Processing device

Abstract

To solve the problem in which it may be difficult to appropriately perform modifications or other processing on portions of text data output by a trained model.SOLUTION: A processing device has a segmentation processing unit that divides text data output by an LLM (Large Language Model) into one or more texts, and an instruction processing unit that executes processing corresponding to instructions on a text-by-text basis, on the basis of instructions for each text segmented by the segmentation processing unit.SELECTED DRAWING: Figure 9

Description

[Technical Field]

[0001] The present invention relates to a processing device, a processing method, and a program. [Background technology]

[0002] Techniques using trained models such as large-scale language models are known.

[0003] For example, Patent Document 1 describes a question-answering system capable of outputting an answer in response to an input of a question. According to Patent Document 1, if the relevance associated with one or more answer statements in response to the question does not satisfy a predetermined condition, the system inputs the question received in a question receiving step as input data into a large-scale language model. Then, the system transmits the answer statement output in response to the input to a user terminal. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 7486863 Summary of the Invention [Problem to be solved by the invention]

[0005] There are cases where a user desires to perform predetermined processing on a portion of an answer, such as changing a portion of an answer from a large-scale language model. However, with the technology described in Patent Document 1, even if a user desires to change only a portion, it can be difficult to achieve processing on only a portion, as asking the question again can change portions other than the portion desired to be changed. Thus, there has been a problem in that it can be difficult to perform processing, such as changing, on a portion of sentence data output by a trained model such as a large-scale language model.

[0006] Therefore, one object of the present disclosure is to provide a processing device, a processing method, and a program that can solve the above-mentioned problems. [Means for solving the problem]

[0007] To achieve this purpose, the processing device of the present disclosure comprises: a segmentation processing unit that segments the text data output by the LLM (Large Language Model) into one or more texts; an instruction processing unit that executes processing according to instructions for each text segmented by the segmentation processing unit; have The structure is as follows.

[0008] In addition, the processing method in the present disclosure includes: The information processing device The text data output by the LLM (Large Language Model) is divided into one or more texts, According to the instructions for each divided text, the processing according to the instructions is performed on a text-by-text basis. The structure is as follows.

[0009] In addition, the program in this disclosure In the information processing device, The text data output by the LLM (Large Language Model) is divided into one or more texts, According to the instructions for each divided text, the processing according to the instructions is performed on a text-by-text basis. It is a program for realizing the processing. [Effects of the Invention]

[0010] According to the configurations described above, it becomes possible to perform processing such as modifying part of the sentence data output by the trained model. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an overview of a processing system. [Figure 2] FIG. 2 is a block diagram showing an example of the configuration of a processing device. [Figure 3] FIG. 10 is a diagram illustrating an example of information included in processing icon information. [Figure 4] FIG. 10 is a diagram illustrating another example of information included in the processing icon information. [Figure 5] FIG. 1 is a diagram illustrating an outline of processing by a processing device. [Figure 6] 10 is a flowchart illustrating an example of the operation of the processing device. [Figure 7] 10 is a flowchart illustrating an example of the operation of the processing device. [Figure 8] FIG. 2 is a diagram illustrating an example of a hardware configuration of a second processing device according to the present disclosure. [Figure 9] FIG. 2 is a block diagram showing an example of the configuration of a processing device. [Figure 10] 10 is a flowchart illustrating an example of the operation of the processing device. DETAILED DESCRIPTION OF THE INVENTION

[0012] [First embodiment] An example configuration of a processing system 100 in the present disclosure will be described with reference to FIGS. 1 to 7. FIG. 1 is a diagram for explaining an overview of the processing system 100. FIG. 2 is a block diagram showing an example configuration of a processing device 200. FIGS. 3 and 4 are diagrams showing an example of information included in processing icon information 241. FIG. 5 is a diagram showing an overview of processing by the processing device 200. FIGS. 6 and 7 are flowcharts showing an example operation of the processing device 200. Note that in the present disclosure, the drawings may be associated with one or more embodiments.

[0013] This disclosure describes a processing system 100 that performs predetermined preprocessing on text data output by a trained model such as an LLM (Large Language Model) and then outputs the data. As will be described later, when the processing system 100 acquires text data output by a model such as an LLM, it divides the acquired text data into one or more texts. The processing system 100 then assigns a predetermined icon to each of the divided texts to instruct processing on a text-by-text basis, and outputs the resulting text. For example, with this configuration, the processing system 100 can perform text-by-text processing on the text to which the icon is assigned, in response to an operation on the icon, etc.

[0014] As described above, the processing system 100 is configured to be able to execute processing according to instructions for each divided text on a text-by-text basis in response to instructions for each divided text. Note that instructions for each divided text may be given by a method other than using icons. For example, the processing system 100 may be configured to display a list of instructions in response to a predetermined operation such as right-clicking on the divided text. Furthermore, the processing system 100 may be configured to accept dragging operations and the like on the divided text.

[0015] For example, FIG. 1 shows an example of how text data representing a travel plan output by an LLM may be divided into one or more texts based on the destinations or time periods included in the travel plan. In the example shown in FIG. 1, the processing system 100 assigns a group of icons 300, including a regeneration icon for instructing the regeneration of the text, a delete icon for instructing the deletion of the text, position change icons such as an up icon and a down icon for instructing the repositioning of the text, a favorite icon for instructing the registration of the text to favorites, and a confirm icon for instructing the provisional confirmation of the text. In this manner, the processing system 100 may assign multiple icons for different operations to each of the divided texts. The processing system 100 may assign only some of the icons listed above, or may assign icons other than those listed above. The configuration of the processing system 100 will be described in more detail below.

[0016] As shown in Fig. 1, the processing system 100 includes a processing device 200, which is an information processing device that performs preprocessing such as segmentation and icon assignment on text data output by a trained model such as an LLM, and outputs the data, and the trained model such as an LLM. For example, in the case of Fig. 1, an information processing device having a trained model such as an LLM exists outside the processing device 200. However, the trained model such as an LLM may be included in the processing device 200.

[0017] The processing device 200 is an information processing device that performs a segmentation process to segment text data output by the LLM into one or more texts. Furthermore, the processing device 200 can execute processing according to instructions for each segmented text on a text-by-text basis. FIG. 2 shows an example of the main configuration of the processing device 200. Referring to FIG. 2, the processing device 200 has, as its main components, an operation input unit 210, a screen display unit 220, a communication interface unit 230, a storage unit 240, and an arithmetic processing unit 250, for example.

[0018] 2 illustrates an example in which the functions of the processing device 200 are realized using one information processing device. However, at least some of the functions of the processing device 200 may be realized using a plurality of information processing devices, for example, on the cloud. Furthermore, the processing device 200 may not include some of the components illustrated above, such as not having the operation input unit 210 or the screen display unit 220, or may have a configuration other than those illustrated above.

[0019] The operation input unit 210 is made up of operation input devices such as a keyboard, a mouse, etc. The operation input unit 210 detects operations of the operator who operates the processing device 200 and outputs the operations to the arithmetic processing unit 250.

[0020] The screen display unit 220 is composed of a screen display device such as a liquid crystal display, an organic EL (electro-luminescence) display, etc. The screen display unit 220 can display various information stored in the storage unit 240 on the screen in response to instructions from the arithmetic processing unit 250.

[0021] The communication interface unit 230 is composed of a data communication circuit, etc. The communication interface unit 230 performs data communication with an external device connected via a communication line.

[0022] The storage unit 240 is a storage device such as a hard disk or memory. The storage unit 240 stores processing information and programs 242 required for various processes in the arithmetic processing unit 250. The programs 242 are read into the arithmetic processing unit 250 and executed to realize various processing units. The programs 242 are read in advance from an external device or recording medium via a data input / output function such as the communication interface unit 230, and are stored in the storage unit 240. Main information stored in the storage unit 240 includes, for example, processing icon information 241.

[0023] The processing icon information 241 includes information about icons to be assigned to each piece of text obtained by dividing the sentence data output from the LLM. In other words, the processing icon information 241 includes information corresponding to each preprocessing performed by the processing device 200. The processing icon information 241 is acquired in advance by means of accepting input using the operation input unit 210, accepting information from an external device via the communication interface unit 230, or the like, and is stored in the storage unit 240.

[0024] FIG. 3 shows an example of the processing icon information 241. Referring to FIG. 3, the processing icon information 241 associates, for example, icon information with processing content information. Here, the icon information may include information for identifying the icon, such as the icon name or identifier. The icon information may also include information indicating the shape or color of the icon. Furthermore, the processing content information indicates the content of the processing to be executed in response to an operation, such as a click, being performed on the related icon. For example, the first line in FIG. 3 indicates that an instruction to regenerate text is to be given to the LLM in response to an operation on the related icon.

[0025] 3, the processing icon information 241 includes information corresponding to a regeneration icon instructing the regeneration of text, a delete icon instructing the deletion of text, position change icons such as a move up icon and a move down icon instructing the reposition of text, a favorites icon instructing the registration of favorites, and a confirm icon instructing the provisional confirmation of text. However, the information included in the processing icon information 241 is not limited to the example shown in FIG. 3. For example, the processing icon information 241 may include at least some of the information shown in FIG. 4 instead of or in addition to at least some of the information shown in FIG. 3. For example, FIG. 4 illustrates an example of a concretization icon instructing the output of more detailed information about a portion of the content of the text, a question icon for searching or asking questions to LLMs or the like about the content of the text, a reservation icon for checking availability or making a reservation, a save icon instructing the temporary saving of text, a compare icon instructing the comparison of text with other text, an add icon for adding a portion of another proposal, and a possibility exploration icon for exploring possibilities. The processing icon information 241 may include at least some of the information corresponding to the icons exemplified in Figures 3 and 4, or may include information about icons other than those exemplified in Figures 3 and 4 that are used to instruct processing on a text-by-text basis.

[0026] The arithmetic processing unit 250 includes an arithmetic device such as a CPU (Central Processing Unit) and its peripheral circuits. The arithmetic processing unit 250 reads and executes a program 242 from the storage unit 240, thereby causing the hardware and the program 242 to cooperate to realize various processing units. Major processing units realized by the arithmetic processing unit 250 include, for example, an instruction processing unit 251, a receiving unit 252, a natural language processing unit 253, a visualization unit 254, a processing icon assignment unit 255, and an output unit 256. Among the above-mentioned processing units, the natural language processing unit 253 and the visualization unit 254 function as segmentation processing units that segment sentence data output from the LLM into one or more texts. In other words, the arithmetic processing unit 250 reads and executes the program 242, thereby realizing the natural language processing unit 253 and the visualization unit 254 that function as segmentation processing units that segment sentence data into one or more texts.

[0027] The instruction processing unit 251 performs processing in accordance with the received instruction or operation. The instruction processing unit 251 may receive the instruction or operation by receiving an input using the operation input unit 210, by receiving information from an external device via the communication interface unit 230, or the like.

[0028] For example, the instruction processing unit 251 acquires a question or any other prompt for the LLM, etc. Then, the instruction processing unit 251 inputs the acquired question, prompt, etc. to the LLM, etc.

[0029] Furthermore, the instruction processing unit 251 accepts an operation on an icon. Then, in response to the accepted operation on the icon, the instruction processing unit 251 performs processing corresponding to the operated icon on the text to which the icon is attached.

[0030] For example, in response to an operation on a regeneration icon, the instruction processing unit 251 instructs the LLM to regenerate a corresponding portion of text. Furthermore, the instruction processing unit 251 deletes corresponding text in response to an operation on a delete icon, or swaps the position of corresponding text with the position of other text in response to an operation on a position change icon. Furthermore, the instruction processing unit 251 can access an external device such as a reservation system in response to an operation on a question icon, a reservation icon, or the like. In response to an operation on a question icon, a reservation icon, or the like, the instruction processing unit 251 may perform predetermined processing, such as searching an external database or checking a database to confirm availability or inventory. For example, as described above, the instruction processing unit 251 can execute or instruct processing corresponding to an icon for each divided piece of text data, such as a travel plan, output by the LLM, in response to an operation on an icon.

[0031] The instruction processing unit 251 may accept instructions for each divided text using a method other than the method using icons. For example, the instruction processing unit 251 may be configured to display a list of instructions corresponding to each icon, etc., in response to a predetermined operation, such as right-clicking on the divided text using the operation input unit 210. In this case, the instruction processing unit 251 can accept instructions by accepting a selection from the displayed list using the operation input unit 210. The instruction processing unit 251 may also be configured to accept a drag operation, etc., on the divided text.

[0032] The receiving unit 252 receives text data output by the LLM from the LLM. For example, the receiving unit 252 can receive text data in response to an input to the LLM, such as a question from the instruction processing unit 251.

[0033] The natural language processing unit 253 divides the text data into one or more texts by performing natural language processing on the text data received by the receiving unit 252. For example, the natural language processing unit 253 performs at least some of morphological analysis, syntactic analysis, semantic analysis, contextual analysis, etc. Then, the natural language processing unit 253 divides the text data into one or more texts according to the results of the processing.

[0034] For example, the natural language processing unit 253 can divide the text data by period or paragraph. The natural language processing unit 253 may also divide the text data into one or more texts based on the results of analyzing the meaning of the text. For example, the natural language processing unit 253 can divide the text data indicating a travel plan output by the LLM based on the destinations or time periods included in the travel plan. As an example, the natural language processing unit 253 may divide the text data by destinations, such as tourist spots, or by predetermined time slots, such as morning and afternoon. The natural language processing unit 253 may divide the text data into one or more texts using any method other than those exemplified above.

[0035] The visualization unit 254 performs a predetermined visualization process so that each piece of text divided by the natural language processing unit 253 can be displayed in a form that can be confirmed by the user. For example, the visualization unit 254 can number each piece of divided text or add an icon indicating the order so that it can be confirmed that each piece of text is independent. The visualization unit 254 may also add a bullet or a middle dot or insert a space at the beginning of each piece of text.

[0036] For example, as described above, the visualization unit 254 performs a predetermined visualization process on the segmentation result by the natural language processing unit 253. Note that the visualization unit 254 may perform visualization processes other than those exemplified above. For example, the visualization unit 254 may manipulate the spacing between each piece of text when displaying sentence data segmented into one or more pieces of text.

[0037] The processing icon assigning unit 255 assigns a predetermined icon to each of the divided texts to instruct processing on a text-by-text basis. For example, the processing icon assigning unit 255 can assign at least some of the icons included in the processing icon information 241 to each of the divided texts. In other words, the processing icon assigning unit 255 can assign a plurality of icons indicating different processing contents to each of the divided texts.

[0038] For example, as shown in Fig. 1, the processing icon assigning unit 255 assigns an icon corresponding to each divided text next to each divided text. In other words, when displaying each divided text, the processing icon assigning unit 255 assigns the icon so that the assigned icon can be displayed near the same line as the corresponding text. The processing icon assigning unit 255 may assign the icon in a manner other than the manner exemplified in Fig. 1, such as assigning an icon between each piece of text.

[0039] The types and numbers of icons assigned by the processing icon assigning unit 255 may be the same for each divided text or may be different. For example, the processing icon assigning unit 255 may be configured to determine the type of icon to assign depending on the content of each text, which can be determined depending on the result of natural language processing by the natural language processing unit 253. The processing icon assigning unit 255 may also determine the type of icon to assign depending on any condition other than those exemplified above, such as whether processing on a text-by-text basis has been executed.

[0040] The output unit 256 outputs sentence data consisting of each piece of text to which an icon has been assigned by the processing icon assigning unit 255. For example, the output unit 256 can output sentence data to which a group of icons 300 such as that illustrated in Fig. 1 has been assigned. The output unit 256 may display the data such as that illustrated above on the screen display unit 220, or may transmit the data to an external device via the communication interface unit 230.

[0041] The above is an example configuration of the processing device 200. With the above configuration, as shown in FIG. 5, the processing device 200 can acquire text data from a trained model such as an LLM, divide the acquired text data, and assign an icon to each segment of the text. The processing device 200 can then output text data consisting of text to which icons have been assigned. As a result, a user who has confirmed the output can perform any operation, such as clicking on an assigned icon, as necessary. This allows the processing device 200 to perform processing on the text to which the manipulated icon has been assigned, in accordance with the manipulated icon. In this case, the processing device 200 may check availability or inventory, or perform any search processing, by accessing an external system, in accordance with the manipulated icon.

[0042] The configuration of the processing device 200 may be other than that exemplified in Fig. 2. For example, the processing device 200 may have only a part of the configuration exemplified in Fig. 2, such as not including the visualization unit 254. For example, the function of the division processing unit may be realized by the natural language processing unit 253 or any other processing unit that divides text data into multiple units. Furthermore, the processing device 200 may have any configuration other than that exemplified in Fig. 2.

[0043] Next, an example of the operation of the processing device 200 will be described with reference to Fig. 6 and Fig. 7. First, an example of the operation of the processing device 200 when text data is acquired from a trained model such as an LLM will be described with reference to Fig. 6.

[0044] 6 is a flowchart showing an example of the operation of the processing device 200 when text data is acquired from a trained model such as an LLM. Referring to FIG. 6, the receiving unit 252 receives the text data output by the LLM from the LLM (step S101).

[0045] The natural language processing unit 253 performs natural language processing on the text data received by the receiving unit 252, thereby dividing the text data into one or more texts (step S102). For example, the natural language processing unit 253 performs at least a part of morphological analysis, syntactic analysis, semantic analysis, contextual analysis, etc. Then, the natural language processing unit 253 divides the text data into one or more texts according to the results of the processing.

[0046] The visualization unit 254 performs a predetermined visualization process so that each piece of text divided by the natural language processing unit 253 can be displayed in a form that can be confirmed by the user (step S103). For example, the visualization unit 254 can number each piece of divided text or add an icon indicating the order so that it can be confirmed that each piece of text is independent. The visualization unit 254 may also add a bullet or a middle dot or insert a space at the beginning of each piece of text.

[0047] The processing icon assigning unit 255 assigns a predetermined icon to each of the divided texts to instruct processing for each text (step S104). For example, the processing icon assigning unit 255 can assign at least a part of the icons included in the processing icon information 241 to each of the texts.

[0048] The output unit 256 outputs sentence data consisting of each text to which an icon has been assigned by the processing icon assigning unit 255 (step S105). For example, the output unit 256 can output sentence data to which an icon group 300 such as that illustrated in FIG.

[0049] The above is an example of the operation of the processing device 200 when text data is acquired from a trained model such as an LLM. Note that the operation of the processing device 200 when text data is acquired may be other than the example shown in FIG. 6. For example, the processing device 200 may omit the processing of step S103. Next, with reference to FIG. 7, an example of the operation of the processing device 200 when an operation on an icon assigned to output text data is accepted will be described.

[0050] 7 is a flowchart showing an example of the operation of the processing device 200 when an operation on an icon assigned to output text data is accepted. Referring to Fig. 7, the instruction processing unit 251 accepts an operation on an icon in response to accepting an input using the operation input unit 210, accepting information from an external device via the communication interface unit 230, etc. (step S201).

[0051] In response to the operation on the accepted icon, the instruction processing unit 251 performs processing corresponding to the operated icon on the text to which the icon on which the operation is accepted is assigned (step S202).

[0052] The above is an example of the operation of the processing device 200 when an operation on an icon added to output text data is received.

[0053] As described above, the processing device 200 includes a segmentation processing unit including the natural language processing unit 253 and the like, and a processing icon assigning unit 255. With this configuration, the processing icon assigning unit 255 can assign a predetermined icon to each piece of text segmented by the segmentation processing unit to instruct processing on a text-by-text basis. This allows the processing device 200 to perform processing corresponding to the operated icon on the text to which the operated icon is assigned, in accordance with an operation on the assigned icon. As a result, the processing device 200 can appropriately perform processing such as modification on part of the sentence data output by a trained model such as an LLM.

[0054] The processing device 200 also includes an instruction processing unit 251. With this configuration, the instruction processing unit 251 can perform processing corresponding to the operated icon on the text to which the icon for which the operation was received is assigned, in response to an operation on the received icon. That is, with the above configuration, the instruction processing unit 251 can execute processing according to the instruction on a text-by-text basis. As a result, the processing device 200 can appropriately perform processing such as changing part of the sentence data output by the trained model.

[0055] Furthermore, the segmentation processing unit of the processing device 200 is composed of a natural language processing unit 253 and a visualization unit 254. With this configuration, the visualization unit 254 can perform a predetermined visualization process so that each piece of text segmented by the natural language processing unit 253 can be displayed in a form that can be confirmed by the user. This allows the processing device 200 to perform visualization processing and then assign an icon. As a result, the processing device 200 can output text data in a state in which the text to be processed by operating the icon can be more easily confirmed, and can more appropriately perform processing such as changing part of the text data output by the trained model.

[0056] The processing device 200 described in this disclosure can be applied to various situations in which text data is received as output from an LLM. For example, the processing device 200 can be applied when an LLM generates and outputs a travel itinerary based on input. In addition to travel itineraries, the processing device 200 can also be applied when an LLM outputs blog posts, novels or other reading material, business plans or proposals, emails or letters, reviews, arbitrary reports, or any other arbitrary text data.

[0057] [Second embodiment] Next, a processing device 400, which is a modified example of the processing device 200, will be described with reference to Fig. 8 to Fig. 10. Fig. 8 is a diagram showing an example of the hardware configuration of the processing device 400, which is a second processing device in the present disclosure. Fig. 9 is a block diagram showing an example of the configuration of the processing device 400. Fig. 10 is a flowchart showing an example of the operation of the processing device 400.

[0058] The processing device 400 is an information processing device that performs preprocessing such as segmentation and icon assignment on sentence data output by a trained model such as LLM, and outputs the data. Fig. 8 shows an example of the hardware configuration of the processing device 400. Referring to Fig. 8, the processing device 400 has, as an example, the following hardware configuration. ·CPU(Central Processing Unit)401(Arithmetic unit) ROM (Read Only Memory) 402 (storage device) RAM (Random Access Memory) 403 (storage device) Programs 404 loaded into RAM 403 A storage device 405 for storing the program group 404 A drive device 406 that reads and writes data from a recording medium 410 outside the information processing device A communication interface 407 for connecting to a communication network 411 outside the information processing device Input / output interface 408 for inputting and outputting data Bus 409 connecting each component

[0059] 9 by the CPU 401 acquiring the program group 404 and executing it. The program group 404 is stored in advance in the storage device 405 or the ROM 402, for example, and is loaded into the RAM 403 or the like by the CPU 401 for execution as needed. The program group 404 may be supplied to the CPU 401 via the communication network 411, or may be stored in advance in the recording medium 410, and the drive device 406 may read out the program and supply it to the CPU 401.

[0060] 8 shows an example of the hardware configuration of the processing device 400. The hardware configuration of the processing device 400 is not limited to the above-described case. For example, the processing device 400 may be configured with only a part of the above-described configuration, such as excluding the drive device 406. Furthermore, the CPU 401 may be a GPU or the like exemplified in the first embodiment.

[0061] The division processing unit 421 divides the text data output by the LLM into one or more texts. The division processing unit 421 may perform the division using any method, such as dividing the text data according to the results of natural language processing.

[0062] The instruction processing unit 422 executes processing according to the instruction for each text unit in response to the instruction for each piece of text divided by the division processing unit 421. For example, the instruction processing unit 422 may execute processing according to the instruction in response to an operation on an icon previously assigned to each piece of text.

[0063] The above is an example of the configuration of the processing device 400. Next, an example of the operation of the processing device 400 will be described with reference to FIG.

[0064] Fig. 10 is a flowchart showing an example of the operation of the processing device 400. Referring to Fig. 10, the division processing unit 421 divides the text data output by the LLM into one or more texts (step S301).

[0065] The instruction processing unit 422 executes processing according to the instruction for each text divided by the division processing unit 421, on a text-by-text basis (step S302).

[0066] The above is an example of the operation of the processing device 400.

[0067] As described above, the processing device 400 includes the segmentation processing unit 421 and the instruction processing unit 422. With this configuration, the instruction processing unit 422 can execute processing according to the instruction for each text unit segmented by the segmentation processing unit 421. This allows the processing device 400 to appropriately perform processing such as changing part of the sentence data output by the trained model.

[0068] The processing device 400 described above can be realized by incorporating a predetermined program into an information processing device such as the processing device 400. Specifically, a program according to another aspect of the present disclosure is a program that causes an information processing device such as the processing device 400 to divide text data output by an LLM into one or more texts, and executes processing according to instructions for each of the divided texts, on a text-by-text basis.

[0069] Furthermore, the processing method executed by an information processing device such as the processing device 400 described above is a method in which the information processing device such as the processing device 400 divides the text data output by the LLM into one or more texts, and executes processing according to the instructions on a text-by-text basis in accordance with the instructions for each divided text.

[0070] A program having the above-described configuration, a computer-readable recording medium having the program recorded thereon, or a processing method, etc., can achieve the same functions and effects as the above-described processing device 400, and therefore can achieve the above-described objective of the present disclosure.

[0071] <Additional Notes> A part or all of the above-described embodiments can be described as follows: The processing device and the like according to the present disclosure will be outlined below. However, the present disclosure is not limited to the following configuration.

[0072] (Appendix 1) a segmentation processing unit that segments the text data output by the LLM (Large Language Model) into one or more texts; an instruction processing unit that executes processing according to instructions for each text segmented by the segmentation processing unit; have Processing equipment. (Appendix 2) an assigning unit that assigns a predetermined icon to each of the texts divided by the division processing unit to instruct processing of the text unit; The instruction processing unit executes a process according to the instruction in units of text in response to an operation on the icon assigned by the assignment unit. 10. The processing device of claim 1. (Appendix 3) The segmentation processing unit includes a natural language processing unit that performs natural language processing on the text data output by the LLM to segment the text data into one or more units, and a visualization unit that performs a predetermined visualization process on the segmentation results by the natural language processing unit. Contains 10. The processing device of claim 1 or 2. (Appendix 4) The assigning unit assigns a plurality of icons each indicating a different process to each piece of text divided by the division processing unit. 3. The processing device of claim 2. (Appendix 5) The assigning unit assigns at least one of a regeneration icon that instructs the regeneration of the text divided by the division processing unit, a delete icon that instructs the deletion of the text divided by the division processing unit, a position change icon that instructs the change of position of the text divided by the division processing unit, and a confirmation icon that instructs the provisional confirmation of the text divided by the division processing unit. 3. The processing device of claim 2. (Appendix 6) the assigning unit is configured to assign at least a reservation icon indicating a reservation process for a reservation target included in the text divided by the division processing unit, The instruction processing unit checks whether or not there is availability for the reservation target in response to an operation on the reservation icon assigned by the assignment unit. 3. The processing device of claim 2. (Appendix 7) the assigning unit is configured to assign at least a regeneration icon that instructs the segmentation processing unit to regenerate the segmented text; The instruction processing unit instructs the LLM to regenerate text to which the operated regeneration icon is attached in response to an operation on the regeneration icon attached by the attachment unit. 3. The processing device of claim 2. (Appendix 8) The division processing unit divides the text data indicating the travel plan output by the LLM into one or more texts according to the destinations or time periods included in the travel plan. 8. The processing device according to any one of claims 1 to 7. (Appendix 9) The information processing device The text data output by the LLM (Large Language Model) is divided into one or more texts, According to the instructions for each divided text, the processing according to the instructions is performed on a text-by-text basis. Processing method. (Appendix 10) In the information processing device, The text data output by the LLM (Large Language Model) is divided into one or more texts, According to the instructions for each divided text, the processing according to the instructions is performed on a text-by-text basis. A program to realize the processing.

[0073] Note that some or all of the configurations described in Supplementary Notes 2 to 8 that are dependent on the processing device described as Supplementary Note 1 may also be dependent in a similar dependent relationship on the processing method described in Supplementary Note 9 and the program described in Supplementary Note 10. Furthermore, not limited to Supplementary Notes 9 and 10, some or all of the configurations described as Supplements may also be dependent on various hardware, software, and various recording means, methods, or systems for recording software, within the scope of each of the above-mentioned embodiments.

[0074] The programs described in the above embodiments and appendices can be stored in various types of non-transitory computer-readable media and supplied to a computer. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The programs may also be supplied to a computer by various types of transitory computer-readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. The transitory computer-readable media can supply the programs to a computer via wired communication paths such as electric wires and optical fibers, or via wireless communication paths.

[0075] Although the present disclosure has been described above with reference to the above-described embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate. [Explanation of symbols]

[0076] 100 Processing Systems 200 Processing Equipment 210 Operation input section 220 Screen display section 230 Communication interface unit 240 Storage section 241 Processing Icon Information 242 Programs 250 Processing Unit 251 Instruction processing unit 252 Receiving Section 253 Natural Language Processing Unit 254 Visualization section 255 Processing icon assignment section 256 output section 300 Icons 400 Processing Equipment 401 CPU 402 ROM 403 RAM 404 Programs 405 Storage device 406 Drive Unit 407 Communication Interface 408 Input / Output Interface 409 Bus 410 Recording Media 411 Communication Network 421 Division Processing Unit 422 Instruction Processing Unit

Claims

1. a segmentation processing unit that segments sentence data output by an LLM (Large Language Model) into one or more texts; an instruction processing unit that executes processing according to instructions for each text segmented by the segmentation processing unit; have Processing equipment.

2. an assigning unit that assigns a predetermined icon to each of the texts divided by the division processing unit to instruct processing of the text unit; The instruction processing unit executes a process according to the instruction in units of text in response to an operation on the icon assigned by the assignment unit. The processing device of claim 1 .

3. The segmentation processing unit includes a natural language processing unit that performs natural language processing on the text data output by the LLM to segment the text data into one or more units, and a visualization unit that performs a predetermined visualization process on the segmentation results by the natural language processing unit. Contains The processing device of claim 1 .

4. The assigning unit assigns a plurality of icons each indicating a different process to each piece of text divided by the division processing unit. The processing device of claim 2 .

5. The assigning unit assigns at least one of a regeneration icon that instructs the regeneration of the text divided by the division processing unit, a delete icon that instructs the deletion of the text divided by the division processing unit, a position change icon that instructs the change of position of the text divided by the division processing unit, and a confirmation icon that instructs the provisional confirmation of the text divided by the division processing unit. The processing device of claim 2 .

6. the assigning unit is configured to assign at least a reservation icon indicating a reservation process for a reservation target included in the text divided by the division processing unit, The instruction processing unit checks whether or not there is availability for the reservation target in response to an operation on the reservation icon assigned by the assignment unit. The processing device of claim 2 .

7. the assigning unit is configured to assign at least a regeneration icon that instructs the segmentation processing unit to regenerate the segmented text; The instruction processing unit instructs the LLM to regenerate the text to which the operated regeneration icon is attached in response to an operation on the regeneration icon attached by the attachment unit. The processing device of claim 2 .

8. The division processing unit divides the text data indicating the travel plan output by the LLM into one or more texts according to the destinations or time periods included in the travel plan. The processing device of claim 1 .

9. The information processing device Divide the text data output by the LLM (Large Language Model) into one or more texts, According to the instructions for each divided text, the processing according to the instructions is performed on a text-by-text basis. Processing method.

10. In the information processing device, Divide the text data output by the LLM (Large Language Model) into one or more texts, According to the instructions for each divided text, the processing according to the instructions is performed on a text-by-text basis. A program to realize the processing.

Images