other')

[1597] return df

[1598] Step 8: Submit your code

[1599] The server transmits the generated data processing code to the terminal.

[1600] The user executes the received code in their own development environment and converts the initial data into processed data.

[1601] This series of processes allows users to quickly convert data into a new format without having to manually write complex data processing code.

[1602] Example 1

[1603] 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."

[1604] Conventional data processing methods require manual coding, which is complicated for users without experience or skills. Furthermore, it requires a lot of time and effort, making it difficult to process data quickly and accurately. Therefore, there is a need for a system that can automatically generate data processing code based on the initial data and processed data provided by the user, and provide this code to significantly improve the efficiency of coding work.

[1605] 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.

[1606] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify field differences and data conversion rules, means for automatically generating a data conversion code based on the identified data conversion rules, and means for transmitting the generated data conversion code to the user, thereby significantly reducing the user's manual coding work and enabling quick and accurate data processing.

[1607] "User" refers to an individual or organization that uses the system to upload data and receive a processing code.

[1608] "Initial data" refers to data before processing that a user uploads to the system.

[1609] "Processed data" is data that a user uploads to the system after processing, and indicates how the initial data should be changed.

[1610] "Means for receiving" refers to the function by which the server receives the initial data and processed data uploaded by the user and stores them in its internal storage.

[1611] "Means for comparing and identifying field differences and data conversion rules" refers to the function by which the server compares the fields (columns) of the initial data and the processed data, and analyzes newly added fields and changed content.

[1612] "Data conversion code" is program code that is automatically generated based on the specified data conversion rules.

[1613] "Means for automatic generation" refers to the function of the server to programmatically generate data processing code based on data conversion rules.

[1614] "Means for transmitting" refers to the function of transmitting the generated data processing code from the server to the user's terminal.

[1615] This invention is a data processing system that automatically generates necessary data processing code based on the initial data and processed data provided by the user. This system is mainly composed of three entities: a server, a terminal, and a user.

[1616] The server is the central hardware that performs the main calculations and data analysis processes. The server receives and stores the initial data and processed data uploaded by users, analyzes the data, and generates data processing code.

[1617] The user is responsible for preparing the initial data and processed data and uploading them to the server. Specifically, the user uses their own device to send a CSV file to the server.

[1618] The terminal is a computer or mobile device that a user uses to upload data to the server. The terminal provides an interface for data upload and receives the generated data processing code from the server.

[1619] Entering and Receiving Data

[1620] The user creates the initial data and processed data as CSV files through the terminal. For example, the initial data is in the following format:

[1621] Initial data (before data)

[1622] csv

[1623] Name, age, address

[1624] Taro Tanaka, 30, Tokyo

[1625] Hanako Yamada, 25, Osaka Prefecture

[1626] The processed data has the following format:

[1627] Post-processing data (after data)

[1628] csv

[1629] Name, Age, Address, Age Category

[1630] Taro Tanaka, 30, Tokyo, 30s

[1631] Hanako Yamada, 25, Osaka Prefecture, 20s

[1632] The user uploads this data from the terminal to the server.

[1633] Receiving and storing data

[1634] The server receives the uploaded CSV file and saves it in its internal storage. The saved file is used for data analysis later.

[1635] Data comparison and analysis

[1636] The server compares the initial data with the processed data and identifies newly added fields and changes. Specifically, for example, it detects that the processed data contains a new field called "age category." The server analyzes that the value of this field is generated based on "age" and infers the rule.

[1637] Generate data manipulation code

[1638] The server automatically generates data processing code, such as Python code, based on the specified data conversion rules. This generated code is provided to users in a format that is easy to understand and use.

[1639] Code Contribution

[1640] The generated data processing code is sent from the server to the user's device, and the user can use this code to convert the initial data into the same format as the processed data.

[1641] Examples and prompts

[1642] As a concrete example, the following prompt sentence is input to the generative AI model:

[1643] Generate data processing code based on the initial data and processed data provided by the user. For example, the initial data and processed data are as follows:

[1644] Initial data:

[1645] Name, age, address

[1646] Taro Tanaka, 30, Tokyo

[1647] Hanako Yamada, 25, Osaka Prefecture

[1648] Processed data:

[1649] Name, Age, Address, Age Category

[1650] Taro Tanaka, 30, Tokyo, 30s

[1651] Hanako Yamada, 25, Osaka Prefecture, 20s

[1652] Based on this data, generate Python code to add age categories.

[1653] Using this prompt, the server can generate the appropriate data manipulation code.

[1654] As described above, the present invention automatically generates data processing code according to the user's needs, significantly reducing the amount of manual coding required, and as a result, data scientists can more efficiently conduct data analysis.

[1655] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1656] Step 1:

[1657] The user prepares the initial data and processed data in CSV file format. The user uploads these files to the server via their terminal. Specifically, the user accesses the system interface using the terminal's browser, opens the file selection dialog, selects the CSV file, and starts uploading to the server. The input is the CSV files of the initial data and processed data, and the output is sending the file to the server.

[1658] Step 2:

[1659] The server receives the CSV file uploaded by the user. The received file is saved in the server's internal storage. This action saves the CSV file in the specified directory (e.g., / data / uploads / ). The input is the CSV file uploaded in step 1, and the output is the file saved in the internal storage.

[1660] Step 3:

[1661] The server loads the saved initial data and processed data, compares them, and analyzes changes in the data. Specifically, the server uses the Pandas library to load the CSV file in DataFrame format and compares the columns of the initial data and processed data. For example, it identifies that a new column, "Age Category," has been added to the processed data. This analysis extracts the differences in the fields between the initial data and processed data. The input is the CSV file saved in Step 2, and the output is the identified data transformation rules.

[1662] Step 4:

[1663] The server automatically generates data processing code based on the specified data conversion rules. Specifically, the server inputs the following prompt sentence into the generating AI model:

[1664] Generate data processing code based on the initial data and processed data provided by the user. For example, the initial data and processed data are as follows:

[1665] Initial data:

[1666] Name, age, address

[1667] Taro Tanaka, 30, Tokyo

[1668] Hanako Yamada, 25, Osaka Prefecture

[1669] Processed data:

[1670] Name, Age, Address, Age Category

[1671] Taro Tanaka, 30, Tokyo, 30s

[1672] Hanako Yamada, 25, Osaka Prefecture, 20s

[1673] Based on this data, generate Python code to add age categories.

[1674] Based on the prompt, the AI ​​model generates data processing code. The input is the specified data transformation rule and the prompt, and the output is the generated data processing code.

[1675] Step 5:

[1676] The server sends the generated data processing code to the user's device. Specifically, the server saves the generated code in file format and provides the file to the user as a download link or sends it directly by email. The input is the generated data processing code, and the output is a code file provided in a form accessible to the user.

[1677] Step 6:

[1678] The user downloads the data processing code provided by the server and runs it in their own development environment. Specifically, the user runs the downloaded code and converts the initial data into a format similar to the processed data. The input is the data processing code sent from the server and a CSV file of the initial data, and the output is the processed data file (CSV format).

[1679] This process allows users to process data without much effort by using automatically generated code.

[1680] (Application example 1)

[1681] 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."

[1682] Conventional data processing systems require users to manually write complex code, which requires a huge amount of time and effort. Furthermore, high levels of automation are required in fields such as logistics centers, where real-time data analysis and immediate decision-making are required. However, much of the data requires processing, such as categorization based on specific attribute values, but there is a lack of automated methods for efficiently performing this process.

[1683] 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.

[1684] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify the processing details of the data, means for automatically generating a data processing code based on the processing details, means for transmitting the generated processing code to the user, means for categorizing the initial data and the processed data based on the original data, and means for adding a new field based on the information obtained by the categorization. This makes it possible to automatically generate the data processing code required by the user and efficiently categorize the data based on specific attribute values.

[1685] "Initial data" refers to data uploaded by a user before processing.

[1686] "Processed data" is data that indicates the state of the initial data after it has been processed.

[1687] "Data processing content" refers to the changes and operations that occur between the initial data and the processed data.

[1688] "Data processing code" is program code for performing data conversion, filtering, aggregation, and joining operations.

[1689] "Categorization" refers to the operation of grouping data based on specific attribute values ​​(e.g., age or delivery time).

[1690] A "field" is a column of data elements used in databases, spreadsheets, etc.

[1691] An embodiment of the present invention will be described below. This system uses smartphones in a logistics center to automate real-time data analysis and processing.

[1692] System Overview

[1693] This system automatically generates a data processing code based on the initial data and processed data uploaded by the user and provides it to the user. It mainly consists of a server, a terminal (smartphone), and the user.

[1694] Hardware and Software Use

[1695] The server is a computer with high-performance data processing capabilities that receives and stores data uploaded by users. The terminals are smartphones used by logistics center staff, which input initial data and processed data and check and use received data. The software uses a Python runtime environment (e.g., Pyodide), Pandas, and Numpy libraries.

[1696] Generate data manipulation code

[1697] The server first receives the initial data and processed data uploaded by the user and saves them in its internal storage. The server then compares the initial data with the processed data to identify the data processing details. In particular, by analyzing newly added fields and changed content, the server categorizes the data based on attribute values. For example, it categorizes delivery efficiency based on delivery time (fast, medium, slow).

[1698] Examples of data processing

[1699] Specifically, the initial data for delivery information includes a "delivery ID" and "delivery time," and the processed data includes a "delivery efficiency category." Based on this analysis, data processing code is generated to add a new field (delivery efficiency category) according to a specific attribute value (delivery time). This code is provided to the user and can be executed on their smartphone.

[1700] Prompt Sentence Examples

[1701] Users can input the following prompt sentence into the generative AI model to generate data processing code.

[1702] Initial data (shipping information)

[1703] Delivery ID, Delivery time (hours)

[1704] 12345, 1.5

[1705] 67890, 3.0

[1706] 54321, 6.5

[1707] Processed data (delivery efficiency category)

[1708] Delivery ID, Delivery time (hours), Delivery efficiency category

[1709] 12345, 1.5, high speed

[1710] 67890, 3.0, medium speed

[1711] 54321, 6.5, slow

[1712] Use this data to generate a Python script that categorizes the data based on delivery time.

[1713] In this way, the system automates data analysis and processing in logistics centers, significantly reducing the workload of staff, and enables instant categorization based on specific data attributes, enabling faster decision-making.

[1714] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1715] Step 1:

[1716] The user prepares the initial data and processed data and uploads them to the server in CSV file format using a smartphone (terminal). The input includes the initial data (e.g., delivery ID and delivery time) and processed data (e.g., delivery ID, delivery time, delivery efficiency category). The output is that the server receives and stores this data.

[1717] Step 2:

[1718] The server compares the uploaded initial data with the processed data. At this stage, it analyzes the structure of the data columns (fields) and changes in data values. Specifically, it identifies new fields (e.g., "Delivery Efficiency Category") and analyzes the rules by which the values ​​of those fields are generated. The input is the initial data and the processed data, and the output is the identified processing details.

[1719] Step 3:

[1720] The server automatically generates data processing code based on the specified processing details. This code is used to convert, filter, aggregate, and combine data. Specifically, it describes a process to add delivery efficiency categories such as "fast," "medium," and "slow" based on delivery time. The input is the processing details specified in the previous step, and the output is the generated data processing code.

[1721] Step 4:

[1722] The generated data processing code is sent from the server to the user's smartphone. By executing this code on the smartphone, the user can convert the initial data into a format similar to the processed data. The input is the generated data processing code, and the output is data processing code that can be executed on the smartphone.

[1723] Step 5:

[1724] The user executes the generated data processing code on their smartphone. This converts the initial data into a format similar to the processed data and adds a new field (delivery efficiency category). The input is the initial data and the data processing code, and the output is the processed data.

[1725] Step 6:

[1726] The generated processed data is saved again as a CSV file, which users can download and use. This enables data analysis and rapid decision-making at the logistics center. The input is the processed data, and the output is a downloadable CSV file.

[1727] 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.

[1728] The following describes an embodiment of the present invention. This system not only automatically generates the necessary data processing code based on the initial data (before data) and processed data (after data) provided by the user, but also has the ability to recognize the user's emotions and adjust the data processing accordingly.

[1729] Overall system overview

[1730] This system is mainly composed of a server, a terminal, a user, and an emotion engine. Users upload initial data and processed data from their own terminals, and the server receives and processes this data. Finally, it generates a data processing code and provides it to the user. During this process, the emotion engine recognizes the user's emotional state and adjusts the data processing content and code delivery method as necessary.

[1731] Entering data

[1732] The user prepares CSV files of the initial data and processed data, and uploads them to the server from their terminal. For example, the following format of data is assumed:

[1733] Initial data (before data)

[1734] csv

[1735] Name, age, address

[1736] Taro Tanaka, 30, Tokyo

[1737] Hanako Yamada, 25, Osaka Prefecture

[1738] Post-processing data (after data)

[1739] csv

[1740] Name, Age, Address, Age Category

[1741] Taro Tanaka, 30, Tokyo, 30s

[1742] Hanako Yamada, 25, Osaka Prefecture, 20s

[1743] Receiving data

[1744] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage, preparing them for subsequent data processing.

[1745] Loading data

[1746] The server reads the initial data and processed data from the internal storage and converts them into an internal data frame format.

[1747] Data comparison and analysis

[1748] The server compares the fields (columns) of the initial data and the processed data to identify new columns or changes. For example, in this example, it identifies that a new column called "Age Category" has been added. Since the values ​​of this field are generated based on "Age," the server analyzes this and infers the distribution rules for the age category.

[1749] Generate data manipulation code

[1750] The server automatically generates a data processing code based on the specified data processing content. In this example, a code for generating the specified age category is automatically generated.

[1751] Emotion engine processing

[1752] The emotion engine recognizes the user's emotional state and reflects it in the data processing work. For example, if the user is feeling stressed, the emotion engine will reduce the complexity of the generated data processing code or provide more detailed explanations. It will also change the way the code is presented (e.g., step-by-step guides) depending on the user's emotional state.

[1753] Code Contribution

[1754] The generated data processing code is sent from the server to the user's terminal. The user executes this code in their own development environment to convert the initial data into the same format as the processed data.

[1755] In this way, this system automatically generates data processing code based on user input, and furthermore, by recognizing the user's emotional state and adjusting the processing content, it significantly reduces the amount of manual coding work and allows users to perform data processing more comfortably. As a result, data scientists can conduct data analysis more efficiently and accurately.

[1756] The processing flow will be explained below.

[1757] Step 1: Enter your data

[1758] The user prepares the initial data (before_data.csv) and the processed data (after_data.csv) and uploads them to the system from the terminal.

[1759] csv

[1760] Initial Data

[1761] Name, age, address

[1762] Taro Tanaka, 30, Tokyo

[1763] Hanako Yamada, 25, Osaka Prefecture

[1764] csv

[1765] Processed data

[1766] Name, Age, Address, Age Category

[1767] Taro Tanaka, 30, Tokyo, 30s

[1768] Hanako Yamada, 25, Osaka Prefecture, 20s

[1769] Step 2: Receiving the data

[1770] The server receives the initial data and processed data uploaded by the user.

[1771] The server stores the received data in its internal storage.

[1772] Step 3: Loading Data

[1773] The server reads the initial data and processed data from the internal storage and converts them into a data frame format.

[1774] Step 4: Compare and analyze the data

[1775] The server compares the fields (columns) of the initial data and the processed data, and identifies any added, deleted, or changed fields.

[1776] In this example, we identify that a new column called "Age Category" has been added.

[1777] Step 5: Data content analysis

[1778] The server analyzes the values ​​of the newly identified column "age category" and infers how they were generated.

[1779] Analyze that "age category" is classified as "20s" or "30s" based on "age."

[1780] Step 6: Estimating the processing logic

[1781] The server estimates a generation group for "age category" based on age.

[1782] For example, if the age is between 20 and 30, it will be "20s," and if the age is between 30 and 40, it will be "30s."

[1783] Step 7: Emotion Engine Emotion Recognition

[1784] The emotion engine analyzes data from the user's camera and microphone to recognize the user's emotional state (e.g., stressed, relaxed).

[1785] Step 8: Emotional Adjustment

[1786] The emotion engine adjusts the difficulty and level of detail of the generated data manipulation code based on the recognized emotional state of the user.

[1787] For example, if the user is feeling stressed, the emotion engine adjusts the code to reduce complexity and provide concise code.

[1788] Also, if the user is relaxed, provide a standard chord.

[1789] Step 9: Generate data manipulation code

[1790] The server automatically generates a data processing code based on the estimated processing logic.

[1791] Step 10: Submit your code

[1792] The server transmits the generated data processing code to the terminal.

[1793] The user executes the received code in their own development environment to convert the initial data into a format similar to the processed data.

[1794] This process eliminates the need for users to manually write complex data processing code, and the emotion engine takes the user's emotional state into consideration, allowing data processing work to be carried out efficiently while maintaining user comfort.

[1795] Example 2

[1796] 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."

[1797] Conventional data processing systems require users to manually create data processing codes, which is inefficient and prone to errors. Furthermore, no system takes into account the user's emotional state, which can increase the stress of the work. Therefore, there was a need for a system that automatically generates data processing codes based on the initial data and processed data provided by the user, and also adjusts the work according to the user's emotional state.

[1798] 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.

[1799] In this invention, the server includes means for receiving initial data and processed data uploaded by the user, means for comparing the initial data with the processed data to identify the data processing details, means for automatically generating a data processing code based on the identified processing details, means for recognizing the user's emotional state and adjusting the data processing details and the code provision method according to that state, and means for transmitting the generated processing code to the user. This frees the user from manual coding work, enables efficient and accurate data processing, and allows the user to work in an emotionally sensitive environment.

[1800] "Initial data" refers to the original data provided by the user before any data processing.

[1801] "Processed data" refers to data that has been processed into a format or content desired by the user.

[1802] "Data processing code" is a program code required to generate processed data from initial data.

[1803] "Emotional state" refers to the user's psychological and emotional state, including stress, frustration, relaxation, and the like.

[1804] "Data column structure" refers to the arrangement and relationships of each field or column of data.

[1805] "Changes in data values" refers to differences in the values ​​of data points or fields that occur between the initial data and the processed data.

[1806] "Data transformation" is the process of changing the format of data from one form to another.

[1807] "Filtering" is the process of extracting only data that meets specific conditions.

[1808] "Aggregation" is the process of calculating statistics, totals, averages, etc. from a collection of data.

[1809] A "join operation" is the process of combining multiple data sets into one.

[1810] A "server" refers to a central computer system for processing data, and has the role of receiving requests from users, performing the necessary processing, and returning the results.

[1811] The following is a detailed description of an embodiment of the present invention. This system automatically generates the necessary data processing code based primarily on the initial data and processed data uploaded by the user. It also has the ability to recognize the user's emotional state and adjust the data processing content and code delivery method accordingly.

[1812] System configuration

[1813] This system consists of a server, a terminal, a user, and an emotion engine. The user uses the terminal to upload the initial data and processed data, and the server receives and processes this data. The server uses the emotion engine to recognize the user's emotional state and adjust the data processing content.

[1814] Hardware and Software Used

[1815] This system uses the following hardware and software:

[1816] Hardware:

[1817] Server: A high-performance computer system.

[1818] Terminal: A personal computer or mobile terminal through which a user enters data.

[1819] software:

[1820] Pandas: A Python data processing library.

[1821] Emotion engine: Software for recognizing the user's emotional state.

[1822] Database Management System (DBMS): Software for storing and managing data.

[1823] Specific examples of processing

[1824] The user prepares the following initial data and processed data. An example of CSV format is shown below:

[1825] Initial data (before data):

[1826] csv

[1827] Name, age, address

[1828] Taro Tanaka, 30, Tokyo

[1829] Hanako Yamada, 25, Osaka Prefecture

[1830] After processing data:

[1831] csv

[1832] Name, Age, Address, Age Category

[1833] Taro Tanaka, 30, Tokyo, 30s

[1834] Hanako Yamada, 25, Osaka Prefecture, 20s

[1835] The server receives this data and converts it into a data frame using Pandas. It then compares the initial data with the processed data to identify new columns or changes. In this example, it identifies that a new column called "Age Category" has been added. Because this column is generated based on "Age," the server infers the distribution rule for the age category.

[1836] Prompt Sentence Examples

[1837] For example, when a user requests data processing, the prompt text is as follows:

[1838] Write code using Pandas to add a new column based on the following initial data. The goal is to add age categories based on the age column.

[1839] Initial data:

[1840] Name, age, address

[1841] Taro Tanaka, 30, Tokyo

[1842] Hanako Yamada, 25, Osaka Prefecture

[1843] Example of processed data:

[1844] Name, Age, Address, Age Category

[1845] Taro Tanaka, 30, Tokyo, 30s

[1846] Hanako Yamada, 25, Osaka Prefecture, 20s

[1847] "

[1848] The emotion engine responds by reducing the complexity of the generated data processing code or by providing more detailed explanations when the user is stressed, and also by changing the way the code is presented (e.g., step-by-step guides) depending on the user's emotional state.

[1849] In this way, our system automatically generates data processing code based on user input and further adjusts the processing content based on the user's emotional state, significantly reducing the amount of manual coding work required and allowing users to perform data processing more comfortably. As a result, data scientists and other users can conduct data analysis more efficiently and accurately.

[1850] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1851] Step 1:

[1852] The user prepares the initial data and processed data.

[1853] Users prepare the initial data and processed data in CSV format on their own devices. These data are used as the basis for data processing.

[1854] Input: Initial data, processed data (CSV file)

[1855] Output: Prepared data file

[1856] Specific behavior: A user creates and edits a CSV file using Excel or a text editor.

[1857] Step 2:

[1858] The user uploads the initial data and processed data to the server.

[1859] Users use a dedicated web interface on their terminal to upload the initial data and processed data to the server.

[1860] Input: Prepared initial data and processed data

[1861] Output: Data file uploaded to the server

[1862] Specific behavior: A user opens a web browser, selects a file on the upload screen, and clicks the "Send" button.

[1863] Step 3:

[1864] The server receives and stores the uploaded data.

[1865] The server receives the CSV file sent by the user via an HTTP request, checks the integrity of the data, and then saves it in its internal storage.

[1866] Input: Data upload request from user

[1867] Output: Initial data and processed data stored in the server storage

[1868] Specific operation: The server checks the format of the data and saves the file in the specified directory.

[1869] Step 4:

[1870] The server reads the stored data and converts it into a data frame format.

[1871] The server reads the data from its internal storage and converts it into a dataframe format using a data processing library such as Pandas.

[1872] Input: Saved initial data and processed data

[1873] Output: Data converted to a data frame format

[1874] Specific operation: The server uses Pandas' read_csv function to read the CSV file and convert it into a data frame.

[1875] Step 5:

[1876] The server compares the initial data with the processed data and identifies the data processing details.

[1877] The server compares the columns of the initial data and the processed data, identifies new columns and changes, and identifies the data processing details.

[1878] Input: Initial data and processed data in data frame format

[1879] Output: Identified data manipulations (new columns and changes)

[1880] Specific operation: The server uses Pandas' merge function or DataFrame's comparison function to extract column differences and detect the generation rules for new columns.

[1881] Step 6:

[1882] The server automatically generates a data processing code based on the specified data processing content.

[1883] The server generates data processing code in the form of a Python script based on the analyzed data processing content.

[1884] Input: Identified data manipulation details

[1885] Output: Automatically generated data processing code

[1886] Specific operation: The server generates Python code based on the specified rules and describes the logic for data processing.

[1887] Step 7:

[1888] The emotion engine recognizes the user's emotional state and reflects it in the data processing process.

[1889] The emotion engine analyzes the user's emotional state (e.g., stress) and adjusts the complexity of the generated data processing code or provides detailed explanations.

[1890] Input: Data about the user's emotional state

[1891] Output: Adjusted data processing code

[1892] How it works: The emotion engine analyzes voice analysis, keyboard typing speed, etc., and adds explanations and comments to the code as needed.

[1893] Step 8:

[1894] The server transmits the generated data processing code to the user's terminal.

[1895] The server transmits the generated data processing code to the user's terminal so that the user can download it.

[1896] Input: Generated data processing code

[1897] Output: Data processing code provided to the user's device

[1898] What happens: The server sends the code file via an HTTP response and provides a link for the user to download it.

[1899] Step 9:

[1900] The user receives the code and runs it.

[1901] The user executes the received code in their own development environment and converts the initial data into a format similar to the processed data.

[1902] Input: Data processing code received from the server

[1903] Output: New data files generated by the executed data manipulation code.

[1904] Specific operation: The user runs the code in a development environment such as Python, and checks and saves the converted data.

[1905] Through the above steps, the system efficiently and accurately processes data based on the data provided by the user, supporting the user's work.

[1906] (Application example 2)

[1907] 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."

[1908] In situations where large amounts of data must be handled efficiently, such as on a production line, data processing and conversion tasks not only require time and effort, but are prone to errors. Furthermore, the emotional state of workers can have a significant impact on productivity and accuracy. However, no existing systems have been able to automatically generate data processing code that takes the user's emotional state into account. This creates the problem of users finding it difficult to understand and execute the code when they are stressed.

[1909] 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.

[1910] In this invention, the server includes means for receiving initial data and processed data uploaded by a user, means for comparing the initial data with the processed data to identify the data processing content, means for automatically generating a data processing code based on the processing content, means for recognizing the user's emotional state using an emotion recognition engine, means for adjusting the generated data processing code based on the emotional state, and means for transmitting the generated processing code to the user. This makes it possible to provide an adaptive data processing code according to the user's emotional state, thereby reducing user stress and improving data processing efficiency.

[1911] "Initial data" refers to data before processing that is first input or uploaded by a user.

[1912] "Processed data" refers to data obtained by performing a specific processing operation on the initial data.

[1913] "Data processing content" refers to the method and content of data conversion or processing, which is identified by comparing the initial data with the processed data.

[1914] The "data processing code" is a program code for executing data processing that is automatically generated based on the specified data processing content.

[1915] An "emotion recognition engine" is a function or system for recognizing a user's emotional state in real time.

[1916] "Emotional state" refers to the internal state that the user is feeling, such as stressed, relaxed, confused, etc.

[1917] This invention is a system that realizes automation of data processing on a manufacturing line and generates data processing codes taking into account the emotional state of staff. The following hardware and software are used to implement this invention.

[1918] Hardware and Software

[1919] 1. Hardware:

[1920] Server: Receives, stores, processes and transmits data.

[1921] Terminal: A device (PC, tablet, etc.) that a user uses to upload data.

[1922] Emotion recognition camera: A camera for recognizing the user's emotional state in real time.

[1923] Sensor: A sensor device that collects data from the production line.

[1924] 2. Software:

[1925] OS and server software: The basic software required to operate a server.

[1926] Data processing libraries: For example, use the Python Pandas library to work with data.

[1927] Emotion Recognition Software: Analyze the user's emotional state using the EmotionRecognition module.

[1928] Generative AI model to use: An AI model that understands the specific data manipulation requirements and generates code.

[1929] System configuration and operation

[1930] 1. Upload your data

[1931] Users use their devices to upload the initial data and processed data to the server. The data is often provided in CSV file format.

[1932] 2. Receipt and storage of data

[1933] The server receives the data uploaded by the user and saves it in the internal storage, then reads the data into the internal data frame format.

[1934] 3. Data Analysis and Code Generation

[1935] The server compares the initial data with the processed data, identifies new columns and changes, and automatically generates data processing code based on this. The Pandas library is used to perform detailed analysis of the column structure of the data frame and changes in data values.

[1936] 4. Emotion recognition

[1937] The emotion recognition camera captures the user's emotional state in real time, and the emotion recognition software (EmotionRecognition module) analyzes it to determine whether the user is feeling stressed or relaxed.

[1938] 5. Adjusting the code

[1939] Based on the emotion recognition results, the server adjusts the generated data processing code. For example, if the user is stressed, the code is simplified and detailed comments are added. On the other hand, if the user is relaxed, efficient and concise code is generated.

[1940] 6. Send the code

[1941] The adjusted data processing code is sent to the user's terminal, and the user can use this code to perform data processing.

[1942] Specific examples

[1943] For example, suppose production line data is provided as follows:

[1944] Initial data (before data)

[1945] csv

[1946] Product ID, Quality

[1947] 1001, 85

[1948] 1002, 92

[1949] Post-processing data (after data)

[1950] csv

[1951] Product ID, Quality, Quality Category

[1952] 1001, 85, Medium

[1953] 1002, 92, High

[1954] Prompt Sentence Examples

[1955] "Tell me how you can process data from the production line in real time and adjust the production process according to the emotions of your staff."

[1956] In this way, it is possible to provide details for specifically implementing the invention and to demonstrate how the user can operate the system effectively.

[1957] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1958] Step 1:

[1959] The user uses the terminal to prepare CSV files of the initial data (before data) and the processed data (after data), and uploads them to the server. Specifically, the user selects the CSV file from the file selection screen on the terminal and clicks the upload button.

[1960] Input: Initial data CSV file, processed data CSV file

[1961] Output: Data is sent to the server

[1962] Step 2:

[1963] The server receives the initial data and processed data uploaded by the user and stores them in its internal storage. The received data is kept as a temporary file and prepared for the next processing.

[1964] Input: Initial data and processed data sent by the user

[1965] Output: Initial data and processed data stored in the server's internal storage

[1966] Step 3:

[1967] The server loads the initial data and processed data from the internal storage and converts them into an internal data frame using the Pandas library, which makes subsequent processing easier.

[1968] Input: CSV file stored in the server's internal storage

[1969] Output: Initial data and processed data in data frame format

[1970] Step 4:

[1971] The server compares the column structure and data values ​​of the initial data with those of the processed data to identify the data processing details. This analysis detects new columns and value changes and estimates the type of processing that has occurred.

[1972] Input: Initial data and processed data in data frame format

[1973] Output: Identification of processing details (e.g., detection of a new column "Quality Category")

[1974] Step 5:

[1975] The server automatically generates data processing code based on the specified processing details. The generated code is Python code, and includes code for deriving the "quality category," for example.

[1976] Input: Processing details identification result

[1977] Output: Data processing code (Python script)

[1978] Step 6:

[1979] The emotion recognition camera captures the user's emotional state, which is then analyzed by the EmotionRecognition module, and the analysis results are sent to the server as data indicating whether the user is stressed or relaxed.

[1980] Input: Video data from emotion recognition camera

[1981] Output: User's emotional state data

[1982] Step 7:

[1983] The server adjusts the data processing code based on the emotion recognition results: if the user is stressed, it adds detailed comments to the code and simplifies the process; if the user is relaxed, it creates a more efficient code structure.

[1984] Input: User's emotional state data, initial data processing code

[1985] Output: Adjusted data processing code

[1986] Step 8:

[1987] The adjusted data processing code is sent from the server to the user's terminal, and the user executes this code in their own development environment to convert the initial data into a format similar to the processed data.

[1988] Input: Adjusted data processing code

[1989] Output: Data manipulation code sent to the user's terminal

[1990] In this way, the entire system processes in a single flow, automating data processing and realizing adaptive data processing that takes into account the user's emotional state.

[1991] 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.

[1992] 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.

[1993] 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.

[1994] 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.

[1995] 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.

[1996] 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.

[1997] 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).

[1998] 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.

[1999] 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."

[2000] 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.

[2001] 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).

[2002] 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.

[2003] 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.

[2004] 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.

[2005] 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.

[2006] 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.

[2007] 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.

[2008] 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.

[2009] 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.

[2010] 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.

[2011] 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.

[2012] The following is further disclosed regarding the above embodiment.

[2013] (Claim 1)

[2014] A means for receiving initial data and processed data uploaded by a user;

[2015] means for comparing the initial data with the processed data to identify the processing details of the data;

[2016] means for automatically generating a data processing code based on the processing content;

[2017] means for transmitting the generated processing code to a user;

[2018] A system including:

[2019] (Claim 2)

[2020] 2. The system according to claim 1, wherein the means for identifying the data processing details analyzes the column structure of the data and changes in data values.

[2021] (Claim 3)

[2022] 2. The system of claim 1, wherein the data manipulation code is a means including data transformation, filtering, aggregation, and join operations.

[2023] "Example 1"

[2024] (Claim 1)

[2025] A means for receiving initial data and processed data uploaded by a user;

[2026] means for comparing the initial data with the processed data to identify field differences and data conversion rules;

[2027] means for automatically generating a data conversion code based on the specified data conversion rule;

[2028] means for transmitting the generated data processing code to a user;

[2029] A system including:

[2030] (Claim 2)

[2031] 2. The system according to claim 1, wherein the means for identifying the data processing details analyzes the column structure of the data and changes in data values.

[2032] (Claim 3)

[2033] 2. The system of claim 1, wherein the data manipulation code includes data transformation, data filtering, data aggregation, and data join operations.

[2034] "Application Example 1"

[2035] (Claim 1)

[2036] A means for receiving initial data and processed data uploaded by a user;

[2037] means for comparing the initial data with the processed data to identify the processing details of the data;

[2038] means for automatically generating a data processing code based on the processing content;

[2039] means for transmitting the generated processing code to a user;

[2040] means for categorizing the initial data and the processed data based on the original data;

[2041] means for adding a new field based on the information obtained by the categorization;

[2042] A system including:

[2043] (Claim 2)

[2044] 2. The system according to claim 1, wherein the means for identifying the data processing details analyzes the column structure of the data and changes in data values.

[2045] (Claim 3)

[2046] 2. The system of claim 1, wherein the data manipulation code is a means including data transformation, filtering, aggregation, and join operations.

[2047] "Example 2: Combining Emotion Engines"

[2048] (Claim 1)

[2049] A means for receiving initial data and processed data uploaded by a user;

[2050] means for comparing the initial data with the processed data to identify the processing details of the data;

[2051] means for automatically generating a data processing code based on the processing content;

[2052] A means for recognizing the emotional state of the user and adjusting the content of data processing and the method of providing code according to the emotional state;

[2053] means for transmitting the generated processing code to a user;

[2054] A system including:

[2055] (Claim 2)

[2056] 2. The system according to claim 1, wherein the means for identifying the data processing details analyzes the column structure of the data and changes in data values.

[2057] (Claim 3)

[2058] 2. The system of claim 1, wherein the data manipulation code is a means including data transformation, filtering, aggregation, and join operations.

[2059] "Application example 2 when combining emotion engines"

[2060] (Claim 1)

[2061] A means for receiving initial data and processed data uploaded by a user;

[2062] means for comparing the initial data with the processed data to identify the processing details of the data;

[2063] means for automatically generating a data processing code based on the processing content;

[2064] means for recognizing an emotional state of a user using an emotion recognition engine;

[2065] means for adjusting the data processing code generated based on the emotional state;

[2066] means for transmitting the generated processing code to a user;

[2067] A system including:

[2068] (Claim 2)

[2069] 10. The system of claim 1, further comprising means for reducing the complexity of the generated data manipulation code or adding detailed explanations to the generated code if the user's emotional state indicates stress.

[2070] (Claim 3)

[2071] 2. The system of claim 1, wherein the data processing code includes data transformation, filtering, aggregation, and combination operations, and further includes means for the emotion recognition engine to provide the data processing code step by step in response to the user's emotional state. [Explanation of symbols]

[2072] 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 means for receiving initial data and processed data uploaded by a user; means for comparing the initial data with the processed data to identify the processing details of the data; means for automatically generating a data processing code based on the processing content; means for transmitting the generated processing code to a user; A system including:

2. 2. The system according to claim 1, wherein the means for identifying the data processing details analyzes the column structure of the data and changes in data values.

3. 2. The system of claim 1, wherein the data manipulation code is a means including data transformation, filtering, aggregation, and join operations.

Images