Information processing device, information processing method, and information processing program

Abstract

When extracting desired information using a trained AI model, it may be possible to extract the desired information suitably by inputting correct examples, but there is a problem in that it is not easy to accurately specify correct examples from data in formats such as images, CAD, or BIM. [Solution] To solve the above problem, an information processing device is provided that has: a first prompt setting unit that sets a desired information acquisition prompt for acquiring desired information, which is information about a desired item, from file data including a target item; a first sample setting unit that sets correct sample file data that is input to a trained AI model together with the set desired information acquisition prompt and serves as a correct example for acquiring the desired information; and a correct information designation unit that designates specific information on the set correct sample file data as correct information on a viewer that displays the set correct sample file data.

Description

[Technical field]

[0001] The present invention relates to an information processing apparatus for acquiring desired information from a file data group including various information. [Background technology]

[0002] In recent years, the use of large-scale language models (hereinafter sometimes abbreviated as LLM) to acquire predetermined information from a group of file data is becoming more widespread. For example, Patent Document 1 discloses a technology that uses LLM to collect character information related to a predetermined item from various printed materials with no fixed format, such as advertising flyers. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7430437 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology of Patent Document 1 collects one or more pieces of character information relating to one or more specified items from a group of character strings printed on a flyer read by OCR by providing the LLM with prompts including instructions for specifying the items to be collected and various other instructions regarding the collection.

[0005] In the technology for collecting desired information as disclosed in Patent Document 1, by inputting a correct answer example into the LLM, it may be possible to more appropriately extract the desired information. However, there is a problem in that it is not easy to accurately specify the correct answer example from data in a format such as an image, CAD, or BIM. [Means for solving the problem]

[0006] Therefore, in order to solve the above problems, the present invention provides the following information processing device etc. That is, an information processing device is provided that has a first prompt setting unit that sets a desired information acquisition prompt for acquiring desired information, which is information on a desired item, from file data including a target item, a first sample setting unit that sets correct sample file data that is input to a trained AI model together with the set desired information acquisition prompt and serves as a correct example for acquiring the desired information, and a correct information designation unit that designates specific information on the set correct sample file data as correct information on a viewer that displays the data.

[0007] In addition to the above features, the present invention provides an information processing device further comprising an incorrect answer information designation unit that designates specific information on the set correct answer sample file data as incorrect answer information on a viewer that displays the data.

[0008] In addition to the above features, the present invention provides an information processing device further comprising a correct information explanation prompt setting unit for setting a correct information explanation prompt for explaining the specified correct information.

[0009] In addition to the above features, the present invention provides an information processing device further having a first desired information acquisition unit that inputs the set desired information acquisition prompt, the set correct sample file data, and the specified correct information into the trained AI model to acquire the desired information from the target file data.

[0010] In addition to the above-mentioned features, the first desired information acquiring unit further inputs the specified incorrect answer information and acquires the desired information from the target file data.

[0011] In addition to the above features, the first desired information acquisition unit further inputs the set correct information explanation prompt to acquire the desired information from the target file data.

[0012] In addition to the above features, the present invention provides an information processing device further comprising a detailed prompt setting unit for setting a detailed prompt that is a detailed prompt for acquiring desired information in the set desired information acquisition prompt.

[0013] In addition to the above features, the present invention provides an information processing device further comprising a verification unit that verifies the acquired desired information.

[0014] In addition to the above features, the present invention provides an information processing device further having an acquisition script generation unit that inputs the set desired information acquisition prompt, the set correct sample file data, and the specified correct information into the trained AI model to generate an acquisition script for acquiring the desired information.

[0015] In addition to the above characteristics, the present invention provides an information processing device further comprising a second desired information acquisition unit that acquires the desired information from the target file data by the generated acquisition script.

[0016] In addition to the above features, the present invention provides an information processing device further comprising an acquisition script storage unit that stores the generated acquisition script.

[0017] In addition to the above features, the present invention provides an information processing device further having an acquisition script evaluation unit that evaluates desired information acquired from file data including the target item by the generated acquisition script in comparison with the specified correct answer information.

[0018] In addition to the above-mentioned features, the present invention provides an information processing device in which the acquisition script generation unit further inputs an evaluation result by the acquisition script evaluation unit to generate the acquisition script.

[0019] In addition to the above features, the present invention provides an information processing device further having an acquisition script correction unit that inputs the generated acquisition script and some or all of the file data including the target items into the trained AI model and corrects the generated acquisition script to adapt it to the target file data.

[0020] In addition to the above features, the information processing device further provides an information processing device in which the acquisition script correction unit inputs a desired information acquisition prompt that is the basis of the generated acquisition script into the trained AI model to correct it.

[0021] In addition to the above features, the present invention provides an information processing device further comprising a detailed prompt setting unit for setting a detailed prompt that is a detailed prompt for acquiring desired information in the set desired information acquisition prompt.

[0022] In addition to the above features, the present invention provides an information processing device further comprising a verification unit that verifies the acquired desired information.

[0023] In addition to the above features, the present invention provides an information processing device in which the acquisition script correction unit corrects the acquisition script by reflecting a result of the verification by the verification unit.

[0024] An information processing device is provided having: a second prompt setting unit that sets a prompt generation prompt for generating an acquisition prompt for acquiring desired information, which is information relating to a desired item, from file data including a target item; a second sample setting unit that sets correct sample file data that is input to a trained AI model together with the set prompt generation prompt and serves as a correct example for acquiring the desired information; and a correct information designation unit that designates specific information on the set correct sample file data as correct information on a viewer that displays the set correct sample file data.

[0025] In addition to the above features, the present invention provides an information processing device further having an acquisition prompt generation unit that inputs the set prompt generation prompt, the set correct answer sample file data, and the specified correct answer information into the trained AI model to generate the acquisition prompt.

[0026] In addition to the above features, the present invention provides an information processing device further having a third desired information acquisition unit that inputs the generated acquisition prompt into the trained AI model and acquires the desired information from the target file data.

[0027] In addition to the above features, the present invention provides an information processing apparatus further comprising an acquisition prompt storage unit that stores the generated acquisition prompt.

[0028] In addition to the above features, the present invention provides an information processing device further having an acquisition prompt evaluation unit that compares and evaluates a result of acquiring the desired information for the correct sample file data using the generated acquisition prompt with the correct information.

[0029] In addition to the above-mentioned features, the present invention provides an information processing device in which the acquisition prompt generating unit generates an acquisition prompt by reflecting a result of evaluation by the acquisition prompt evaluating unit.

[0030] In addition to the above features, an information processing device is provided in which the third desired information acquisition unit acquires desired information by further inputting the prompt generation prompt, the correct answer sample file data, and correct answer information input to generate the generated acquisition prompt.

[0031] In addition to the above-mentioned characteristics, the present invention provides an information processing device further comprising a detailed prompt setting unit that sets a detailed prompt, which is a detailed prompt for generating an acquisition prompt from the set prompt generating prompt.

[0032] In addition to the above features, the present invention provides an information processing device further comprising a verification unit that verifies the acquisition result acquired by the third desired information acquisition unit.

[0033] In addition to the above-mentioned features, the information processing device further provides an information processing apparatus in which the acquisition prompt generating unit generates an acquisition prompt by reflecting a result of the verification by the verifying unit.

[0034] The present invention also provides an information processing method executed by an information processing device, the information processing method including: a first prompt setting step of setting an acquisition prompt for acquiring desired information, which is information relating to a desired item, from file data including a target item; a first sample setting step of setting correct sample file data that is input to a trained AI model together with the set acquisition prompt and serves as a correct example for acquiring the desired information; and a correct information designation step of designating specific information on the set correct sample file data as correct information on a viewer that displays the data.

[0035] The present invention also provides an information processing program that causes an information processing device to execute a first prompt setting step of setting an acquisition prompt for acquiring desired information, which is information relating to a desired item, from file data including a target item; a first sample setting step of setting correct sample file data that is input to a trained AI model together with the set acquisition prompt and serves as a correct example for acquiring the desired information; and a correct information designation step of designating specific information on the set correct sample file data as correct information on a viewer that displays the data.

[0036] Also provided is an information processing method executed by an information processing device, the information processing method including: a second prompt setting step of setting a prompt generation prompt for generating an acquisition prompt for acquiring desired information, which is information relating to a desired item, from file data including a target item; a second sample setting step of setting correct sample file data that is input to a trained AI model together with the set prompt generation prompt and serves as a correct example for acquiring the desired information; and a correct information designation step of designating specific information on the set correct sample file data as correct information on a viewer that displays the set correct sample file data.

[0037] The present invention also provides an information processing program that causes an information processing device to execute a second prompt setting step of setting a prompt generation prompt for generating an acquisition prompt for acquiring desired information, which is information related to a desired item, from file data including a target item; a second sample setting step of setting correct sample file data that is input to a trained AI model together with the set prompt generation prompt and serves as a correct example for acquiring the desired information; and a correct information designation step of designating specific information on the set correct sample file data as correct information on a viewer that displays the set correct sample file data. Effect of the Invention

[0038] The present invention makes it easy to accurately specify preferred correct examples for outputting desired information from a trained AI model. [Brief description of the drawings]

[0039] [Figure 1] FIG. 1 is a block diagram showing an example of a functional configuration of an information processing apparatus according to a first embodiment; [Diagram 2] A conceptual diagram showing an example of a viewer that displays the correct sample file data [Diagram 3] FIG. 1 is a conceptual diagram showing an example of the hardware configuration for implementing an information processing device according to a first embodiment of the present invention; [Figure 4] FIG. 1 is a flow chart showing an example of a process flow of an information processing apparatus according to a first embodiment. [Diagram 5] FIG. 11 is a block diagram showing an example of a functional configuration of an information processing apparatus according to a second embodiment. [Figure 6] FIG. 11 is a block diagram showing an example of a functional configuration of an information processing apparatus according to a third embodiment. [Figure 7] FIG. 11 is a flow chart showing an example of a process flow of an information processing apparatus according to a third embodiment. [Figure 8] A diagram showing the detailed prompt settings and examples [Figure 9] A diagram showing how each setting in the Advanced prompt is applied [Figure 10] Conceptual diagram showing an example of an input screen when setting detailed prompts [Figure 11] A diagram showing various settings for performing verification. [Figure 12] Conceptual diagram showing an example of converting PDF file data into a text file with location information added [Figure 13] Conceptual diagram showing another example of converting file data formats [Figure 14] A conceptual diagram showing another aspect of data reduction. [Figure 15] A conceptual diagram showing an example of the extraction range displayed on a 3D model as evidence. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0040] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. Note that the present invention should not be limited to these embodiments, and can be embodied in various forms without departing from the spirit of the present invention.

[0041] <Example 1> <Summary> The present invention is a system that, when acquiring desired information from a variety of file data groups, displays sample file data in a viewer as a correct example to be input to a trained AI model together with prompts, etc., and allows the user to specify correct information by specifying specific information on the data. This makes it easy to specify correct information.

[0042] The following describes the functions and processing flow of the information processing device, as well as the contents of the hardware. The functional blocks of the present system described below can be realized as a combination of hardware and software. Specifically, if a computer is used, the hardware components include a CPU (Central Processing Unit), main memory, bus, or secondary storage device (hard disk drive, non-volatile memory, storage media such as CDs and DVDs, and drives for reading these media, etc.), input devices used for inputting information, printers, display devices, and other external peripheral devices, as well as interfaces for the external peripheral devices, communication interfaces, driver programs and other application programs for controlling these hardware devices, and user interface applications. Then, by the arithmetic processing of the CPU according to the program deployed on the main memory, data input from input devices and other interfaces and stored in the memory or hard disk is processed and stored, and commands for controlling the above hardware and software are generated. Alternatively, the functional blocks of the present system may be realized by dedicated hardware.

[0043] This invention can be realized not only as a system, but also as a method. A part of such an invention can be configured as software. Furthermore, a program used to cause a computer to execute such software, and a recording medium on which the program is fixed, are naturally included in the technical scope of this invention (the same applies throughout this specification).

[0044] <Functional configuration> Fig. 1 is a block diagram showing an example of the functional configuration of an information processing device according to the present embodiment. As shown in Fig. 1, the information processing device 100 includes a first prompt setting unit 101, a first sample setting unit 102, a correct answer information designation unit 103, and a first desired information acquisition unit 104.

[0045] In this embodiment, the trained AI model is a machine learning model that can be trained in advance to handle general-purpose tasks. A representative example is the LLM, but it may be a different model such as a small language model or a multimodal language model that can handle images and other formats.

[0046] <First prompt setting section> The first prompt setting unit 101 has a function of setting a desired information acquisition prompt for acquiring desired information, which is information related to a desired item, from file data including a target item. The target file data may be stored in a storage device provided in the information processing device, or may be stored in a storage device connected to the information processing device via a communication line or the like. In addition, there are many types of file formats for the file data, and the file formats are not limited to these, but include, for example, Word files, Portable Document Format (PDF) files, Excel files, image files, Comma Separated Values ​​(CSV) files, text files, Building Information Modeling (BIM) files, 2D Computer Aided Design (2D CAD) files, and 3D model files.

[0047] Additionally, "desired information" means information on a desired item or information obtained by performing some kind of calculation or processing on the information on that item (total number, average information, maximum information, coordinate information, spatial relationships such as distance and collision, three-dimensional model information, three-dimensional graphic information, an image, a specific part of an image, the contents of an image, text information, etc.).

[0048] For example, if the "total number of elevators" is desired from a group of file data of CSV files related to the facilities of multiple buildings, the number of elevators in the buildings included in each file is extracted, and the total number of these numbers becomes the desired information. In addition to calculating the number information, the results of processing such as 3D space processing and 2D graphic processing may be set as the desired information. For example, if the "collision points between columns and beams" are desired from 3D model files of multiple buildings, all the models of columns and beams included in each file are extracted, the presence or absence of collisions is calculated, and the 3D space information obtained by extracting the collision points becomes the desired information.

[0049] Furthermore, for example, if the target is 2D drawing files of multiple buildings and the desire is to find "inconsistencies between the elevations and floor plans," all architectural design information for the elevations and floor plans contained in each file is extracted, and consistency is checked when the information is reconstructed into 3D solids, and the text that documents the inconsistencies becomes the desired information.

[0050] The prompt for desired information can include not only instructions to the trained AI model, but also conditions for leading to an appropriate answer and examples to refer to. For example, when setting a prompt for desired information that gives instructions to extract a "column object" that is part of a BIM model, "Extract the value of 'Column Object'. 'Column Object' is a part of the BIM model of a building, and has a long, vertical, 3D structure that extends vertically from the ground." A sentence such as the above is set as a prompt for obtaining desired information.

[0051] Furthermore, the desired information acquisition prompt is not limited to one, but can be set in multiple ways. For example, in addition to the instruction to extract the above-mentioned "column object", an instruction to extract a "beam object" or an instruction to extract the "type and number of elevators" can be set. In the case of extracting a "beam object", "Extract the value of 'Beam Object'. 'Beam Object' is a part of the BIM model of a building, and has a 3D structure that is horizontal and more than 2m off the ground." Also, to extract "type and number of elevators", "Please extract the type and number of elevators in the BIM model. If not applicable, please output blank." It is set by sentences such as:

[0052] <First sample setting section> The first sample setting unit 102 has a function of setting correct sample file data that is input to the trained AI model together with the set desired information acquisition prompt and serves as a correct example for acquiring the desired information.

[0053] The correct sample file data is a sample file data when obtaining desired information from the target file data, and contains correct information that is a correct example. For example, if the desired information is the illuminance distribution in a room, BIM data that shows the room in which lighting and other equipment are arranged corresponds to the correct sample file data. Such correct sample file data and the lighting shown in it are the correct information.

[0054] In addition, not only one correct answer information is set for multiple target correct answer sample file data, but also each correct answer information may be set for multiple correct answer sample file data. For example, when a 3D model file for multiple architectural structures including information on columns and beams is the correct answer sample file data, and the desired information is the "collision point between the column and the beam" in each architectural structure, the actual number of "collision points between the column and the beam" in each architectural structure is not limited to "1" and varies, and each collision point between the column and the beam is specified as the correct answer information for each correct answer sample file data. In this case, the correct answer information may be coordinate information on a 3D image showing the collision points, or image information that clarifies the collision points by showing them with a surrounding line, etc.

[0055] <Correct answer information specification section> The correct answer information designation unit 103 has a function of designating specific information on the data as correct answer information on a viewer that displays the correct answer sample file data that has been set. The operation of a user designating a 3D space model, 2D vector data, image, table data, numerical value, text, etc. that will be the correct answer information requires expertise in operation, but by providing a viewer as in this configuration, it is possible to easily designate a 3D model, 3D space, a part of a 2D figure, an area of ​​an image, a cell on table data, etc. that will be the correct answer information, which is beneficial.

[0056] Fig. 2 is a conceptual diagram showing an example of a viewer that displays correct sample file data. As shown in Fig. 2(a), the viewer 201 displays BIM data representing a room in which lighting and other equipment are arranged as correct sample file data. This BIM data includes various information about objects such as the dimensions and materials of the displayed room, and each piece of equipment (ceiling light 202, bracket light 203, bench 204, counter 205), and each of these can be extracted.

[0057] Here, when the desired information is the illuminance distribution in the room, and it is desired to specify the ceiling light 202 as the correct information from this correct sample file data, for example, as shown in FIG. 2(b), the ceiling light 202 can be selected by encircling it with a line 206, thereby specifying it as the correct information. In addition, the bracket light 205 can also be similarly specified as the correct information. In this way, by specifying the correct information, information such as the illuminance and position of each of the ceiling light and the bracket light is specified, which becomes the correct information for obtaining the illuminance distribution in the room. Note that the specification of the correct information in this case may not only be done by encircling it, but may also be done by directly selecting and specifying the 3D object.

[0058] The correct answer information can be specified in various ways depending on the correct answer sample file data. For example, if the correct answer sample file data is an image file, by selecting a specific range on the viewer that opens the image file, the range can be set as the correct answer information to be extracted. Also, by selecting a specific layer on the viewer that opens a CAD file, the layer can be set as the correct answer information to be extracted.

[0059] It is also possible to specify content that does not explicitly exist in the data. For example, by opening a BIM file in a viewer and selecting the space between specific objects in the viewer, the distance between those objects can be used as the correct information to be extracted. Also, by opening spreadsheet data such as Excel in a viewer and selecting a specific cell, that cell can be used as the correct information to be extracted.

[0060] As described above, the specified correct answer information may be in any format, such as numerical information, a three-dimensional space model, a two-dimensional figure, an image, or text. In addition, the result of a calculation process may be specified as the correct answer information. In addition, the correct answer information may not only be information on the desired final result, but may also be information on the correct answer in the process leading up to it. For example, in the example of extracting "collision points between pillars and beams" from the above-mentioned three-dimensional model, (1) the pillar and beam models included in each file, (2) the presence or absence of a collision between them, and (3) information on the three-dimensional space from which the collision points are extracted may be used as the correct answer information in the process.

[0061] <Incorrect information specification part> The incorrect information designation unit has a function of designating specific information on the data as incorrect information on the viewer that displays the set correct sample file data. In 3D models, etc., there are often objects that are confusingly similar to objects of correct information. For example, when you want to extract an "air conditioning duct," "water supply and drainage piping" and "wiring rack" may be placed near the object, which are similar objects. In this case, by designating not only "air conditioning duct" as the correct answer but also "water supply and drainage piping" and "wiring rack" as incorrect answers, the trained AI can avoid excessive detection of piping and accurately obtain the desired information.

[0062] Also, a file that does not contain correct answer information and contains only incorrect answer information may be set as the correct answer sample file data.

[0063] <Correct answer information explanation prompt setting section> The correct answer information explanation prompt setting unit has a function of setting a correct answer information explanation prompt that explains the specified correct answer information. In 3D models, etc., there are often objects that are confusable with the correct answer information object. For example, when trying to extract an "air conditioning duct", "water supply and drainage piping" and "wiring rack" may be placed near the object, which are similar objects. In this case, instead of simply specifying "air conditioning duct" as the correct answer information, In this sample file data, the "air conditioning duct" is the correct answer for the desired information. This is because it is a long, thin cylindrical model, and its end is connected to the "air intake." By setting a prompt to explain the correct answer information in this way, the trained AI can avoid detecting incorrect information and accurately obtain the desired information. In addition, if multiple pairs of correct answer sample file data and correct answer information are input as samples to the trained AI model, a prompt to explain the correct answer information may be set for each pair.

[0064] Furthermore, when incorrect answer information is specified by the incorrect answer information specifying unit, an explanation for this incorrect answer information may be included in the correct answer information explanation prompt.

[0065] In addition, the correct sample file data is often naturally a small number compared to the multiple file data to be acquired by the first desired information acquisition unit, but the opposite is also possible. Also, the correct sample file data may be a part of the multiple file data to be acquired, or may be a different file data. The correct sample file data and the correct information may be set by the user, or may be set in advance by a person who provides the device to the user.

[0066] <First desired information acquisition unit> The first desired information acquisition unit 105 has a function of inputting the set desired information acquisition prompt, the set correct sample file data, and the specified correct information into the trained AI model, and acquiring the desired information from the target file data.

[0067] The target file data is input into the trained AI model, the extraction target is extracted according to the instructions of the desired information acquisition prompt, processing such as calculation is performed as necessary, and finally the desired information is acquired. In addition, it is possible to extract and acquire by further inputting a detailed prompt, which will be described later. It is also possible to extract and acquire by inputting the accumulated desired information acquisition prompt and detailed prompt.

[0068] When a desired information acquisition prompt that instructs the extraction of the above-mentioned "pillar object" is input, the "pillar object" is extracted and can be output together with its file name and a thumbnail image of the file data. The extracted information can then be tagged and entered and saved in an Excel file, or the extracted information can be registered in a database, making the unstructured file data structured data suitable for use in search, statistical processing, and AI learning data.

[0069] In addition to importing the extracted information into an Excel file or the like and creating a database, the extracted information can also be processed according to the format of the file data from which it was extracted. For example, in the case of a CSV file, the extracted information can be added to a new column (row) in the CSV file and saved as appended information. In the case of an Excel file, the extracted information can be added to an added column or sheet in the Excel file and saved as appended information. In the case of a BIM file, the extracted information can be added to the BIM file and saved as appended information.

[0070] In addition, by inputting correct sample file data and correct information in various formats, information can be appropriately acquired from file data in each format. This is also true when acquiring desired information using an acquisition script or acquisition prompt, which will be described later.

[0071] The first desired information acquisition unit may be further configured to input the specified incorrect answer information and acquire the desired information from the target file data. With this configuration, the desired information can be acquired more accurately.

[0072] The first desired information acquisition unit may be further configured to input the correct information explanation prompt set to acquire the desired information from the target file data. With this configuration, the desired information can be acquired more accurately.

[0073] <Hardware configuration> 3 is a conceptual diagram showing an example of the configuration of hardware for realizing the information processing device of the first embodiment. As shown in the figure, the information processing device 300 has a CPU 301 that performs various arithmetic processing, a RAM 302 that is a volatile recording medium, a storage 303 such as a flash memory or HDD that is a non-volatile storage medium, a communication interface 304, and an input / output interface 305. The RAM 302 reads out a program that performs various arithmetic processing to cause the CPU 301 to execute the program, and provides a work area (working area) for the program. In addition, a plurality of addresses are assigned to the RAM 302, and the programs executed by the CPU 301 can exchange data with each other and perform processing by identifying and accessing the addresses (the same applies throughout this specification).

[0074] Here, the functions of the first prompt setting unit 101, the first sample setting unit 102, and the first desired information acquisition unit 104 of the information processing device 100 in FIG. 1 are mainly realized by the CPU 301 and the RAM 302 in FIG. 3. The functions of the correct answer information designation unit 103 are mainly realized by the CPU 301, the RAM 302, and the input / output interface 305 in FIG. 3. In addition, when a database that stores the target file data exists externally, or when the first desired information acquisition unit uses a trained AI model that exists externally, each function is realized by mutually sending and receiving signals and information via the communication interface 304 and the input / output interface 305. In addition, each function of the incorrect answer information designation unit and the correct answer information explanation prompt setting unit, which are not shown in FIG. 1, is realized by the CPU 301, the RAM 302, and the input / output interface 305.

[0075] <Processing flow> FIG. 4 is a flow diagram simply illustrating an example of the flow of processing of the information processing device of the first embodiment. First, a desired information acquisition prompt is set to acquire desired information, which is information on a desired item, from file data including a target item (S401: first prompt setting step). Then, correct sample file data is set, which is input to the trained AI model together with the set desired information acquisition prompt and serves as a correct example for acquiring the desired information (S402: first sample setting step). Then, the set correct sample file data is displayed on a viewer (S403: correct sample file data display step). Then, specific information on the displayed data is designated as correct information (S404: correct information designation step). Then, the set desired information acquisition prompt, the set correct sample file data, and the designated correct information are input to the trained AI model to acquire the desired information from the target file data (S405: first desired information acquisition step). Note that the correct information designation step may include a correct sample file data display step. The method may also include an incorrect answer information specifying step and a correct answer information explanation prompt setting step.

[0076] <Effects> According to the information processing device of this embodiment, it is possible to easily and accurately specify a suitable correct answer example for outputting desired information from a trained AI model.

[0077] <Example 2> <Summary> In the information processing device of Example 1, instead of the mode in which the desired information is acquired by inputting a desired information acquisition prompt together with correct answer information, etc. into a trained AI model, the present invention acquires the desired information by executing a script (simple program) generated by inputting the desired information acquisition prompt and correct answer information, etc. into a trained AI model.

[0078] <Functional configuration> Fig. 5 is a block diagram showing an example of the functional configuration of the information processing device of this embodiment. As shown in Fig. 5, the information processing device 500 has a first prompt setting unit 501, a first sample setting unit 502, a correct answer information designation unit 503, an acquisition script generation unit 504, an acquisition script storage unit 505, and a second desired information acquisition unit 506. Each of the components of the first prompt setting unit, the first sample setting unit, and the correct answer information designation unit has the same function as the components of the same name in the first embodiment, so a description thereof will be omitted.

[0079] <Acquisition script generation part> The acquisition script generation unit 504 has a function of inputting the set desired information acquisition prompt, the set correct sample file data, and the specified correct information into the trained AI model, and generating an acquisition script for acquiring the desired information.

[0080] As explained in the first embodiment, the desired information acquisition prompt is a prompt for acquiring desired information. In this embodiment, the desired information acquisition prompt is input to the trained AI model together with a correct answer example to generate an acquisition script, and the acquisition script is executed to acquire the desired information. For example, "We will now provide you with several BIM files as samples, each showing a room in which various facilities are located. Please create a script that extracts various types of lighting from these BIM files and calculates the lighting distribution in each room." This instructs the generation of an acquisition script for calculating the desired information, that is, the lighting distribution in the room.

[0081] Also, when the process for acquiring the desired information by the acquisition script becomes complicated, the desired information acquisition prompt may be set to generate an acquisition script divided into multiple steps. For example, in the case of extracting "collision points between pillars and beams" from a 3D model, the process may be divided into (1) a desired information acquisition prompt that generates an acquisition script that extracts models of pillars and beams contained in each file, (2) a desired information acquisition prompt that generates an acquisition script that checks whether or not there is a collision between them, and (3) a desired information acquisition prompt that generates an acquisition script that acquires information on the 3D space where the collision points are extracted, and the like, and a desired information acquisition prompt that generates an acquisition script for each step may be set.

[0082] <Acquisition script storage section> The acquisition script storage unit 505 has a function of storing the generated acquisition script. By having the acquisition script storage unit, it is possible to reuse the generated acquisition script, and to acquire values ​​with reproducibility from a large amount of target file data. In addition, the generated acquisition script may be stored in association with the acquisition results acquired by the second desired information acquisition unit described later, the original desired information acquisition prompt and the correct sample file data input together, etc.

[0083] <Second desired information acquisition unit> The second desired information acquisition unit 506 has a function of acquiring the desired information from the target file data by the generated acquisition script. The second desired information acquisition unit 506 executes the generated acquisition script on the target file data to perform a process of acquiring the desired information. It is preferable to save the acquired results. This is to provide the acquired results for post-processing such as verifying the acquired results, as will be described later.

[0084] In addition, the desired information acquired by the second desired information acquisition unit may be passed to another acquisition script as new target file data. In other words, the generation of the acquisition script and the acquisition of desired information from the target file data in the present invention can be linked, making it possible to configure more complicated processing.

[0085] As described above, the process of obtaining the desired information is performed by executing the acquisition script, which reduces the time and cost required compared to calling up a trained AI model each time to obtain the desired information, and also enables the extraction of reproducible information with a certain degree of extraction accuracy.

[0086] Furthermore, even if one tried to prepare a static script to solve this problem, only engineers with specialized knowledge could create the script themselves. However, by generating the acquisition script using a trained AI model, it has the effect of enabling anyone to create the acquisition script themselves.

[0087] <Hardware configuration> The information processing device of this embodiment can be realized by the hardware configuration shown in Fig. 3 according to the embodiment 1. The functions of the acquisition script generation unit 504 and the second desired information acquisition unit 506, which are components unique to the information processing device 500 of the embodiment 2 shown in Fig. 5, are mainly realized by the CPU 301 and the RAM 302 in Fig. 3. Also, the function of the acquisition script accumulation unit 505 is mainly realized by the storage 303 in Fig. 3.

[0088] <Processing flow> The process flow of the information processing device of this embodiment is basically the same as the process flow of the information processing device of the embodiment 1 up to the correct answer information designation step (S404). The process further includes an acquisition script generation step of inputting the set desired information acquisition prompt, the set correct answer sample file data, and the specified correct answer information into the trained AI model to generate an acquisition script for acquiring the desired information, an acquisition script accumulation step of accumulating the generated acquisition script, and a second desired information acquisition step of acquiring the desired information from the target file data by the generated acquisition script. The acquisition script accumulation step may be performed after the second desired information acquisition step.

[0089] <Effects> According to the information processing device of this embodiment, it is easy to accurately specify correct examples, and it is possible to reduce the time and cost required compared to calling up a trained AI model each time to obtain desired information.

[0090] <Example 3> <Summary> The present invention generates a prompt (hereinafter referred to as an acquisition prompt) to be input to a trained AI model when acquiring desired information for various file data groups by inputting correct sample file data, which is a correct example for acquiring the desired information, and correct information together with the prompt to the trained AI model. This allows even an inexperienced user to appropriately generate an acquisition prompt.

[0091] <Functional configuration> Fig. 6 is a block diagram showing an example of the functional configuration of the information processing device of this embodiment. As shown in Fig. 6, the information processing device 600 has a second prompt setting unit 601, a second sample setting unit 602, a correct answer information designation unit 603, an acquisition prompt generation unit 604, an acquisition prompt storage unit 605, and a third desired information acquisition unit 606.

[0092] <Second prompt setting section> The second prompt setting unit 601 has a function of setting a prompt generating prompt for generating an acquisition prompt for acquiring desired information, which is information related to a desired item, from file data including the target item. The desired information in this configuration is as described in the first and second embodiments.

[0093] An acquisition prompt is generated by inputting the prompt generation prompt set in the second prompt setting unit and the correct answer sample file data and correct answer information described later into the acquisition prompt generation unit.The prompt generation prompt set here may be set in a form such that desired information is specified and an acquisition prompt is generated by referring to the correct answer sample file data, or it may be set in a form such that a prompt is generated that acquires correct answer information from the correct answer sample file data.

[0094] For example, if the desired information is "illuminance distribution in the room" as in the example above, you can set a prompt generation prompt such as, "Please refer to the sample file data and correct answer information below to extract all indoor lighting for each of the multiple BIM files, and generate a prompt (obtainment prompt) that obtains the indoor illuminance distribution from the information about each light."

[0095] Furthermore, when the process for acquiring desired information is complicated, the prompt generating prompt may be set to generate an acquisition prompt divided into a plurality of steps. For example, in the example of acquiring the indoor illuminance distribution described above, the prompt generating prompt may be divided into (1) a prompt for generating an acquisition prompt for extracting information required for calculating the illuminance distribution from various information about all lighting contained in each file, (2) a prompt for generating an acquisition prompt for calculating the indoor illuminance distribution using the extracted information, and the prompt generating prompt may be set to generate an acquisition prompt for each step.

[0096] <Second sample setting section> The second sample setting unit 602 has a function of setting correct sample file data that is input to the trained AI model together with the set prompt generation prompt and serves as a correct example for acquiring the desired information. The correct sample file data in this configuration is the same as the correct sample file data in the first and second embodiments.

[0097] <Correct answer information specification section> The correct answer information designation unit 603 has a function of designating specific information on the data as correct answer information on the viewer that displays the correct answer sample file data that has been set. The function of this configuration is the same as that of the correct answer information designation unit in the first and second embodiments.

[0098] In addition, the incorrect answer information designating unit and the correct answer information explanation prompt setting unit described in the first embodiment may be provided.

[0099] <Acquisition prompt generation part> The acquisition prompt generation unit 604 has a function of inputting the set prompt generation prompt, the set correct answer sample file data, and the specified correct answer information into the trained AI model, and generating the acquisition prompt.

[0100] For example, in the case of the acquisition prompt generated to obtain the above-mentioned illuminance distribution, by inputting the above-mentioned prompt generation prompt and the BIM file described in Example 1 and the correct answer example specified in the file into the trained AI model, "Please extract all the lights in the room for each of multiple BIM files, and generate a prompt to obtain the illuminance distribution in the room from the information about each light. Please set the height of the work plane 1mm higher than the height of the objects in the room." A prompt like this is generated.

[0101] In addition, generating an acquisition prompt is not limited to generating a prompt alone, but may also involve generating a static script at the same time, in which case the static script can stably and quickly obtain the desired information from the target file data. In addition, the generated prompt may call a script, or the script may call a prompt.

[0102] In addition, the incorrect answer information specified by the incorrect answer information specification unit and the correct answer information explanation prompt set by the correct answer information explanation prompt setting unit may be further input to the trained AI model to generate an acquisition prompt.

[0103] <Acquisition prompt storage section> The acquisition prompt storage unit 605 has a function of storing the generated acquisition prompt. By having the acquisition prompt storage unit, it is possible to reuse an acquisition prompt once generated, and to acquire values ​​with reproducibility from a large amount of target file data. In addition, the generated acquisition prompt may be stored in association with an acquisition result acquired by a third desired information acquisition unit described later, the original prompt generation prompt, the correct sample file data, and the correct answer information input for generation.

[0104] <Third desired information acquisition unit> The third desired information acquisition unit 606 has a function of inputting the generated acquisition prompt into the trained AI model and acquiring the desired information from the target file data. It is preferable to store the acquired results. This is to provide the acquired results for post-processing such as verifying and reformatting the acquired results, as described below. Note that the trained AI model used in the third desired information acquisition unit may be the same as or different from the trained AI model used in the acquisition prompt generation unit.

[0105] The third desired information acquisition unit may be configured to acquire desired information by further inputting the prompt generating prompt, the correct sample file data, and the correct answer information input to generate the generated acquisition prompt. Alternatively, the third desired information acquisition unit may be configured to acquire desired information by further inputting the specified incorrect answer information and the set correct answer information explanation prompt. By configuring in this way, it is possible to easily generate an acquisition prompt suitable for acquiring desired information.

[0106] In addition, the desired information acquired by the third desired information acquisition unit may be passed to another process by an acquisition prompt as new target file data. In other words, the generation of the acquisition prompt and the acquisition of desired information from the target file in the present invention can be linked, and more complicated processes can be configured.

[0107] <Hardware configuration> The information processing device of the third embodiment can be realized by hardware that realizes the information processing device of the first embodiment shown in Fig. 3. That is, the functions of the second prompt setting unit 601, the second sample setting unit 602, the correct answer information designation unit 603, the acquisition prompt generation unit 604, and the third desired information acquisition unit 606 of the information processing device 600 of Fig. 6 are mainly realized by the CPU 301 and the RAM 302 of Fig. 3. Also, the function of the acquisition prompt accumulation unit 605 is mainly realized by the storage 303 of Fig. 3. Also, when a database that accumulates the target file data exists outside, or when the acquisition prompt generation unit or the third desired information acquisition unit uses a trained AI model that exists outside, each function is realized by mutually sending and receiving signals and information via the communication interface 304 and the input / output interface 305.

[0108] <Processing flow> FIG. 7 is a flow diagram simply illustrating an example of a process flow of the information processing device of the third embodiment. First, a prompt generating prompt for generating an acquisition prompt for acquiring desired information, which is information on a desired item, from file data including a target item is set (S701: second prompt setting step). Then, correct sample file data that is input to the trained AI model together with the set prompt generating prompt and serves as a correct example for acquiring the desired information is set (S702: second sample setting step). Then, the set correct sample file data is displayed on a viewer (S703: correct sample file data display step). Then, specific information on the displayed data is designated as correct information (S704: correct information designation step). Then, the set prompt generating prompt, the set correct sample file data, and the designated correct information are input to the trained AI model to acquire the desired information from the target file data (S705: third desired information acquisition step). Note that the correct information designation step may include a correct sample file data display step.

[0109] <Effects> According to the information processing device of this embodiment, it is easy to accurately specify correct answer examples, and it is also easy for even inexperienced users to create suitable prompts for extracting desired information.

[0110] <Additional features> Below, functions that can be added to any of the above-mentioned embodiments 1 to 3 will be described. First, functions that can be added to embodiment 1 will be described. In cases where the functions can also be added to embodiment 2 or embodiment 3, that fact will be explained.

[0111] <Detailed prompt settings section> The detailed prompt setting unit has a function of setting a detailed prompt which is a detailed prompt for acquiring desired information in the set desired information acquisition prompt.

[0112] 8 is a diagram showing an example of a detailed prompt. As shown in the figure, in this example, the desired information acquisition prompt is "Please extract the value of 'Drawing Number'", and the setting items "No", "Name", "Description", "Necessity", and "Example" are shown as items for setting the instructions of this prompt in detail.

[0113] For example, setting item 1 is called "Assign multiple tag names," and is indicated as a setting item for "dealing with variations in character notation." The explanation states, "Explicitly assign multiple data item names to be extracted," with an example being "["Drawing number," "Drawing ID"]." By setting this detailed prompt, an instruction is added to the instruction "Extract the value of 'Drawing number,'" to include not only "Drawing number," but also what is written as "Drawing ID" in the extraction target.

[0114] Other setting items of the detailed prompt include "Add tag description" which adds a description of the data item name to be extracted to deal with inconsistencies in character notation, "Specify absolute position" which specifies the range where the data item exists on the image to narrow down the range of extraction targets, "Specify target page" which specifies which page the data item is on in a multi-page PDF, "Specify sample" which specifies a group of samples close to or far from the extracted value to prevent erroneous extraction, "Specify format" which allows the user to specify the format to be extracted to prevent erroneous extraction and unify the format of the output results, "Specify relative position" which allows the user to specify the relative position of some content to deal with table format, and "Set condition" which changes the extracted content according to specific conditions to deal with cases where the content to be extracted is not available in all files. Of course, users can set various setting items themselves to set the detailed prompt.

[0115] Here, the application methods for each of the setting items mentioned above can be broadly divided into three: Method 1 "narrowing down the file contents," Method 2 "connecting prompts," and Method 3 "checking and reformatting the detection results." Method 1 refers to narrowing down the file data to be input before inputting it into the trained AI model, and Method 2 refers to connecting the configured detailed prompt to the main prompt. Method 3 refers to reformatting the extraction results according to the specified sample, format, etc.

[0116] FIG. 9 is a diagram showing how each setting item of the detailed prompt is applied. As shown in the figure, for each item of "Assign multiple tag names", "Assign tag description", and "Set conditions", "Connect prompts" of method 2 is applied. Furthermore, for "Specify absolute position" and "Specify target page", "Narrow file contents" of method 1 and method 2 are applied. Furthermore, for "Specify sample", "Confirm extracted results and reformat" of method 2 and method 3 are applied. And for "Specify format" and "Specify relative position", all of methods 1 to 3 are applied. Application examples will be described later.

[0117] FIG. 10 is a conceptual diagram showing an example of an input screen when a detailed prompt is set. As shown in the figure, a desired information acquisition prompt 1002 that has already been set is displayed on the upper left side of a screen 1001. Then, input fields 1003 for each setting item of "tag name", "absolute position designation", "sample designation" and "relative position designation" are displayed on the left side of the screen. In addition, input fields for other setting items are displayed by a user's operation. A detailed prompt is set by accepting an input operation by the user into each of these input fields. Then, the first desired information acquisition unit applies the setting of the detailed prompt and extracts it. By setting and extracting a detailed prompt in this way, it is possible to improve the extraction accuracy.

[0118] An example of applying the above detailed prompt is shown below. For example, if you set "Similar content to D-00033, F-00102" in the "Sample specification" field and "This item is located at the bottom left of the page" in the "Relative position specification" field, this detailed prompt is connected to the desired information acquisition prompt and input. Then, by applying "Relative position specification", only the bottom left of the page is input for the file data to be input to the trained AI model (Method 1: Narrow down the file contents). Then, by applying "Sample specification", the extracted "Drawing number" is extracted from the drawing number that is similar to "D-00033, F-00102" (Method 3: Check the extraction result and reformat). The reformat at this time may be performed using the trained AI model, or may be performed by inputting a separate script that instructs reformatting.

[0119] Furthermore, the detailed prompt setting unit can be configured to automatically set each setting item according to the set desired information acquisition prompt when setting the detailed prompt. Alternatively, it may be configured to accept the settings made by the user and recommend some settings for items that have not been set. By accepting the detailed prompt settings from the user, information can be acquired flexibly and appropriately according to the user's wishes, but it may be difficult for the user to set the optimal prompt. Therefore, the automatic entry and suggestion functions for the detailed prompt are effective. These functions can simplify the process and improve operability.

[0120] In order to simplify and improve operability, it is also preferable that the desired information acquisition unit is configured to perform a test acquisition using the set desired information acquisition prompt, or using the set desired information acquisition prompt and a detailed prompt, before acquiring all of the target file data. A test acquisition is an acquisition of a portion of the target file data. Based on the results of this test acquisition, the user can determine whether the set desired information acquisition prompt or detailed prompt will bring about the acquisition results he or she desires, and can reconfigure the prompts to obtain more desirable acquisition results.

[0121] As shown in Fig. 10, on the left side of a screen 1001, below an input field 1003 for a detailed prompt and a display field 1004 for a desired information acquisition prompt, a "Test" button 1005 is displayed, and test extraction is performed by pressing this button. The results of the test extraction are then displayed in a dotted frame 1006, which is shown for explanatory purposes in the figure. Based on the extraction results, the user can reset the prompt or perform actual extraction using the prompt from which the test extraction results were obtained.

[0122] The detailed prompt setting unit can also be applied as an additional configuration to the second and third embodiments. For example, in the second embodiment, the detailed prompt can be set as a detailed prompt for acquiring desired information in the set desired information acquisition prompt. In the third embodiment, the detailed prompt can be set as a detailed prompt for generating an acquisition prompt by the set prompt generation prompt.

[0123] <Verification Department> The verification unit has a function of verifying the acquired desired information. There are various specific aspects of verification by the verification unit. Fig. 11 is a diagram illustrating various settings when performing verification. As shown in the figure, four types of settings can be made, namely "use detailed prompt", "verification prompt", "verification script" and "inter-file comparison".

[0124] "Use detailed prompt" uses the extraction settings set in the detailed prompt for validation. For example, if a negative sample is specified in the "Specify sample" setting of the detailed prompt, the specified negative sample is reused to validate whether the extraction result is similar to the negative sample. In addition, the setting in "Specify relative position" is used to validate whether the word "rooftop" is present to the left of the extracted value.

[0125] Furthermore, the "verification prompt" is used to set a unique prompt for verification, for example, by setting and inputting a prompt such as "Please check whether this value indicates the material of the elevator door." Furthermore, the "verification script" is used to set a unique script for verification, for example, as shown in the figure, by inputting a command to return "Error" if the extraction result is less than "1" and to return "OK" otherwise.

[0126] Furthermore, when extracting from multiple files, "file comparison" checks the validity of the extracted results by comparing them with other files. As an example, when comparing extracted files A to D, file A, file C, and file D are all written using numbers and symbols only, whereas file B is written mainly in kanji. In such a case, the verification result is that "file B is not valid compared to the others."

[0127] Here, when the verification unit verifies the obtained result, the first desired information acquisition unit can be configured to reflect the verification result and perform re-acquisition. For example, if the value of the extraction result is an error as described above, an instruction such as "The value XXX was extracted in the previous extraction, but the verification result was an error. Please consider this error result and extract the value again" is input to obtain the desired information again.

[0128] The verification unit can also be applied as an additional configuration in the second and third embodiments. In the second embodiment, the verification unit can be applied as a configuration for verifying the desired information acquired by the second desired information acquisition unit, and in the third embodiment, the verification unit can be applied as a configuration for verifying the desired information acquired by the third desired information acquisition unit.

[0129] Next, functions that can be added to the second embodiment will be described.

[0130] <Acquisition script evaluation part> The acquisition script evaluation unit has a function of evaluating the desired information acquired from the file data including the target item by the generated acquisition script in comparison with the specified correct answer information. This correct answer information is as described in the first sample setting unit and the correct answer information designation unit of the first embodiment. The generated acquisition script actually acquires the desired information from the correct answer sample file data, and the result is compared with the correct answer information, so that it is possible to evaluate how accurate the acquisition script is. In other words, if the acquired result matches the correct answer information, it can be evaluated as accurate.

[0131] In addition, by configuring the acquisition script generation unit to further input the evaluation results into the trained AI model, an acquisition script based on the evaluation results can be generated, which can be useful for generating a more accurate acquisition script. For example, it can be configured to continue regenerating the acquisition script until the acquired information matches the correct answer information. Note that the evaluation of the acquisition script may be performed on the acquisition script stored in the acquisition script storage unit.

[0132] <Acquisition script modification part> The acquisition script correction unit has a function of inputting the generated acquisition script and a part or all of the target file data into the trained AI model, and correcting the generated acquisition script so as to adapt it to the target file data. Note that the trained AI model used for the correction may be the same as the trained AI model used in the acquisition script generation unit described above, or may be a different one.

[0133] For example, if the target file data contains file data in a file format that was not included in the sample file data entered when creating the acquisition script, or contains item names to be acquired, the desired information may not be acquired accurately. To prevent such a situation, the generated acquisition script is input into the trained AI model together with the target file data.

[0134] Then modify the acquisition script by providing a prompt like the example below: "This script was written with the following goal in mind: Select column objects from the list of 3D objects of the building in the BIM file, and calculate the total number of them. However, it may not work properly with the file data you are processing. Please find out what is not working properly and fix the script." For example, if an acquisition script created to acquire the "total number of pillar objects" executes a script to extract objects having a property value of "pillar", if the target file data contains a pillar object having a property value of "Pillar", the information of this file data will be omitted from the acquisition targets, and accurate desired information cannot be obtained. Therefore, by inputting the created acquisition script and the target file data into the trained AI model along with the above prompt, an acquisition script adapted to the target file data can be generated.

[0135] The modification to adapt to the file data may be performed by inputting the file data from the target file data one by one into the trained AI model, or may be performed by inputting all the file data into the trained AI model. In addition, the desired information acquisition prompt that was the basis for creating the modified acquisition script may also be input.

[0136] Also, the acquisition scripts stored in the above-mentioned acquisition script storage unit can be modified in the same way as the generated acquisition scripts are modified. Since the stored acquisition scripts may need to be modified due to an increase, decrease, or change in the target file data, it is preferable to configure the scripts so that they can be modified.

[0137] Furthermore, when the verification unit described as one of the additional functions is applied to the second embodiment, the acquisition script correction unit can be configured to correct the acquisition script by reflecting the verification result by this verification unit. For example, if the information of the acquisition result is an error as described above, a prompt such as "In the previous extraction, information XXX was extracted, but the verification result was an error. Please correct the script taking this error result into consideration" is input to the trained AI model to correct the acquisition script.

[0138] Next, functions that can be added to the third embodiment will be described.

[0139] <Acquisition prompt evaluation section> The acquisition prompt evaluation unit has a function of comparing the result of acquiring the desired information for the correct sample file data by the generated acquisition prompt with the correct information and evaluating it. In the same manner as the acquisition script evaluation unit, which is an additional function of the second embodiment, the generated acquisition script is evaluated in this configuration. Similarly, the acquisition prompt generation unit can be configured to further input the evaluation result by the acquisition prompt evaluation unit to the trained AI model, and an acquisition prompt reflecting the evaluation result can be generated.

[0140] Furthermore, functions that can be added to any of the first to third embodiments will be described.

[0141] <Filtering section> The filtering unit has a function of removing predetermined file data from among the target file data, from the target of acquisition by any of the first desired information acquisition unit to the third desired information acquisition unit. There are various filtering methods. For example, filtering is performed based on file attributes (extension, size, file name, data items associated with the file, etc.). Also, filtering is performed based on individual keywords set. Specifically, filtering is performed by generating a script for filtering by performing semantic search, clustering, character search, etc., and executing the script. Also, filtering may be performed by giving instructions to a trained AI model. For example, by inputting an instruction such as "Does this file contain elevator contents?", filtering can be performed based on whether or not the file contains elevator contents.

[0142] This filtering function can meet user requests such as, for example, wanting to obtain column objects from a structural model among 500 target file data, but skipping equipment models.

[0143] <Conversion section> The conversion unit has a function of converting the format of the target file data according to the characteristics of the file data. When the conversion unit is included, any one of the first desired information acquisition unit to the third desired information acquisition unit acquires desired information from the file data converted by the conversion unit. For example, if the file data is in PDF format, it is converted into a text file format. In addition, in the case of image data, character recognition is performed using OCR to convert it into a text file format. In addition, in the case of three-dimensional data, it may be converted into two-dimensional data or an image. Such conversion contributes to improving robustness.

[0144] Furthermore, when converting to a text file, it is also preferable to convert so that the location information of the text is added. FIG. 12 is a conceptual diagram showing an example of converting PDF format file data into a text file with location information added. FIG. 12(a) shows a part of a PDF format file showing a building area table of a house. FIG. 12(b) shows an example of converting each text of "shape", "formula", and "area" into a JSON format described with their location information. FIG. 12(c) shows an example of converting text into an Array format described with location information. In this way, by adding location information, extraction is performed taking into account the relationship between texts, which contributes to improving robustness. FIG. 12(d) shows an example of converting text showing a table showing the "area" and "tatami" of each of "Western-style room 1", "Western-style room 2", and "Western-style room 3" in the original file into text with table information instead of location information (within the dotted line frame in the figure). By converting in this way, it is possible to obtain the target while maintaining the table structure.

[0145] Fig. 13 is a conceptual diagram showing another example of converting the format of file data. As shown in Fig. 13, in the case of a file containing figures (kitchen floor plan), converting it into SVG format and making it text containing figure information makes it easier to obtain using a script. Conversely, two-dimensional vector information may be converted into a raster image, or data may be converted from three-dimensional to two-dimensional.

[0146] <Data Reduction Division> The data reduction unit has the function of reducing the target file data. Data reduction can be performed in various ways. For example, data reduction can be performed by narrowing down the target file data to a specific space, property, area, specific page or section, paragraph, table, etc. It is also possible to filter by file attributes (page number, position, etc.), by individual keywords (semantic search, clustering, character search), or by spatial position (x, y, z, coordinates). Filtering can also be performed by inputting instructions to a trained AI model ("Does this file contain elevator contents?").

[0147] FIG. 14 is a conceptual diagram showing another aspect of data reduction. As shown in FIG. 14(a), a specific portion 1402 is cut out from one file data 1401, and it is checked whether the target data is included therein. As a result, if the target data is included, the portion is provided for acquisition processing from the first desired information acquisition unit to the third desired information acquisition unit. If the target data is not included, a portion 1403 shifted from the previous portion is cut out and checked in the same manner. In this way, by excluding from the acquisition target those that do not include the target data in the check before acquisition, it is possible to improve the processing efficiency. Note that this check may be performed by executing a script, using a trained AI model, or by other methods. Also, such processing may be performed in a three-dimensional space.

[0148] 14(b), the above-mentioned check is performed while shifting the specific portion, and the portion containing the target data is temporarily stored in memory 1404. Then, it is checked whether processing memory 1404 contains all the elements necessary to acquire the target data, and if it does, the portion held in the memory is provided for acquisition processing by any of the first desired information acquisition unit to the third desired information acquisition unit. On the other hand, if it does not contain all the elements, the specific portion is shifted further and the series of processes from the above-mentioned check are repeated.

[0149] <Ground indication section> The reason display unit has a function of displaying the reason why the acquisition result obtained by any one of the first desired information acquisition unit to the third desired information acquisition unit was obtained.

[0150] In the information processing device of each embodiment, the desired information is acquired through each process. For example, in the second embodiment, the desired information acquisition prompt, the correct sample file data, and the correct answer information are inputted into the trained AI model to generate an acquisition script, and the desired information is acquired by inputting the acquired script into the trained AI model. Here, it may be difficult to set the desired information acquisition prompt to generate an optimal acquisition script for acquiring the desired information. Therefore, by displaying the reason (such as the intermediate process) that led to the acquisition result, it is possible to show the user "what and how to improve the acquisition result."

[0151] Fig. 15 is a conceptual diagram showing an example of displaying an extraction range on a 3D model as evidence. The figure shows a 3D model representing a building, and the position of information (pillar object) acquired from this model is highlighted by being surrounded by a thick dotted frame 1501 on the 3D. This allows the user to know where the acquisition results were acquired from. In addition, in the case of an acquisition script that processes a 3D model, displaying the process of the acquisition script and highlighting the information used at that time are also useful for checking the evidence.

[0152] Also, a display explaining the reason for the acquisition may be provided. For example, as a pre-processing step, an instruction such as "Please output the reason for outputting this information as the acquisition result for each detailed process" is input to the trained AI model before acquisition. Then, after acquisition, the acquisition result is displayed, and the reason is displayed, for example, "Various types of lighting in the room are placed near the ceiling, and the object names contain the character "lighting", so these objects were extracted as lighting." In this way, the desired information acquisition prompt that the user set and the effect of the acquisition script generated by it on the acquisition result are displayed, so that the user can reflect on various settings and contribute to optimizing the desired information acquisition. Similarly, in the first and third embodiments, it is useful to display the reason for the acquisition of the desired information and the intermediate process. [Explanation of symbols]

[0153] 100, 500, 600: Information processing equipment 101, 501: First prompt setting section 102, 502: First sample setting section 103, 503, 603: Correct answer information specification section 104: First desired information acquisition unit 504: Acquisition script generation unit 505: Acquisition script storage unit 506: Second desired information acquisition unit 601: Second prompt setting section 602: Second sample setting unit 604: Acquisition prompt generation unit 605: Acquisition prompt storage unit 606: Third desired information acquisition unit 301:CPU 302:RAM 303: Storage 304: Communication interface 305: Input / Output Interface

Claims

1. a first prompt setting unit that sets a desired information acquisition prompt for acquiring desired information, which is information related to a desired item, from file data including the target item; A first sample setting unit that sets correct sample file data that is input to a trained AI model together with the set desired information acquisition prompt and serves as a correct example for acquiring the desired information; a correct answer information designation unit that designates specific information on the data as correct answer information on a viewer that displays the set correct answer sample file data; An information processing device having the above configuration.

2. 2. The information processing apparatus according to claim 1, further comprising an incorrect answer information designation unit that designates specific information on the set correct answer sample file data as incorrect answer information on a viewer that displays the data.

3. The information processing apparatus according to claim 2 , further comprising a correct answer information explanation prompt setting unit for setting a correct answer information explanation prompt for explaining the specified correct answer information.

4. The information processing device according to claim 3, further comprising a first desired information acquisition unit that inputs the set desired information acquisition prompt, the set correct sample file data, and the specified correct information into the trained AI model to acquire the desired information from the file data.

5. The information processing apparatus according to claim 4 , wherein the first desired information acquiring unit further inputs the specified incorrect answer information and acquires the desired information from the file data.

6. 6. The information processing apparatus according to claim 4, wherein the first desired information acquiring unit further inputs the set correct information explanation prompt to acquire the desired information from the file data.

7. 3. The information processing apparatus according to claim 1, further comprising a detailed prompt setting unit for setting a detailed prompt which is a detailed prompt for acquiring the desired information in the set desired information acquisition prompt.

8. The information processing apparatus according to claim 4 , further comprising a verification unit that verifies the acquired desired information.

9. 2. The information processing device according to claim 1, further comprising: an acquisition script generation unit that inputs the set desired information acquisition prompt, the set correct sample file data, and the specified correct information into the trained AI model to generate an acquisition script for acquiring the desired information.

10. The information processing apparatus according to claim 9 , further comprising a second desired information acquisition unit that acquires the desired information from the file data by the generated acquisition script.

11. 11. The information providing device according to claim 9, further comprising an acquisition script storage unit that stores the generated acquisition script.

12. 11. The information processing apparatus according to claim 10, further comprising an acquisition script evaluation unit that evaluates desired information acquired from the file data by the generated acquisition script in comparison with the specified correct answer information.

13. The information processing apparatus according to claim 12 , wherein the acquisition script generating section further receives an evaluation result by the acquisition script evaluating section to generate the acquisition script.

14. The information processing device according to claim 9 or 10, further comprising an acquisition script correction unit that inputs the generated acquisition script and a part or all of the file data into the trained AI model and corrects the generated acquisition script to adapt it to the file data.

15. The information processing device according to claim 14 , wherein the acquisition script correction unit further inputs a desired information acquisition prompt that is the basis of the generated acquisition script into the trained AI model to correct it.

16. 11. The information processing apparatus according to claim 9, further comprising a detailed prompt setting unit for setting a detailed prompt which is a detailed prompt for acquiring the desired information in the set desired information acquisition prompt.

17. The information processing apparatus according to claim 15 , further comprising a verification unit that verifies the acquired desired information.

18. The information processing apparatus according to claim 17 , wherein the acquisition script correction unit corrects the acquisition script by reflecting a result of the verification by the verification unit.

19. a second prompt setting unit that sets a prompt generating prompt for generating an acquisition prompt for acquiring desired information, which is information related to a desired item, from file data including the target item; A second sample setting unit that sets correct sample file data that is input to a trained AI model together with the set prompt generation prompt and serves as a correct example for acquiring the desired information; a correct answer information designation unit that designates specific information on the data as correct answer information on a viewer that displays the set correct answer sample file data; An information processing device having the above configuration.

20. The information processing device according to claim 19 , further comprising an acquisition prompt generation unit that inputs the set prompt generation prompt, the set correct answer sample file data, and the specified correct answer information into the trained AI model to generate the acquisition prompt.

21. The information processing device according to claim 20 , further comprising a third desired information acquisition unit that inputs the generated acquisition prompt into the trained AI model to acquire the desired information from the file data.

22. 22. The information processing apparatus according to claim 20, further comprising an acquisition prompt storage unit that stores the generated acquisition prompt.

23. 22. The information processing apparatus according to claim 21, further comprising an acquisition prompt evaluation unit that compares a result of acquiring the desired information for the correct sample file data by the generated acquisition prompt with the correct information and evaluates it.

24. The information processing apparatus according to claim 23 , wherein the acquisition prompt generating unit generates an acquisition prompt by reflecting a result of the evaluation by the acquisition prompt evaluating unit.

25. 22. The information processing apparatus according to claim 21, wherein the third desired information acquisition unit acquires desired information by further inputting the prompt generating prompt, the correct sample file data, and the correct answer information input to generate the generated acquisition prompt.

26. 21. The information processing apparatus according to claim 19, further comprising a detailed prompt setting unit configured to set a detailed prompt that is a detailed prompt for generating an acquisition prompt from the set prompt generating prompt.

27. The information processing apparatus according to claim 21 , further comprising a verifying unit that verifies an acquisition result acquired by the third desired information acquiring unit.

28. The information processing apparatus according to claim 27 , wherein the acquisition prompt generating unit generates an acquisition prompt by reflecting a result of the verification performed by the verifying unit.

29. An information processing method executed by an information processing device, a first prompt setting step of setting a desired information acquisition prompt for acquiring desired information, which is information related to a desired item, from file data including the target item; A first sample setting step of setting a correct answer sample file data that is input to a trained AI model together with the set desired information acquisition prompt and serves as a correct answer example for acquiring the desired information; a correct answer information designation step of designating specific information on the data as correct answer information on a viewer that displays the set correct answer sample file data; An information processing method comprising the steps of:

30. a first prompt setting step of setting a desired information acquisition prompt for acquiring desired information, which is information related to a desired item, from file data including the target item; A first sample setting step of setting a correct answer sample file data that is input to a trained AI model together with the set desired information acquisition prompt and serves as a correct answer example for acquiring the desired information; a correct answer information designation step of designating specific information on the data as correct answer information on a viewer that displays the set correct answer sample file data; An information processing program that causes an information processing device to execute the above.

31. An information processing method executed by an information processing device, a second prompt setting step of setting a prompt generating prompt for generating an acquisition prompt for acquiring desired information, which is information related to a desired item, from file data including the target item; A second sample setting step of setting a correct answer sample file data that is input to the trained AI model together with the set prompt generation prompt and serves as a correct answer example for acquiring the desired information; a correct answer information designation step of designating specific information on the data as correct answer information on a viewer that displays the set correct answer sample file data; An information processing method comprising the steps of:

32. a second prompt setting step of setting a prompt generating prompt for generating an acquisition prompt for acquiring desired information, which is information related to a desired item, from file data including the target item; A second sample setting step of setting a correct answer sample file data that is input to the trained AI model together with the set prompt generation prompt and serves as a correct answer example for acquiring the desired information; a correct answer information designation step of designating specific information on the data as correct answer information on a viewer that displays the set correct answer sample file data; An information processing program that causes an information processing device to execute the above.