Data processing device, data processing method, and data processing program

Abstract

To provide a data processing device capable of contributing to efficient analysis of data.SOLUTION: A data processing device includes: an input unit which accepts an instruction sentence on data analysis; a first output unit which outputs the instruction sentence and an output message when the instruction sentence is input to a data generation model for generating data according to input data; a second output unit which outputs output program code when a program generation instruction sentence for generating a program on data analysis according to the instruction sentence is input to the data generation model; and a third output unit which outputs the execution results of the output program.SELECTED DRAWING: Figure 4C

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a data processing device, a data processing method, and a data processing program. [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] However, there is room for improvement in utilizing conventional techniques for data analysis. [Means for solving the problem]

[0005] A first aspect of the technology of the present disclosure is a data processing device including an input unit that accepts an instruction statement related to data analysis, a first output unit that outputs the instruction statement and an output message when the instruction statement is input into a data generation model that generates data according to input data, a second output unit that outputs code of an output program when a program generation instruction statement that generates a program related to data analysis according to the instruction statement is input into the data generation model, and a third output unit that outputs a result of executing the output program.

[0006] A second aspect of the technology of the present disclosure is a data processing method in which a computer accepts an instruction statement related to data analysis, outputs the instruction statement and an output message when the instruction statement is input into a data generation model that generates data according to input data, outputs code for an output program when a program generation instruction statement that generates a program related to data analysis according to the instruction statement is input into the data generation model, and outputs the results of executing the output program.

[0007] A third aspect of the technology of the present disclosure is a data processing program that causes a computer to execute the following steps: accept an instruction statement related to data analysis; output the instruction statement and an output message when the instruction statement is input into a data generation model that generates data according to input data; output code for an output program when a program generation instruction statement that generates a program related to data analysis according to the instruction statement is input into the data generation model; and output the results of executing the output program. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a configuration of a data processing system. [Figure 2] FIG. 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device. [Figure 3A] 2 shows a schematic functional configuration of a specific processing unit of the data processing device. [Figure 3B] 2 is a diagram illustrating a functional configuration of an output unit of the data processing device. [Figure 4A] 10 is a diagram illustrating an example of an operational flow of specific processing by a data processing device. [Figure 4B] An example of an output screen is shown. [Figure 4C] An example of an output screen is shown. [Figure 4D] An example of an output screen is shown. [Figure 4E] An example of an output screen is shown. [Figure 4F] An example of an output screen is shown. [Figure 5] An overview of the specific processing is shown below. [Figure 6] An overview of the specific processing is shown below. [Figure 7] An overview of the specific processing is shown below. [Figure 8] An overview of the specific processing is shown below. [Figure 9] An overview of the specific processing is shown below. [Figure 10] An overview of the specific processing is shown below. [Figure 11] An overview of the specific processing is shown below. [Figure 12] An overview of the specific processing is shown below. [Figure 13] An overview of the specific processing is shown below. [Figure 14] An overview of the specific processing is shown below. [Figure 15] An overview of the specific processing is shown below. [Figure 16] An overview of the specific processing is shown below. [Figure 17] An overview of the specific processing is shown below. [Figure 18] An overview of the specific processing is shown below. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a program according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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.

[0015] 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."

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the embodiment.

[0017] As shown in FIG. 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. An example of the smart device 14 is a smartphone. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the person 20 by outputting the data in a form of expression that the person 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] The storage 32 stores a data generation model 58. The data generation model 58 is used by the specific processing unit 290.

[0026] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 62. The reception output program 62 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 62 from the storage 50 and executes the read reception output program 62 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 62 executed on the RAM 48.

[0027] Next, the processing of the specific processing unit 290 when the data processing device 12 performs specific processing as analysis processing will be described.

[0028] As shown in FIG. 3A, the specific processing unit 290 includes an input unit 292, a processing unit 294, and an output unit 296.

[0029] The input unit 292 acquires a user input received by the smart device 14. Specifically, the input unit 292 acquires an instruction statement related to data analysis received by the smart device 14. For example, the input unit 292 acquires an instruction statement for acquiring data. As an example, the input unit 292 acquires an instruction statement such as "Please read XX data from DB."

[0030] The input unit 292 also acquires instructions for preprocessing the data. For example, the input unit 292 acquires instructions such as "Integrate the data based on the contract history and aggregate it by day. Then, complete any missing data."

[0031] The input unit 292 also acquires an instruction statement for generating a graph showing the relationship between parameters. For example, the instruction statement acquired is, "Please create a model using the number of new contracts as the objective variable and XX as the explanatory variable, and estimate the acquisition effect of the ICp."

[0032] The input unit 292 also acquires an instruction statement for predicting parameters. For example, the instruction statement acquired is "Please predict XX using the model."

[0033] The processing unit 294 performs specific processing using the data generation model 58. Specifically, the processing unit 294 generates a prompt that instructs the generation and execution of code in accordance with the instruction statement, and inputs the prompt to the data generation model 58.

[0034] For example, in response to an instruction statement such as "Please read XX data from the DB," a prompt such as "Please read XX data from the DB. Please generate and execute the program code to achieve this" is generated and input to the data generation model 58. In other words, a predetermined fixed sentence such as "Please generate and execute the program code to achieve this" is added to the instruction statement to generate the prompt.

[0035] The processing unit 294 obtains, as outputs of the data generation model 58, an output message for the directive, the code of the output program, and the results of executing the output program.

[0036] The output unit 296 transmits the result of the identification process to the smart device 14. Specifically, as shown in FIG. 3B, the output unit 296 includes a first output unit 296A, a second output unit 296B, and a third output unit 296C.

[0037] The first output unit 296A outputs a directive and an output message of the data generation model 58 in response to the directive.

[0038] The second output unit 296B outputs the code of the output program when a program generation directive for generating a program relating to data analysis in accordance with the directive is input to the data generation model 58.

[0039] The third output unit 296C outputs the results of executing the output program. Specifically, the third output unit 296C outputs the output contents in a switchable manner according to the selection of tags according to the classification of the results of executing the output program.

[0040] More specifically, the third output unit 296C outputs the first to fourth output contents switchably according to the selection of the tag. The first output content outputs acquired data as a result of executing an output program for acquiring data. The second output content outputs preprocessed data as a result of executing an output program for preprocessing data. The third output content outputs a graph as a result of executing an output program for generating a graph showing the relationship between parameters on the preprocessed data. The fourth output content outputs a parameter prediction result as a result of executing an output program for predicting parameters from the preprocessed data.

[0041] 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 a voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0042] 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> ) 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.

[0043] Next, the operation of the data processing system 10 will be described.

[0044] An example of the flow of the identification process will be described with reference to Fig. 4A. Note that the flow of the identification process shown in Fig. 4A is an example of a "data processing method" according to the technology of the present disclosure.

[0045] In step S300, the processing unit 294 determines whether a predetermined trigger condition is met.

[0046] If the trigger condition is met in step S300 (step S300; Yes), the data processing system 10 proceeds to step S301. On the other hand, if the trigger condition is not met in step S300 (step S300; No), the data processing system 10 ends the identification process. Specifically, when an instruction statement related to data analysis accepted by the smart device 14 is acquired, it is determined that the trigger condition is met.

[0047] In step S301, the processing unit 294 generates a prompt by adding an instruction sentence for obtaining the result of a specific process to the text representing the input. Specifically, the processing unit 294 generates the prompt by adding a predetermined fixed sentence, such as "Please generate and execute the program code to achieve this," to the instruction sentence obtained in step S300.

[0048] In step S303, the processing unit 294 inputs the generated prompt to the data generation model 58 and acquires the result of the specific processing based on the output of the data generation model 58. Specifically, the processing unit 294 acquires, as the output of the data generation model 58, the output message for the instruction statement, the code of the output program, and the result of executing the output program.

[0049] In step S304, the output unit 296 outputs the result of the identification process to the user terminal, and the identification process ends.

[0050] Specifically, the first output unit 296A outputs an instruction statement and an output message of the data generation model 58 in response to that instruction statement, the second output unit 296B outputs the code of the output program when a program generation instruction statement that generates a program related to data analysis in accordance with the instruction statement is input into the data generation model 58, and the third output unit 296C outputs the output content in a switchable manner in accordance with the selection of a tag in accordance with the classification of the results of executing the output program.

[0051] For example, as shown in Fig. 4B, output screen data representing an instruction statement 400A, an output message 400B, output program code 400C, and a result 400D of executing the output program are sent to the smart device 14 and displayed. Fig. 4B shows an example in which acquired data is output as a result 400D of executing an output program generated in accordance with the instruction statement 400A for acquiring data. In this example, the "Acquire Data" tab T1 is selected.

[0052] 4C, output screen data representing instruction statements 400A, 400D, output messages 400B, 400E, 400F, output program codes 400C, 400G, 400H, and a result 400I of the execution of the output program are sent to the smart device 14 and displayed. FIG. 4C shows an example in which preprocessed data is output as a result 400I of the execution of an output program generated in accordance with instruction statement 400D for performing preprocessing on data. In this example, the "Preprocessing" tab T2 is selected.

[0053] 4D, output screen data representing instruction statements 400A, 400J, output messages 400B, 400K, output program codes 400C, 400L, and a result 400M of executing the output program are sent to the smart device 14 and displayed. FIG. 4D shows an example in which a graph is output as a result 400M of executing an output program generated in accordance with instruction statement 400J for generating a graph showing the relationship between parameters on preprocessed data. In this example, the "Data Search" tab T3 is selected.

[0054] 4E, output screen data representing instruction statements 400A, 400N, and 400P, output messages 400B and 400K, output program codes 400C and 400R, and execution result 400S of the output program are transmitted to and displayed on the smart device 14. FIG. 4E shows an example in which a graph showing the predicted results of parameters is output as the result 400S of execution of an output program generated in accordance with instruction statements 400N and 400P for predicting parameters from data that has undergone preprocessing. In this example, the "Modeling" tab T4 is selected.

[0055] 4F, output screen data representing instruction statements 400A, 400T, 400V, output messages 400B, 400U, 400W, output program codes 400C, 400X, and a result 400Y of executing the output program are transmitted to and displayed on the smart device 14. FIG. 4F shows an example in which a graph showing the predicted results of parameters is output as the result 400Y of executing an output program generated in accordance with instruction statements 400T, 400V for predicting parameters from data that has undergone preprocessing. In this example, the "Modeling" tab T4 is selected.

[0056] The specific processing of this embodiment will be further explained below with reference to Figures 5 to 18. The specific processing of this embodiment has the following functions to achieve the following objectives.

[0057] In the process from identifying specific issues to considering countermeasures, data scientists spend 80% of their work time processing data, and communication between the business side, which lacks data science knowledge, and the data scientists takes time (see Figure 5). Therefore, in this embodiment, we aim to reduce work time and increase the time for business consideration by utilizing generative AI (see Figure 6).

[0058] To address this issue, the specific processing of this embodiment is provided as a BI (Business Intelligence) tool (see FIG. 7), and the processing is executed in the following manner.

[0059] First, in this embodiment, the content to be processed is accepted as a chat from a user. As a result, a code corresponding to the accepted chat content is generated (see FIG. 8). Then, processing is executed on the dashboard based on the generated code (see FIG. 9).

[0060] in particular, Based on the user's instruction to load data via chat, the corresponding data is loaded onto the dashboard (see Figure 10). Next, preprocessing is performed on the dashboard based on the user's instructions via chat. This preprocessing involves filling in any data defects and creating tables (see Figure 11). Next, once preprocessing is complete, data exploration continues (see Figure 12). Next, modeling is performed based on instructions from the user via chat regarding the creation of the model (see FIG. 13). Finally, the report is created based on the user's instructions to the chat regarding report creation (see Figure 14).

[0061] As described above, according to this embodiment, when performing a series of processes from data acquisition to preprocessing, search, and modeling, an analyst (e.g., a data scientist) currently creates code from scratch, but this allows for tuning of AI output (see FIG. 15). As the amount of data required for analysis continues to increase and data analysis becomes more complex, efficient analysis is required, and this embodiment can contribute to efficient analysis (see FIG. 17).

[0062] Furthermore, according to this embodiment, a business model can be established between users (including corporations and individuals) who wish to analyze data and an analysis company that provides the system of this embodiment (see FIG. 16).

[0063] In this embodiment, it is possible to provide reference information related to the analysis. Then, the code and reference information used in the analysis can be used, for example, for training the generation AI (see FIG. 18).

[0064] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 290, 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).

[0065] Although the smart device 14 is described as a smartphone, the present invention is not limited to this. A user terminal or smart glasses may be used as the smart device 14. When smart glasses are used, the above-described specific processing may provide an "assistant" function that assists in data analysis as an agent function for interacting with the user in the smart glasses.

[0066] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0067] 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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. [Explanation of symbols]

[0076] 10 Data Processing System 12 Data Processing Device 14 Smart Devices 290 Special Processing Department 292 Input section 294 Processing Section 296 Output Section 296A 1st output section 296B 2nd output section 296C 3rd output section

Claims

1. an input unit for receiving instructions regarding data analysis; a first output unit that outputs the instruction statement and an output message when the instruction statement is input to a data generation model that generates data according to input data; a second output unit that outputs a code of an output program when a program generation directive for generating a program related to data analysis in response to the directive is input to the data generation model; a third output unit that outputs a result of executing the output program; 2. A data processing device comprising:

2. 2 . The data processing apparatus according to claim 1 , wherein the third output section outputs output contents in a switchable manner in response to a selection of a tag corresponding to a classification of a result of execution of the output program.

3. 2 . The data processing apparatus according to claim 1 , further comprising a processing unit that generates a prompt instructing the generation and execution of code in response to the instruction statement, and inputs the prompt to the data generation model.

4. The third output unit is outputting the acquired data as a result of executing the output program for acquiring the data; outputting the preprocessed data as a result of executing the output program for preprocessing the data; outputting the graph as a result of executing the output program for generating a graph representing a relationship between parameters on the data on which the preprocessing has been performed; and outputting a prediction result of the parameter as a result of executing the output program for predicting a parameter from the data on which the preprocessing has been performed; 3. The data processing device according to claim 2, wherein said data processing device outputs said one of said plurality of tags in a switchable manner in response to a selection of said tag.

5. The computer Accepts instructions regarding data analysis, outputting the instruction statement and an output message when the instruction statement is input to a data generation model that generates data according to input data; outputting code for an output program when a program generation directive for generating a program related to data analysis in response to the directive is input to the data generation model; Output the results of executing the output program Data processing methods.

6. Accepts instructions regarding data analysis, outputting the instruction statement and an output message when the instruction statement is input to a data generation model that generates data according to input data; outputting code for an output program when a program generation directive for generating a program related to data analysis in response to the directive is input to the data generation model; Output the results of executing the output program A data processing program that causes a computer to carry out

Images