Information processing systems, information processing methods, and programs

Abstract

This invention provides an information processing system, information processing method, and program that easily generate forms having any structure. [Solution] In an information processing system 1 in which an information processing device and a user terminal are connected via a general-purpose or dedicated communication network, the information processing device includes a control unit which is a processor, an acquisition unit which acquires structural information, and an output unit which outputs form information based on the structural information, pre-set auxiliary information, and a first trained model. The structural information includes natural language information relating to the structure of the form. The auxiliary information includes instruction information for outputting the form information in a predetermined format, and the form information includes information that can generate a form, created in a predetermined format.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, and a program.

Background Art

[0002] Patent Document 1 discloses a system that can generate a prompt for inputting into a language model according to an input by a user.

[0003] This system includes a selection means for accepting the selection of one or more options from a plurality of options corresponding to each of a plurality of keywords in response to an input from a user terminal operated by the user, and a first generation means for generating a prompt for inputting into a language model so as to include a keyword corresponding to the option accepted by the selection means, or for generating a temporary prompt for generating the prompt.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, there is still room for improvement in the functions according to the above-known technology.

[0006] In view of the above circumstances, the present invention aims to provide a technology that can easily generate a form having an arbitrary structure.

Means for Solving the Problems

[0007] According to one aspect of the present invention, an information processing system is provided, comprising at least one processor, the processor being configured to execute a program such that the following steps are performed: an acquisition step, which acquires structural information, the structural information including natural language information relating to the structure of a form; a first output step, which outputs form information based on the structural information, pre-configured auxiliary information, and a first trained model, the auxiliary information including instruction information to cause the form information to be output in a predetermined format, and the form information including information capable of generating a form, created in a predetermined format.

[0008] According to this disclosure, a technology can be provided that can easily generate forms having any structure. [Brief explanation of the drawing]

[0009] [Figure 1] This is a diagram showing the configuration of the information processing system 1 according to this embodiment. [Figure 2] This is a block diagram showing the hardware configuration of the information processing device 2. [Figure 3] This is a block diagram showing the hardware configuration of user terminal 3. [Figure 4] This is a functional block diagram showing the functions of the information processing system 1 according to this embodiment. [Figure 5] This flowchart shows an overview of the processes performed by Information Processing System 1. [Figure 6] This is an activity diagram showing specific examples of processes performed by Information Processing System 1. [Figure 7] This is an activity diagram showing specific examples of processes performed by Information Processing System 1. [Figure 8] This is an overview diagram showing an example of form creation screen 4a, which is one of the form creation screens 4 in which the visual information IFv for inputting structural information IFs is displayed. [Figure 9] This is a schematic diagram showing an example of form creation screen 4b, which is one of the form creation screens 4, where the specified input has been entered into the visual information IFv. [Figure 10] This is an overview diagram showing an example of form creation screen 4c, which displays a preview of form F, which is generated based on form information IFf, from form creation screen 4. [Figure 11] This is an overview diagram showing an example of form creation screen 4d, in which form F and form information IFf are displayed in a list, as part of form creation screen 4. [Figure 12] This is an overview diagram showing an example of form creation screen 4e, in which form F and form information IFf are displayed in a list, as part of form creation screen 4. [Figure 13] This is an overview diagram showing an example of form creation screen 4f, which is one of the form creation screens 4, where arbitrary information has been entered into form F, which is drawn in the preview. [Figure 14] This is an overview diagram showing an example of form creation screen 4g, which displays the output information IFo as a result of using form F, which was drawn in the preview, from form creation screen 4. [Figure 15] This is a schematic diagram showing an example of AI Assistant Screen 5. [Modes for carrying out the invention]

[0010] Embodiments of this disclosure will be described below with reference to the drawings. The various features shown in the embodiments below are interchangeable.

[0011] Incidentally, the program for implementing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or it may be provided as a downloadable medium from an external server, or it may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0012] Also, in various information processing according to an embodiment, an input and an output corresponding to the input can be realized. Here, if an output is obtained as a result of the input, the form of information (hereinafter referred to as reference information) referred to in such information processing is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, a predetermined function (including a judgment formula such as a regression formula constructed by a statistical method), a learned model in which the correlation between the input and the output has been learned in advance, or a generative AI such as a large language model or a vision language model that can output a desired result by inputting a prompt.

[0013] Also, in one embodiment, the "unit" may include, for example, hardware resources implemented by a circuit in a broad sense and information processing of software that can be specifically realized by these hardware resources. Also, in one embodiment, various information is handled, and these information are represented, for example, by physical values of signal values representing voltage and current, the high and low of signal values as a set of binary bits composed of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be executed on a circuit in a broad sense.

[0014] Furthermore, a circuit in a broad sense is a circuit realized by appropriately combining at least a circuit, circuitry, a processor, a memory, etc. Also, the processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (for example, a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0015] 1. Hardware Configuration In this section, the hardware configuration will be described.

[0016] 1.1 Information Processing System 1 FIG. 1 is a configuration diagram showing an information processing system 1 according to the present embodiment. The information processing system 1 includes an information processing apparatus 2 and a user terminal 3, which are connected through a general-purpose or dedicated communication network 11. Here, the system exemplified by the information processing system 1 consists of one or more devices or components. Therefore, even the information processing apparatus 2 alone or the user terminal 3 alone is included in the system exemplified by the information processing system 1. Hereinafter, each component included in the information processing system 1 will be further described.

[0017] 1.2 Information Processing Apparatus 2 FIG. 2 is a block diagram showing the hardware configuration of the information processing apparatus 2. The information processing apparatus 2 is preferably configured by a server. The information processing apparatus 2 has a communication unit 21, a storage unit 22, and a control unit 23, and these components are electrically connected via a communication bus 20 inside the information processing apparatus 2. Each component will be further described.

[0018] The communication unit 21 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, Bluetooth (registered trademark) communication, etc. as needed. That is, it is more preferable to implement it as a set of these plural communication means. That is, the information processing apparatus 2 may communicate various information from the outside via the communication unit 21 and the communication network 11.

[0019] The storage unit 22 stores various types of information as defined above. This can be done, for example, as a storage device such as a solid-state drive (SSD) that stores various programs related to the information processing device 2 executed by the control unit 23, or as a memory such as random access memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to program calculations. The storage unit 22 stores various programs and variables related to the information processing device 2 executed by the control unit 23.

[0020] The control unit 23 performs processing and control of the overall operation related to the information processing device 2. The control unit 23 is a general-purpose processor such as a Central Processing Unit (CPU) (not shown), or a dedicated processor specialized for a specific process. A dedicated processor is, for example, a GPU (graphics processing unit), an FPGA (field-programmable gate array), or an ASIC (application-specific integrated circuit). The GPU may have GPU memory such as VRAM (an example of a storage unit 22), and examples of GPU memory include random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), and other forms of memory known in the art. In an example where the GPU is configured as part of another processor, such as a host processor, the GPU memory can be accessed by components other than the GPU.

[0021] The control unit 23 realizes various functions related to the information processing device 2 by reading a predetermined program stored in the storage unit 22. That is, information processing by software stored in the storage unit 22 is concretely realized by the control unit 23, which is an example of hardware, and can be executed as each functional unit included in the control unit 23. These will be described in more detail in the next section. Note that the control unit 23 is not limited to being a single unit, and may be implemented with multiple control units 23 for each function, or a combination thereof. That is, the information processing system 1 includes at least one control unit 23 as a processor. The control unit 23, which is a processor, is configured to execute a program so that each of the steps described later is performed.

[0022] 1.3 User Terminal 3 Figure 3 is a block diagram showing the hardware configuration of the user terminal 3. The user terminal 3 can be operated by a user and can access the information processing device 2 via a smartphone, tablet, computer, or other telecommunication line, regardless of its form. Specifically, the user terminal 3 comprises a communication unit 31, a storage unit 32, a control unit 33, a display unit 34, and an input unit 35, and these components are electrically connected within the user terminal 3 via a communication bus 30. The explanation of the communication unit 31, storage unit 32, and control unit 33 is the same as the explanation of each part of the information processing device 2 and is therefore omitted.

[0023] The display unit 34 may be included in the casing of the user terminal 3, for example, or it may be an external component. The display unit 34 displays a graphical user interface (GUI) screen that can be operated by the user. This is preferably done by using different display devices such as a CRT display, liquid crystal display, organic EL display, and plasma display, depending on the type of user terminal 3.

[0024] The input unit 35 may be included in the casing of the user terminal 3 or it may be an external component. For example, the input unit 35 may be integrated with the display unit 34 and implemented as a touch panel. If it is a touch panel, the user can input tap operations, swipe operations, etc. Of course, a switch button, mouse, QWERTY keyboard, etc. may be used instead of a touch panel. In other words, the input unit 35 receives operation input made by the user. This input is transmitted as a command signal to the control unit 33 via the communication bus 30, and the control unit 33 can perform predetermined controls and calculations as needed.

[0025] 2. Functional Configuration This section describes the functional configuration of this embodiment. As mentioned above, information processing by software stored in the memory unit 22 is specifically realized by the control unit 23, which is an example of hardware, and each functional unit included in the control unit 23 can be executed.

[0026] Figure 4 is a functional block diagram showing the functions of the information processing system 1 according to this embodiment. Specifically, an information processing device 2, which is an example of the information processing system 1, includes an acquisition unit 231, a reception unit 232, a calculation unit 233, an output unit 234, and a display control unit 235.

[0027] The acquisition unit 231 is configured to acquire various types of information as an acquisition step. For example, the acquisition unit 231 acquires data, user input information, structural information IFs, etc., from the storage unit 22 or from the user terminal 3 or other external devices via the communication network 11. In one embodiment, the various types of information acquired by the acquisition unit 231 are described as being stored in the storage unit 22.

[0028] The reception unit 232 is configured to receive various types of information as a reception step. For example, the reception unit 232 receives data, user input information, input information IFi, etc., from the storage unit 22, or from the input unit 35 of the user terminal 3 or other external devices via the communication network 11. In one embodiment, the various types of information received by the reception unit 232 are described as being stored in the storage unit 22.

[0029] The arithmetic unit 233 is configured to perform various information processing calculations related to the information processing device 2.

[0030] The output unit 234 is configured to output various information as a first output step or a second output step. For example, the output unit 234 is configured to output form information IFf, output information IFo, etc.

[0031] The display control unit 235 is configured to perform various display processes as a display control step. For example, the display control unit 235 controls the display unit 34 of the user terminal 3 to display visually recognizable information such as images including screens, still images, or moving images, icons, and messages. The display control unit 235 may also generate only rendering information for displaying visually recognizable information on the display unit 34 of the user terminal 3.

[0032] 3. Operation of Information Processing System 1 This section describes the information processing method of the aforementioned information processing system 1 with reference to the figures. The order of processing can be changed as appropriate, multiple processes may be executed simultaneously, and some processes may be omitted. Furthermore, the results of the processes described below may be output in a manner that can be recognized by the user using the display unit 34 of the user terminal 3, etc. Note that this information processing may include arbitrary exception handling not shown. Exception handling includes interruption of the information processing and omission of each process. The selection or input performed in this information processing may be based on user operation or may be performed automatically without user operation.

[0033] 3.1 Overview Figure 5 is a flowchart illustrating the overview of the processing performed by the information processing system 1. In this process, first, the acquisition unit 231 acquires structural information IFs (step S001). In this case, the structural information IFs includes natural language information about the structure of form F. Then, the output unit 234 outputs form information IFf based on the structural information IFs, pre-set auxiliary information IFa, and the first trained model M1 (step S002). The auxiliary information IFa includes information instructing the output of form information IFf in a predetermined format. The form information IFf includes information that can generate form F, created in a predetermined format.

[0034] In summary, the information processing system 1 according to one embodiment comprises at least one processor (for example, a control unit 23). The processor is configured to perform the following steps by reading a program. The acquisition unit 231 acquires structural information IFs as an acquisition step. The structural information IFs includes natural language information about the structure of form F. The output unit 234 outputs form information IFf as a first output step, based on the structural information IFs, pre-set auxiliary information IFa, and a first trained model M1. The auxiliary information IFa includes information instructing the output of form information IFf in a predetermined format. The form information IFf includes information capable of generating form F, created in a predetermined format. According to this embodiment, form F having any structure can be easily created.

[0035] 3.2 Specific Examples Next, a specific example of the process according to one embodiment will be described with reference to the activity diagram. The specific example may be included within the scope defined in the overview described above.

[0036] Figures 6 and 7 are activity diagrams showing specific examples of processes performed by the information processing system 1. Below, we will first outline the information processing flow for creating form F, following the activity diagram in Figure 6.

[0037] <Information processing for creating Form F> First, the user accesses an AI assistant application, which is executed by the information processing system 1, using a browser on the user terminal 3. In this case, the AI ​​assistant application is an application that, based on the user's operations, can use a pre-trained model M, create a form F to be used when using the pre-trained model M, etc. The AI ​​assistant application may also be provided as a dedicated desktop or mobile application, in which case the user launches the application. Alternatively, the AI ​​assistant application may be provided as a web application or in SaaS (Software as a Service) format that does not require downloading to the terminal. The process of creating form F may be configured to be executable only by users with specific privileges, such as administrator privileges, or it may be configured to be executable by all users.

[0038] When the AI ​​assistant app is accessed, the display control unit 235 controls the display unit 34 of the user terminal 3 to display the top screen (not shown) (Activity A001).

[0039] The reception unit 232 accepts user login information input (e.g., click, tap, swipe, select, etc.) through user operations via the top screen, completing the login to the AI ​​assistant app. Subsequently, when input is received to transition from the top screen to the form creation screen 4 (see Figures 8-10), the display control unit 235 controls the display unit 34 of the user terminal 3 to display the form creation screen 4 (Activity A002).

[0040] The acquisition unit 231 acquires structural information IFs based on user input via the form creation screen 4 (Activity A003).

[0041] In this case, the structural information IFs are the information used to create form F, and include the title of form F, natural language information about the structure of form F, and information about the trained model M used in form F. Specifically, for example, the acquired structural information IFs include the title of form F as "Anything Translator", the natural language information about the structure of form F as "There are fields for "Target Language", "Text", and "Taste". The target language can be selected from Japanese, English, Korean, and Chinese," and information about the trained model M used as "Model X".

[0042] Next, the output unit 234 outputs form information IFf based on the acquired structural information IFs, the pre-configured auxiliary information IFa, and the first trained model M1 (Activity A004).

[0043] Here, auxiliary information IFa is information input to the first trained model M1, and includes information instructing the output of form information IFf in a predetermined format. In this case, the predetermined format can be any format that can generate form F, such as JSON Schema format or HTML+JavaScript format. Furthermore, by adopting the JSON Schema format, form F is defined by the UI structure, which minimizes modifications when updating the system or switching trained models M, thereby improving scalability and maintainability. The following explanation will use the case where the predetermined format is JSON Schema format as an example.

[0044] The first pre-trained model M1 is an example of a pre-trained model M, and may be a pre-trained model M in which the correlation between input and output has been learned in advance, or it may be a generative AI such as a large-scale language model or visual language model that can output a desired result by inputting a prompt. Furthermore, the pre-trained model M may be trained by machine learning using a machine learning algorithm, and may be a machine learning model constructed on the basis of a decision tree, for example. Machine learning models constructed on the basis of a decision tree include, but are not limited to, Light GBM and XGBoost. Alternatively, the prediction model may be a model generated based on machine learning algorithms such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), or other deep learning methods.

[0045] Form information IFf contains information that can generate form F, created in a predetermined format. Specifically, for example, form information IFf contains information that can generate form F, created in JSON Schema format.

[0046] Then, the display control unit 235 displays form F, which is generated based on form information IFf, in response to the output of form information IFf (activity A005). In other words, the display control unit 235 displays the form creation screen 4 on which form F has been drawn. With this configuration, the created form F can be confirmed in response to the output of form information IFf. As a result, it is easy to confirm whether form F with the desired structure has been created.

[0047] <Information processing when using the pre-trained model M with the created form F> Next, following the activity diagram in Figure 7, we will outline the information processing flow when using the trained model M with the created form F. Note that the explanation of the information processing similar to that used to create form F will be omitted.

[0048] When the display control unit 235 receives input to transition from the top screen (not shown) to the AI ​​assistant screen 5 (see Figure 15), it controls the display unit 34 of the user terminal 3 to display the AI ​​assistant screen 5 (Activity A101).

[0049] The reception unit 232 accepts input from the user via the AI ​​assistant screen 5 to select a form F (activity A102). Specifically, for example, it accepts input to select any form F from the created forms F. In the following explanation, we will assume that the form F titled "Anything Translator" has been selected.

[0050] The display control unit 235 displays the selected form F (activity A103). That is, the display control unit 235 displays the AI ​​assistant screen 5 on which form F, titled "Anything Translator," is drawn.

[0051] The reception unit 232 receives input via the generated form F as input information IFi (Activity A104). Specifically, for example, the reception unit 232 receives information corresponding to the "target language," "text," "style," etc., entered in form F as input information IFi.

[0052] The output unit 234 then outputs output information IFo based on the received input information IFi and the second trained model M2 (activity A105). Specifically, for example, the output unit 234 inputs the input information IFi corresponding to the "target language," "text," and "style" entered in form F into the second trained model M2, and outputs a text translated in a predetermined language and style as output information IFo. In this case, the second trained model M2 is an example of a trained model M. With this configuration, information for input to the trained model M can be easily created using form F which is configured with any structure. As a result, the trained model M can be easily used.

[0053] 3.3 Details Next, the aforementioned information processing will be further explained using a separate diagram.

[0054] Figure 8 is a schematic diagram showing an example of form creation screen 4a, in which visual information IFv for inputting structural information IFs is displayed.

[0055] As shown in Figure 8, the form creation screen 4a, which displays the title "Create Form," has areas 401 to 405, a button 406, and area 407. Areas 401 to 405 are configured to allow input of information used to create form F. In other words, the display control unit 235 displays visual information IFv for inputting structural information IFs. Furthermore, the information entered in areas 401 to 405, which is used to create form F, is configured to be obtainable as structural information IFs.

[0056] Specifically, area 401 is configured to allow input of the title of form F, and area 402 is configured to allow input of the description of form F.

[0057] Area 403 is configured to allow input for selecting a template type. The template types must include at least "Form," which is an option for creating Form F. In addition to "Form," the template types should also include other options such as "Chat."

[0058] Area 404 is configured to allow input of natural language information regarding the structure of form F.

[0059] Area 405 is configured to allow input for selecting a second pre-trained model M2 (an example of a pre-trained model M) to be used in form F. In area 405, it is preferable to input the selection of the second pre-trained model M2 to be used in form F by selecting any pre-trained model M from a set of pre-configured pre-trained models M. Specifically, for example, "Model X," "Model Y," and "Model Z" may be pre-configured as multiple pre-trained models M, and area 405 may employ a select box as an input component with "Model X," "Model Y," and "Model Z" as options.

[0060] Button 406, which displays the text "Create", is configured to output form information IFf when pressed after completing predetermined inputs in areas 401 to 405. Area 407 is configured to display a preview of form F, which will be generated based on form information IFf, in response to the output of form information IFf. Specifically, when button 406 is pressed, the acquisition unit 231 acquires the input information via visual information IFv as structural information IFs. Subsequently, the output unit 234 outputs form information IFf based on structural information IFs, pre-set auxiliary information IFa, and the first trained model M1. Then, the display control unit 235 displays form F, which will be generated based on form information IFf.

[0061] Figure 9 is a schematic diagram showing an example of form creation screen 4b, which is part of form creation screen 4 and shows the state in which the visual information IFv has been entered as specified. In form creation screen 4b shown in Figure 9, the information used to create form F is entered in areas 401 to 405 of form creation screen 4a. Note that the same configuration as form creation screen 4a will not be explained.

[0062] Specifically, in domain 401, "Anything Translator" is entered as the title of Form F, in domain 402, "It can translate the entered Japanese into various languages" is entered as the description of Form F, and in domain 403, "Form" is selected as the template type. In addition, in domain 404, the following natural language information regarding the structure of Form F is entered: "- There are fields for "Target Language," "Text," and "Taste," "- For Taste, you can select Casual, Formal, or Kansai dialect style," and "- For Target Language, you can select Japanese, English, Korean, or Chinese." In domain 405, "Model X" is selected as the second pre-trained model M2 to be used in Form F.

[0063] In area 404, it is desirable that pre-configured input examples be displayed in response to the input of some information necessary to create form F. In other words, the visual information IFv should include information about pre-configured input examples. Specifically, for example, if "Anything Translator" is entered in area 401, and "Form" is selected in area 403, it is desirable that the following be displayed in area 404 as input examples: "- There are fields for the items "Target Language" and "Text", "- The target language can be selected from Japanese, English, Korean, and Chinese". In this case, the output unit 234 outputs the input example information based on the information entered in areas 401 and 403 and the pre-configured reference information. The display control unit 235 displays area 404 (an example of visual information IFv) in which the outputted input examples are displayed. In this case, the reference information may be, for example, rule-based information such as a database or lookup table, or a pre-trained model M that has learned the correlation between input and output in advance, or a generating AI such as a large-scale language model or visual language model that can output desired results by inputting prompts. According to this embodiment, natural language information regarding the structure of form F can be easily input, and form F having any arbitrary structure can be created even more easily.

[0064] Figure 10 is a schematic diagram showing an example of form creation screen 4c, which displays a preview of form F, generated based on form information IFf, from form creation screen 4. In form creation screen 4c shown in Figure 10, information used to create form F is entered in areas 401 to 405 of form creation screen 4b, and when button 406 is pressed, a preview of form F is displayed in area 407. Note that the same configuration as form creation screens 4a and 4b will not be explained.

[0065] Specifically, in area 407, the title of form F is displayed as "Anything Translator," and the description of form F is displayed as "You can translate the entered Japanese into various languages." Furthermore, below the description of form F in area 407, areas 407a to 407c and button 407d are provided. Area 407a is configured to allow input for selecting the "target language," area 407b is configured to allow input for the "main text," which is the sentence to be translated, and area 407c is configured to allow input for selecting the "style."

[0066] Button 407d, on which the text "Send" is displayed, is configured to output output information IFo when pressed after completing predetermined inputs to regions 407a to 407c. Specifically, when button 407d is pressed, the reception unit 232 receives predetermined inputs to regions 407a to 407c as input information IFi. The output unit 234 then outputs output information IFo based on the received input information IFi and the second trained model M2. With this configuration, information for input to the trained model M can be easily created using a form F configured with any structure. As a result, the trained model M can be easily used.

[0067] Furthermore, in the case of "Anything Translator," an example of form F, "Model X" is associated as the second trained model M2 selected via visual information IFv (for example, region 405). In other words, in the form information IFf that enables the creation of form F for "Anything Translator," "Model X" is identified as the second trained model M2. To put it another way, "Model X," an example of the second trained model M2, is a trained model M identified by the form information IFf from among multiple trained models M. With this configuration, it becomes possible to associate any trained model M with form F, and as a result, it becomes possible to select an appropriate trained model M according to the purpose, items, etc. of form F.

[0068] Furthermore, in the form creation screen 4c shown in Figure 10, a seek bar 408 is drawn in response to the button 406 being pressed, which draws a preview of form F in area 407. The seek bar 408 is configured to allow sliding operation, and sliding it causes the display of visual information IFv to slide.

[0069] Figure 11 is a schematic diagram showing an example of form creation screen 4d, in which form F and form information IFf are displayed in a list. In form creation screen 4d shown in Figure 11, form information IFf is displayed by sliding the seek bar 408 in form creation screen 4c, and form F and form information IFf are displayed in a list. Note that the same configuration as form creation screens 4a to 4c will not be explained.

[0070] Specifically, in area 409 located below button 406, the form information IFf is drawn. As a result, area 407, where the preview of form F is drawn, and area 409, where the form information IFf is drawn, are displayed in a list. In other words, when the form information IFf is output, the display control unit 235 displays a list of form F, which is generated based on the form information IFf, and the form information IFf itself. With this configuration, form F and the form information IFf can be viewed in a list in response to the output of the form information IFf.

[0071] Furthermore, area 409 is configured to allow editing of the drawn form information IFf. When the form information IFf drawn in area 409 is edited, the contents of form F drawn in area 407 are also changed according to the edit. With this configuration, if form F needs to be modified, the form information IFf can be modified and the modified form F can be further verified.

[0072] Figure 12 is a schematic diagram showing an example of form creation screen 4e, in which form F and form information IFf are displayed in a list. In form creation screen 4d shown in Figure 12, system prompt information IFp is further displayed as form information IFf by sliding the seek bar 408 in form creation screen 4d. Note that the same configuration as form creation screens 4a to 4d will not be explained.

[0073] Specifically, in area 410, located below area 409, system prompt information IFp is drawn as form information IFf.

[0074] In this case, the system prompt information IFp is information that provides instructions for controlling the response of the second trained model M2, such as the content of the response of the second trained model M2, the tone of expression, the criteria for selecting information, the range of operation, etc. Specifically, for example, in region 410, the system prompt information IFp is shown as information that provides instructions for controlling the output information IFo (an example of the response of the second trained model M2) output using form F of the "Anything Translator".

[0075] Furthermore, on the form creation screen 4e, the area 407 where the preview of form F is drawn, the area 409 where the information that can generate form F is drawn, and the area 410 where the system prompt information IFp is drawn are displayed in a list. In this case, the form information IFf includes at least the information that can generate form F, created in a predetermined format, and the system prompt information IFp. In other words, when form information IFf is output, the display control unit 235 displays a list of form F, which is generated based on form information IFf, and form information IFf, which includes the information that can generate form F and the system prompt information IFp. With this configuration, form F and form information IFf can be checked in a list in response to the output of form information IFf.

[0076] Figure 13 is a schematic diagram showing an example of form creation screen 4f, which is part of form creation screen 4 and shows a state where arbitrary information has been entered into form F, which is drawn in the preview. In form creation screen 4f shown in Figure 13, arbitrary information has been entered into areas 407a to 407c of form creation screen 4e in order to confirm the operation when using form F, which is drawn in the preview. Note that the same configuration as form creation screens 4a to 4e will not be explained.

[0077] Specifically, in area 407a, the user selects "English" as the "target language," in area 407b, an arbitrary sentence is entered in Japanese as the "main text" to be translated, and in area 407c, the user selects "casual" as the "style."

[0078] Figure 14 is a schematic diagram showing an example of form creation screen 4g, which shows the output information IFo displayed as a result of using form F, which was drawn in the preview, from form creation screen 4. In form creation screen 4g shown in Figure 14, arbitrary information is entered into areas 407a to 407c in form creation screen 4f, and when button 407d is pressed, the output information IFo is displayed and shown. Note that the same configuration as form creation screens 4a to 4f will not be explained.

[0079] Specifically, when button 407d is pressed, the reception unit 232 receives a predetermined input for regions 407a to 407c as input information IFi. The output unit 234 then outputs output information IFo based on the input information IFi, system prompt information IFp, and the second trained model M2. In this configuration, the system prompt information IFp can be used to control the second trained model M2 to give a desired response. As a result, it is possible to obtain output information IFo with a controlled response.

[0080] Furthermore, on the form creation screen 4g, when button 407d is pressed, a new area 411 is drawn below area 407 where the preview of form F is drawn. On the form creation screen 4c, a seek bar 412 is drawn in response to the new drawing of area 411. The seek bar 412 is configured to allow sliding operation, and sliding it slides the display of areas 407 and 411.

[0081] Area 411 displays the output information IFo, which is an English translation of any text entered in area 407b. In other words, when output information IFo is output, the display control unit 235 displays a list of the form F into which the input information IFi was entered, the form information IFf, and the output information IFo. With this configuration, each piece of information can be grasped through the list display, and as a result, it becomes easy to modify the form information IFf in accordance with the output information IFo.

[0082] Figure 15 is a schematic diagram showing an example of the AI ​​Assistant screen 5.

[0083] As shown in Figure 15, the AI ​​assistant screen 5, which has the title "AI app" displayed on it, has regions 501 and 502.

[0084] Area 501, which is labeled "Standard Assistant," contains areas 501a to 501c. Areas 501a to 501c list the titles of Form F created on Form Creation Screen 4. Specifically, area 501 contains area 501a, which is labeled "Anything Translator," area 501, which is labeled "File Analysis Assistant," and area 501, which is labeled "Document Proofreading Form."

[0085] Furthermore, in the AI ​​assistant screen 5 shown in Figure 15, the area 501a where the title "Anything Translator" is drawn is pressed, and as a result, the form F of "Anything Translator" is drawn in area 502.

[0086] Area 502 contains areas 502a to 502c and a button 502d. The configuration of area 502 is the same as the configuration of form F of the "Anything Translator" shown in area 407 of the form creation screen 4. Specifically, for example, in area 502a, where the text "Target Language" is displayed, it is configured to allow input of one of the following languages: Japanese, English, Korean, or Chinese. In area 502b, where the text "Body Text" is displayed, it is configured to allow input of the text to be translated. In this case, the text to be translated can be entered directly as text, or the text can be entered via a file. In area 502c, where the text "Taste" is displayed, it is configured to allow input of one of the following tastes: casual, formal, or Kansai dialect style.

[0087] Button 502d, on which the text "Send" is displayed, is configured to output output information IFo when pressed after completing predetermined inputs to regions 502a to 502c. That is, when button 502d is pressed, the receiving unit 232 receives predetermined inputs to regions 502a to 502c as input information IFi. The output unit 234 then outputs the translation result as output information IFo based on the received input information IFi and "Model X". With this configuration, information for input to the trained model M can be easily created using a form F configured with any structure. As a result, the trained model M can be easily used.

[0088] [others] With respect to the information processing system 1 according to the above embodiment, the following configurations may be adopted.

[0089] In the embodiment shown in Figure 9, the case in region 405 where a second trained model M2 to be used in form F is selected from a plurality of trained models M is described as an example, but the embodiment is not limited to this. For example, in region 405, a second trained model M2 to be used in form F may be suggested in response to the input of some information for creating form F. Specifically, for example, the calculation unit 233 may identify the second trained model M2 to be used in form F in response to the input of the title of form F, the input of the description of form F, and the reference information. Subsequently, the display control unit 235 may display region 405 in which the identified second trained model M2 is drawn. In detail, the calculation unit 233 may identify "Model X" in response to the input "Anything Translator" in region 401, the input "It can translate the input Japanese into various languages" in region 402, and the reference information. According to this embodiment, it is possible to select the second trained model M2 that is optimal for form F to be created.

[0090] In this case, the reference information should pre-define the processing capabilities, processing quality, inference performance, inference speed, usage fees, and acceptable file formats for each pre-trained model M. Specifically, for example, it would be good to define the processing tasks associated with each pre-trained model M, such as "Model X" for document creation, summarization, and translation; "Model Y" for image generation and graph creation; and "Model Z" for high-precision Japanese text generation.

[0091] Furthermore, although the embodiment shown in Figure 9 describes an example where reference information for each trained model M is not shown, the embodiment is not limited to this. For example, the display control unit 235 may display the contents of the reference information within or related to the region 405 as a basis for selecting a trained model M. Specifically, for example, the display control unit 235 may display information regarding the fee for each trained model M (for example, an amount corresponding to the number of input tokens) within or related to the region 405. According to this embodiment, it becomes possible to select the second trained model M2 that is optimal for the form F to be created based on the reference information.

[0092] Furthermore, while the embodiments shown in Figures 10 to 15 describe an example where the file formats that can be input to form F are not specified, the invention is not limited to this. For example, in each form F, the file formats that can be input to form F may be specified according to the selected second trained model M2. In other words, each form F may be configured to accept only files of the specified file format. Specifically, for example, if "Model X" is selected, file formats such as text files and document files may be specified, and if "Model Y" is selected, file formats such as image files and spreadsheet files may be specified. Furthermore, if "Model Z" is selected, it may be possible to prevent the input of files to form F by making it impossible to specify a file format.

[0093] In the above embodiment, the case in which the second trained model M2 used in form F is selected when creating form F was described as an example, but it is not limited to this. For example, the second trained model M2 used in form F may be changed after the start of using form F. Specifically, for example, the second trained model M2 used in form F may be changed depending on the usage status of form F.

[0094] In this case, the usage information includes the amount of tokens used, the usage fee for the second trained model M2, and processing speed. In other words, the display control unit 235 displays information regarding the usage status of the trained model M in a manner that corresponds to each form F or to each trained model M. With this configuration, the user who creates and manages form F can consider which trained model M to select as the second trained model M2 by checking information such as the amount of tokens used, the usage fee for the second trained model M2, and processing speed. That is, it is preferable that a usage fee be displayed for each trained model M based on the input data and prompts. In this case, the usage fee should be calculated from the number of tokens used for input and output of the trained model M.

[0095] Furthermore, depending on the usage of form F, a second trained model M2 to be used in form F may be proposed. That is, the calculation unit 233 may identify a trained model M to be selected as the second trained model M2 based on the usage of form F and reference information. In this case, the reference information may pre-define the processing strengths, processing quality, usage fees, etc., of each trained model M. Subsequently, the display control unit 235 displays visual information IFv, which is drawn so that the identified trained model M can be selected as the second trained model M2. The acquisition unit 231 also acquires the newly selected second trained model M2 as structural information IFs. The output unit 234 outputs form information IFf based on the structural information IFs, pre-set auxiliary information IFa, and the first trained model M1. With this configuration, it is possible to propose the optimal second trained model M2 for form F.

[0096] In the embodiments shown in Figures 12 to 14, the example described is one in which form information IFf includes at least information capable of generating form F, created in a predetermined format, and system prompt information IFp, but it is not limited to this. For example, form information IFf may consist only of information capable of generating form F, created in a predetermined format, or it may consist of information capable of generating form F, created in a predetermined format, and system prompt information IFp, or it may further include other information.

[0097] Furthermore, an information processing method comprising each step of the information processing system 1 may be implemented. That is, this information processing method includes each step of the information processing system 1. According to this embodiment, a form F having any structure can be easily created through information processing. The above embodiment may also be implemented as a distributable program. That is, this program causes at least one computer to execute each step of the information processing system 1. According to this embodiment, a form F having any structure can be easily created through information processing by the program.

[0098] At least one of the devices included in the information processing system 1 may be located outside of Japan. For example, the information processing device 2 may be located outside of Japan, and a user in Japan may access the information processing device 2 using their user terminal 3, or the information processing device 2 may be located in Japan, and a user outside of Japan may access the information processing device 2 using their user terminal 3.

[0099] The information processing device 2 may be on-premise or in a cloud-based configuration. In the case of a cloud-based information processing device 2, for example, the above-mentioned functions and processing may be provided in the form of SaaS or cloud computing.

[0100] In one embodiment, the acquisition unit 231, reception unit 232, calculation unit 233, output unit 234, and display control unit 235 are described as functional units realized by the control unit 23 of the information processing device 2. However, at least a part of these may be implemented as functional units realized by the control unit 33 of the user terminal 3. Furthermore, the various types of information described in the above example may be stored not only in the storage unit 22 of the information processing device 2, but also distributedly in other external devices. In such cases, distributed ledger management based on blockchain or the like may be implemented.

[0101] The product may be provided in any of the following embodiments.

[0102] (1) An information processing system comprising at least one processor, wherein the processor is configured to execute a program such that the following steps are performed: an acquisition step, which acquires structural information, wherein the structural information includes natural language information relating to the structure of a form; and a first output step, which outputs form information based on the structural information, pre-configured auxiliary information and a first trained model, wherein the auxiliary information includes information instructing the output of the form information in a predetermined format, and the form information includes information capable of generating the form, which has been created in the predetermined format.

[0103] According to this embodiment, forms having any structure can be easily created.

[0104] (2) In the information processing system described in (1) above, the display control step further includes displaying the form generated based on the form information in response to the output of the form information.

[0105] In this configuration, the created form can be checked as the form information is output. As a result, it is easy to confirm whether a form with the desired structure has been created.

[0106] (3) In the information processing system described in (2) above, the display control step displays a list of the form generated based on the form information and the form information when the form information is output.

[0107] In this configuration, the form and its information can be viewed in a list once the form information has been output. Furthermore, if the form needs to be modified, the form information can be corrected, and the modified form can be viewed again.

[0108] (4) An information processing system according to any one of (1) to (3) above, wherein in the display control step, visual information for inputting the structural information is displayed, and the visual information includes information of a pre-set input example, and in the acquisition step, the information input via the visual information is acquired as the structural information.

[0109] According to this embodiment, it becomes possible to easily input natural language information regarding the structure of the form, and to create forms with any arbitrary structure even more easily.

[0110] (5) An information processing system as described in any one of (1) to (4) above, wherein in the reception step, input via the generated form is received as input information, and in the second output step, output information is output based on the input information and a second trained model.

[0111] In this configuration, information for input into a trained model can be easily created using a form with an arbitrary structure. As a result, the trained model can be easily used.

[0112] (6) In the information processing system described in (5) above, the form information includes at least information capable of generating the form, which is created in the predetermined format, and system prompt information, wherein the system prompt information is information of instructions for controlling the response of the second trained model, and in the second output step, the system outputs the output information based on the input information, the system prompt information, and the second trained model.

[0113] In this embodiment, the second trained model can be controlled by system prompt information to produce a desired response. As a result, it becomes possible to obtain output information with a controlled response.

[0114] (7) In the information processing system described in (6) above, the display control step further includes displaying a list of the form on which the input information was entered, the form information, and the output information when the output information is output.

[0115] In this configuration, each piece of information can be grasped in a list view, and as a result, it becomes easy to modify the form information according to the output information.

[0116] (8) In an information processing system described in any one of (5) to (7) above, the second trained model is a trained model identified by the form information from among a plurality of trained models.

[0117] In this configuration, it becomes possible to associate any pre-trained model with a form, and as a result, an appropriate pre-trained model can be selected according to the form's purpose, items, etc.

[0118] (9) An information processing method comprising each step of an information processing system described in any one of (1) to (8) above.

[0119] According to this embodiment, a form having any structure can be easily created through information processing.

[0120] (10) A program that causes at least one computer to perform each step of the information processing system described in any one of (1) to (8) above.

[0121] In this embodiment, a form having any structure can be easily created through programmatic information processing. Of course, this is not always the case.

[0122] Finally, while various embodiments relating to this disclosure have been described, these are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0123] 1: Information Processing System 11: Communication Network 2: Information Processing Device 20: Communications bus 21: Communications Department 22: Storage section 23: Control Unit 231: Acquisition Department 232: Reception Department 233: Arithmetic section 234: Output section 235: Display Control Unit 3: User terminal 30: Communications bus 31: Communications Department 32: Storage section 33: Control Unit 34:Display section 35: Input section 4: Form creation screen 4a: Form creation screen 4b: Form creation screen 4c: Form creation screen 4D: Form creation screen 4e: Form creation screen 4f: Form creation screen 4g: Form creation screen 401 :Region 402 :Region 403 :Region 404 :Region 405 :Region 406: Button 407 :Area 407a :Area 407b :Region 407c :Region 407d: Button 408: Seek bar 409 :Area 410 :Area 411 :Area 412: Seek bar 5: AI Assistant Screen 501 :Area 501a :Region 501b :Region 501c: area 502 :Area 502a :Area 502b :Region 502c :Region 502d: Button F: Form IFa: Supplementary Information IFf: Form Information IFi: Input Information IFo: Output information IFs: Structural information IFv: Visual Information M: Trained model M1: First pre-trained model M2: Second pre-trained model

Claims

1. An information processing system, The system comprises at least one processor, the processor configured to execute a program such that the following steps are performed: In the acquisition step, structural information is acquired, and here, the structural information includes natural language information about the structure of the form. In the first output step, form information is output based on the structural information, pre-configured auxiliary information, and the first trained model, where, The aforementioned auxiliary information includes information that instructs the output of the form information in a predetermined format. The system includes information capable of generating the form, which is created in the predetermined format.

2. In the information processing system described in claim 1, Furthermore, in the display control step, the system displays the form generated based on the form information in response to the output of the form information.

3. In the information processing system described in claim 2, In the display control step, when the form information is output, the system displays the form generated based on the form information and the form information in a list.

4. In the information processing system described in claim 1, Furthermore, in the display control step, visual information for inputting the structural information is displayed, and here the visual information includes information of a pre-set input example. In the acquisition step, the system acquires the information input via the visual information as structural information.

5. In the information processing system described in claim 1, Furthermore, in the reception step, the input via the generated form is accepted as input information. Furthermore, in a second output step, the system outputs output information based on the input information and a second trained model.

6. In the information processing system described in claim 5, The form information includes at least information capable of generating the form, created in the predetermined format, and system prompt information, wherein the system prompt information is information of instructions for controlling the response of the second trained model. In the second output step, the system outputs the output information based on the input information, the system prompt information, and the second trained model.

7. In the information processing system described in claim 6, Furthermore, in the display control step, when the output information is output, the system displays a list of the form into which the input information was entered, the form information, and the output information.

8. In the information processing system described in claim 5, The system wherein the second pre-trained model is a pre-trained model identified by the form information among a plurality of pre-trained models.

9. Information processing method, A method comprising each step of the information processing system described in any one of claims 1 to 8.

10. It is a program, A program that causes at least one computer to perform each step of the information processing system described in any one of claims 1 to 8.

Images