Information processing device, information processing method, and information processing program
The information processing device enhances drawing data search by using trained models for symbol detection and interpretation, addressing the limitations of existing technologies in semantic interpretation and data conversion.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- CADDI INC
- Filing Date
- 2025-03-10
- Publication Date
- 2026-07-02
AI Technical Summary
Existing technologies lack the ability to perform semantic interpretation and data conversion in combination with detected symbols, making it difficult to specify and search for drawing data effectively.
An information processing device that utilizes trained models for symbol region detection, type identification, and character recognition to extract and associate symbol-related information, enabling intuitive specification and search of drawing data.
Enables efficient and intuitive searching of drawing data by identifying and interpreting symbol-related information, improving data extraction and aggregation processes.
Smart Images

Figure 0007884163000001 
Figure 0007884163000002 
Figure 0007884163000003
Abstract
Description
Technical Field
[0004] , , , , ,
[0005] , ,
[0001] The present disclosure relates to an information processing apparatus, an information processing method, and an information processing program.
Background Art
[0002] There is known a symbol extraction device that enables reduction of the burden of searching for a desired partial image in an image (for example, Japanese Patent Application Laid-Open No. 2023-181686). This symbol extraction device includes a template setting unit that acquires a template image, which is an image to be extracted from an image (design drawing data), an analysis condition setting unit that acquires a threshold value used for determining whether extraction is successful, a collation unit that extracts a partial image from the image whose similarity to the template image is equal to or greater than the threshold value, and an extraction result management unit that displays an extraction result including at least one item among the extracted partial image, the identification number of the partial image, the position of the partial image in the image, and the similarity between the partial image and the template image.
[0003] There is also known a processing device that suppresses a decrease in the accuracy of processing while suppressing an increase in the amount of learning work (for example, Japanese Patent Application Laid-Open No. 2021-028841). This processing device includes at least an input unit, a processing unit, and an output unit. The input unit inputs a drawing including symbols belonging to a plurality of systems. The processing unit detects the systems of the symbols included in the drawing and the number of each system by executing processing of a neural network learned for the drawing input to the input unit. The output unit outputs the systems of the symbols detected by the processing unit and the number of each system.
Summary of the Invention
Problems to be Solved by the Invention
[0004] In the above-mentioned patent documents, only symbol detection is performed, and semantic interpretation and data conversion in combination with the description near the detected symbol cannot be performed. Therefore, there is room for improvement in specifying information related to processing and searching for drawing data.
[0005] This disclosure is made in view of the above circumstances and aims to provide an information processing device, an information processing method, and an information processing program that can intuitively specify information related to processing and search for drawing data. [Means for solving the problem]
[0006] The information processing device according to the first embodiment includes a receiving unit that receives the designation of a graphic symbol related to the processing of an object, and an output unit that outputs target image data corresponding to the received graphic symbol from among a plurality of image data in which the object to be processed and the graphic symbol are drawn.
[0007] The information processing apparatus according to the second embodiment, in the information processing apparatus according to the first embodiment, the receiving unit receives the designation of the graphic symbol and also receives the designation of symbol-related information, which is additional information related to the received graphic symbol, and the output unit outputs the target image data corresponding to the graphic symbol and the symbol-related information when outputting the target image data.
[0008] The third embodiment of the information processing device includes a display control unit that displays a plurality of symbol images representing the graphic symbol in the first or second embodiment of the information processing device, and the receiving unit, when receiving the designation of the graphic symbol, receives the graphic symbol represented by the symbol image selected from the plurality of symbol images displayed.
[0009] The information processing device according to the fourth embodiment is an information processing device according to any one of the first to third embodiments, wherein the output unit highlights the area corresponding to the specified graphic symbol included in the output target image data.
[0010] The information processing device according to the fifth embodiment further comprises a search unit that searches for the target image data from a database in which a plurality of the image data is stored, in an information processing device according to any one of the first to fourth embodiments, and the output unit outputs the target image data retrieved by the search unit.
[0011] The information processing device according to the sixth embodiment, in the information processing device according to the fifth embodiment, searches for the target image data from among a plurality of image data stored in the database by referring to symbol-related information, which is obtained by recognizing the plurality of image data in advance and is associated with each of the image data, and which includes the type of graphic symbol drawn on each of the image data, to search for the target image data.
[0012] The information processing device according to the seventh embodiment is an information processing device according to the sixth embodiment in which the type of graphic symbol associated with the symbol-related information is data obtained in advance by identifying the region in the image data where the graphic symbol is drawn and identifying the type of graphic symbol in the identified region.
[0013] The information processing device according to the eighth embodiment is an information processing device according to the seventh embodiment in which the region is identified by a trained model for identifying the region in the image data where the graphic symbol is drawn, and the type of the graphic symbol is identified by a trained model for identifying the type of the graphic symbol in the identified region.
[0014] The information processing device according to the ninth embodiment, in the information processing device according to the seventh or eighth embodiment, includes data obtained in advance by identifying the descriptions of numbers and strings in the identified area.
[0015] In the information processing device according to the tenth embodiment, the related information is identified by a trained model for identifying the descriptions of numbers and strings in the identified area, as in the information processing device according to the ninth embodiment.
[0016] The information processing device according to the 11th embodiment is an information processing device according to any one of the first to tenth embodiments, wherein the receiving unit receives the graphic symbol specified by the user operating the user terminal from an input screen for receiving the specification of the graphic symbol displayed on the user terminal, and the output unit displays an output screen on the user terminal showing the target image data.
[0017] The information processing device according to the twelfth embodiment is an information processing device according to any one of the first to eleventh embodiments, wherein the data format of the image data is at least one of raster data format and vector data format.
[0018] The information processing method according to the 13th embodiment involves a computer that receives a specification of a graphic symbol related to the processing of an object, and outputs a target image data corresponding to the received graphic symbol from among a plurality of image data in which the object to be processed and the graphic symbol are drawn.
[0019] The information processing program according to the 14th embodiment receives a specification of a graphic symbol related to the processing of an object, and causes a computer to perform a process that outputs target image data corresponding to the received graphic symbol from among a plurality of image data in which the object to be processed and the graphic symbol are drawn. [Effects of the Invention]
[0020] According to this disclosure, drawing data can be searched by intuitively specifying information related to the processing. [Brief explanation of the drawing]
[0021] [Figure 1] This figure shows an example of the schematic configuration of the information processing system of this embodiment. [Figure 2] This figure shows an example of the schematic configuration of the trained model storage unit of this embodiment. [Figure 3] This figure shows an example of symbol-related information used in this embodiment. [Figure 4] It is a schematic block diagram of a computer that functions as each device of the information processing system of this embodiment. [Figure 5] It is a block diagram showing an example of the functional configuration of the information processing apparatus of this embodiment. [Figure 6] It is a diagram showing an example of the image data of this embodiment. [Figure 7] It is a diagram showing an example of the image data of this embodiment. [Figure 8] It is a diagram showing an example of the image data of this embodiment. [Figure 9] It is an example of a screen displayed on the display unit of the user terminal of this embodiment. [Figure 10] It is an example of a screen displayed on the display unit of the user terminal of this embodiment. [Figure 11] It is an example of a screen displayed on the display unit of the user terminal of this embodiment. [Figure 12] It is an example of a screen displayed on the display unit of the user terminal of this embodiment. [Figure 13] It is a flowchart showing an example of the flow of the creation process of this embodiment. [Figure 14] It is a sequence diagram showing an example of the information exchange between the user terminal and the information processing apparatus of this embodiment. [Figure 15] It is a flowchart showing an example of the flow of the search process of this embodiment.
Mode for Carrying Out the Invention
[0022] Hereinafter, the information processing system 10 according to this embodiment will be described with reference to the drawings. In each drawing, the same or equivalent components are given the same reference numerals. Also, the dimensional ratios in the drawings are exaggerated for convenience of explanation and may be different from the actual ratios. Further, the present disclosure is not limited to the following embodiments, and can be implemented with appropriate modifications within the scope of the object of the present disclosure.
[0023] <Summary of this embodiment> Drawings contain various elements in addition to depicting the object itself, such as a title block containing management information, dimension lines and values, and various notes. Furthermore, some drawings use various symbols to indicate processing methods and specifications; the position, number, and type of these symbols vary depending on the intended processing method. Hereafter, the object will also be referred to as the "workpiece."
[0024] Symbols include, for example, welding symbols that indicate the method of joining components, and geometric tolerance symbols that indicate dimensional and machining precision. These symbols are written in a symbolic system specific to each field in order to accurately communicate manufacturing processes and quality requirements, and their interpretation requires specialized knowledge.
[0025] On the other hand, since the symbols included in drawings affect the difficulty of machining and the complexity of the process, converting them into computer-handled data can be expected to significantly improve the efficiency of various tasks, such as data extraction, aggregation, and searching for drawings based on machining difficulty.
[0026] Incidentally, there is prior art related to symbol recognition. Such prior art claims to be able to extract symbols written on drawings and count the number of extracted symbols. However, such prior art evaluates the degree of agreement with a pre-set template, but for example, even if the welding symbol is the same fillet weld symbol, its shape changes depending on its position in the drawing, so it cannot recognize symbols with different shapes that mean the same fillet weld as the same data.
[0027] In the case of fillet welding, the leg length, number of welds, and total weld length vary depending on the welding location. Therefore, numbers indicating leg length and other parameters are sometimes written near the symbol. This welding symbol only makes sense when it is used in conjunction with the numerical indications for leg length and other parameters, as well as the right-angled isosceles triangle shape representing fillet welding. Here, "near the symbol" refers to areas such as the same baseline and the area around the symbol where numerical values and strings of characters related to the symbol are usually written. In addition, among the leader lines used to explain drawings, the arrow portion is called an "arrow," and the straight line to which numbers and symbols are attached is called the "baseline."
[0028] In another example, the symbol for geometric tolerance indicating flatness is a parallelogram. The degree of flatness specified must be interpreted in conjunction with the notation written near the symbol, such as 0.02 / 1000 (allowing deviation of up to 0.02 millimeters within a range of 1000 millimeters), for the symbol to be meaningful.
[0029] Therefore, the information processing device 16 of this embodiment performs a search of drawing data using symbol-related information (see Figure 3), which is pre-dataified by combining various symbols that indicate processing methods and specifications with descriptions in the vicinity of those symbols.
[0030] <Configuration of Information Processing System 10> Figure 1 is a block diagram showing an example of the schematic configuration of the information processing system 10 according to this embodiment. As shown in Figure 1, the information processing system 10 of this embodiment comprises an information processing device 16 and a plurality of user terminals 18A, 18B, and 18C. In the following, unless a specific terminal is being referred to, one user terminal will be referred to as user terminal 18. The information processing device 16 and the user terminals 18 are connected to each other via a network 19, such as the Internet. Although three user terminals 18 are shown in Figure 1, at least one user terminal 18 is sufficient.
[0031] (Information processing device 16) The information processing device 16 is a server that responds to information transmitted from the user terminal 18. As shown in Figure 1, the information processing device 16 includes a trained model storage unit 28, an image database 30, and a related data storage unit 32. The image database 30 is an example of a "database" as defined in this disclosure.
[0032] The information processing device 16 receives drawing data (hereinafter referred to as image data) on which a workpiece such as a part is drawn, and stores it in the image database 30. The information processing device 16 also identifies various information drawn on the image data using a trained model, which will be described later, and creates symbol-related information for searching multiple image data stored in the image database 30 based on the identification result. The symbol-related information in this embodiment is in table format. When the information processing device 16 searches for image data that satisfies the search conditions from among multiple image data stored in the image database 30, it searches for the image data by referring to the symbol-related information.
[0033] The trained model storage unit 28 stores trained models for identifying information within image data. Figure 2 is a block diagram showing an example of trained models stored in the trained model storage unit 28. As shown in Figure 2, the trained model storage unit 28 stores a trained model 28A for symbol region detection, a trained model 28B for symbol type identification, and a trained model 28C for character identification. These trained models are models that have been pre-built using known artificial intelligence techniques and known machine learning techniques. Machine learning models equivalent to trained models include, for example, convolutional neural networks. In this embodiment, the case of identifying information within image data using a machine learning-based trained model will be explained as an example, but instead of using only trained models, rule-based methods may also be used in combination.
[0034] The pre-trained model 28A for symbol region detection in Figure 2 is a pre-trained model that, upon input of image data, detects and outputs a symbol region, which is the region containing the machining symbols described in the image data. The symbol region may also include a region where values related to the machining symbols are drawn. Hereinafter, machining symbols will also be referred to as "machining symbols." Values related to machining symbols will also be referred to as "specified values." Specifically, upon input of image data, image data of the symbol region, which is part of the image data, is output. At this time, coordinate data indicating the coordinates of the output image may be acquired as metadata. The acquired coordinate data may also be used as symbol-related information. As an example, if the machining symbol is a welding symbol, the symbol region is a rectangular region containing the "baseline," "welding symbol," and "numerical and string descriptions." Note that the symbol region may also include an "arrow." As another example, if the machining symbol is a geometric tolerance symbol, the symbol region is a rectangular region containing the "geometric tolerance symbol" enclosed in a square frame, and "numerical and alphabetical descriptions." The output coordinate data includes, for example, the x-coordinate representing the horizontal coordinate of the image data and the y-coordinate representing the vertical coordinate of the image data. The processing symbol is an example of the "graphic symbol" in this disclosure.
[0035] The pre-trained model 28B for symbol type identification is a pre-trained model that, upon input of image data of a symbol region, identifies and outputs the type of processing symbol described in the image data of the symbol region. Specifically, when image data of a symbol region output by the pre-trained model 28A for symbol region detection is input, symbol type data indicating the type of processing symbol contained in the symbol region is output. The type of processing symbol may be a broad category such as welding symbols and geometric tolerance symbols, a medium category such as fillet welds, groove welds and flatness, or a minor category such as staggered intermittent welds and V-groove welds. By using a machine learning model for symbol type identification, it becomes possible to identify "arrows" and "baselines" whose shapes differ depending on the location on the drawing. The type of processing symbol is an example of the "type of graphic symbol" in this disclosure.
[0036] The pre-trained model 28C for character recognition is a pre-trained model that, upon input of image data of a symbol region, identifies numbers and strings related to the processing symbols written in the symbol region and outputs them as structured data with a certain meaning. Hereinafter, numbers and strings will be collectively referred to as "strings". Specifically, when image data of a symbol region output by the pre-trained model 28A for symbol region detection is input, the strings contained in the symbol region are obtained and data with a certain meaning is output. Identified strings include, for example, strings located above and below the same baseline as the baseline on which the welding symbol is drawn, and strings located within a frame continuous with the rectangular frame on which the geometric tolerance symbol is drawn. More specifically, the data with a certain meaning is not just the character data "6", but numerical data with meaning such as "the welding pitch is 6 millimeters". This data is an example of the "symbol-related information" in this disclosure.
[0037] Furthermore, when the pre-trained character recognition model 28C identifies a string of characters above the baseline and a string of characters below the baseline, it outputs each identified string as separate data associated with the basic shape on each side of the baseline.
[0038] The image database 30 in Figure 1 stores image data. Specifically, the image database 30 stores image data received by the information processing device 16. The file size of the image data stored in the image database 30 is not a factor. The image data stored in the image database 30 may be resized (reduced) to the minimum size necessary for analysis. The data format of the multiple image data stored in the image database 30 is, for example, at least one of raster data format and vector data format.
[0039] Here, each image data stored in the image database 30 is input to the pre-trained model 28A for symbol region detection described above, and image data of the symbol region, which is a part of the image data, is output. At this time, coordinate data indicating the coordinates of the output image may be obtained as metadata. Furthermore, by inputting the image data output by the pre-trained model 28A for symbol region detection to the pre-trained model 28B for symbol type identification, the symbol type data of the processed symbols included in the symbol region is identified. Then, by inputting the image data output by the pre-trained model 28A for symbol region detection to the pre-trained model 28C for character recognition, the strings included in the symbol region are identified and output as structured data with a certain meaning. Alternatively, the pre-trained model 28A for symbol region detection and the pre-trained model 28B for symbol type identification may be configured as a single pre-trained model, and coordinate data and symbol type data may be output by inputting image data into this pre-trained model.
[0040] The related data storage unit 32 stores symbol-related information for each graphic symbol in the multiple image data stored in the image database 30. Figure 3 shows an example of symbol-related information. As shown in Figure 3, the symbol-related information is associated with "Symbol No.", "Drawing ID", coordinates, symbol type, instruction, instruction value, and "Pair No.". Note that the part after "..." in the symbol-related information of Figure 3 stores various data about other image data.
[0041] The symbol number is a number used to identify symbol-related information for each processing symbol. The drawing ID is an ID used to identify the image data associated with the symbol-related information.
[0042] The coordinates are the coordinates of a specified symbolic area. Specifically, the coordinates include "position1x" indicating the x-coordinate of the lower left corner of the rectangular area, "position1y" indicating the y-coordinate, and "position2x" indicating the x-coordinate of the upper right corner of the rectangular area, and "position2y" indicating the y-coordinate.
[0043] The symbol type includes "Symbol Type 1," "Symbol Type 2," and "Symbol Type 3" as items, corresponding to the classification of the processing symbol types.
[0044] The instructions and instruction values include items such as "Instruction 1," "Instruction 1 Value," "Instruction 2," and "Instruction 2 Value," depending on the type of processing symbol. Note that the number of items for symbol type, instruction, and instruction value is not limited to the number shown in Figure 3. Furthermore, the symbol-related information may consist of, for example, a table holding coordinate data, a table holding symbol type data, and a table holding data in which strings are identified and given a certain meaning.
[0045] The symbol-related information shown in Figure 3 provides, as an example, details of the data obtained from each symbol region acquired from image data with drawing ID "dr0000001". For example, symbol No. "0001" includes position 1x "10", position 1y "10", position 2x "30", position 2y "30", symbol type 1 "welding", symbol type 2 "fillet weld", and symbol type 3 "staggered intermittent weld", and is further associated with image data with drawing ID "dr0000001". In addition, symbol No. "0001" includes instruction 1 "number", instruction 1 numerical value "2", instruction 2 "pitch", instruction 2 numerical value "6", and pair No. "0002".
[0046] Here, position 1x "10", position 1y "10", position 2x "30", and position 2y "30" are coordinates that indicate the symbol region detected by inputting the image data of drawing ID "dr0000001" into the aforementioned trained model 28A for symbol region detection. Furthermore, symbol type 1 "welding", symbol type 2 "fillet weld", and symbol type 3 "staggered intermittent" are symbol type data output by inputting the image data of the symbol region obtained by inputting the image data of drawing ID "dr0000001" into the aforementioned trained model 28A for symbol region detection into the aforementioned trained model 28B for symbol type identification. In other words, the symbol type of symbol No. "0001" is a welding symbol, and it is indicated that it is a staggered intermittent fillet weld, a type of fillet weld.
[0047] Furthermore, instruction 1 "Number", instruction 1 numerical value "2", instruction 2 "Pitch", and instruction 2 numerical value "6" are data output by inputting the image data of the symbol region obtained by inputting the image data of drawing ID "dr0000001" into the aforementioned trained model 28A for symbol region detection into the aforementioned trained model 28C for character recognition. In other words, the processing instruction indicated by symbol No. "0001" indicates that the number of welds is 2 and the pitch is 6 (for example, 6 millimeters).
[0048] Furthermore, the pair No. "0002" indicates the symbol No. that is paired with symbol No. "0001". In other words, the symbol-related information for symbol No. "0001" and the symbol-related information for symbol No. "0002" refer to the same symbol area, and each indicates a string of characters written above or below the baseline. For example, the symbol-related information for symbol No. "0001" contains data indicating a string of characters written above the baseline, while the symbol-related information for symbol No. "0002" contains data indicating a string of characters written below the baseline.
[0049] The processing program 40 is a program that executes various processes, including those described later (see Figures 13 to 15). When the processing program 40 is executed, the information processing device 16 uses various hardware resources (see Figure 4) to execute the processes based on the processing program 40.
[0050] (User terminal 18) The user terminal 18 is a terminal operated by the user. Specifically, the user exchanges information with the information processing device 16 by operating the user terminal 18. Specifically, the user terminal 18 displays a display screen (not shown) transmitted from the information processing device 16, which will be described later, on the display unit (not shown) that the user terminal 18 has. In addition, the user terminal 18 transmits search conditions for searching image data to the information processing device 16 through user operation.
[0051] <Hardware configuration of each device> Figure 4 is a schematic block diagram of the computer 70, which functions as one of the devices in the information processing system 10 according to this embodiment.
[0052] The information processing device 16 and the user terminal 18 of the information processing system 10 can each be implemented by, for example, the computer 70 shown in Figure 4. The computer 70 includes a CPU 71, a memory 72 as a temporary storage area, and a non-volatile storage unit 73. The computer 70 also includes an input / output interface (I / F) 74 to which input / output devices (not shown) are connected, and a read / write (R / W) unit 75 that controls the reading and writing of data to the recording medium. The computer 70 also includes a network I / F 76 that connects to a network such as the Internet. The CPU 71, memory 72, storage unit 73, input / output I / F 74, R / W unit 75, and network I / F 76 are connected to each other via a bus 77.
[0053] The storage unit 73 can be implemented using a hard disk drive (HDD), solid state drive (SSD), flash memory, etc. The storage unit 73, as a storage medium, stores the program necessary for the computer 70 to function. The CPU 71 reads the program from the storage unit 73, loads it into memory 72, and sequentially executes the processes contained in the program.
[0054] <Functional configuration of the information processing device 16> Figure 5 is a block diagram showing an example of the functional configuration of the information processing device 16 according to this embodiment.
[0055] In this embodiment, the information processing device 16 functions as a receiving unit 16A, a creation unit 16B, a display control unit 16C, a search unit 16D, and an output unit 16E when the CPU 71 executes a program (not shown).
[0056] The reception unit 16A has the function of receiving various types of data. Specifically, the reception unit 16A receives image data. For example, the reception unit 16A receives image data provided by the user terminal 18 and stores it in the image database 30.
[0057] Furthermore, the reception unit 16A receives data for search conditions to search for multiple image data stored in the image database 30. Specifically, the reception unit 16A receives data indicating the specification of processing symbols transmitted from the user terminal 18. The reception unit 16A also receives data such as specified values related to processing symbols transmitted from the user terminal 18. Specified values related to processing symbols are, for example, numerical values indicating the total number of welding locations and the range of geometric tolerances. Specified values related to processing symbols are an example of "symbol-related information".
[0058] The creation unit 16B has the function of creating symbol-related information. Specifically, the creation unit 16B creates symbol-related information from the output data by inputting the image data received by the reception unit 16A into the trained model stored in the trained model storage unit 28.
[0059] Furthermore, the creation unit 16B stores the symbol-related information output from the trained model in association with the original image data. Specifically, the creation unit 16B creates a table as shown in Figure 3. The creation unit 16B may also create paired symbol-related information depending on the type of processing symbol. For example, the creation unit 16B may create paired symbol-related information when the type of processing symbol is a type of processing symbol in which a string of characters is written above and below the baseline, such as staggered intermittent fillet welding.
[0060] The display control unit 16C has a function to display an input screen. Specifically, the display control unit 16C displays an input screen that includes an area where processing symbols can be specified. The display control unit 16C then displays multiple images in which processing symbols are drawn in the area where processing symbols can be specified (see Figure 10, etc.). An image in which processing symbols are drawn is an example of a "symbol image" in this disclosure.
[0061] The search unit 16D has the function of searching for image data that satisfies the received search conditions (hereinafter also referred to as target image data). Specifically, the search unit 16D identifies the target image data by searching for multiple image data stored in the image database 30 based on the search condition data received by the reception unit 16A.
[0062] Furthermore, when the search unit 16D searches for target image data that meets the search criteria from among multiple image data stored in the image database 30, it refers to the symbol-related information stored in the related data storage unit 32 to perform the search.
[0063] The output unit 16E has the function of outputting search results. Specifically, the output unit 16E outputs an output screen containing the target image data searched by the search unit 16D as the search result (see Figure 9, etc.).
[0064] Furthermore, the output unit 16E highlights and displays the areas of the output image data that match the accepted search conditions. For example, when displaying the output image data, the output unit 16E highlights the symbol area containing the processing symbol specified as a search condition. Here, highlighting is a display method that involves inverting the character color and background color of a string or changing the background color to a specific color. The area that matches the search conditions is an example of the "area corresponding to the specified graphic symbol" in this disclosure.
[0065] <Image data> Figures 6 to 8 show examples of image data according to this embodiment.
[0066] (Drawing DW1) The image data shown in Figure 6 contains drawing DW1, which is an example of a drawing that includes welding symbols. Drawing DW1 includes a top view V10, a front view V11, a side view V12, machining instructions Ins10, Ins11, Ins12, and a title block T.
[0067] Plan view V10 is a plan view of the workpiece O1 as seen from above. Plan view V10 also contains machining instructions Ins10 for the workpiece O1. Machining instructions Ins10 include the notation "2, welding symbol indicating fillet weld, (2), 6" above the baseline and the notation "2, welding symbol indicating fillet weld, (3), 6" below the baseline. The notation above the baseline is slightly shifted to the left compared to the notation below the baseline. This shift is such that the positions of the welding symbols indicating fillet welds above the baseline and below the baseline partially overlap. Based on these notations, machining instructions Ins10 indicates that the machining at the location indicated by the arrow tip is a staggered intermittent fillet weld, the weld leg length is 2 millimeters, there is no specification for the weld width, there are 3 welding locations (2 on the opposite side), and the weld pitch is 6 millimeters.
[0068] Front view V11 is a front view of the workpiece O1 as seen from the front. Front view V11 also shows the machining instruction Ins11 for the workpiece O1. Note that the location indicated by the arrow tip of machining instruction Ins10 and the location indicated by the arrow tip of machining instruction Ins11 are the same location, and since machining instruction Ins10 and machining instruction Ins11 have the same content, a detailed explanation of machining instruction Ins11 is omitted.
[0069] Side view V12 is a side view of the workpiece O1 as seen from the right side. Side view V12 also includes machining instruction Ins12 for the workpiece O1. Machining instruction Ins12 includes the notation "1.5, welding symbol indicating a V-groove weld" below the baseline and the notation "45" below the welding symbol indicating a V-groove weld. These notations indicate that machining instruction Ins12 is a V-groove weld at the location indicated by the tip of the arrow, with a groove depth of 6 millimeters and a groove angle of 45 degrees.
[0070] The title block T is an area for organizing and displaying information related to the drawing.
[0071] As shown in the machining instructions Ins10, Ins11, and Ins12 above, the entire description of the arrow, baseline, welding symbol, and numbers represents a single machining instruction.
[0072] (Drawing DW2) The image data shown in Figure 7 contains drawing DW2, an example of a drawing with geometric tolerance symbols. Drawing DW2 includes a front view V20, a bottom view V21, machining instructions Ins20 and Ins21, and a title block T. Since title block T is the same as that in Figure 6, a detailed explanation is omitted.
[0073] Figure 7, front view V20, is a front view of the workpiece O2 as seen from the front. Front view V20 also includes machining instruction Ins20 for the workpiece O2. Machining instruction Ins20 includes the notation "Geometric tolerance symbol indicating perpendicularity, 0.02, A" enclosed in a square frame. These notations indicate that machining instruction Ins20 must be located within two parallel planes separated by 0.02 millimeters and perpendicular to the datum plane A described later. Here, the datum plane refers to a reference plane, for example, a plane used as a reference plane in the vertical direction.
[0074] The bottom view V21 is a bottom view of the workpiece O2 as seen from below. The bottom view V21 also contains the machining instruction Ins21 for the workpiece O2. The machining instruction Ins21 includes the letter "A" enclosed in a square frame. This indicates that the plane indicated by the straight line with a downward-pointing black triangle is the datum plane A.
[0075] (Drawing DW3) The image data shown in Figure 8 contains drawing DW3, an example of a drawing with geometric tolerance symbols. Drawing DW3 includes a front view V30, a side view V31, machining instructions Ins30, and a title block T. Since title block T is the same as that in Figure 6, a detailed explanation is omitted.
[0076] Figure 8, front view V30, is a front view of the workpiece O3 as seen from the front. Front view V30 also includes machining instruction Ins30 for the workpiece O3. Machining instruction Ins30 includes the geometric tolerance symbol indicating roundness, 0.1, enclosed in a square frame. These markings indicate that machining instruction Ins30 requires that the outer circumference of the cross section perpendicular to the axis at the point indicated by the arrowhead must lie between two concentric circles separated by 0.1 millimeters on the same plane.
[0077] Side view V31 is a side view of the workpiece O3 as seen from the side.
[0078] As shown in machining instructions Ins20 and Ins21 in Figure 7, and machining instruction Ins30 in Figure 8, the geometric tolerance symbol and the surrounding inscription together represent a single machining instruction.
[0079] Users may want to uniformly search for image data containing their desired machining instructions from a database that stores a mixture of drawings, such as drawings with welding symbols (see Figure 6) and drawings with geometric tolerance symbols (see Figures 7 and 8). However, as mentioned above, the entire description of arrows, baselines, welding symbols, and numbers represents a single machining instruction, and the entire description of geometric tolerance symbols and their surroundings also represents a single machining instruction. Therefore, even if symbol identification or character identification is performed on the image data, it is not possible to obtain information about the entire machining instruction from that alone. For this reason, processing is required to identify information related to a single machining symbol and aggregate information about the entire machining instruction (for example, identification using a machine learning model, and identification using a rule-based system). In this embodiment, various identification processes are performed using various trained models as described above, and symbol-related information is created based on the identification results.
[0080] <Display screen> Figures 9 to 12 show examples of display screens shown on the user terminal 18 according to this embodiment. The user searches for image data that satisfies the search conditions set by operating the screens shown in Figures 9 to 12. In each drawing, similar components are denoted by the same reference numerals, and detailed explanations are omitted. Display screens S1, S2, S3, and S4, described later, are examples of "input screens" in this disclosure. Display screens S1 and S4, described later, are examples of "output screens" in this disclosure.
[0081] (Display screen S1) The display screen S1 shown in Figure 9 consists of a search bar B for specifying search criteria and a results area R for displaying search results. The search bar B is displayed at the top of the display screen S1. The results area R is displayed below the search bar B.
[0082] Search bar B has an input field where search criteria can be entered. Search bar B also has a button to display screen S2 (see Figure 10), where detailed search criteria can be specified. For example, a user can enter keywords in the "Enter Keyword" field on screen S1 and click the magnifying glass icon to perform a search for image data that meets the search criteria represented by the entered keywords.
[0083] The results area R is the area that displays the search results for image data that meet the search criteria. In this embodiment, the results area R displays thumbnail images of multiple target image data. In addition, supplementary information such as the order history of the drawing drawn on the target image data is displayed along with the thumbnail image of each target image data. When the user clicks on the thumbnail image of each target image data, the original size image data, as shown in drawing DW1 (see Figure 6), is displayed.
[0084] (Display screen S2) As shown in Figure 10, the display screen S2 consists of a selection area J1, an input area J2, a selection area J3, an input area J4, and a confirmation area J5. The selection area J1 is displayed in the left-hand area when the middle section of the display screen S2 is divided into left and right sections. The input areas J2, J3, and J4 are displayed in the right-hand area when the middle section of the display screen S2 is divided into left and right sections. The confirmation area J5 is displayed at the bottom of the display screen S2.
[0085] Selection area J1 is equipped with checkboxes that allow the user to select the symbol classification to be used for searching. In this embodiment, selection area J1 displays a "Welding" checkbox for specifying welding symbols and a "Geometric Tolerance" checkbox for specifying geometric tolerance symbols. In this embodiment, checking each checkbox displays the corresponding selection area or input area. For example, in display screen S2, the "Welding" checkbox is checked, and input area J2, selection area J3, and input area J4 are displayed.
[0086] Input area J2 has an input field for specifying the range of the total number of welding symbols shown in the drawing, regardless of the type of welding symbol. In the example drawing, the total number of welding symbols is specified, but it may also be possible to specify the total number of welds or the total length of the welds.
[0087] Selection area J3 contains multiple images on which welding symbols are drawn. The images in selection area J3 of this embodiment are images on which welding symbols for "fillet weld / parallel intermittent / staggered intermittent," "spot / projection," "V-groove," "V-groove," "V-flare," "I-groove," and "full circumference weld" are drawn. When an image is selected, the welding symbol corresponding to the selected image is specified as a search criterion. In addition, an input field where the user can specify values related to the welding symbol specified in selection area J3 is displayed in input area J4, which will be described later. In this embodiment, an image on which the welding symbol for fillet welding is drawn, an image on which the welding symbol for V-groove welding is drawn, and an image on which the welding symbol for I-groove welding is drawn are selected. The user can select one or more welding symbols to search for.
[0088] Input area J4 includes input fields for specifying the range of the total number of welding symbols for each type of welding symbol. In this embodiment, input area J4 displays input fields for specifying the range of the total number of welding symbols for I-groove welds, for specifying the range of the total number of welding symbols for V-groove welds, and for specifying the range of the total number of welding symbols for fillet welds. In this embodiment, the input field for specifying the range of the total number of welding symbols for I-groove welds is set to a minimum value of 0 and a maximum value of 20. Similarly, the input field for specifying the range of the total number of welding symbols for V-groove welds is set to a minimum value of 0 and a maximum value of 20. Similarly, the input field for specifying the range of the total number of welding symbols for fillet welds is set to a minimum value of 0 and a maximum value of 20. Input area J4 may also include input fields for specifying other values for each welding symbol. For example, input area J4 may include input fields for specifying the leg length, number of weld locations, weld length, and pitch of a fillet weld.
[0089] The decision area J5 is equipped with buttons for determining search conditions. The decision area J5 is equipped with a "Cancel" button to cancel the specified search conditions and a "Refine" button to confirm the specified search conditions. Specifically, clicking the "Cancel" button allows the user to transition from display screen S2 to display screen S1 (see Figure 9) without changing the search conditions. Clicking the "Refine" button allows the user to perform a search with the specified search conditions.
[0090] (Display screen S3) As shown in Figure 11, the display screen S3 consists of a selection area J1, an input area J2, a selection area J3, a confirmation area J5, an input area J6, a selection area J7, and an input area J8. The selection area J1 is displayed in the left-hand area when the middle section of the display screen S3 is divided into left and right sections. The input areas J2, J3, J6, J7, and J8 are displayed in the right-hand area when the middle section of the display screen S3 is divided into left and right sections. The confirmation area J5 is displayed at the bottom right of the display screen S3.
[0091] Selection area J1 has checkboxes that allow you to select the symbol classification to use for searching. For example, on display screen S3, the "Welding" checkbox and the "Geometric Tolerance" checkbox are checked, and input area J2 and selection area J3 for specifying search conditions related to welding symbols, as well as input area J6, selection area J7, and input area J8 for specifying search conditions related to geometric tolerance symbols are displayed.
[0092] Input area J6 includes an input field for specifying the range of geometric tolerances for the entire drawing. In this embodiment, the input field of input area J6 is set to input 0.002 as the minimum value and 0.5 as the maximum value.
[0093] The selection area J7 contains multiple images on which geometric tolerance symbols are drawn. The images in the selection area J7 of this embodiment are images on which the geometric tolerance symbols for "flatness," "roundness," "parallelism," "perpendicularity," "positionality," "coaxiality / concentricity," and "symmetry" are drawn. When an image is selected, the geometric tolerance symbol corresponding to the selected image is specified as a search criterion. In addition, an input field where you can specify values related to the geometric tolerance symbol specified in the selection area J7 is displayed in the input area J8, which will be described later. In this embodiment, the image on which the geometric tolerance symbol for parallelism is drawn and the image on which the geometric tolerance symbol for positionality is drawn are selected.
[0094] Input area J8 is provided with input fields for specifying tolerance ranges for each type of geometric tolerance symbol. In this embodiment, input area J8 displays input fields for specifying the tolerance range for parallelism and input fields for specifying the tolerance range for positional tolerance. In this embodiment, the input field for specifying the tolerance range for parallelism is set to a minimum value of 0.002 and a maximum value of 0.5. Similarly, the input field for specifying the tolerance range for positional tolerance is set to a minimum value of 0.002 and a maximum value of 0.5.
[0095] (Display screen S4) As shown in Figure 12, the display screen S4 consists of a search bar B, selection area J7, selection area J3, confirmation area J9, and result area R. The search bar B is displayed at the top of the display screen S4. The selection areas J7, J3, and confirmation area J9 are located below the search bar B and are displayed in the left-hand area when the display screen S4 is divided into left and right sections. The result area R is located below the search bar B and is displayed in the right-hand area when the display screen S4 is divided into left and right sections. In this embodiment, download and share buttons are located below the search bar B, allowing users to download symbol-related information (see Figure 3) corresponding to the search results.
[0096] The determination area J9 is equipped with a "Search" button to perform a search. Specifically, clicking the "Search" button allows the user to specify the processing symbols corresponding to the images selected in the selection areas J7 and J3 as search criteria and perform a search. Then, thumbnail images of target image data that satisfy the search criteria are displayed in the results area R.
[0097] By operating screens as shown in Figures 9 to 12, users can search the image database 30 for image data containing a specified processing symbol. Furthermore, by specifying a processing symbol along with related values, users can search for image data that matches those values. Since the symbol-related information is stored in association with the type of processing symbol for each image data and the related values, users can search the image database 30 simply by specifying the search conditions as described above, without any input burden.
[0098] Furthermore, by using the screen configuration shown in Figure 12, it is possible to specify search criteria and execute a search within a single screen without transitioning to another screen. Also, the "Cancel" button that was displayed on display screen S2 (see Figure 10) becomes unnecessary. Moreover, the buttons for executing the search can be placed anywhere on the screen, and there can be multiple buttons. For example, the buttons for executing the search are the magnifying glass icon displayed on search bar B and the "Search" button placed in the selection area J9. Therefore, after specifying the search criteria, the user can easily execute the search.
[0099] <Operation of Information Processing System 10> Next, the operation of the information processing system 10 of this embodiment will be described.
[0100] (Process for creating symbol-related information) The information processing device 16 creates symbol-related information based on image data by executing a creation process. Figure 13 is a flowchart of an example of the creation process according to this embodiment. The creation process is performed by the CPU 71 of the information processing device 16 reading a program from the storage unit 73, loading it into the memory 72, and executing it. In this embodiment, the information processing device 16 updates the symbol-related information by executing the creation process on the image data each time new image data is received.
[0101] In step S100 of Figure 13, the CPU 71 accepts the registration of image data on which a drawing will be rendered. Specifically, the CPU 71 accepts the image data, assigns a drawing ID to it, and stores it in the image database 30. Each time the CPU 71 accepts new image data, it assigns a drawing ID to the accepted image data and stores it in the image database 30. As a result, multiple image data files are stored in the image database 30.
[0102] In step S102, the CPU 71 detects symbol regions containing symbols to be drawn in the image data. Specifically, the CPU 71 outputs image data of symbol regions by inputting the image data received in step S100 into a trained model 28A for symbol region detection. For example, if image data on which drawing DW1 (see Figure 6) is drawn is input, the image data of the rectangular region indicated by the x-coordinates "10" and y-coordinates "10" of the lower left corner, and the x-coordinates "30" and y-coordinates "30" of the upper right corner is output as one of the symbol regions.
[0103] In step S104, the CPU 71 identifies the type of symbol. Specifically, the CPU 71 inputs the image data of the symbol region output in step S102 into a trained model 28B for symbol type identification, thereby outputting symbol type data of the machining symbol contained in the symbol region. For example, if image data of the symbol region corresponding to machining instruction Ins10 detected from drawing DW1 (see Figure 6) is input, the CPU 71 outputs that the type of machining symbol contained in the detected symbol region is staggered intermittent fillet welding.
[0104] In step S106, the CPU 71 identifies the string in the symbol region. Specifically, the CPU 71 inputs the image data of the symbol region output in step S102 into a trained model 28C for character recognition, thereby identifying the string contained in the symbol region and outputting data with a certain meaning. For example, if image data of drawing DW1 (see Figure 6) is input, the data of the string contained in the detected symbol region will be output as leg length "2", number of welds "2", and pitch "6". In addition, the corresponding data will be output as leg length "2", number of welds "3", and pitch "6".
[0105] The CPU 71 processes the results obtained by the various trained models described above (for example, coordinate data, symbol type data, and data representing strings) into a more manageable format or performs editing to remove inappropriate data. For example, it removes the character "φ" from the reading result "φ0.197" to obtain only numerical data. The CPU 71 also processes the results obtained by the various trained models into a more manageable format or performs editing to remove inappropriate data, for example, using a method disclosed in Japanese Patent Publication No. 7377565.
[0106] In step S108, the CPU 71 stores the detected information and identified information. Specifically, the CPU 71 stores symbol-related information, which is formatted for each symbol number, such as coordinate data which is metadata of the symbol region image detected in step S102, symbol type data identified in step S104, and data indicating the string identified in step S106, in the related data storage unit 32. Specifically, the CPU 71 assigns a "Symbol No." to each of the coordinate data, symbol type data, and string data output for each symbol region obtained in each step. Next, if there is a pair of symbol-related information, the CPU 71 assigns the symbol No. of the pair of symbol-related information as the "Pair No." Then, the CPU 71 formats this data for each symbol No. and adds a drawing ID to create symbol-related information that is associated with the image data. The CPU 71 creates symbol-related information as shown in Figure 3, for example. This symbol-related information is referenced in the search process described later. Then, the CPU 71 terminates the creation process.
[0107] (Sequence diagram of information processing system 10) Next, we will describe a scenario in which a user operates their user terminal 18 to search for and display target image data. Figure 14 is a sequence diagram showing an example of information exchange between the information processing device 16 and the user terminal 18 according to this embodiment. By operating their user terminal 18 and specifying search conditions that include processing symbols, the user can display image data on the display unit of the user terminal 18 in which a drawing containing the specified processing symbols is drawn.
[0108] In step S10 of Figure 14, the information processing device 16 displays the search criteria input screen on the user terminal 18. The information processing device 16 displays, for example, display screen S2 (see Figure 10) on the display unit of the user terminal 18.
[0109] In step S12, the user terminal 18 transmits the search criteria to the information processing device 16. For example, the user terminal 18 transmits data to the information processing device 16 that includes the welding symbol specified on the display screen S2 and the range of the total number of welding locations entered.
[0110] In step S14, the information processing device 16 executes a search process (see Figure 14) described later. The information processing device 16 obtains the search results output by executing the search process.
[0111] In step S16, the information processing device 16 displays the search results on the user terminal 18, highlighting the areas that match the search criteria. The information processing device 16 displays the search results output in step S14 on the user terminal 18. The information processing device 16 displays thumbnail images of multiple target image data, for example, as shown in the result area R of the display screen S1 (see Figure 9), on the display unit of the user terminal 18. When displaying thumbnail images of multiple target image data, the information processing device 16 highlights the symbol area containing the specified processing symbol. The information processing device 16 may also highlight the symbol area containing the specified processing symbol on the original-size image data displayed when a thumbnail image of the target image data is clicked.
[0112] (Search process) Figure 15 is a flowchart showing an example of the search process according to this embodiment. The search process is performed by the CPU 71 of the information processing device 16 reading a program from the storage unit 73, loading it into the memory 72, and executing it. The search process is, as an example, the process performed in step S14 of Figure 13.
[0113] In step S200 of Figure 15, the CPU 71 receives the search conditions. Specifically, the CPU 71 receives the search conditions sent in step S12.
[0114] In step S202, the CPU 71 searches for image data that satisfies the search criteria by referring to symbol-related information. Specifically, the CPU 71 searches for target image data that matches the range of welding symbols and the total number of welds specified as search criteria by referring to symbol-related information (see Figure 3).
[0115] In step S204, the CPU 71 outputs the search results. Specifically, the CPU 71 reads the target image data searched in step S202 from the image database 30 and outputs it as the search results. Alternatively, the CPU 71 may output thumbnail images of the target image data as the search results. Then, the CPU 71 terminates the search process.
[0116] (Summary of this embodiment) The information processing device 16 of this embodiment accepts the specification of a processing symbol as a search condition and outputs target image data in which the accepted processing symbol is drawn as a search result. Therefore, according to the information processing device 16 of this embodiment, drawing data can be searched by intuitively specifying information related to processing.
[0117] The information processing device 16 of this embodiment accepts the specification of a processing symbol as a search condition, and also accepts data such as specified values related to the accepted processing symbol, and outputs target image data that matches the specified processing symbol and the accepted specified values as a search result. Therefore, the information processing device 16 of this embodiment can improve the accuracy of the search results desired by the user.
[0118] In this embodiment, the information processing device 16, when receiving a specification of a processing symbol, displays multiple images on which processing symbols are drawn, and accepts the processing symbol indicated by the selected image as the search condition. Therefore, according to the information processing device 16 of this embodiment, even users who do not know the name of the processing symbol can perform a search. In addition, compared to searching by entering keywords, it is possible to prevent inconsistencies in search results due to variations in keyword spelling.
[0119] The information processing device 16 of this embodiment highlights the symbol area in the target image data that contains the processing symbol received as a search condition. Therefore, with the information processing device 16 of this embodiment, the user can intuitively understand where in the drawing the processing symbol they searched for is located, which contributes to the convenience of their work.
[0120] The information processing device 16 of this embodiment searches for target image data from an image database 30 containing multiple image data, and outputs the searched target image data as a search result. Therefore, according to the information processing device 16 of this embodiment, it is possible to search for target image data from among the image data registered by the user.
[0121] The information processing device 16 of this embodiment searches for target image data by referring to symbol-related information, which includes the type of processing symbol and specified values associated with each processing symbol, obtained by pre-recognizing multiple image data and associated with each of the multiple image data. Therefore, the information processing device 16 of this embodiment can display search results more quickly compared to cases where image data is recognized each time a search is performed. Furthermore, it becomes possible to perform searches by specifying search conditions that include strings that form meaning together with the processing symbols.
[0122] In this embodiment, the information processing device 16 outputs image data of a symbol region on which processed symbols are drawn, when image data is input to a trained model 28A for symbol region detection. Furthermore, the information processing device 16 outputs symbol type data of the processed symbols drawn in the symbol region, when image data of the symbol region is input to a trained model 28B for symbol type identification. Therefore, according to the information processing device 16 of this embodiment, the accuracy of the search results can be improved by using pre-identified symbol type data.
[0123] In this embodiment, the information processing device 16 receives image data of a symbol region as input to a trained model 28C for character recognition, acquires data of numerical values and strings drawn in the symbol region, and outputs data with a certain meaning assigned to it. Therefore, according to the information processing device 16 of this embodiment, the accuracy of search results can be improved by utilizing the descriptions of numbers and strings that have been identified in advance.
[0124] The information processing device 16 of this embodiment receives the specification of a processing symbol from a display screen shown on the user terminal 18 and displays the display screen showing the target image data on the user terminal 18. Therefore, the information processing device 16 of this embodiment can reduce the processing load on the user terminal 18.
[0125] Furthermore, the configurations of the information processing system 10, information processing device 16, and user terminal 18 described in the above embodiment are examples and may be modified as needed without departing from the main purpose.
[0126] Furthermore, the program processing flow described in the above embodiment is just one example, and unnecessary steps may be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.
[0127] Furthermore, in the above embodiment, each process that the CPU reads and executes the software (program) may be executed by various processors other than the CPU. Examples of processors in this case include PLDs (Programmable Logic Devices) such as FPGAs (Field-Programmable Gate Arrays) whose circuit configuration can be changed after manufacturing, and dedicated electrical circuits such as ASICs (Application Specific Integrated Circuits) which have a circuit configuration specifically designed to execute a particular process.
[0128] Furthermore, the operation of the processor in the above embodiment may not be performed by a single processor, but may be performed by multiple processors located in physically separate locations working together. Also, the order of the processor operations is not limited to the order described in the above embodiment, but may be changed as appropriate.
[0129] Furthermore, although the above embodiments describe a configuration in which the information processing program is pre-stored (installed) on storage, the invention is not limited to this. The program may be provided in the form of recording on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), and USB (Universal Serial Bus) memory. Alternatively, the program may be provided in the form of download from an external device via a network. Moreover, this disclosure is also applicable to programs and program products.
[0130] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.
[0131] (Note) The following is an addendum regarding the nature of this disclosure.
[0132] (Note 1) A reception desk that accepts the designation of graphic symbols related to the processing of the object, An output unit outputs target image data corresponding to the received graphic symbol from among multiple image data in which the object to be processed and the graphic symbol are drawn, An information processing device equipped with the following features. (Note 2) The reception unit receives the designation of the graphic symbol and also receives the designation of symbol-related information, which is additional information related to the received graphic symbol. The output unit outputs the target image data corresponding to the graphic symbol and the symbol-related information when outputting the target image data. The information processing device described in Appendix 1. (Note 3) The system includes a display control unit that displays a plurality of symbolic images representing the aforementioned graphic symbols, When the receiving unit receives the designation of the graphic symbol, it receives the graphic symbol indicated by the symbol image selected from among the multiple symbol images displayed. The information processing device described in Appendix 1 or Appendix 2. (Note 4) The output unit is, The system highlights the region in the output target image data that corresponds to the specified graphic symbol. An information processing device as described in any one of the appendices 1 to 3. (Note 5) The system further includes a search unit that searches for the target image data from a database in which multiple image data are stored, The output unit outputs the target image data retrieved by the search unit. An information processing device as described in any one of the appendices 1 through 4. (Note 6) The aforementioned search unit, When searching for the target image data from among the multiple image data stored in the database, The target image data is searched by referring to symbol-related information, which is obtained by pre-recognizing multiple image data associated with the aforementioned image data and which includes the type of graphic symbol drawn in each of the image data associated with each of the aforementioned image data. The information processing device described in Appendix 5. (Note 7) The types of the aforementioned graphic symbols are: The data is obtained in advance by identifying the region in the image data where the graphic symbol is drawn, and identifying the type of graphic symbol in the identified region. The information processing device described in Appendix 6. (Note 8) The region is identified by a trained model for identifying the region in the image data where the graphic symbol is drawn. The type of graphic symbol is identified by a trained model for identifying the type of graphic symbol in the identified region. The information processing device described in Appendix 7. (Note 9) The aforementioned symbol-related information is, The data includes data obtained in advance by identifying the numerical and string entries in the identified area, The information processing device described in Appendix 7 or Appendix 8. (Note 10) The symbol-related information is identified by a trained model for identifying the digits and strings of characters in the identified region. The information processing device described in Appendix 9. (Note 11) The aforementioned reception unit is The system receives the graphic symbol specified by the user operating the user terminal from an input screen for receiving the specification of the graphic symbol displayed on the user terminal, The output unit is, The output screen displaying the aforementioned target image data is displayed on the user terminal. An information processing device as described in any one of the appendices 1 through 10. (Note 12) The data format of the aforementioned image data is at least one of a raster data format and a vector data format. An information processing device as described in any one of the appendices 1 through 11. (Note 13) We accept requests for the designation of graphic symbols related to the processing of the object. From among multiple image data in which the object to be processed and the graphic symbol are drawn, the system outputs the target image data corresponding to the received graphic symbol. An information processing method in which a computer performs the processing. (Note 14) We accept requests for the designation of graphic symbols related to the processing of the object. From among multiple image data in which the object to be processed and the graphic symbol are drawn, the system outputs the target image data corresponding to the received graphic symbol. An information processing program that causes a computer to perform a task.
Claims
1. A reception desk that accepts the designation of graphic symbols related to the processing of the object, An output unit outputs target image data corresponding to the received graphic symbol from among multiple image data in which the object to be processed and the graphic symbol are drawn, An information processing device equipped with the following features.
2. The reception unit receives the designation of the graphic symbol and also receives the designation of symbol-related information, which is additional information related to the received graphic symbol. The output unit outputs the target image data corresponding to the graphic symbol and the symbol-related information when outputting the target image data. The information processing apparatus according to claim 1.
3. The system includes a display control unit that displays a plurality of symbolic images representing the aforementioned graphic symbols, When the receiving unit receives the designation of the graphic symbol, it receives the graphic symbol indicated by the symbol image selected from among the multiple symbol images displayed. The information processing apparatus according to claim 1.
4. The output unit is, The system highlights the region in the output target image data that corresponds to the specified graphic symbol. The information processing apparatus according to claim 1.
5. The system further includes a search unit that searches for the target image data from a database in which multiple image data are stored, The output unit outputs the target image data retrieved by the search unit. The information processing apparatus according to claim 1.
6. The aforementioned search unit, When searching for the target image data from among the multiple image data stored in the database, The target image data is searched by referring to symbol-related information, which is obtained by pre-recognizing multiple image data and is associated with each of the image data, and which includes the type of graphic symbol drawn on each of the image data. The information processing apparatus according to claim 5.
7. The type of graphic symbol associated with the aforementioned symbol-related information is: The data is obtained in advance by identifying the region in the image data where the graphic symbol is drawn, and identifying the type of graphic symbol in the identified region. The information processing apparatus according to claim 6.
8. The region is identified by a trained model for identifying the region in the image data where the graphic symbol is drawn. The type of graphic symbol is identified by a trained model for identifying the type of graphic symbol in the identified region. The information processing apparatus according to claim 7.
9. The aforementioned symbol-related information is, The data includes data obtained in advance by identifying the numerical and string entries in the identified area, The information processing apparatus according to claim 7.
10. The symbol-related information is identified by a trained model for identifying the digits and strings of characters in the identified region. The information processing apparatus according to claim 9.
11. The aforementioned reception unit is The system receives the graphic symbol specified by the user operating the user terminal from an input screen for receiving the specification of the graphic symbol displayed on the user terminal, The output unit is, The output screen displaying the aforementioned target image data is displayed on the user terminal. The information processing apparatus according to claim 1.
12. The data format of the aforementioned image data is at least one of a raster data format and a vector data format. The information processing apparatus according to claim 1.
13. We accept requests for the designation of graphic symbols related to the processing of the object. From among multiple image data in which the object to be processed and the graphic symbol are drawn, the system outputs the target image data corresponding to the received graphic symbol. An information processing method in which a computer performs the processing.
14. We accept requests for the designation of graphic symbols related to the processing of the object. From among multiple image data in which the object to be processed and the graphic symbol are drawn, the system outputs the target image data corresponding to the received graphic symbol. An information processing program that causes a computer to perform a task.