Business analysis support device, business analysis support method, and program

Abstract

To provide a business analysis support technique that uses a machine learning model.SOLUTION: One aspect of the present disclosure relates to a business analysis support device having a user interface unit configured to transmit a series of questions about a business to be analyzed to a user terminal and acquire a series of replies to the series of questions from the user terminal, and an information generation unit configured to use a machine learning model to generate business process information based on the series of questions and the series of replies.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a business analysis support device, a business analysis support method, and a program. [Background technology]

[0002] In manufacturing, transportation, back office, and other industries, business operations and daily tasks can be expressed by processes and steps such as business processing and factory lines. By visualizing these operations as processes, it is possible to improve the operations through visualization, optimization, bottleneck analysis, and the like, using business analysis tools such as schedulers and simulators. For example, as disclosed in Patent Document 1, a technology for constructing a manufacturing line simulation model has been proposed. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2013-120397 A Summary of the Invention [Problem to be solved by the invention]

[0004] On the other hand, recent advances in deep learning research have led to the evolution of natural language processing based on BERT (Bidirectional Encoder Representations from Transformers) and GPT (Generative Pretrained Transformer).In addition, machine learning models have been used to recognize, convert, and generate multimodal data such as images, video, and audio.

[0005] One objective of the present disclosure is to provide a business analysis support technology that utilizes a machine learning model. [Means for solving the problem]

[0006] One aspect of the present disclosure relates to a business analysis support device having a user interface unit that transmits a series of questions related to a business to be analyzed to a user terminal and acquires a series of answers to the series of questions from the user terminal, and an information generation unit that utilizes a machine learning model to generate business process information based on the series of questions and the series of answers. Effect of the Invention

[0007] According to the present disclosure, a business analysis support technology that uses a machine learning model can be provided. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram illustrating a task analysis support process according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a block diagram illustrating a hardware configuration of a business analysis support device according to an embodiment of the present disclosure. [Diagram 3] FIG. 3 is a block diagram illustrating a functional configuration of a business analysis support device according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram showing a series of questions and answers exchanged in a dialogue format according to one embodiment of the present disclosure. [Diagram 5] 5A to 5C are diagrams illustrating text data generated from a question sequence and an answer sequence according to an embodiment of the present disclosure. [Figure 6] FIG. 6 is a diagram illustrating business process information in JSON format according to an embodiment of the present disclosure. [Figure 7] FIG. 7 is a flowchart illustrating a task analysis support process according to an embodiment of the present disclosure. [Figure 8] FIG. 8 is a diagram showing a series of questions and answers exchanged in a dialogue format according to one embodiment of the present disclosure. [Figure 9] FIG. 9 is a diagram showing a series of questions and answers exchanged in a dialogue format according to one embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0010] In the following embodiment, a business analysis support device that generates business process information from a series of questions and a series of answers related to a business to be analyzed will be disclosed.

[0011] As shown in Fig. 1, a business analysis support device 100 according to an embodiment described later interacts with a user terminal 50 to generate business process information describing the work content of each process / step in a business to be analyzed and / or the relationship between the processes / steps constituting the business. Specifically, the business analysis support device 100 presents a series of questions (e.g., question #1, question #2, ...) related to the business to be analyzed to the user terminal 50, and acquires a series of answers to the series of questions (e.g., answer #1, answer #2, ...) from the user terminal 50. For example, the business analysis support device 100 may exchange the series of questions and the series of answers with the user terminal 50 in an interactive format, such as presenting question #1 to the user terminal 50, acquiring answer #1 to question #1 from the user terminal 50, then presenting question #2 to the user terminal 50, and acquiring answer #2 to question #2 from the user terminal 50.

[0012] When the interaction with the user terminal 50 is completed, the business analysis support device 100 generates business process information from the question series and the answer series using the machine learning model 60. For example, the business analysis support device 100 uses any appropriate generation model such as GPT as the machine learning model 60 to acquire text data related to the business process from the question series and the answer series, and generates business process information by converting the acquired text data into a data format suitable for input to a business analysis tool, such as JSON format. The business process information may then be analyzed by the business analysis tool, and business analysis results may be acquired.

[0013] Here, the business analysis support device 100 may be realized by a computing device such as a server, a personal computer (PC), a smartphone, or a tablet, or an information processing device, and may have a hardware configuration such as that shown in Fig. 2. That is, the business analysis support device 100 has a drive device 101, a storage device 102, a memory device 103, a processor 104, a user interface (UI) device 105, and a communication device 106, which are interconnected via a bus B.

[0014] The programs or instructions for implementing the various functions and processes in the business analysis support device 100 may be stored in a removable storage medium such as a CD-ROM (Compact Disk-Read Only Memory) or a flash memory. When the storage medium is set in the drive device 101, the programs or instructions are installed from the storage medium via the drive device 101 into the storage device 102 or the memory device 103. However, the programs or instructions do not necessarily have to be installed from the storage medium, and may be downloaded from any external device via a network or the like.

[0015] The storage device 102 is realized by a hard disk drive or the like, and stores installed programs or instructions as well as files, data, etc. used in executing the programs or instructions.

[0016] The memory device 103 is realized by a random access memory, a static memory, or the like, and when a program or an instruction is activated, reads and stores the program or instruction, data, or the like from the storage device 102. The storage device 102, the memory device 103, and the removable storage medium may be collectively referred to as a non-transitory storage medium.

[0017] The processor 104 may be realized by one or more CPUs (Central Processing Units), GPUs (Graphics Processing Units), processing circuitry, etc., which may be composed of one or more processor cores, and performs various functions and processing of the business analysis support device 100 in accordance with programs, instructions, data such as parameters necessary to execute the programs or instructions, etc. stored in the memory device 103.

[0018] The user interface (UI) device 105 may be composed of input devices such as a keyboard, a mouse, a camera, a microphone, etc., output devices such as a display, a speaker, a headset, a printer, etc., and input / output devices such as a touch panel, and realizes an interface between a user and the business analysis support device 100. For example, a user operates the business analysis support device 100 by operating a GUI (Graphical User Interface) displayed on a display or a touch panel using a keyboard, a mouse, etc.

[0019] The communication device 106 is realized by various communication circuits that execute wired and / or wireless communication processing with an external device, the Internet, a LAN (Local Area Network), a cellular network, or other communication network.

[0020] However, the above-described hardware configuration is merely an example, and the business analysis support device 100 according to the present disclosure may be realized by any other appropriate hardware configuration.

[0021] [Business analysis support device] Next, a business analysis support device 100 according to an embodiment of the present disclosure will be described. Fig. 3 is a block diagram showing a functional configuration of the business analysis support device 100 according to an embodiment of the present disclosure. As shown in Fig. 3, the business analysis support device 100 has a user interface unit 110 and an information generation unit 120. Each functional unit of the user interface unit 110 and the information generation unit 120 may be realized by a processor 104 executing a computer program stored in a memory device 103 of the business analysis support device 100.

[0022] The user interface unit 110 transmits a series of questions related to the business to be analyzed to the user terminal 50, and acquires a series of answers to the series of questions from the user terminal 50. For example, the user interface unit 110 may exchange the series of questions and the series of answers with the user terminal 50 in a dialogue format. Specifically, the user interface unit 110 may use a chatbot to present questions to the user terminal 50 in a chat format, and acquire answers to the presented questions from the user terminal 50. As shown in FIG. 4, the user interface unit 110 first presents a question, "What is your business?" to the user terminal 50, and acquires an answer to this question, "We are manufacturing A." from the user terminal 50. Next, the user interface unit 110 presents a question, "What materials are necessary for manufacturing A?" to the user terminal 50, and acquires an answer to this question, "The materials are X, Y, and Z." from the user terminal 50. Next, the user interface unit 110 presents the question "What do you do with material X?" to the user terminal 50, and obtains the answer "Press material X" from the user terminal 50. In the same manner, the user interface unit 110 repeats the exchange of questions and answers with the user terminal 50 until a predetermined end condition is satisfied.

[0023] Here, the series of questions to be presented to the user terminal 50 may be prepared in advance. For example, the user interface unit 110 may present questions associated with the tree structure to the user terminal 50 in the order defined by the tree structure. Alternatively, the series of questions may be presented to the user terminal 50 using a generative model such as GPT. For example, the user interface unit 110 may initially input a prompt such as "Please present a question to ask to determine the business process" to the generative model, and present a question generated by the generative model to the user terminal 50. When an answer to the presented question is obtained from the user terminal 50, the user interface unit 110 may input the obtained answer to the generative model as the next prompt, and obtain a further question from the generative model to present to the user terminal 50. In the same manner, the user interface unit 110 may present a question generated by the generative model to the user terminal 50, and obtain an answer to the presented question from the user terminal 50.

[0024] Note that the predetermined termination condition for the dialogue-style exchange of questions and answers may be, for example, that all prepared questions have been presented to the user terminal 50, that a search has been completed from the root node to the leaf nodes in the tree structure, that a predetermined number or more pairs of questions and answers have been acquired, etc. When the predetermined termination condition is satisfied, the user interface unit 110 passes the acquired question sequence and answer sequence to the information generation unit 120.

[0025] The information generating unit 120 uses a machine learning model to generate business process information based on the question sequence and the answer sequence. Specifically, the information generating unit 120 may input the question sequence and the answer sequence into a generating model such as GPT, and instruct the generating model to summarize the question sequence and the answer sequence as a business process. For example, for the example shown in FIG. 4, the information generating unit 120 may input a prompt of text data, "Please summarize 'What is your business? You are manufacturing A. What materials are needed to manufacture A? The materials are X, Y, and Z. What do you do with material X? Press material X. ...' as a business process," as shown in FIG. 5A, into the generating model. That is, the information generating unit 120 may add the phrase "Please summarize as a business process" to the end of the text data of the question sequence and the answer sequence, and input the created prompt into the generating model. Note that the phrase to be added is not limited to this, and any other phrase that is a prompt suitable for the generating model may be applied.

[0026] When the output result for the prompt is obtained from the generative model, the information generating unit 120 may output the business process information in a data format that can be used by the business analysis tool. For example, when the data format that can be processed by the business analysis tool is JSON (JavaScript Object Notation), the information generating unit 120 may instruct the generative model to convert the output result obtained from the generative model into the JSON format. For example, when the generative model outputs the text data "When receiving goods, product A is generated at 5-minute intervals. The generated products are stored in warehouse B. Warehouse B contains 1,000 products. Processing machine A retrieves product A one by one from the warehouse and processes it over 3 minutes. The processed products are shipped," as shown in FIG. 5B, the information generation unit 120 may input the text data prompt "When receiving goods, product A is generated at 5-minute intervals. The generated products are stored in warehouse B. Warehouse B contains 1,000 products. Processing machine A retrieves product A one by one from the warehouse and processes it over 3 minutes. The processed products are shipped. Please output this process in JSON. When outputting in JSON, please use cycle_time as the label for the occurrence interval, capacity for the warehouse capacity, and processing_time for the processing time," as shown in FIG. 5C to the generative model. That is, the information generating unit 120 may add a sentence such as "Please output this process in JSON. When outputting in JSON, please use cycle_time as the label for the occurrence interval, capacity as the label for the warehouse capacity, and processing_time as the label for the processing time" to the end of the text data of the generated result, and input the created prompt to the generative model. Note that the sentence to be added is not limited to this, and any other sentence that is a prompt suitable for the generative model may be applied.

[0027] In this case, the information generating unit 120 may obtain data in a JSON format as shown in FIG. 6 from the generation model. When the information generating unit 120 obtains business process information in a data format that can be processed by such a business analysis tool, the information generating unit 120 may provide the obtained business process information to the business analysis tool, or may pass the information to the user terminal 50. The information generating unit 120 may generate a spatial layout of the process from the business process as position information data from the generation model. For example, the business analysis tool may be input with an equipment layout, and may be able to calculate business efficiency based on the movement of equipment and people in executing the business process. That is, the machine learning model 60 may generate a floor layout or an equipment layout. For example, a machine learning model such as GPT may output a floor layout or an equipment layout as text data, program code such as C# code, various drawing formats such as JSON and yaml, or a layout coordinate format, independent of the business process. The generated floor layout or equipment layout may be input to the business analysis tool and used to optimize the movement of equipment and people.

[0028] When business process information is analyzed by business analysis tools such as a simulator and a scheduler, the analysis results are provided to a user terminal 50, enabling the user to perform business process visualization, optimization, bottleneck analysis, etc. based on the analysis results.

[0029] In the above-described embodiment, the question sequence and the answer sequence are described by text data, but the question sequence and / or the answer sequence according to the present disclosure are not limited to this. For example, the question sequence and / or the answer sequence may be composed of one or any combination of voice data, image data, video data, and biometric data.

[0030] For example, the user interface unit 110 may exchange questions and / or answers composed of image data and / or video data of a factory, a production line, a product, etc. In this case, the information generator 120 may generate business process information based on a series of questions and a series of answers including image data and / or video data, using any appropriate multimodal type generative model compatible with image data and / or video data.

[0031] Also, for example, the user interface unit 110 may exchange questions and / or answers composed of voice data. In this case, the information generation unit 120 may generate business process information based on a question sequence and an answer sequence including voice data, using a multimodal type generation model. Alternatively, the user interface unit 110 may acquire a question sequence and / or an answer sequence based on biometric data. For example, the user interface unit 110 may generate a question sequence and / or an answer sequence from data generated by signal processing of biometric data such as an electroencephalogram signal.

[0032] Furthermore, in the above-described embodiment, the information generating unit 120 generates business process information from a series of questions and a series of answers, but the generation of business process information according to the present disclosure is not limited to this. For example, the information generating unit 120 may use a generation model to generate summary information of the series of questions and the series of answers, and generate business process information from the summary information. Specifically, the information generating unit 120 may input the series of questions and the series of answers into a generation model such as GPT, and instruct the generation model to create the summary information. Then, the information generating unit 120 may input the summary information into the generation model and instruct it to summarize it as a business process. In this way, by generating business process information based on the summary information, it may be possible to generate business process information that is consistent with the gist of the series of questions and the series of answers.

[0033] In one embodiment, the user interface unit 110 may hold the acquired question sequence and answer sequence in order to (re)learn the generative model. In one embodiment, an individual generative model may be prepared according to the business type, industry, business analysis tool used, etc. of the business to be analyzed. In this case, a generative model corresponding to the business type, industry, business analysis tool used, etc. similar to the business to be analyzed may be used. This may enable more appropriate business process information to be generated.

[0034] [Business analysis support processing] Next, a task analysis support process according to an embodiment of the present disclosure will be described. The task analysis support process is executed by the task analysis support device 100, and more specifically, may be realized by one or more processors 104 of the task analysis support device 100 executing one or more programs or instructions stored in one or more memory devices 103. Fig. 7 is a flowchart showing the task analysis support process according to an embodiment of the present disclosure.

[0035] In step S101, the business analysis support device 100 transmits a question about the business to be analyzed to the user terminal 50. For example, as shown in Figs. 8 and 9, the business analysis support device 100 may execute a chatbot to first present the question "What is the purpose of the business process?" to the user terminal 50.

[0036] In step S102, the business analysis support device 100 acquires an answer to the question from the user terminal 50. For example, in the example shown in Fig. 8, the business analysis support device 100 may acquire the answer "Manufacture automobiles." from the user terminal 50. Also, in the example shown in Fig. 9, the business analysis support device 100 may acquire the answer "Load products onto trucks in response to orders and ship them." from the user terminal 50.

[0037] In step S103, the business analysis support device 100 determines whether the termination condition is satisfied. For example, the business analysis support device 100 may determine that the termination condition is satisfied when all prepared questions have been presented to the user terminal 50, when a search has been completed from the root node to the leaf nodes in the tree structure, or when a predetermined number or more pairs of questions and answers have been acquired. If the termination condition is satisfied (S103: YES), the business analysis support device 100 proceeds to step S104.

[0038] On the other hand, if the termination condition is not satisfied (S103: NO), the business analysis support device 100 returns to step S101 and transmits the next question to the user terminal 50. For example, in the example shown in Fig. 8, the business analysis support device 100 may sequentially transmit questions such as "What parts are needed?", "What processes are there?", "Please tell me the parts needed for the pressing process and the time it takes," ... to the user terminal 50. In response to these questions, in the illustrated example, the business analysis support device 100 may sequentially obtain questions such as "The engine and the casing...", "There are six processes: pressing process, welding process, painting process, engine manufacturing process, assembly process, and inspection process," ... from the user terminal 50.

[0039] 9, the business analysis support device 100 may sequentially transmit questions such as "What kind of processes are there?", "How many of which products will be received?", etc. to the user terminal 50. In response to these questions, in the illustrated example, the business analysis support device 100 may sequentially obtain questions such as "Receive products, store them in a warehouse, and when an order is received, attach a shipping label and load them onto a truck," etc. from the user terminal 50.

[0040] In step S104, the business analysis support device 100 generates business process information based on the question sequence and the answer sequence using the machine learning model 60. Specifically, the business analysis support device 100 may input the question sequence acquired in step S101 and the answer sequence acquired in step S102 to the generative model, and acquire business process information in a desired data format from the generative model. The generated business process information may be analyzed by a business analysis tool such as a simulator or a scheduler.

[0041] According to the above-mentioned embodiment, business process information in a desired data format can be acquired by exchanging a series of questions and answers related to the business to be analyzed with a user. In addition, the series of questions and answers can be exchanged with the user in an interactive format, and a machine learning model such as GPT can be used to generate business process information in a data format suitable for a business analysis tool based on the series of questions and answers.

[0042] (Appendix 1) a user interface unit that transmits a series of questions related to a task to be analyzed to a user terminal and acquires a series of answers to the series of questions from the user terminal; an information generation unit that generates business process information based on the question sequence and the answer sequence by utilizing a machine learning model; A business analysis support device having the above configuration. (Appendix 2) The business analysis support device according to claim 1, wherein the information generation unit generates the business process information from the question sequence and the answer sequence by using a generation model. (Appendix 3) 3. The business analysis support device according to claim 2, wherein the information generation unit uses the generation model to generate summary information of the question sequence and the answer sequence, and generates the business process information from the summary information. (Appendix 4) 4. The business analysis support device according to any one of claims 1 to 3, wherein the information generating unit outputs the business process information in a data format usable by a business analysis tool. (Appendix 5) 5. The business analysis support device according to any one of claims 1 to 4, wherein the user interface unit communicates with the user terminal using one or a combination of text data, voice data, video data, and biometric data. (Appendix 6) 6. The business analysis support device according to any one of claims 1 to 5, wherein the user interface unit exchanges the series of questions and the series of answers with the user terminal in an interactive format. (Appendix 7) 7. The business analysis support device according to any one of claims 1 to 6, wherein the machine learning model generates a floor layout or an equipment arrangement layout. (Appendix 8) Transmitting a series of questions related to a task to be analyzed to a user terminal, and acquiring a series of answers to the series of questions from the user terminal; generating business process information based on the sequence of questions and the sequence of answers using a machine learning model; A computer-implemented business analysis support method comprising: (Appendix 9) Transmitting a series of questions related to a task to be analyzed to a user terminal, and acquiring a series of answers to the series of questions from the user terminal; generating business process information based on the sequence of questions and the sequence of answers using a machine learning model; A program that causes a computer to execute the following.

[0043] Although the examples of the present disclosure have been described in detail above, the present disclosure is not limited to the specific embodiments described above, and various modifications and variations are possible within the scope of the gist of the present disclosure described in the claims. [Explanation of symbols]

[0044] 50 User terminals 60 Machine Learning Models 100 Business analysis support device 110 User Interface Section 120 Information Generation Unit

Claims

1. a user interface unit that transmits a series of questions related to a task to be analyzed to a user terminal and acquires a series of answers to the series of questions from the user terminal; an information generation unit that generates business process information based on the question sequence and the answer sequence by utilizing a machine learning model; A business analysis support device having the above configuration.

2. The business analysis support device according to claim 1 , wherein the information generation unit generates the business process information from the question sequence and the answer sequence by using a generation model.

3. 3. The business analysis support device according to claim 2, wherein the information generation unit generates summary information of the question sequence and the answer sequence by using the generation model, and generates the business process information from the summary information.

4. The business analysis support device according to claim 1 , wherein the information generating unit outputs the business process information in a data format that can be used by a business analysis tool.

5. 2. The business analysis support device according to claim 1, wherein the user interface unit communicates with the user terminal using one or a combination of text data, voice data, and video data.

6. 2. The business analysis support device according to claim 1, wherein said user interface unit exchanges said series of questions and said series of answers with said user terminal in an interactive format.

7. The business analysis support device according to claim 1 , wherein the machine learning model generates a floor layout or an equipment arrangement layout.

8. Transmitting a series of questions related to a task to be analyzed to a user terminal, and acquiring a series of answers to the series of questions from the user terminal; generating business process information based on the sequence of questions and the sequence of answers using a machine learning model; A computer-implemented business analysis support method comprising:

9. Transmitting a series of questions related to a task to be analyzed to a user terminal, and acquiring a series of answers to the series of questions from the user terminal; generating business process information based on the sequence of questions and the sequence of answers using a machine learning model; A program that causes a computer to execute the following.

Images