AI usage support device, AI usage support method, and program

Abstract

To provide an apparatus, a method, and a program for assisting users in using AI. [Solution] The AI ​​usage assistance device of the present invention comprises a morphological analysis unit that performs morphological analysis of text information representing commands to be executed by an AI, keyword master data storing pre-registered words, processing attribute codes corresponding to processing attributes predetermined for each word, and scores predetermined for the processing attribute codes, a keyword extraction unit that extracts words obtained by morphological analysis from the words stored in the keyword master data as keywords, a score calculation unit that calculates a total score by summing up the scores for each processing attribute code, and a first decision unit that decides to proceed to execute the processing attribute corresponding to the processing attribute code with the highest total score calculated by the score calculation unit.

Description

[Technical field]

[0001] The present invention relates to an AI usage support device, an AI usage support method, and a program for determining whether or not it is necessary to input an instruction to an AI such as a generative AI (Artificial Intelligence), and for determining the optimal AI to which an instruction should be input. [Background technology]

[0002] In recent years, generative AI has made remarkable progress. Some well-known examples of generative AI (hereafter simply referred to as "AI") include ChatGPT, Microsoft 365 Copilot, and Gemini, and new products are being developed every day. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6735392 [Non-patent literature]

[0004] [Non-Patent Document 1] https: / / zenn.dev / knowledgesense / articles / 2b6aa64f27ea89 (searched on October 7, 2020) Summary of the Invention [Problem to be solved by the invention]

[0005] These AIs are very useful, but each product has its own characteristics. In addition, the functions provided free of charge are generally limited, and some functions require payment. In this case, the fee is determined by the amount of tokens, which is the size of the instructions input to the AI.

[0006] Therefore, in order to obtain a more appropriate answer from the AI ​​while minimizing the costs incurred, it is necessary to input commands to the most appropriate AI in simple terms, i.e., with a small amount of tokens, according to the content of the command. Also, some commands can be executed without using AI, such as desktop operations, so for such commands, the costs can be reduced by processing them locally within the PC without using AI.

[0007] The present invention has been made in consideration of the above circumstances, and aims to provide an AI usage support device, an AI usage support method, and a program that support a user's use of AI by determining whether or not it is necessary to input an instruction to an AI, determining the optimal AI to which an instruction should be input, and generating instructions with a small number of tokens when inputting instructions to an AI. [Means for solving the problem]

[0008] In order to achieve the above object, the present invention takes the following measures.

[0009] The first aspect is an AI usage assistance device including: a morphological analysis unit that performs morphological analysis on text information that represents an instruction to be executed by an AI (Artificial Intelligence); keyword master data that stores pre-registered words, processing attribute codes corresponding to processing attributes predetermined for each word, and scores predetermined for the processing attribute codes; a keyword extraction unit that extracts, as keywords, words obtained by the morphological analysis from the words stored in the keyword master data; a score calculation unit that obtains, from the keyword master data, the processing attribute codes predetermined for the words extracted as keywords and the scores predetermined for the processing attribute codes and calculates a total score by summing up the scores for each processing attribute code; a first determination unit that determines to proceed to the execution of a processing attribute corresponding to the processing attribute code having a higher total score calculated by the score calculation unit; and a second determination unit that determines whether to use AI for the execution of the processing attribute determined to proceed by the first determination unit, and if it is determined to use AI, further determines the AI ​​to use.

[0010] The second aspect is an AI usage assistance device of the first aspect, which further includes processing attribute master data that stores processing attribute codes in association with AIs used to execute processing attributes corresponding to the processing attribute codes, and the second decision unit refers to the processing attribute master data to determine whether or not to use an AI to execute the processing attribute determined to be subsequent by the first decision unit, and if it is determined that an AI should be used, further determines the AI ​​to use.

[0011] A third aspect is an AI usage assistance device of the first aspect, further comprising an input creation unit that creates input to the AI ​​by abbreviating text information when the second decision unit determines that the AI ​​should be used.

[0012] A fourth aspect is the AI ​​usage assistance device of the first aspect, further comprising a text information conversion unit that, when a command is input by voice, converts the voice into text information and provides the text information to the morphological analysis unit for morphological analysis.

[0013] The fifth aspect is an AI usage assistance method implemented by an AI usage assistance device, in which a processor of the AI ​​usage assistance device executes the following steps: a first step of morphologically analyzing text information representing commands to be executed by an AI (Artificial Intelligence), a second step of extracting words obtained by the morphological analysis as keywords from among words prepared in advance, a third step of calculating a total score by summing up the scores for each processing attribute code based on processing attribute codes predetermined for the words extracted as keywords and scores predetermined specified for the processing attribute codes, a fourth step of deciding to proceed to the execution of a processing attribute corresponding to the processing attribute code having a high total score, and a fifth step of deciding whether to use AI for the execution of the processing attribute decided to proceed, and if it is decided to use AI, further deciding the AI ​​to use.

[0014] A sixth aspect is a method for supporting use of AI of the fifth aspect, in which the fifth step refers to the processing attribute master data stored in association with the processing attribute code and the AI ​​used to execute the processing attribute corresponding to the processing attribute code to determine whether or not to use an AI to execute the processing attribute that has been determined to follow, and if it is determined that an AI should be used, the method further determines the AI ​​to be used.

[0015] A seventh aspect is a method of assisting use of AI of the fifth aspect, in which the processor further performs a sixth step of creating input to the AI ​​by shortening the text information if it is determined by the fifth step that the AI ​​will be used.

[0016] An eighth aspect is a method of assisting use of AI according to the fifth aspect, in which the processor further executes a seventh step of converting the voice into text information if the command is input by voice, and the first step performs morphological analysis of the text information converted in the fifth step.

[0017] The ninth aspect is a program for causing a processor to realize the following functions: a function for performing morphological analysis on text information representing commands to be executed by an AI (Artificial Intelligence); a function for extracting words obtained by the morphological analysis as keywords from among words prepared in advance; a function for calculating a total score by summing up the scores for each processing attribute code based on the processing attribute code predetermined for the word extracted as the keyword and the scores predetermined for the processing attribute code; a function for deciding to proceed to the execution of a processing attribute corresponding to the processing attribute code having a high total score; and a function for deciding whether to use AI in the execution of the processing attribute determined to proceed, and if it is determined that AI should be used, further deciding the AI ​​to use.

[0018] A tenth aspect is a program of the ninth aspect, in which the function of determining the AI ​​to be used refers to processing attribute master data in which the processing attribute code and the AI ​​to be used for executing the processing attribute corresponding to the processing attribute code are stored in association with each other, to determine whether or not to use an AI to execute the processing attribute that has been determined to be subsequent, and if it is determined that an AI should be used, further includes a function of determining the AI ​​to be used.

[0019] An eleventh aspect is a program of the ninth aspect, further causing the processor to realize a function of creating input to the AI ​​by abbreviating the text information when it is determined that the AI ​​is to be used.

[0020] A twelfth aspect is the program of the ninth aspect, further causing the processor to implement a function of converting speech to text information to generate text information that is morphologically analyzed when the command is input by voice. Effect of the Invention

[0021] The AI ​​usage support device, method, and program of the present invention can determine whether or not to input commands to the AI. This allows commands to be executed on a local PC without using the AI, thereby reducing costs.

[0022] The AI ​​usage support device, method, and program of the present invention can also determine the optimal AI to which a command should be input, allowing the user to use an appropriate AI according to the command.

[0023] Furthermore, the AI ​​usage support device, method, and program of the present invention can generate commands with fewer tokens when inputting commands to the AI, allowing users to use the AI ​​while minimizing costs associated with using the AI. [Brief description of the drawings]

[0024] [Figure 1] FIG. 1 is a simplified block diagram illustrating the concept of the functional configuration of a typical AI usage assistance device. [Diagram 2] FIG. 2 is a simplified block diagram illustrating a concept of the functional configuration of an AI usage assistance device to which the AI ​​usage assistance method according to an embodiment of the present invention is applied. [Diagram 3] FIG. 3 is an electronic circuit block diagram showing an example of the configuration of an AI usage assistance device according to an embodiment of the present invention. [Figure 4] FIG. 4 is a functional block diagram corresponding to the electronic circuitry of the AI ​​assistance device illustrated in FIG. [Diagram 5] FIG. 5 is a data structure diagram showing an example of keyword master data. [Figure 6] FIG. 6 is a data structure diagram illustrating an example of the processing attribute master data. [Figure 7] FIG. 7 is a table for explaining the processing attributes. [Figure 8] FIG. 8 is a diagram showing a process flow of an AI usage support device to which the AI ​​usage support method according to the embodiment of the present invention is applied. [Figure 9] FIG. 9 is a diagram showing an example of abbreviations made by the AI ​​input creation unit. [Figure 10] FIG. 10 is a diagram for explaining the local processing. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The drawings are schematic or conceptual. In this specification and each drawing, elements similar to those described in the previous drawings are given the same reference numerals, and detailed and overlapping descriptions are omitted as appropriate.

[0026] First, an overview of an AI usage assistance device to which a method for assisting use of AI according to an embodiment of the present invention is applied will be described.

[0027] FIG. 1 is a simplified block diagram illustrating the concept of the functional configuration of a typical AI usage assistance device.

[0028] (1) A user U using a general AI usage assistance device 100 as shown in FIG. 1 uses a microphone MC to input commands that the user wants the AI ​​to execute into a PC by voice.

[0029] (2) The PC converts this voice input into text information as commands for the AI. Specifically, the PC (2-1) converts the voice input into text information, and (2-3) generates a script for the AI. In the following, as an example, the AI ​​usage assistance device 100 will be described as using ChatGPT as the AI.

[0030] (3) The PC inputs the script for ChatGPT generated in (2-3) into ChatGPT. ChatGPT performs an analysis based on the script for ChatGPT, and returns the analysis answer to the PC. For example, if the result of this analysis is a screen operation command (3-1), the PC inputs the screen operation command (4-1) into the screen operation program as feedback for the operation (4), and performs the PC screen operation (4-2) according to the execution result by the screen operation program (4-2).

[0031] In this way, a fixed AI such as ChatGPT is used in a general AI usage assistance device 100. In contrast, an AI usage assistance device to which the AI ​​usage assistance method according to an embodiment of the present invention is applied has additional functions that general AI usage assistance devices 100 do not have, as described below.

[0032] FIG. 2 is a simplified block diagram illustrating a concept of the functional configuration of an AI usage assistance device to which the AI ​​usage assistance method according to an embodiment of the present invention is applied.

[0033] The AI ​​usage assistance device 10 has a subsystem (2-2) that the AI ​​usage assistance device 100 does not have. In addition, the AI ​​to be used is not fixed, and all AIs currently being used in the world can be used, and it is possible to handle not only the establishment of new services but also the discontinuation of services. Therefore, the AI ​​usage assistance device 10 can use the subsystem (2-2) to (a) determine which AI to use from among multiple AIs such as ChatGPT, Microsoft 365 Copilot, and Gemnini, according to the command content, and (b) generate and input a script to the determined AI. At this time, the amount of tokens can be reduced by generating the script with as short a sentence as possible. In addition, it can also (c) determine that there is no appropriate AI to use according to the command content. In that case, the script is not generated for the AI, that is, the operation of (2-3) is not performed, and the script is not input to the AI ​​of (3), and a screen operation command is generated by local processing in the PC (3-1).

[0034] The specific configuration of the AI ​​usage assistance device 10 that realizes such functions will be described below.

[0035] FIG. 3 is an electronic circuit block diagram showing an example of the configuration of an AI usage assistance device according to an embodiment of the present invention.

[0036] FIG. 4 is a functional block diagram corresponding to the electronic circuitry of the AI ​​assistance device illustrated in FIG.

[0037] An AI usage support device 10 according to an embodiment of the present invention is a device for determining whether or not to input an instruction to an AI, such as a generative AI, determining the optimal AI to which an instruction should be input, and generating an instruction with a small amount of tokens when inputting an instruction to an AI, and includes a CPU 12, a recording medium reader 14, a display 16, a voice input unit 17 including a microphone, etc., a text information input unit 18 including a mouse, keyboard, etc., a memory 20, a storage device 40, and a communication unit 50, all connected to each other by a bus 11, as shown in Fig. 3. Such an AI usage support device 10 can be realized by, but is not limited to, a PC or a tablet terminal.

[0038] The CPU 12 is a computer that controls the operation of each part of the circuit in accordance with the programs stored in the memory 20. This allows the AI ​​usage assistance device 10 to operate in a manner in which the software and hardware work together, as will be described later.

[0039] The memory 20 stores programs that realize a text information conversion unit 21, a morphological analysis unit 22, a keyword extraction unit 23, a score calculation unit 24, a first determination unit 25, a second determination unit 26, an AI input creation unit 27, an AI input input unit 28, and a local input input unit 29.

[0040] These programs may be pre-stored in the memory 20, or may be read from an external recording medium 13 such as a memory card via the recording medium reading unit 14 and stored in the memory 20. These programs are designed not to be rewritable.

[0041] In addition to the non-rewritable area in which such programs are stored, the memory 20 also has a writable data area 30 secured therein as an area for storing rewritable data.

[0042] The storage device 40 is, for example, a solid state drive (SSD) or a hard disk drive (HDD), and stores keyword master data 42 and processing attribute master data 44.

[0043] FIG. 5 is a data structure diagram showing an example of keyword master data.

[0044] As illustrated in FIG. 5, the keyword master data 42 is a table storing data corresponding to items consisting of a pre-registered word a, a processing attribute code b predetermined for each word a, a processing attribute name c corresponding to the processing attribute code b, and a predetermined processing attribute score d.

[0045] FIG. 6 is a data structure diagram illustrating an example of the processing attribute master data.

[0046] As illustrated in Figure 6, the processing attribute master data 44 is a table that stores data corresponding to items consisting of a processing attribute code b, a processing attribute name c corresponding to the processing attribute code b, and an "AI to be used" e corresponding to the processing attribute code b.

[0047] Next, the processing attributes will be described.

[0048] FIG. 7 is a table for explaining the processing attributes.

[0049] The processing attribute classifies and defines the operations that the user wants to perform, and can include, but is not limited to, PowerAutomate (RPA) operations, MS app operations, screen acquisition instruction operations, desktop operations, browser operations, and resolution processes, as shown in the processing attribute names c in Fig. 7. The processing attribute codes b are code numbers 01, 02, 03, 04, 05, and 80 assigned to these operations. The outline of each of these operations is as described in the processing attribute outline f in Fig. 7.

[0050] The communication unit 50 can communicate with the AI ​​engine 80 via a communication network 60 such as the Internet. Therefore, the AI ​​usage assistance device 10 can send and receive data to and from the AI ​​engine 80 via the communication unit 50.

[0051] Based on text information, the AI ​​usage assistance device 10 determines whether or not a command needs to be input to an AI, determines the most suitable AI to which the command should be input, and generates commands with a small number of tokens when inputting commands to an AI.

[0052] The text information input unit 18 is a portion for the user to input text information for this purpose. The user inputs the content that the user wants to implement using the AI ​​as text information A from the text information input unit 18, which includes, for example, a mouse, a keyboard, and the like.

[0053] On the other hand, in the AI ​​usage assistance device 10, the user can input text information by voice from the voice input unit 17, which is, for example, a microphone, without having to input text information using, for example, a mouse or keyboard. The voice B input from the voice input unit 17 is converted into text information C by the text information conversion unit 21 using, for example, a technique such as that disclosed in Patent Document 1. This allows even users who have difficulty operating a mouse or keyboard due to a disability in their hands, users who cannot use their hands while working at a construction site, or users who cannot use their hands while cooking, to input necessary information into the AI ​​usage assistance device 10.

[0054] The morphological analysis unit 22 performs morphological analysis on the text information A from the text information input unit 18 and the text information C from the text information conversion unit 21, and outputs the result D to the keyword extraction unit .

[0055] The keyword extraction unit 23 refers to the keyword master data 42 and extracts, from the words a preregistered in the keyword master data 42, the words obtained as the result D of the morphological analysis by the morphological analysis unit 22 as keywords.

[0056] The score calculation unit 24 acquires the processing attribute code b and the score d that are designated in advance for the word a extracted as a keyword from the keyword master data 42. Then, the score calculation unit 24 calculates the total score E by summing up the scores d for each processing attribute code b.

[0057] Based on the total score E for each process attribute code b obtained by the score calculation unit 24, the first determination unit 25 determines to proceed to the execution of the process attribute corresponding to the process attribute code b with the highest total score.

[0058] The second decision unit 26 refers to the processing attribute master data 44 to determine whether or not to use an AI to execute the processing attribute that has been determined to be subsequent by the first decision unit 25, and if it is determined that an AI should be used, it further determines the AI ​​to be used.

[0059] When the second decision unit 26 determines that a command should be input to the AI, the AI ​​input creation unit 27 creates an input F for the AI ​​by abbreviating the text information A or the text information C.

[0060] The AI ​​input input unit 28 associates the input F created by the AI ​​input creation unit 27 with the optimal AI determined by the second determination unit 26 and outputs it to the communication unit 50.

[0061] The communication unit 50 transmits the input F via the communication network 60 to the AI ​​engine 80, which executes the optimal AI output from the AI ​​input input unit .

[0062] The AI ​​engine 80 executes processing based on the input F, and returns the processing result G to the communication unit 50 via the communication network 60. The user can view the processing result G on the display 16 to confirm it.

[0063] On the other hand, if the second decision unit 26 determines that the command should not be input to the AI, the local input input unit 29 creates a command H for the local PC 70 based on the text information A or the text information C to have the local PC 70 execute the command, and has the local PC 70 execute the command. The local PC 70 is a PC in which the AI ​​usage assistance device 10 is implemented. The command H is also created by abbreviating the text information A or the text information C.

[0064] The local PC 70 performs processing based on the command H. The user can view and confirm the processing result I on the display 16.

[0065] Next, an example of the operation of the AI ​​usage assistance device to which the AI ​​usage assistance method according to the embodiment of the present invention configured as described above is applied will be described.

[0066] FIG. 8 is a diagram showing a process flow of an AI usage support device to which the AI ​​usage support method according to the embodiment of the present invention is applied.

[0067] For example, as illustrated in the second row of Figure 8, we will explain the case where the user speaks the command he wants the AI ​​to execute through the voice input unit 17, such as "Sort column C in Excel in descending order."

[0068] The spoken content g of the voice B input from the voice input unit 17 is converted by the text information conversion unit 21 into text information C of "sort column C of Excel in descending order."

[0069] This text information C is subjected to Japanese morphological analysis by the morphological analysis unit 22, and morphemes such as "Excel", "C", "column", "descending order", and "sort" are obtained. See the second line of "Japanese morphological analysis" h in FIG. 8.

[0070] The keyword extraction unit 23 refers to the keyword master data 42, and extracts, as a keyword, the word obtained by the morphological analysis unit 22 from the words a stored in the keyword master data 42. The keyword master data 42 illustrated in Fig. 5 stores words a such as "Excel", "cursor", "move", "screen", and "click", and among these, "Excel" is a word obtained by the morphological analysis unit 22, so in this case, the word a "Excel" is extracted as a keyword.

[0071] In the score calculation unit 24, the processing attribute code b "02" that is pre-determined for the word a "Excel" extracted as a keyword, and the pre-specified score d "1 point" are obtained from the keyword master data 42. Furthermore, the scores d for each processing attribute code b "02" are summed up to calculate the total score E "1 point". Please refer to the second line of "Calculate processing attribute score from keyword" i in FIG. 8.

[0072] The first determination unit 25 determines to proceed to the execution of the processing attribute corresponding to the processing attribute code b having the highest total score E calculated by the score calculation unit 24. In this example, since the processing attribute code b is only "02", the processing attribute name of the processing attribute to be followed is "MS application operation". See the second line of "Subsequent processing branches" j in FIG. 8.

[0073] In the second decision unit 26, the processing attribute master data 44 is referred to, and a determination is made as to whether or not to use AI for the processing attribute “MS app operation” determined to be subsequent by the first decision unit 25, and if it is determined that AI should be used, the AI ​​to be used is further determined.

[0074] In the process attribute master data 44, the AI ​​to be used for the "MS app operation" with the process attribute code b of "02" is specified to be "Copilot". Therefore, in this case, the second determination unit 26 determines to use the AI ​​"Copilot". Please refer to the second line of "AI to be used in subsequent process or not to be used" k in FIG. 8.

[0075] When the second decision unit 26 determines that the command should be input to the AI, the AI ​​input creation unit 27 creates an input F for the AI. At this time, when the text information A or text information C indicating the command is long, the input F is created by shortening the text information A or text information C.

[0076] FIG. 9 is a diagram showing an example of abbreviations made by the AI ​​input creation unit.

[0077] For example, as shown in Fig. 9, the AI ​​input creation unit 27 can shorten text information A consisting of 142 characters such as "Um, well, I have a favor to ask of you. I want you to tell me how to do conditional branching in Excel. Specifically, can you give me an example of the values ​​in cells A1 and B1? And, I want you to set a function in cell C1, but I don't know how to do it. Can you do that?" to create an input F consisting of 53 characters such as "Teach me how to do conditional branching in Excel. Give me an example of setting a function in cell C1 using the values ​​in cells A1 and B1." In this case, the text is shortened by about 1 / 3.

[0078] For such shortening, the AI ​​input creation unit 27 can use existing character compression technology, such as that disclosed in Non-Patent Document 1.

[0079] The AI ​​input input unit 28 associates the input F created by the AI ​​input creation unit 27 with the optimal AI determined by the second determination unit 26 and outputs it to the communication unit 50.

[0080] The communication unit 50 transmits the input F via the communication network 60 to the AI ​​engine 80 which executes the AI ​​associated with the input F output from the AI ​​input input unit 28.

[0081] The AI ​​engine 80 executes processing based on the input F, and the processing result is returned from the AI ​​engine 80 to the communication unit 50 via the communication network 60. The user can view and confirm the processing result G on the display 16.

[0082] As mentioned above, the input F input to the AI ​​is shortened, so the amount of tokens can be reduced, which makes it possible to reduce the cost of using the AI. In addition, shortening the input F also shortens the waiting time for a response from the AI, making it possible to improve the response speed.

[0083] On the other hand, if the second decision unit 26 determines that the command should not be input to the AI, the local input input unit 29 creates a command H to be executed by the local PC 70 based on the text information A or the text information C, and inputs it to the local PC 70.

[0084] The local PC 70 performs processing based on the command H. The user can view and confirm the processing result I on the display 16.

[0085] FIG. 10 is a diagram for explaining such local processing.

[0086] For example, suppose that the user inputs text information A, "move cursor to the left," from the text information input unit 18. In this case, the morpheme analysis unit 22 obtains the morphemes "cursor," "left," and "move."

[0087] The keyword extraction unit 23 refers to the keyword master data 42 and extracts, as keywords, the words obtained by the morphological analysis unit 22 from the words a stored in the keyword master data 42. Among the words a stored in the keyword master data 42 illustrated in Fig. 5, the words a "cursor" and "movement" are extracted as keywords.

[0088] In the score calculation unit 24, the processing attribute code b "04" predetermined for the words a "cursor" and "move" extracted as keywords and the score d "1 point" designated in advance are obtained from the keyword master data 42. Furthermore, the scores d for each processing attribute code b "04" are summed up to calculate the total score E "2 points." See the third line of "Calculate processing attribute score from keywords" i in FIG. 8.

[0089] The first determination unit 25 determines to proceed to the execution of the process attribute corresponding to the process attribute code b having the highest total score E calculated by the score calculation unit 24. In this example, since the process attribute code b is only "04", the process attribute name of the process attribute to be followed is "desktop operation". See the third line of "Subsequent process branches" j in FIG. 8.

[0090] In the second determination unit 26, the process attribute master data 44 is referred to, and it is determined whether or not to use AI for the process attribute “desktop operation” determined by the first determination unit 25 to be subsequent.

[0091] In the processing attribute master data 44, it is specified that AI is not used in the case of "desktop operation" in which the processing attribute code b is "04". Therefore, in this case, the second determination unit 26 determines that AI is not used. Please refer to the third line of "AI to be used in subsequent processing or not to be used" k in FIG. 8.

[0092] When the second determination unit 26 determines not to use AI, the local input input unit 29 creates a command H for the local PC 70. Like the AI ​​input creation unit 27, the local input input unit 29 can also create the command H by abbreviating the text information C indicating the command.

[0093] In response to this, the local PC 70 executes a desktop operation to move the cursor to the left based on the command H "move cursor to the left."

[0094] As described above, the AI ​​usage support device to which the AI ​​usage support method according to the embodiment of the present invention is applied can determine the necessity of inputting a command to the AI ​​by the above-mentioned action. As a result, the user is notified of a command that can be executed without using the AI, and the user can suppress the cost by executing the command on a local PC without using the AI.

[0095] The AI ​​usage support device to which the AI ​​usage support method according to an embodiment of the present invention is applied also makes it possible to prevent vendor lock-in and flexibly determine the optimal AI to which commands should be input from among any AIs by excluding AIs whose services have been discontinued from the list of candidates and adding AIs that have just started new services as new candidates.

[0096] This allows users to always use the appropriate AI according to their commands, for example by selecting and using the highest performance AI at the lowest cost, regardless of whether a service is discontinued or a new service is launched.

[0097] According to the AI ​​usage support device to which the AI ​​usage support method according to the embodiment of the present invention is applied, when inputting a command to the AI, it is possible to generate a command with a small amount of tokens. This allows the user to use the AI ​​while minimizing the costs associated with using the AI. This also reduces the response waiting time of the AI, leading to a significant improvement in the reaction speed of the system.

[0098] Although the best mode for carrying out the present invention has been described above with reference to the attached drawings, the present invention is not limited to such a configuration. Within the scope of the technical idea of ​​the invention defined in the claims, a person skilled in the art may conceive of various modifications and alterations, and it is understood that such modifications and alterations also belong to the technical scope of the present invention. [Explanation of symbols]

[0099] 10 AI usage support device 11 Bus 12 CPU 13 External recording media 14 Recording medium reading unit 16 Display 17 Audio input section 18 Text information input section 20 Memory 21 Text information conversion section 22 Morphological analysis section 23 Keyword Extraction Section 24 Point calculation section 25 First Decision Section 26 Second Decision Section 27 AI Input Creation Department 28 AI input section 29 Local input input section 30 Writable Data Area 40 Storage device 42 Keyword Master Data 44 Processing Attribute Master Data 50 Communications Department 60 Communication Network 70 Local PC 80 AI Engine 100 AI usage support equipment a word A. Text information b Processing attribute code B Audio c Processing attribute name C. Text information d Score D Morphological analysis results E Total score f Processing Attributes Overview F Input g Vocal content G Processing results H command I Processing results U User

Claims

1. A morphological analysis unit that performs morphological analysis on text information representing a command to be executed by an AI (Artificial Intelligence); keyword master data storing a preregistered word, a processing attribute code corresponding to a processing attribute determined in advance for each of the words, and a score designated in advance for the processing attribute code in association with each other; a keyword extraction unit that extracts, from among the words stored in the keyword master data, the words obtained by the morphological analysis as keywords; a score calculation unit that acquires, from the keyword master data, the processing attribute code that is predetermined for the word extracted as the keyword and a score that is predetermined for the processing attribute code, and calculates a total score by summing up the scores for each processing attribute code; a first determination unit that determines to proceed to the execution of a process attribute corresponding to a process attribute code having a high total score calculated by the score calculation unit; a second determination unit that determines whether or not to use an AI for the execution of the processing attribute determined to be performed by the first determination unit, and when it is determined that the AI ​​is to be used, further determines an AI to be used; An AI usage support device equipped with the above.

2. The method further includes storing processing attribute master data in which the processing attribute code is associated with an AI used for executing the processing attribute corresponding to the processing attribute code, The AI ​​usage support device of claim 1, wherein the second decision unit refers to the processing attribute master data to determine whether or not to use AI to execute the processing attribute determined to be subsequent by the first decision unit, and if it is determined that AI is to be used, further determines the AI ​​to be used.

3. The AI ​​usage support device according to claim 1 , further comprising an input creation unit that creates input to the AI ​​by abbreviating the text information when the second decision unit determines that AI should be used.

4. 2. The AI ​​usage support device according to claim 1, further comprising a text information conversion unit that, when the command is input by voice, converts the voice into text information and provides the text information to the morphological analysis unit for the morphological analysis.

5. An AI usage support method implemented by an AI usage support device, The processor of the AI ​​usage support device, A first step of morphologically analyzing text information representing a command to be executed by an AI (Artificial Intelligence); A second step of extracting, as keywords, the words obtained by the morphological analysis from among words prepared in advance; a third step of calculating a total score by summing up the scores for each processing attribute code based on processing attribute codes that are predetermined for the words extracted as the keywords and the scores that are predetermined for the processing attribute codes; a fourth step of determining to proceed to the execution of a process attribute corresponding to the process attribute code having a higher total score; A fifth step of determining whether or not to use AI for the execution of the processing attribute determined to be subsequent, and when it is determined that AI is to be used, determining an AI to be used. A method for assisting in the use of AI.

6. The method for supporting use of AI described in claim 5, wherein the fifth step refers to processing attribute master data in which the processing attribute code and the AI ​​used to execute the processing attribute corresponding to the processing attribute code are stored in association with each other, to determine whether or not to use AI to execute the processing attribute determined to be subsequent, and if it is determined that AI will be used, further determines the AI ​​to be used.

7. The method for assisting in the use of AI according to claim 5, wherein the processor further executes a sixth step of creating an input to the AI ​​by shortening the text information when it is determined in the fifth step that an AI will be used.

8. The processor further performs a seventh step of converting the voice into text information if the command is input by voice; The method for supporting use of AI according to claim 5 , wherein the first step performs morphological analysis on the text information converted in the fifth step.

9. A function to perform morphological analysis of text information that represents commands to be executed by AI (Artificial Intelligence); A function of extracting words obtained by the morphological analysis as keywords from words prepared in advance; a function of calculating a total score by summing up the scores of processing attribute codes, which are predetermined for the words extracted as the keywords and the scores of the processing attribute codes, which are predetermined for the processing attribute codes; determining whether to proceed to the execution of a process attribute corresponding to the process attribute code having a higher total score; A function of determining whether or not to use AI in the execution of the processing attribute determined to be subsequent, and when it is determined that AI is to be used, further determining the AI ​​to be used. A program that causes a processor to realize the above.

10. The function of determining the AI ​​to be used is The program described in claim 9 includes a function of referring to processing attribute master data in which the processing attribute code and an AI used to execute the processing attribute corresponding to the processing attribute code are stored in association with each other, determining whether or not to use an AI to execute the processing attribute determined to be subsequent, and if it is determined that an AI will be used, further determining the AI ​​to be used.

11. When it is determined that AI is to be used, a function of creating input for the AI ​​by abbreviating the text information The program of claim 9 , further implemented by the processor.

12. If the command is input by voice, converting the voice into text information to generate the text information to be morphologically analyzed. The program of claim 9 , further implemented by the processor.

Images