AI support device, AI support method, and program

Abstract

To provide devices, methods, and programs that assist users in using AI. [Solution] The AI ​​support device of the present invention comprises: a morphological analysis unit that performs morphological analysis on text information representing a command to be performed by the AI; keyword master data that stores pre-registered words, processing attribute codes corresponding to pre-determined processing attributes for each word, and pre-specified scores associated with 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 the scores for each processing attribute code; and a first decision unit that determines to proceed to the execution of the processing attribute corresponding to the processing attribute code with the highest total score obtained 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 the necessity of inputting commands to AI such as generative AI (Artificial Intelligence) and determining the optimal AI to which commands should be input.

Background Art

[0002] In recent years, the development of generative AI has been remarkable. As generative AI (hereinafter simply referred to as "AI"), for example, ChatGPT, Microsoft 365 Copilot, Gemini, etc. are known, and new products are also being developed every day.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] These AIs are very convenient, but each product has its own characteristics. In addition, the functions provided for free are generally limited, and some functions are charged. In this case, the fee is determined by the token amount, which is the size of the commands input to the AI.

[0006] Therefore, in order to obtain more appropriate answers from AI while minimizing costs, it is necessary to input commands to the most appropriate AI, using concise language and a small number of tokens, depending on the content of the command. Also, some commands, such as desktop operations, can be performed without using AI, so costs can be reduced by processing such commands locally on the PC without using AI.

[0007] This invention has been made in view of these circumstances, and aims to provide an AI usage support device, an AI usage support method, and a program that support the user's use of AI by determining whether or not it is necessary to issue commands to the AI, determining the optimal AI to issue commands to, and generating commands with a small number of tokens when issuing commands to the AI. [Means for solving the problem]

[0008] To achieve the above objectives, the present invention employs the following measures.

[0009] The first embodiment is an AI usage support device comprising: a morphological analysis unit that performs morphological analysis on text information representing a command to be performed by an AI (Artificial Intelligence); keyword master data that stores pre-registered words, processing attribute codes corresponding to pre-determined processing attributes for each word, and points pre-specified for each processing attribute code in association with each other; 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 obtains pre-determined processing attribute codes and points pre-specified for each processing attribute code from the keyword master data, and calculates a total score by summing the scores for each processing attribute code; a first decision unit that decides to proceed to the execution of the processing attribute corresponding to the processing attribute code with the highest total score obtained by the score calculation unit; and a second decision unit that determines whether or not to use an AI for the execution of the processing attribute that the first decision unit has decided to proceed with, and if it has been determined that an AI should be used, further determines which AI to use.

[0010] The second embodiment is an AI usage support device of the first embodiment, further comprising processing attribute master data which stores processing attribute codes associated with AIs used for executing processing attributes corresponding to the processing attribute codes, the second determination unit refers to the processing attribute master data to determine whether or not to use AI for executing processing attributes that the first determination unit has determined to follow, and if it has determined that AI should be used, it further determines which AI to use.

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

[0012] The fourth embodiment is an AI user support device of the first embodiment, 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 a morphological analysis unit for morphological analysis.

[0013] The fifth aspect is an AI usage support method implemented by an AI usage support device, the method comprising: a first step in which the processor of the AI ​​usage support device performs morphological analysis on text information representing a command to be performed by the AI ​​(Artificial Intelligence); a second step in which the words obtained from the morphological analysis are extracted as keywords from a pre-prepared set of words; a third step in which the processor of the AI ​​usage support device calculates a total score by summing the scores for each processing attribute code based on a processing attribute code predetermined for the extracted keywords and a score predetermined for each processing attribute code; a fourth step in which it is determined to proceed to the execution of the processing attribute corresponding to the processing attribute with the highest total score; and a fifth step in which it is determined whether or not to use AI for the execution of the processing attribute to be followed, and if it is determined that AI should be used, it further determines which AI to use.

[0014] The sixth aspect is an AI usage support method 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 for executing the processing attribute corresponding to the processing attribute code, to determine whether or not to use the AI ​​for executing the subsequent processing attribute, and if it is determined that the AI ​​should be used, further determines which AI to use.

[0015] The seventh aspect is an AI-assisted method of the fifth aspect, wherein the processor further performs a sixth step of creating input to the AI ​​by shortening text information if it is determined by the fifth step to use the AI.

[0016] The eighth aspect is an AI usage support method of the fifth aspect, wherein the processor further performs a seventh step of converting speech to text information when the instruction is input by voice, and the first step is to perform morphological analysis on the text information converted in the fifth step.

[0017] The ninth aspect is a program for a processor to implement the following functions: a function to perform morphological analysis on text information representing a command to be performed by an AI (Artificial Intelligence); a function to extract words obtained from morphological analysis as keywords from a pre-prepared set of words; a function to calculate a total score for each processing attribute code by summing the scores based on a predetermined processing attribute code for the extracted keywords and a predetermined score for each processing attribute code; a function to decide whether to proceed with the execution of the processing attribute corresponding to the processing attribute code with the highest total score; and a function to determine whether or not to use an AI for the execution of the processing attribute to be followed, and if it is determined that an AI should be used, further to determine which AI to use.

[0018] The tenth aspect is a program of the ninth aspect, in which a function for determining which AI to use refers to processing attribute master data that is stored in association with processing attribute codes and AI used for executing processing attributes corresponding to processing attribute codes, determines whether or not to use an AI for executing the subsequent processing attribute, and if it is determined that an AI should be used, further includes a function for determining which AI to use.

[0019] The eleventh aspect is a program of the ninth aspect, which, when it is determined that AI should be used, further enables the processor to create input for AI by shortening text information.

[0020] The twelfth aspect is a program of the ninth aspect, which, when a command is input via speech, further enables the processor to implement a function to convert speech into text information in order to generate text information that will be morphologically analyzed. [Effects of the Invention]

[0021] According to the AI ​​support device, method, and program of the present invention, it is possible to determine whether or not it is necessary to issue commands to the AI. This makes it possible to reduce costs by executing commands on a local PC without using the AI.

[0022] According to the AI usage support device, method, and program of the present invention, it is also possible to determine the optimal AI to which an instruction should be input. As a result, the user can use an appropriate AI according to the instruction.

[0023] Furthermore, according to the AI usage support device, method, and program of the present invention, when inputting an instruction to the AI, it is possible to generate an instruction with a small token amount. As a result, the user can use the AI while suppressing the occurrence of costs related to AI usage as much as possible.

Brief Description of Drawings

[0024] [Figure 1] FIG. is a simplified block diagram illustrating the concept of the functional configuration of a general AI usage support device. [Figure 2] FIG. 2 is a simplified block diagram illustrating the concept of the functional configuration of an AI usage support device to which the AI usage support method according to an embodiment of the present invention is applied. [Figure 3] FIG. 3 is an electronic circuit block diagram showing a configuration example of an AI usage support device according to an embodiment of the present invention. [Figure 4] FIG. 4 is a functional block diagram corresponding to the electronic circuit of the AI usage support device illustrated in FIG. 3. [Figure 5] FIG. 5 is a data structure diagram showing an example of keyword master data. [Figure 6] FIG. 6 is a data structure diagram showing an example of process attribute master data. [Figure 7] FIG. 7 is a table for explaining process attributes. [Figure 8] FIG. 8 is a diagram showing the flow of processing by an AI usage support device to which the AI usage support method according to an embodiment of the present invention is applied. [Figure 9] FIG. 9 is a diagram showing an example of sentence shortening performed by an AI input creation unit. [Figure 10] FIG. 10 is a diagram for explaining local processing. It should be noted that in the above translation, there seems to be an error in the "[[ID=1又]]" in the original text, which is translated as "FIG. 1 and" in the English version. It is recommended to check and correct the original text for a more accurate translation. [Modes for carrying out the invention]

[0025] Embodiments of the present invention will be described below with reference to the drawings. The drawings are schematic or conceptual. In this specification and in each figure, elements similar to those described in previously shown figures are denoted by the same reference numerals, and detailed or redundant explanations are omitted as appropriate.

[0026] First, an overview of the AI ​​user support device to which the AI ​​user support method according to the present invention is applied will be described.

[0027] Figure 1 is a simplified block diagram illustrating the conceptual functional configuration of a typical AI user support device.

[0028] (1) A user U using a typical AI user support device 100 as illustrated in Figure 1 inputs commands that they want the AI ​​to execute into the PC via voice input using the microphone MC.

[0029] (2) The PC converts the voice input into text information for commands to the AI. Specifically, the PC (2-1) converts the voice input into text information and (2-3) generates a script for the AI. As an example, the AI ​​user support device 100 will be described assuming that ChatGPT is used as the AI.

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

[0031] Thus, in a typical AI user support device 100, a fixed AI, such as ChatGPT, is used. In contrast, an AI user support device to which the AI ​​user support method according to the embodiment of the present invention is applied has additional functions that are not present in a typical AI user support device 100, as will be described below.

[0032] Figure 2 is a simplified block diagram illustrating the conceptual functional configuration of an AI user support device to which an AI user support method according to an embodiment of the present invention is applied.

[0033] AI User Support Device 10 is equipped with a subsystem (2-2) that AI User Support Device 100 does not have. Furthermore, the AI ​​to be used is not fixed and can use all AIs that are in service in the world, and can respond to the establishment of new services as well as the discontinuation of services.Therefore, using the subsystem (2-2), AI User Support Device 10 can (a) decide which AI to use from among multiple AIs such as ChatGPT, Microsoft 365 Copilot, and Gemnini according to the content of the command, and (b) generate a script for the determined AI and input it.At this time, the number of tokens can be reduced by generating the script with the shortest possible sentences.In addition, (c) it can also determine that there is no suitable AI to use according to the content of the command.In that case, a script for the AI ​​is not generated, that is, the operation of (2-3) is not performed, and the script for the AI ​​in (3) is not input, and (3-1) screen operation commands are generated by local processing within the PC.

[0034] The specific configuration of the AI ​​user support device 10 that realizes these functions is described below.

[0035] Figure 3 is an electronic circuit block diagram showing an example configuration of an AI user support device according to an embodiment of the present invention.

[0036] Figure 4 is a functional block diagram corresponding to the electronic circuit of the AI ​​user support device illustrated in Figure 3.

[0037] An AI user support device 10 according to an embodiment of the present invention is a device for determining whether or not to issue commands to an AI, such as a generative AI, determining the optimal AI to issue commands to, and generating commands with a small token size when issuing commands to an AI. As illustrated in Figure 3, it comprises a CPU 12 connected to each other by a bus 11, a recording medium reading unit 14, a display 16, an audio input unit 17 including a microphone, a text information input unit 18 including a mouse or keyboard, a memory 20, a storage device 40, and a communication unit 50. Such an AI user support device 10 can be implemented on a PC or a tablet terminal, although this is not an exhaustive description.

[0038] The CPU 12 is a computer that controls the operation of each part of the circuit according to the program stored in the memory 20. As a result, the AI ​​user support device 10 operates with the cooperation of software and hardware, as will be described later.

[0039] Memory 20 stores programs that implement the text information conversion unit 21, morphological analysis unit 22, keyword extraction unit 23, score calculation unit 24, first decision unit 25, second decision unit 26, AI input creation unit 27, AI input input unit 28, and local input input unit 29.

[0040] These programs may be pre-stored in memory 20, or they may be read into memory 20 from an external recording medium 13 such as a memory card via the recording medium reading unit 14. These programs are designed to be unrewritable.

[0041] In addition to the non-rewritable area where such programs are stored, the memory 20 also includes a writable data area 30 for storing rewritable data.

[0042] The storage device 40 consists of, for example, an SSD (Solid State Drive) or an HDD (Hard Disk Drive), and stores keyword master data 42 and processing attribute master data 44.

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

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

[0045] Figure 6 is a data structure diagram showing an example of 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 the "AI to use" e corresponding to the processing attribute code b.

[0047] Next, we will explain the processing attributes.

[0048] Figure 7 is a table illustrating the processing attributes.

[0049] Processing attributes classify and define the operations that users want to perform. As shown in processing attribute name c in Figure 7, they can include, but are not limited to, Power Automate (RPA) operations, MS application operations, screen acquisition instruction operations, desktop operations, browser operations, and resolution processes. Processing attribute code b refers to the code numbers 01, 02, 03, 04, 05, and 80 assigned to these operations. Furthermore, an overview of each of these operations is described in processing attribute overview f in Figure 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 ​​user support device 10 can exchange data with the AI ​​engine 80 via the communication unit 50.

[0051] The AI ​​support device 10 performs the following processes based on text information: determining whether or not it is necessary to issue a command to the AI, determining the optimal AI to issue the command to, and generating a command with a small token size when issuing a command to the AI.

[0052] The text information input unit 18 is a part for the user to input text information for this purpose. The user inputs the content they want to perform using the AI ​​as text information A from the text information input unit 18, which may include a mouse or keyboard, for example.

[0053] On the other hand, with the AI ​​user support device 10, users can input information by voice, for example, through the voice input unit 17, which is 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 a technology such as that disclosed in Patent Document 1. This allows users who have difficulty operating a mouse or keyboard due to hand disabilities, users who cannot use their hands while working at a construction site, or users who cannot use their hands while cooking to input the necessary information into the AI ​​user support 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 23.

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

[0056] The score calculation unit 24 obtains the pre-specified processing attribute code b and score d for the word a extracted as a keyword from the keyword master data 42. Then, it calculates the total score E by summing the scores d for each processing attribute code b.

[0057] The first decision unit 25, based on the total score E for each processing attribute code b obtained by the score calculation unit 24, decides to proceed with the execution of the processing attribute corresponding to the processing attribute code b with the highest total score.

[0058] The second decision unit 26 refers to the processing attribute master data 44 and determines whether or not to use AI for the execution of the processing attribute that the first decision unit 25 has decided to follow. If it determines that AI should be used, it further determines which AI to use.

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

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

[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 28.

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

[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 text information A or text information C, and has the local PC 70 execute the command. The local PC 70 is the PC on which the AI ​​user support device 10 is implemented. Command H is also created by shortening text information A or text information C.

[0064] On the local PC 70, processing is carried out based on instruction H. The user can view and confirm the result I of this processing on the display 16.

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

[0066] Figure 8 shows the processing flow by an AI user support device to which the AI ​​user support method according to an embodiment of the present invention is applied.

[0067] For example, as illustrated in the second row of Figure 8, let's consider the case where the user gives a command to the AI ​​by voice, saying "Sort column C of Excel in descending order" through the voice input unit 17.

[0068] The spoken content g from voice B input from the voice input unit 17 is converted by the text information conversion unit 21 into text information C, which reads, "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. Please refer to the second line of "Japanese morphological analysis" h in Figure 8.

[0070] In the keyword extraction unit 23, the keyword master data 42 is referenced, and the words obtained by the morphological analysis unit 22 from among the words a stored in the keyword master data 42 are extracted as keywords. The keyword master data 42 exemplified in Figure 5 contains the words a "Excel", "cursor", "move", "screen", and "click". Of 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 predetermined processing attribute code b, "02", and the predetermined score d, "1 point", are obtained from the keyword master data 42 for the extracted keyword word a, "Excel". Furthermore, the score d is summed up for each processing attribute code b "02", and a total score E "1 point" is calculated. Please refer to the second row of "Calculation of processing attribute score from keyword" i in Figure 8.

[0072] In the first decision unit 25, it is decided to proceed to the execution of the processing attribute corresponding to the processing attribute code b with the highest total score E obtained by the score calculation unit 24. In this example, since the processing attribute code b is only "02", the processing attribute name of the subsequent processing attribute will be "MS application operation". Please refer to the second line of "Subsequent processing branches" j in Figure 8.

[0073] In the second decision unit 26, the processing attribute master data 44 is referenced, and it is determined whether or not to use AI for the processing attribute "MS application operation" which was determined by the first decision unit 25 to be the next step. If it is determined that AI should be used, the AI ​​to be used is then determined.

[0074] The processing attribute master data 44 specifies that the AI ​​used for "MS application operation" with processing attribute code b "02" is "Copilot". Therefore, in this case, the second decision unit 26 decides to use the AI ​​"Copilot". Please refer to the second line of "AI to use or not to use in subsequent processing" k in Figure 8.

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

[0076] Figure 9 shows an example of a shortened text created by the AI ​​input generation unit.

[0077] For example, as illustrated in Figure 9, the AI ​​input creation unit 27 can shorten text information A, which consists of 142 characters, such as "Um, well, I have a favor to ask. I'd like you to teach me how to do conditional branching in Excel. Specifically, could you use the numbers in cells A1 and B1 as an example? And, well, I'd like you to set a function in cell C1, but I don't know how to do it. Could you do it for me?", to create input F, which consists of 53 characters, such as "Teach me how to do conditional branching in Excel. Show me an example using the numbers in cells A1 and B1 and setting a function in cell C1." In this case, the text has been shortened to about one-third of its original length.

[0078] The AI ​​input creation unit 27 can use existing character compression techniques, such as those disclosed in Non-Patent Document 1, for such shortening purposes.

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

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

[0081] The AI ​​engine 80 performs 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, since the input F provided to the AI ​​is shortened, the amount of tokens can be reduced, thereby lowering the cost of using the AI. Furthermore, shortening the input F also reduces the waiting time for responses from the AI, making it possible to improve response speed.

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

[0084] On the local PC70, processing is carried out based on instruction H. The user can view and confirm the processing result I on the display 16.

[0085] Figure 10 is a diagram illustrating this type of local processing.

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

[0087] In the keyword extraction unit 23, the keyword master data 42 is referenced, and words obtained by the morphological analysis unit 22 are extracted as keywords from among the words a stored in the keyword master data 42. Among the words a stored in the keyword master data 42 as illustrated in Figure 5, the words a "cursor" and "movement" are extracted as keywords.

[0088] In the score calculation unit 24, the pre-determined processing attribute code b, "04", and the pre-specified score d, "1 point", are obtained from the keyword master data 42 for the extracted keyword words a, "cursor" and "move". Furthermore, the score d is summed up for each processing attribute code b "04", and a total score E "2 points" is calculated. Please refer to the third line of "Calculation of processing attribute score from keyword" i in Figure 8.

[0089] In the first decision unit 25, it is decided to proceed to the execution of the processing attribute corresponding to the processing attribute code b with the highest total score E obtained by the score calculation unit 24. In this example, since the processing attribute code b is only "04", the processing attribute name of the subsequent processing attribute will be "Desktop Operation". See the third line of "Subsequent processing branches" j in Figure 8.

[0090] In the second decision unit 26, the processing attribute master data 44 is referenced, and a determination is made as to whether or not to use AI for the processing attribute "desktop operation" that was determined to follow by the first decision unit 25.

[0091] The processing attribute master data 44 specifies that AI should not be used when the processing attribute code b is "04", which corresponds to "desktop operation". Therefore, in this case, the second decision unit 26 decides not to use AI. Please refer to the third line of "AI to be used or not used in subsequent processing" k in Figure 8.

[0092] If the second decision unit 26 determines that AI will not be used, the local input input unit 29 creates an instruction H for the local PC 70. The local input input unit 29, like the AI ​​input creation unit 27, can also create instruction H by shortening the text information C that indicates the instruction.

[0093] In response, the local PC70 performs a desktop operation that moves the cursor to the left based on the command H, which is "move cursor to the left".

[0094] As described above, an AI user support device to which the AI ​​user support method according to an embodiment of the present invention is applied can determine whether or not it is necessary to issue commands to the AI ​​through the above-described operation. As a result, for commands that can be executed without using the AI, the user is notified accordingly, and the user can reduce costs by executing the commands on a local PC without using the AI.

[0095] According to an AI usage support device to which the AI ​​usage support method according to an embodiment of the present invention is applied, vendor lock-in can be prevented, and the optimal AI to which commands should be issued can be flexibly determined from among any AI by excluding AIs whose services have been discontinued from candidates and adding AIs whose services have been newly started as new candidates.

[0096] This means that regardless of service discontinuation or the launch of new services, users will always be able to use the appropriate AI according to their commands, for example, by selecting and using the high-performance AI at the lowest cost.

[0097] According to an AI user support device to which the AI ​​user support method according to an embodiment of the present invention is applied, it is possible to generate commands with a small number of tokens when inputting commands to the AI. This makes it possible for users to use the AI ​​while minimizing the costs associated with using the AI. This also reduces the AI's response waiting time and leads to a significant improvement in the system's response speed.

[0098] The best mode for carrying out the present invention has been described above with reference to the accompanying drawings, but the present invention is not limited to this configuration. Within the scope of the invented technical idea of ​​the claims, a person skilled in the art can conceive of various modifications and alterations, and it is understood that such modifications and alterations also fall within 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 displays 17. Voice input section 18 Text Information Input Section 20 memory 21 Text Information Conversion Unit 22 Morphological analysis section 23 Keyword Extraction Section 24 Point calculation section 25. First Decision Section 26. Second Decision Section 27 AI Input Creation Section 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 Networks 70 Local PC 80 AI Engines 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 performs morphological analysis on text information representing commands that you want the AI ​​(Artificial Intelligence) to execute, Keyword master data stored by associating pre-registered words, processing attribute codes corresponding to pre-determined processing attributes for each word, and points pre-specified for each processing attribute code, A keyword extraction unit extracts words obtained from the morphological analysis from the words stored in the keyword master data as keywords. A score calculation unit obtains a predetermined processing attribute code for each keyword extracted from the keyword master data, and a predetermined score for each processing attribute code, and calculates a total score by summing the scores for each processing attribute code. A first determination unit determines that the execution of the processing attribute corresponding to the processing attribute code with the highest total score obtained by the score calculation unit proceeds, The first decision unit determines whether or not to use AI for the execution of the processing attribute that is to be followed, and if it is determined that AI should be used, the second decision unit further determines which AI to use. An AI user support device equipped with the necessary features.

2. The system further comprises a processing attribute master data in which the processing attribute code and the AI ​​used for executing the processing attribute corresponding to the processing attribute code are stored in association, The AI ​​usage support device according to claim 1, wherein the second determination unit refers to the processing attribute master data to determine whether or not to use AI for the execution of the processing attribute determined by the first determination unit to follow, and if it is determined that AI should be used, it further determines which AI to use.

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

4. The AI ​​user 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 morphological analysis.

5. An AI usage support method implemented by an AI usage support device, The processor of the AI ​​user support device The first step involves morphological analysis of text information representing the commands that you want the AI ​​(Artificial Intelligence) to execute, The second step involves extracting words obtained from the morphological analysis from a pre-prepared list of words as keywords. A third step involves calculating a total score by summing the scores for each processing attribute code, based on a predetermined processing attribute code for the extracted keyword and a predetermined score for the processing attribute code. The fourth step is to decide to proceed to the execution of the processing attribute corresponding to the processing attribute code with the highest total score, The fifth step involves determining whether or not to use AI for the execution of the subsequent processing attributes, and if it is determined that AI should be used, then determining which AI to use. A method for supporting the use of AI to perform this task.

6. The fifth step is to refer to processing attribute master data in which the processing attribute code and the AI ​​used for executing the processing attribute corresponding to the processing attribute code are stored in association, to determine whether or not to use an AI for executing the subsequent processing attribute, and if it is determined that an AI should be used, to further determine which AI to use, the AI ​​usage support method according to claim 5.

7. The AI ​​usage support method according to claim 5, wherein the processor determines in the fifth step that it is necessary to use the AI, and further performs a sixth step of creating input to the AI ​​by shortening the text information.

8. If the instruction is input via voice, the processor further performs a seventh step of converting the voice into text information. The AI ​​support method according to claim 5, wherein the first step is to perform morphological analysis on the text information converted in the fifth step.

9. A function that performs morphological analysis on text information representing commands that you want the AI ​​(Artificial Intelligence) to execute, A function to extract words obtained from the morphological analysis described above as keywords from a pre-prepared list of words, A function to calculate a total score by summing the scores for each processing attribute code, based on a predetermined processing attribute code for each word extracted as a keyword and a predetermined score for each processing attribute code. A function that determines to proceed to the execution of the processing attribute corresponding to the processing attribute code with the highest total score, The system determines whether or not to use AI for the execution of the subsequent processing attributes, and if it determines that AI should be used, it further determines which AI to use. A program to implement this on the processor.

10. The function that determines which AI to use is: The program according to claim 9, further comprising a function that refers to processing attribute master data stored in association with the processing attribute code and the AI ​​used for executing the processing attribute corresponding to the processing attribute code, to determine whether or not to use AI for executing the subsequent processing attribute, and if it is determined that AI should be used, to determine which AI to use.

11. If it is determined that AI should be used, a function is created to create input for the AI ​​by shortening the text information. Furthermore, the program according to claim 9 is implemented in the processor.

12. If the command is input via voice, a function is provided to convert the voice into text information in order to generate the text information to be morphologically analyzed. Furthermore, the program according to claim 9 is implemented in the processor.

Images