Method for outputting explanations of patent drawing reference numerals and apparatus and system therefor.

Abstract

This invention provides a method for recognizing patent drawing reference numerals, and for outputting explanations of those reference numerals. [Solution] The method for recognizing patent drawing symbols includes the steps of: constructing a drawing symbol position recognition model and a drawing symbol recognition model by learning from multiple patent drawing samples; inputting a patent drawing to be used for recognition of drawing symbols; recognizing the positions of drawing symbols included in the patent drawing using the drawing symbol position recognition model; cutting out the drawing symbols at the recognized positions from the patent drawing as an image piece; and recognizing the drawing symbols included in the image piece using the drawing symbol recognition model.

Description

Technical Field

[0001] This specification proposes a method for outputting descriptions of patent drawing reference numbers, a device therefor, and a system (patent drawing reference numbers description output method, device and system therefor).

Background Art

[0002] Knowledge information contents such as papers and patent documents are generally composed of a large number of pages. Such contents include drawings, mathematical formulas, and texts explaining them. In particular, when there are format limitations, the drawings and the texts associated with them are frequently arranged on different pages. As a result, readers of the content have to read the content many times while changing pages back and forth to understand the explanations for the drawings and mathematical formulas, and a problem occurs in that time and effort are consumed more than necessary for obtaining knowledge information.

[0003] Recently, in order to solve such problems, a method has been provided to improve the access speed to the necessary information inside the content by precisely recognizing characters and / or numbers on knowledge information contents using optical character recognition technology (OCR). However, this method also only provides a simple character-based search function, so it is difficult to quickly obtain information related to drawings.

[0004] Nevertheless, the actual situation is that no solution has been provided so far that can quickly obtain knowledge information by utilizing the format structure information of the content to extract the linkage information between the drawings and the content and providing a drawing-centered content analysis method.

Summary of the Invention

Problems to be Solved by the Invention

[0005] Therefore, the technical problem that this invention aims to solve is to provide a solution for efficiently analyzing knowledge information content, primarily drawing information.

[0006] Specifically, the technical problem that the present invention aims to solve is to provide a method and apparatus for identifying characters associated with drawing symbols (particularly descriptions of drawing symbols) by optical character recognition and / or machine learning for the symbols in the drawing.

[0007] And / or, another technical problem that the present invention seeks to solve is to provide a method for searching for drawings based on letters (in particular, descriptions of drawing references) based on reference numerals in drawings, as well as a method for searching for drawings based on letters.

[0008] Specifically, another technical problem that the present invention aims to solve is to provide a drawing-centric content analysis method by filtering all drawings that contain drawing references based on text linked to the drawing references (particularly, descriptions of the drawing references).

[0009] And / or another technical problem that the present invention seeks to solve is to provide the user with intuitive drawing-related information by positioning a description of the matching drawing reference within the area where the drawing reference is displayed on the drawing.

[0010] Specifically, another technical problem that the present invention aims to solve is to provide a solution for positioning / moving explanatory text for drawing references to an appropriate area in response to changes in the state of the drawing.

[0011] The technical problems of the present invention are not limited to those mentioned above, and other technical problems not mentioned can be clearly understood by a person ordinary in the art of the present invention from the following description. [Means for solving the problem]

[0012] A method for recognizing patent drawing symbols according to one embodiment of the present invention may include the steps of: constructing a position recognition model for drawing symbols and a recognition model for drawing symbols by learning from a plurality of patent drawing samples; inputting a patent drawing to be recognized for drawing symbols; recognizing the positions of drawing symbols included in the patent drawing using the position recognition model for drawing symbols; cutting out the drawing symbols at the recognized positions from the patent drawing as an image piece; and recognizing the drawing symbols included in the image piece using the recognition model for drawing symbols. [Effects of the Invention]

[0013] According to one embodiment of the present invention, by replacing the reference numerals shown in the drawings with explanations of the reference numerals, it is possible for users to more easily and intuitively obtain information about the invention from the drawings. In particular, since all related drawings can be filtered based on the explanations of the reference numerals, aggregative analysis of the filtered drawings enables a drawing-centered analysis of knowledge information content.

[0014] Furthermore, according to another embodiment of the present invention, not only drawings containing descriptions of reference numerals, but also text and paragraphs can be visually identified based on the descriptions of the reference numerals. Therefore, users can quickly access desired information through the descriptions of reference numerals in large amounts of text.

[0015] Furthermore, according to yet another embodiment of the present invention, even when the state of the drawing is changed, such as by enlarging, reducing, moving, or resizing, the explanation of the drawing reference numerals can be placed in a highly readable area within the changed drawing, thereby providing convenience for knowledge information content analysis using drawings in various analysis environments.

[0016] The effects of the invention are not limited to those mentioned above, and other effects not mentioned can be clearly understood by a person of the art in the field of the present invention from the following description. [Brief explanation of the drawing]

[0017] [Figure 1] This is a diagram illustrating an example of providing patent drawings according to an embodiment of the present invention. [Figure 2] This is a flowchart relating to a method for recognizing drawing reference numerals according to an embodiment of the present invention. [Figure 3] This is a diagram illustrating a method for constructing a recognition model of drawing reference numerals according to an embodiment of the present invention. [Figure 4] This is a flowchart relating to a method for extracting descriptions of drawing reference numerals according to an embodiment of the present invention. [Figure 5] This is a diagram illustrating an example of extracting descriptions of drawing reference numerals according to an embodiment of the present invention. [Figure 6] This is a flowchart illustrating a method for outputting descriptions of drawing reference numerals corresponding to drawing reference numerals according to an embodiment of the present invention. [Figure 7] This is a flowchart illustrating a method for outputting descriptions of drawing reference numerals using an SVG (Scalable Vector Graphics) image according to an embodiment of the present invention. [Figure 8] This is a diagram illustrating a method for outputting descriptions of drawing reference numerals using an SVG image according to an embodiment of the present invention. [Figure 9] This is a diagram illustrating a method for outputting descriptions of drawing reference numerals using an SVG image according to an embodiment of the present invention. [Figure 10] This is a diagram illustrating an example of patent documents according to an embodiment of the present invention. [Figure 11] This is a diagram illustrating a drawing interface in which drawing reference numerals and descriptions of drawing reference numerals are interlocked with each other according to an embodiment of the present invention. [Figure 12] This is a diagram illustrating a drawing interface in which drawing reference numerals and descriptions of drawing reference numerals are interlocked with each other according to an embodiment of the present invention. [Figure 13] This is a diagram illustrating a keyword setting interface according to an embodiment of the present invention. [Figure 14] This is a diagram illustrating an example of an inter-category linkage implementation using descriptions of drawing reference numerals as a medium according to an embodiment of the present invention. [Figure 15]FIG. is a diagram illustrating an example of an inter-category linkage example using an explanation of reference numerals according to an embodiment of the present invention as a medium. [Figure 16] FIG. is a diagram illustrating a patent information search system according to an embodiment of the present invention. [Figure 17] FIG. is a block diagram of a web server according to an embodiment of the present invention.

MODE FOR CARRYING OUT THE INVENTION

[0018] The technology described below can be subject to various modifications and can have various embodiments. Therefore, specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the technology described below to specific embodiments, and it should be understood to include all modifications, equivalents, and alternatives included in the spirit and technical scope of the technology described below.

[0019] Terms such as first, second, A, B, etc. can be used to describe various components, but the components are not limited by the terms and are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the rights of the technology described below, the first component can be named the second component, and similarly, the second component can also be named the first component. The term "and / or" includes a combination of a plurality of related described items or any one of a plurality of related described items. For example, "A and / or B" can be interpreted to mean "at least one of A or B". Also, " / " can be interpreted as "and" or "or".

[0020] In the terms used herein, singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as “includes” should be understood to mean that the described features, numbers, stages, actions, components, parts, or combinations thereof exist, and not to exclude the possibility of the existence or addition of one or more other features, numbers, stages, actions, components, parts, or combinations thereof.

[0021] Prior to a detailed explanation of the drawings, it should be noted that the classification of components in this specification is merely based on the primary function each component is responsible for. That is, two or more components described below may be integrated into one component, or one component may be divided into two or more components based on more subdivided functions. Furthermore, each component described below may additionally perform some or all of the functions performed by other components, in addition to its own primary function, and some of the primary functions of each component may be exclusively performed by other components.

[0022] Furthermore, in carrying out a method or operation, each step in achieving the method may occur in a different order than specified unless the context clearly indicates a specific order. That is, each step may occur in the same order as specified, substantially simultaneously, or in reverse order.

[0023] Figure 1 is a diagram illustrating an example of an embodiment of the present invention as provided in the patent drawings.

[0024] More specifically, Figure 1(a) is an example of a typical patent drawing, and Figure 1(b) is an example of a patent drawing provided in which the reference numerals in the drawing are replaced with descriptions of the reference numerals, according to one embodiment of the present invention.

[0025] Knowledge information content, such as academic papers and patent documents, frequently uses diagrams as a means of explaining information to users more easily and intuitively. Users can grasp the content of knowledge information content more easily and efficiently by simultaneously understanding the diagrams and their corresponding explanations. However, knowledge information content generally consists of many pages, and users had to read through the material multiple times, turning pages each time, in order to grasp the diagrams and their explanations simultaneously. This acted as a significant obstacle to users easily and efficiently grasping the content of knowledge information content.

[0026] In particular, in the case of patent document drawings within knowledge information content, it is common for each component to be assigned a reference numeral and explained, as shown in Figure 1(a). Since such reference numerals are arbitrarily assigned by the inventor for the convenience of explaining the drawings, they lack regularity and vary greatly from one patent document to another. Therefore, in order for users to understand the content of the drawings (especially the explanations for each reference numeral), it is very important to understand the drawings and their explanations simultaneously. However, this not only causes inconvenience to the user but also increases the consumption of time and money.

[0027] Therefore, in this specification, in order to enable users to understand the invention more easily and efficiently through the drawings, we propose a patent drawing provisioning technique in which each reference numeral in the drawings is directly replaced with a description of the corresponding reference numeral, as shown in Figure 1(b).

[0028] This patented drawing-providing technology can be broadly divided into three categories as follows: 1. Recognition technology for drawing symbols 2. Techniques for extracting explanations of drawing reference symbols 3. Technology to replace the recognized drawing symbols with the extracted drawing symbol descriptions.

[0029] The aforementioned technologies 1 through 3 can be integrated into a single technology and carried out sequentially according to the embodiment, or they can be carried out / borrowed independently as individual technologies. The aforementioned technologies 1 through 3 will be described in detail later with reference to the following drawings.

[0030] The patent drawing provision technology proposed herein is described in terms of its application to a website that provides a patent document search service. Therefore, the embodiments described below can be interpreted as being performed by a web server managing / operating a patent document search website. However, the embodiments herein can also be applied to programs, applications, etc., that provide patent document search services, in which case the website may be replaced by a program or application, and the web server by a program server or application server, respectively.

[0031] In this specification, patent documents are used as an example of knowledge information content, but the explanation is not limited to this. It can, of course, be extended and applied to various other knowledge information content such as academic papers and books.

[0032] Figure 2 is a flowchart showing a method for recognizing reference numerals in drawings according to one embodiment of the present invention.

[0033] Referring to Figure 2, the web server can first learn from multiple patent drawing samples to build a drawing symbol position recognition model and a drawing symbol recognition model (S201). Both the drawing symbol position recognition model and the drawing symbol recognition model can be built based on deep learning technology.

[0034] More specifically, a web server can recognize the positions of drawing symbols contained in multiple patent drawing samples based on deep learning technology. An example of the deep learning technology used is the Fully Convolutional Network (FCN). The FCN is a deep learning model useful for determining whether or not characters exist within image pixels, and is a modified model derived from Convolutional Neural Networks (CNNs). Unlike existing CNNs, the FCN uses only convolutional layers (i.e., convolutionalization) instead of fully connected layers. This feature allows the FCN to be used very effectively to recognize the positional information of objects (especially characters) contained within an image without losing positional information, unlike CNNs.

[0035] A web server can use such FCNs to recognize the positions of drawing symbols included in multiple patent drawing samples and extract common features from the recognized positions of the drawing symbols. For example, the web server can extract common features of the positions of drawing symbols such as not being located in the center of the drawing, not being located on the outer edge of the drawing, and not overlapping with other drawing symbols. Furthermore, the web server can learn the positions of drawing symbols and extract a variety of common features as a result of the learning, but is not limited to the features mentioned above. Based on the common features extracted in this way, the web server can construct a drawing symbol position recognition model. The drawing symbol position recognition model can take a patent drawing as input and recognize and output the positions of drawing symbols included in the patent drawing based on the extracted common features.

[0036] In other words, the web server can learn the positions of drawing symbols included in multiple patent drawing samples, extract common features, and build a drawing symbol position recognition model based on the extracted common features.

[0037] A web server that has built a position recognition model for drawing symbols can use this model to build a recognition model for drawing symbols, which will be described in more detail later with reference to Figure 3.

[0038] Figure 3 illustrates a method for constructing a recognition model of reference numerals according to one embodiment of the present invention.

[0039] To construct a recognition model for drawing symbols, the web server can first use a pre-constructed drawing position recognition model to recognize the positions of drawing symbols 10-14, 16, and 18 included in the patent drawing sample 301. The web server can then cut out the drawing symbols 10-14, 16, and 18 at these recognized positions from the patent drawing sample 301 and collect them as image fragments 302. The web server can then recognize the drawing symbols 10-14, 16, and 18 contained in each of the collected image fragments 302 using image character recognition technology (for example, deep learning technology (particularly C-RNN) and / or OCR (Optical Character Recognition)).

[0040] The reason for separating drawing reference numerals 10-14, 16, and 18 into smaller images for recognition is that recognizing them within an image fragment 302 containing only the drawing reference numerals is far more efficient in terms of recognition rate and accuracy than recognizing them within the entire patent drawing 301, and the recognition speed is also significantly faster. In fact, when recognition simulations were performed by separating the drawing reference numerals into smaller images according to this method, the recognition accuracy was recorded as 99.43%, and the recognition time for each drawing was recorded as less than 0.02 seconds, demonstrating a level where real-time recognition of drawing reference numerals on a drawing-by-drawing basis is possible.

[0041] The web server can extract common features from the recognized drawing symbols 10-14, 16, and 18 to construct a drawing symbol recognition model. Common features that the web server can derive include, but is not limited to, the fact that drawing symbols consist of numbers, English letters, or a combination thereof, and that drawing symbols have a length of 5 characters or less.

[0042] The web server can build a drawing code recognition model based on the common features extracted in this way. The drawing code recognition model can recognize and output the drawing codes contained in each image piece based on the extracted common features.

[0043] In other words, the web server can learn the drawing codes contained in the image fragments, extract common features, and build a drawing code recognition model based on the extracted common features.

[0044] The resulting position recognition model and recognition model for drawing symbols will be used to recognize drawing symbols in patent drawings selected / input by the user.

[0045] Referring again to Figure 2, the web server can then input / select patent drawings that are the subject of drawing reference recognition (S202). More specifically, the web server can receive selection / input for a specific patent drawing (or a specific patent drawing) from the user device, which is a client device.

[0046] Next, the web server uses the position recognition model for drawing symbols constructed in step S201 to recognize the positions of drawing symbols included in the input / selected patent drawing (S203), and can cut out the drawing symbols at the recognized positions from the patent drawing to obtain an image piece containing the drawing symbols (S204). The web server can recognize the drawing symbols contained in the image piece thus obtained using the drawing symbol recognition model constructed in step S201 (S205). In this case, depending on the embodiment, the web server can collect image pieces in units of a predetermined number (e.g., 200) to generate a single image, and can recognize multiple drawing symbols contained in multiple image pieces included in the generated image using image character recognition technology (e.g., deep learning technology (especially C-RNN) and / or OCR (Optical character recognition)). Aside from this, the detailed explanation of steps S203 to S205 is substantially the same as that detailed in Figure 3, so redundant explanations are omitted.

[0047] In the embodiment proposed in Figures 2 and 3, the web server first determines the location of the drawing symbols and then selectively recognizes only the drawing symbols at specific locations. Compared to conventional techniques that recognize drawing symbols for the entire drawing, this not only dramatically reduces the recognition time (i.e., improves recognition speed) but also dramatically improves the accuracy of drawing symbol recognition.

[0048] Figure 4 is a flowchart showing a method for extracting explanatory symbols in drawings according to one embodiment of the present invention.

[0049] According to one embodiment of the present invention, a web server can extract descriptions of reference numerals from a patent specification. Patent documents can be broadly categorized into patent specifications and drawings, and descriptions of reference numerals can be extracted from the patent specifications. A detailed explanation of the structure of patent documents will be described below with reference to Figure 10. In particular, the web server can extract descriptions of reference numerals corresponding to the reference numerals recognized by the embodiments proposed in Figures 2 and 3 from the patent specification.

[0050] To this end, the web server can first establish rules for extracting descriptions of drawing reference numerals (S401). While the rules for extracting descriptions of drawing reference numerals can be established in various embodiments / methods, this specification focuses on the fact that the format of patent documents differs depending on the country in which the patent documents are filed, and proposes the following establishment embodiment based on text mining technology.

[0051] The web server can first classify multiple patent specification samples by country of application, and then extract common features for each classified country of application. These common features can be extracted based on at least one of the following: the relative position of the drawing reference numerals relative to the drawing reference numerals, the formatting applied to the drawing reference numerals or the drawing reference numerals themselves, or the year of application.

[0052] For example, for South Korea, common features can be extracted such as the description of the drawing reference numerals being placed before the numerals themselves, and the numerals being enclosed in parentheses. For the United States, common features can be extracted such as the description of the drawing reference numerals being placed before the numerals themselves, the use of bold formatting for the numerals, and, unlike South Korea, the fact that the numerals are not separated by parentheses. Depending on the country of application, there may be a separate "Description of Symbols" category in the patent specification containing the numerals and their descriptions. This can also be extracted as a common feature, and the "Description of Symbols" category can be used later to extract the descriptions of the numerals. In addition to this, as a result of learning from various patent specification samples, the web server can extract a variety of common features for each country of application.

[0053] After establishing extraction rules (or models) for the descriptions of drawing reference numerals based on the common features extracted in this way, the web server can use these rules to extract the descriptions of drawing reference numerals from the patent specification (S402).

[0054] More specifically, if the extraction rules for the descriptions of drawing symbols are established based on the relative position of the description of the drawing symbol to the drawing symbol (or if the extraction rules for the descriptions of drawing symbols include rules for the relative position of the descriptions of drawing symbols), the web server can search for drawing symbols included in the patent specification. Furthermore, the web server can predict the position of the description of the drawing symbol corresponding to the searched drawing symbol using the established relative position rules, and can extract the characters at the predicted position as the description of the drawing symbol.

[0055] For example, if a rule is established that the explanation of a drawing reference numeral is placed before the drawing reference numeral, the web server can search for drawing reference numeral 16 in a patent specification that contains the following description, and then extract the word "bolt," which is placed before drawing reference numeral 16, as the explanation for drawing reference numeral 16.

[0056] - Bolt 16

[0057] As in the example above, when the description of a drawing reference consists of a single word, the likelihood of errors in extracting the description of the drawing reference is low. However, when it is a compound word consisting of multiple words, there may be ambiguity as to which words should be extracted as the description of the drawing reference. To resolve this ambiguity, the embodiment shown in Figure 5 is proposed in this specification.

[0058] Figure 5 is a diagram illustrating an example of the extraction of explanatory reference numerals in a drawing according to one embodiment of the present invention.

[0059] In the present invention, which extracts explanations of drawing symbols based on their relative position to the drawing symbols, a problem may arise in which it is unclear to what extent the explanation of the drawing symbol should be extracted in the case of compound words such as "organic light-emitting display 10" as exemplified in this drawing. For example, if the explanation of the drawing symbol is extracted based on the rule that the explanation of the drawing symbol is located before the drawing symbol, then from the example in Figure 5, "display (1)", "light-emitting display (2)", "organic light-emitting display (3)", etc., can be extracted as explanations of the drawing symbol.

[0060] Therefore, in order to resolve such ambiguity, this specification proposes the following example for selecting the correct description of a drawing reference when multiple descriptions of drawing references are extracted.

[0061] As one embodiment, if multiple descriptions of a drawing reference are extracted, the web server can search the patent specification for the extracted descriptions of the drawing reference and then determine and extract the description of the drawing reference that is found most frequently as the final description of the drawing reference. Using this drawing as an example, if the web server searches the patent specification for display, light-emitting display, and organic light-emitting display and finds that organic light-emitting display is found 3 times, light-emitting display is found 0 times, and display is found 1 time, then organic light-emitting display can be extracted as the final description of the drawing reference.

[0062] In this case, the number of words that the web server extracts as candidates for the description of a drawing symbol can be limited to a predetermined number based on the drawing symbol description data accumulated to date. More specifically, the web server can create a database for patent drawing searches by creating a database of the recognition results of drawing symbols and their descriptions. In this case, the web server can calculate statistics on the number of compound words extracted as descriptions of drawing symbols based on the drawing symbol description data accumulated to date in the database, and set the number of words with a statistically low extraction ratio / probability as the limit. For example, if, as a result of analyzing the drawing symbol description data accumulated to date, the ratio of compound words with 5 or more words extracted as descriptions of drawing symbols is 0.0001%, the web server can limit the number of words that can be extracted as descriptions of drawing symbols to a maximum of 4. In this case, when the web server extracts descriptions of drawing symbols according to the extraction rules for drawing symbol descriptions, it can extract a maximum of 4 words as descriptions of drawing symbols.

[0063] Although not shown in this flowchart, the web server can establish error detection rules to determine whether the extracted descriptions of drawing symbols contain errors, and can correct / complete any errors found, in order to further improve the accuracy of extracting the descriptions of drawing symbols.

[0064] More specifically, the web server can extract descriptions of technical symbols from a sample patent specification based on established rules for extracting technical symbol descriptions, and can search the patent specification for the extracted technical symbol descriptions. If there are technical symbol descriptions that were not found in the search results or in the patent specification, the web server can classify these descriptions as technical symbol descriptions containing errors. The web server can then extract (i.e., learn) common features from these erroneous technical symbol descriptions to establish error extraction rules (or models). The web server can then use these established error extraction rules to determine whether or not the technical symbol descriptions extracted from the patent specification contain errors.

[0065] Examples of common features include the misinterpretation of the number 0 as the letters o, O, or D; the misinterpretation of the number 9 as the number 0; the extraction of non-noun parts of speech such as adjectives, conjunctions, and adverbs like "~na"; and the extraction of symbols such as !, @, #, $, %, ^, (, and ).

[0066] If the web server determines that there is an error in the description of a drawing symbol based on established error detection rules, it can supplement / correct the extracted description of the drawing symbol according to a predetermined method. For example, if the web server finds an error where a number / alphabet is mistakenly recognized as an alphabet / number, it can replace the number / alphabet with the corresponding alphabet / number. If it finds an error that includes a part of speech that is not a noun, a symbol, etc., it can delete that part of speech or symbol.

[0067] Furthermore, the web server can build a drawing code description extraction model with improved performance by learning established drawing code description extraction rules and error detection rules based on deep learning technology (CNN, RNN (Recurrent Neural Network), or a combination thereof). In particular, the web server can utilize the set of correct answers for drawing codes and their descriptions accumulated to date in the patent drawing search database that has already been built, to construct a drawing code description extraction model with extremely high recognition rate and accuracy, which can then be used to extract drawing code descriptions.

[0068] On the other hand, although not mentioned separately earlier, in order to extract corresponding drawing symbols and their descriptions, it is necessary to recognize the drawing symbols with high accuracy not only in the drawings but also in the specification. This is because the drawing description extraction rules proposed herein are based on the premise of extracting the descriptions of drawing symbols based on the "drawing symbols." In other words, the specification and drawings can be considered to be interconnected through the drawing symbols. Therefore, the web server can determine whether the drawing symbols have been accurately extracted in both the specification and the drawings, and can supplement any drawing symbols that were determined not to have been accurately extracted. This further improves the accuracy of matching between drawing symbols and their descriptions.

[0069] As a first embodiment of this, the web server can improve the accuracy of recognizing drawing symbols in drawings by matching the drawing symbols extracted from the drawings with the drawing symbols included in the patent specification. More specifically, the web server can search for drawing symbols recognized in the patent drawings in the patent specification corresponding to the patent drawings according to the above embodiment. If a drawing symbol recognized in the patent drawing is found in the patent specification, the web server can determine that the recognized drawing symbol is an appropriate drawing symbol and decide on it as the final drawing symbol. Conversely, if the recognized drawing symbol is not found in the patent specification, the web server can determine that the drawing symbol is an inappropriate drawing symbol and search the patent specification for characters / words / terms that have a similarity in shape to the drawing symbol at a predetermined ratio or higher, and decide on these as the final drawing symbols.

[0070] For example, if 36D is recognized in a drawing but not found in the actual specification, the web server can determine 360, which has the highest geometric similarity to 36D, as the final drawing reference numeral.

[0071] Similarly, in a second embodiment, the web server can improve the accuracy of recognizing drawing symbols in the specification by matching the drawing symbols recognized in the specification with the drawing symbols recognized in the drawings. More specifically, the web server can search for drawing symbols recognized in the patent specification according to the above embodiment among the drawing symbols recognized from the patent drawings corresponding to the patent specification. If a drawing symbol recognized in the patent specification is found among the drawing symbols recognized from the patent drawings, the web server can determine that the recognized drawing symbol is an appropriate drawing symbol and decide it as the final drawing symbol. Conversely, if the recognized drawing symbol is not found among the drawing symbols recognized from the patent drawings, the web server can determine that the drawing symbol is an inappropriate drawing symbol and search for a character / word / term that has a shape similarity to the drawing symbol at a predetermined ratio or higher among the drawing symbols recognized from the patent drawings and decide it as the final drawing symbol.

[0072] For example, if 36D is identified in the patent specification, but 36D is not found among the reference numerals identified in the actual patent drawings, the web server can determine 360, which has the highest shape similarity to 36D among the reference numerals identified in the patent drawings, as the final reference numeral.

[0073] In other words, according to the first embodiment, the web server can match and complement the reference numerals recognized in the patent drawings with the reference numerals recognized in the patent specification, and according to the second embodiment, the web server can match and complement the reference numerals recognized in the patent specification with the reference numerals recognized in the patent drawings.

[0074] The first and second embodiments described above can be used selectively or in combination and simultaneously, depending on the purpose and effect. When used in combination and simultaneously, only the reference numerals that mutually match between the patent drawings and the patent specification can be determined / extracted / confirmed as the final reference numerals, significantly reducing the probability of reference numeral recognition errors compared to when the first and second embodiments are applied selectively.

[0075] The above describes in detail the method for recognizing drawing symbols and their descriptions. Below, we propose a method for outputting the recognized drawing symbols in place of their descriptions.

[0076] In particular, the method for outputting explanations of drawing symbols proposed herein differs from the prior art in that it is independent of changes in the state of the drawing itself (e.g., movement, rotation, enlargement, or reduction), and the relative position within the drawing is always maintained / fixed. This means that even if the user changes the state of the drawing itself, the explanation of the drawing symbols can always accurately track and replace the position of the drawing symbols.

[0077] Figure 6 is a flowchart illustrating a method for outputting explanations for reference numerals corresponding to reference numerals in one embodiment of the present invention.

[0078] Referring to Figure 6, the web server can first recognize the size of the patent drawing and the position of the drawing reference numerals contained within the patent drawing, and obtain the relative position coordinates of the drawing reference numerals within the patent drawing (S601). In other words, the web server can obtain the relative position coordinates of the drawing reference numerals with respect to the size of the patent drawing. The reason for obtaining these relative position coordinates is, as mentioned above, to accurately track the position of the drawing reference numerals even when the state of the drawing changes.

[0079] Next, the web server can set the relative position coordinates obtained in the previous step to the relative position coordinates of the description of the drawing symbol corresponding to the drawing symbol (S602).

[0080] Finally, the web server can output a description of the drawing symbol at the configured relative position coordinates (S603). In this case, the output description of the drawing symbol can be in the form of an icon / GUI (Graphic User Interface) with an opaque background color, and as a result of being output at the same relative position coordinates as the drawing, it will cover / conceal at least a part of the drawing symbol. In other words, the description of the drawing symbol is output at the same position as the drawing symbol in the drawing, and as a result, it will be output as a substitute for the drawing symbol. For example, in Figure 1(a), all drawing symbols will be replaced by the description of the drawing symbol as shown in Figure 1(b).

[0081] In this embodiment, an example is given where the explanation of the drawing symbol is output so as to cover / conceal at least a part of the drawing symbol, but it is not necessarily limited to this, and the explanation of the drawing symbol can be output anywhere as long as it is in a position corresponding to the drawing symbol (for example, a position above / below / left / right / diagonally / adjacent to the drawing symbol, including the position that covers / conceals at least a part of it). If it is to output the explanation of the drawing symbol in an area adjacent to the drawing symbol, the web server can set / assign the coordinates of the explanation of the drawing symbol to coordinates obtained in step S601 by moving the relative position coordinates of the drawing symbol in a predetermined direction and / or by a predetermined distance. Below, for the sake of explanation, a specific embodiment of replacing the drawing symbol with an explanation of the drawing symbol will be described in detail based on the embodiment of Figure 6 described above.

[0082] Figures 7 to 9 are flowcharts illustrating an example of an output method for explaining drawing reference numerals using an SVG image according to one embodiment of the present invention.

[0083] More specifically, Figure 7 is a flowchart illustrating a method for outputting explanations of drawing symbols using SVG (Scalable Vector Graphics) images according to one embodiment of the present invention, and Figures 8 and 9 are diagrams illustrating a method for outputting explanations of drawing symbols using SVG images according to one embodiment of the present invention.

[0084] Referring to Figures 7 and 8, the web server first generates an SVG image 802 the same size as the patent drawing 801, then overlays the SVG image 802 onto the patent drawing 801, and then fixes it to the patent drawing 801 (S701). That is, after generating a transparent SVG image 802 that is the same size as the patent drawing 801, it can be fixed to the patent drawing 801 while covering the entire drawing. As a result, the SVG image 802 is either unrecognizable from the user's perspective or changes state in the same way as the state of the patent drawing 801 changes. For reference, an SVG image is an XML (Extensible Markup Language) based image file format for representing two-dimensional vector graphics, and has the characteristic that its quality does not deteriorate even when the image changes state (especially when it is enlarged).

[0085] Referring to Figures 7 and 9, the web server can then write / add / display / assign a description of the drawing symbol 902 to a default relative position coordinate 901 within the SVG image 802 (S702). Here, the default relative position coordinate 901 refers to the relative position coordinates of the drawing symbol and its description obtained in steps S601 and S602 of Figure 6. The description of the drawing symbol 902 can be written / added / display / assigned within the SVG image 802 in the form of an icon / GUI with an opaque background color.

[0086] As a result, within the SVG image 802, the description of the drawing reference 902 is written / added / displayed / assigned to the position 901 corresponding to the drawing reference (903). The web server can output the SVG image 903 with the description of the drawing reference 902 written / added / displayed / assigned on top of the drawing 801, and as a result, the drawing reference in the drawing 801 is covered by the description of the drawing reference 902 written / added / displayed / assigned on the SVG image 903 (S703).

[0087] For example, if the description 902 for the drawing reference numeral "16" in drawing 801 is "bolt," then an SVG image 903 can be generated in which "bolt" 902 is written / added / displayed / assigned in the same position as drawing reference numeral "16." When the SVG image 903 is superimposed on drawing 801 and output, drawing reference numeral "16" can be covered by "bolt" 902. As a result, from the user's perspective, it appears as if drawing reference numeral "16" has been replaced by "bolt" 902.

[0088] In other words, in this embodiment, the web server generates an SVG image 903 in which a description of the drawing reference 902 is written / added / assigned / displayed at the position 901 corresponding to the drawing reference, and can output the thus generated SVG image 903 in matching / linking / corresponding to the drawing 801. As a result, the drawing references in the drawing 801 are replaced by the descriptions 902 of the drawing references in the output.

[0089] Due to the characteristics of SVG images, their state can be freely changed without quality degradation. Since the explanation of the drawing symbols is assigned position coordinates within the image as an object / component that constitutes the SVG image, the position coordinates of the explanation of the drawing symbols are automatically scaled in accordance with the state changes of the SVG image, eliminating the need to recalculate the position coordinates. In a drawing, the drawing symbols are included as image objects that constitute the drawing image, and in an SVG image, the explanation of the drawing symbols is also included as an image object that constitutes the SVG image. The explanation of the drawing symbols is displayed (or written, added, or assigned) at a position corresponding to the drawing symbols. Therefore, in accordance with the state changes of the two linked images, the position coordinates of the drawing symbols and the explanation of the drawing symbols, which are components of the image, are automatically scaled, and the resulting position changes are the same. Consequently, even if the state of a patent drawing is changed (e.g., moved, rotated, enlarged, or reduced), the SVG image fixed on the patent drawing will also change state in the same way as the patent drawing. As a result, the explanation of the drawing symbols written / added / assigned / displayed on the SVG image will also remain fixed in its relative position within the SVG image, even if the SVG image is moved, rotated, enlarged, or reduced.

[0090] When using SVG images, specific formatting (such as yellow highlighting) can be displayed at the location of drawing symbols to inform the user of the drawing symbols that the web server has currently recognized. Later, explanations of the drawing symbols can be displayed in the locations indicated by this specific formatting, such as tooltips, using HTML.

[0091] According to this embodiment, the speed of replacing explanations for drawing symbols is significantly faster compared to existing methods that track / recalculate the position of drawing symbols each time in response to changes in the state of the drawing and assign explanations for those symbols. In particular, with existing / conventional methods, the position of drawing symbols must be tracked / recalculated each time in response to changes in the state of the drawing, resulting in a very slow replacement speed. Therefore, explanations for only one drawing symbol at a time could be replaced / output. However, according to this embodiment, the replacement speed is very fast, and it is possible to replace / output explanations for all drawing symbols (i.e., multiple drawing symbols) contained in a single drawing at once.

[0092] On the other hand, although not shown in this drawing, assigning relative position coordinates to the descriptions of all drawing symbols may result in some descriptions of drawing symbols overlapping on the SVG image. In this case, the web server can arbitrarily adjust the relative position coordinates of at least one of the overlapping descriptions of drawing symbols in a direction that prevents mutual overlap, and then write / display / add / assign them to the SVG image. For example, if the descriptions of the first and second drawing symbols overlap, the web server can move the description of the first drawing symbol in the first direction and the description of the second drawing symbol in the second direction, opposite to the first direction, by a predetermined length.

[0093] In this specification, "SVG images" are given as a representative example of images used for outputting explanations of drawing references, but the specification is not limited to this, and various image formats can certainly be used. Therefore, in this specification, SVG images can be referred to or replaced by "images," and in this case, "images" can refer to various image formats that, like SVG images, do not degrade in quality even when their state changes.

[0094] On the other hand, although not specifically mentioned in the flowcharts and diagrams, if a diagram, such as a block diagram or flowchart, already includes a description of each drawing symbol, the web server can apply highlighting formatting to the description of that drawing symbol instead of replacing it with the description. To this end, the web server can perform actions in advance to recognize the characters contained in the diagram.

[0095] The methods for recognizing drawing reference numerals, extracting explanations for drawing reference numerals, and substituting drawing reference numerals for explanations have been described in detail above. Using the extracted / recognized drawing reference numerals and / or explanations as intermediaries, each category of patent documents can be interconnected / synchronized. As a result, users can selectively search / retrieve desired information using drawing reference numerals and / or explanations, enabling them to grasp the invention more efficiently. Examples of the interconnection / synchronization of each category of patent documents will be described below with reference to Figures 11 to 15, and before going into detail therein, we will briefly describe the categories of patent documents as defined herein.

[0096] Figure 10 is a diagram illustrating a patent document relating to one embodiment of the present invention.

[0097] Referring to Figure 10, Patent Document 1000 can be divided into several categories 1001 and 1002. Patent Document 1000 can be broadly divided into Patent Specification 1001 and Patent Drawings 1002, and Patent Specification 1001 can again be divided into Claims 1001-1, Detailed Description of the Invention 1001-2 and / or Description of Reference Numerals (not shown).

[0098] The multiple categories 1001 and 1002 thus divided can be output in multiple areas / windows. For example, the patent specification 1001 and the patent drawings 1002 can be output in separate first and second areas within a single window. Alternatively, the patent specification 1001 and the patent drawings 1002 can be output in separate first and second windows. Alternatively, the patent specification 1001 and the patent drawings 1002 can be output in separate areas within a single window, and the patent specification 1001 or the patent drawings 1002 can also be output as separate windows.

[0099] The reason for outputting the information in this way, separated by area / window, is to allow all categories 1001 and 1002 to fit into the user's field of view at once, providing convenience for the user to grasp the information more easily and efficiently.

[0100] In this specification, several categories 1001, 1002 can be linked to one another via reference numerals and / or descriptions of reference numerals.

[0101] More specifically, when a selection input is received for a drawing symbol belonging to any one of the multiple categories 1001 and 1002, the web server can search for the drawing symbol from multiple / all categories 1001 and 1002. Furthermore, the web server can apply highlighting formatting to all drawing symbols found from multiple / all categories 1001 and 1002 and output them.

[0102] If a drawing reference is found in patent specification category 1001, the web server can highlight all found drawing references by applying default formatting (e.g., underlining, bolding, applying a different text color, highlighting, etc.). Similarly, if a drawing reference is found in patent drawing category 1002, the web server can highlight all found drawing references or the descriptions of all corresponding alternatively outputted drawing references by applying default formatting (e.g., underlining, bolding, applying a different text color, highlighting, etc.).

[0103] For example, if the user selects the reference numeral "16" in patent specification category 1001, drawings containing reference numeral "16" will be automatically selected and output from patent drawing category 1002, and then reference numeral "16" will be highlighted. Alternatively, if the user selects reference numeral "16" in patent drawing category 1002, all reference numerals "16" will be highlighted in patent specification category 1001, and at the same time, automatic scrolling / output operations can be performed on the text / paragraphs containing reference numeral "16".

[0104] To receive user input regarding drawing reference numerals, drawing reference numerals can be output in hyperlink format in patent specification category 1001, and drawing reference numerals (or descriptions of drawing reference numerals) can be output in a selectable GUI / icon format in patent drawing category 1002.

[0105] Figures 11 and 12 illustrate a drawing interface in which reference numerals and descriptions of reference numerals according to one embodiment of the present invention are interconnected.

[0106] The drawing interface proposed herein can be output in the drawing category as a user interface that provides the user with various drawing-related functions. Such a drawing interface can basically output drawings as shown in this drawing. In addition, the drawing interface can provide the user with various drawing-related functions, such as a preview and shortcut function for the entire drawing included in the patent document, a function to change the drawing state (e.g., rotation, movement, scaling, and zooming of the drawing), and an alternative function for explaining drawing reference numerals. Here, the alternative function for explaining drawing reference numerals corresponds to the function to which the above-described embodiment is applied.

[0107] In particular, the drawing interface can provide a function to recognize all drawing symbols in a selected drawing, extract descriptions for all corresponding drawing symbols, and list all extracted descriptions for the user. In this case, corresponding drawing symbols and their descriptions can be matched / paired before output. The recognition of drawing symbols and the extraction of their descriptions can be performed using the embodiments described above.

[0108] Furthermore, as shown in Figure 12, if the web server receives a user selection input for at least one drawing symbol description (or drawing symbol description) from the list of drawing symbol description inputs output via the drawing interface, it can selectively output only the selected drawing symbol description (or drawing symbol). For example, as shown in Figure 12, if the user selection input for bolt 16 is received, the web server can output only the drawing symbol description for bolt, which is drawing symbol 16.

[0109] In this embodiment, the user can selectively view only the desired reference numerals or descriptions of the reference numerals, enabling them to easily and efficiently grasp the drawings / invention. Figure 13 illustrates a keyword setting interface according to one embodiment of the present invention.

[0110] The drawing interface proposed herein may provide a keyword setting interface. The keyword setting interface corresponds to a user interface provided via drawing categories to enable setting at least a portion of the descriptions of drawing references as keywords.

[0111] The keyword setting interface may include, as illustrated in this drawing, an input window for entering a description of the drawing reference to be set as a keyword, a color setting window for setting the highlight color of the set keyword, and / or a keyword indicator showing the keywords set to date. However, the keyword setting interface is not limited to this, and various functions may be added or at least some of the functions described above may be excluded.

[0112] Through these keyword setting interfaces, users can register / set the descriptions of specific drawing symbols as keywords, and the web server can highlight the registered / set keywords within the drawing or highlight the drawing containing the keywords so that users can easily find them.

[0113] For example, if a user wants to specify "bolt 16" as a keyword from the explanation of the drawing reference shown in Figure 11, they can enter "bolt" into the input window as shown in Figure 12, set a highlight color, and then press the register button. This allows the web server to set / register "bolt" as a keyword and output a keyword indicator in a designated area of ​​the keyword setting interface to indicate that "bolt" has been set / registered as a keyword. Furthermore, the web server can search for "bolt" within the drawing category and apply a highlight color to the keyword in the currently selected and enlarged drawing. The web server can also output an indicator in the same color as the keyword highlight color for drawings in which the keyword has been found while a preview is being provided.

[0114] As a result, users can easily identify keywords within the drawing they are currently viewing, and also easily identify which drawings they are not currently viewing contain those keywords. This significantly improves the efficiency of users in accessing the information they desire. Furthermore, users can set / register multiple keywords, and in this case, they can set different colors for each keyword, making it easy to distinguish keywords by color.

[0115] Figures 14 and 15 illustrate an example of the interdependence between categories, mediated by the explanation of the reference numerals in the drawings according to one embodiment of the present invention.

[0116] As shown in Figure 14, when the system receives user input for a description 1402 of a drawing reference numeral that has been output covering the drawing reference numeral, it can output a selection window for selecting at least one function. In this case, the function 1403 provided may be a function to search for the selected description 1402 of the drawing reference numeral within the patent specification. If the user selects this function 1403, the web server can search for the selected description 1402 of the drawing reference numeral or the drawing reference numeral corresponding to it in all categories, and can apply highlighting 1502 to the found description 1402 of the drawing reference numeral and output it as shown in Figure 15.

[0117] Referring to Figure 15, if the web server searches for a description of a selected drawing symbol or a corresponding drawing symbol from the patent specification category, it can highlight all the descriptions of the found drawing symbols or drawing symbols 1506-1, 1506-2 by applying a default format (e.g., underlining, bolding, applying a different text color, highlighting, etc.).

[0118] And / or, the web server can automatically scroll the web page to the location / page / text / paragraph of the description of the found drawing reference or drawing reference 1506-1, which is located at the top of the patent specification categories (particularly the claim category and the detailed description of the invention category) among the searched drawing references.

[0119] Alternatively, the web server may output a first indicator 1505 in the scroll bar area (or adjacent scroll bar area) corresponding to the description or location of all searched drawing symbols within the overall scroll bar area provided in the patent specification category (particularly the claim category and the detailed description of the invention category). That is, by displaying the page area where the description or drawing symbol is located in a minimap format in the scroll bar area via the first indicator 1505, the user can move the scroll bar to the position of the first indicator 1505 and more easily access the desired information. Furthermore, the first indicator output in minimap format allows the user to grasp at a glance how much of the searched description and / or drawing symbol is distributed in which category, which can be useful in determining the importance of the components.

[0120] And / or, the web server may provide / output search windows 1504-1, 1504-2 within the patent specification category (in particular the claims category and the detailed description of the invention category) for searching for the description or reference numeral of the reference numeral being searched. Thus, the user can immediately find the paragraph, page, or document containing the description or reference numeral of the reference numeral being searched via the search windows 1504-1, 1504-2.

[0121] Alternatively, the web server can also search for the description of the selected drawing symbol or the corresponding drawing symbol in the patent drawing category, and can provide / output the second indicator 1507 to drawings that contain the description of the drawing symbol or the corresponding drawing symbol among the drawings being previewed. Therefore, by selecting the drawing on which the second indicator 1507 is provided / output, the user can immediately search for / find a drawing that contains the description of the drawing symbol they wish to search for.

[0122] On the other hand, although not shown in this drawing, the web server can automatically select and enlarge the drawing corresponding to the paragraph / text portion that the user is currently reading / exploring within the patent specification category. To this end, the web server can understand the content of the patent specification category (particularly the detailed description of the invention category), partition the area according to the description for each drawing (e.g., paragraph, text, page), and automatically select and enlarge the drawing corresponding to the area that is being output at the highest ratio on the current web page. For example, if the user's device is outputting the detailed description of the invention for Figure 1, the web server can automatically select Figure 1 and enlarge it within the drawing category.

[0123] Similarly, if a user selects a specific area (e.g., paragraph, text, page) within a patent specification category, the web server can automatically select and enlarge the corresponding drawing from the drawing category. Furthermore, the web server can automatically replace the drawing references contained within the selected area with explanations for those references.

[0124] The web server can create a database of at least one piece of information obtained / recognized by the aforementioned operation / method / example (i.e., store it separately in the database as data) and construct a patent drawing search database.

[0125] For example, a web server can group patent documents, patent drawings, the size of the patent drawings, the reference numerals included in the patent drawings, descriptions of each reference numeral and / or the relative position coordinates of the reference numerals into a single data set and store this in a database to build a patent drawing search database.

[0126] Therefore, users can easily obtain information about the patent drawings they are looking for from among patent drawings worldwide by entering search terms related to the patent document through the patent drawing search database constructed in this manner.

[0127] Furthermore, the web server can improve recognition accuracy and speed by updating the various models / rules mentioned above by learning various patent drawing data in real time / periodically through the patent drawing search database constructed in this way.

[0128] Figure 16 illustrates a patent information search system according to one embodiment of the present invention.

[0129] Referring to Figure 16, the patent information retrieval system proposed herein may include a web server and a user device.

[0130] The web server 1601 and the user device 1602 are interconnected primarily via an internet connection and can communicate with each other, enabling them to provide and receive patent information search services via web services / pages.

[0131] The web server 1601 may correspond to a server / device comprising at least one software and hardware component designed to perform the embodiments proposed herein. In particular, the web server 1601 can provide the patent information retrieval service proposed herein via an internet web page to a user device which is a client device.

[0132] User device 1602 can be a client device that receives a patent information search service provided via a web server. User device 1602 can receive a patent information search service provided by a web server via an internet web page.

[0133] In this specification, an example has been given in which a patent information retrieval system is composed of a web server 1601 and a user device 1602. However, the invention is not limited to this, and in some embodiments, the web server 1601 may be replaced by an application server, a program server, or a service provider. Furthermore, in this specification, the entity performing the embodiments is described as the web server 1601. However, the invention is not limited to this, and the web server 1601 may be replaced by a program or application designed to embody the embodiments described above, and the operation of the web server 1601 may be interpreted as these functions.

[0134] Figure 17 is a block diagram of a web server according to one embodiment of the present invention.

[0135] Referring to Figure 17, the web server may include a processor 1710, a memory unit 1720, and a communication unit 1730.

[0136] The processor 1710 can communicate with or control other components to carry out the embodiments proposed herein, execute various programs and / or applications stored in the memory unit 1720, and process internal data. The processor 1710 may consist of at least one CPU (Central Processing Unit), MPU (Micro Processor Unit), MCU (Micro Controller Unit), AP (Application Processor), or any form of processor well known in the art of the present invention. Accordingly, in this specification, a web server may also be described as a processor.

[0137] The memory unit 1720 refers not only to an internally stored digital data storage space such as flash memory, HDD (Hard Disk Drive), and SSD (Solid State Drive), but also to an external storage space where data can be stored via communication connectivity, such as the cloud. Therefore, the memory unit 1720 can store various digital data such as video, audio, photographs, movies, images, text, applications, and programs. In particular, the memory unit 1720 proposed herein can store various knowledge information content (especially patent document) data and can store the patent document search database and / or patent drawing search database 1720-1 constructed by the processor 1710. Therefore, according to the embodiment, the processor 1710 can load various data from the patent document and / or patent drawing search database stored in the memory unit 1720 and perform data processing / output operations, etc.

[0138] The communication unit 1730 can perform communication and transmit / receive data using at least one wired / wireless communication protocol.

[0139] Embodiments of the present invention can be embodied by various means, such as hardware, firmware, software, or a combination thereof. In the case of hardware embodiment, one embodiment of the present invention can be embodied by one or more ASICs (application-specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), processors, controllers, microcontrollers, microprocessors, etc.

[0140] Furthermore, in the case of implementation by firmware or software, one embodiment of the present invention may be implemented in the form of a module, procedure, function, etc., that performs the functions or operations described above, and may be recorded on a recording medium readable by various computer means. Here, the recording medium may include program instructions, data files, data structures, etc., individually or in combination. The program instructions recorded on the recording medium may be specially designed and configured for the present invention, or they may be publicly known and usable by those skilled in the computer software art. For example, the recording medium includes magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs (Compact Disk Read Only Memory) and DVDs (Digital Video Disks), magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program instructions, such as ROMs, RAMs, and flash memory. Examples of program instructions may include not only machine code, such as that produced by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. Such hardware devices can be configured to operate as one or more software programs to perform the operations of the present invention, and vice versa.

[0141] Furthermore, the devices and terminals according to the present invention can be driven by instructions that cause one or more processors to perform the aforementioned functions and processes. For example, such instructions may include instructions that are interpreted as script instructions, such as JavaScript or ECMAScript instructions, or other instructions stored in executable code or a computer-readable medium. Furthermore, the devices according to the present invention can be implemented in a distributed manner across a network, such as a server farm, or they can be implemented in a single computer device.

[0142] Furthermore, a computer program (also known as a program, software, software application, script, or code) mounted on an apparatus according to the present invention and performing a method according to the present invention can be written in any form of programming language, including compiled or interpreted languages, a priori or procedural languages, and can be deployed in any form, including standalone programs or modules, components, subroutines, or other units suitable for use in a computer environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a single file provided to the requested program, in multiple interacting files (e.g., a file storing one or more modules, subprograms, or parts of code), or in part of a file containing other programs or data (e.g., one or more scripts stored within a markup language document). A computer program can be located at one site or deployed to run on multiple computers interconnected by a communication network across multiple sites.

[0143] For the sake of explanation, each drawing has been described separately, but it is also possible to combine the embodiments described in each drawing to design a new embodiment. Furthermore, the present invention is not limited to the configuration and methods of the embodiments described above, and the embodiments described above can be configured by selectively combining all or part of each embodiment so that various modifications can be made.

[0144] Furthermore, although preferred embodiments have been illustrated and described above, this specification is not limited to the specific embodiments described herein, and various modifications are possible for a person with ordinary skill in the art to which the invention pertains, without departing from the gist of the claims. Moreover, such modifications should not be understood individually from the technical ideas or prospects of this specification. [Industrial applicability]

[0145] This invention can be utilized in various patent search systems / devices / methods. [Explanation of symbols]

[0146] 10 Organic Light-Emitting Displays 301 Patent Drawing Sample 302 Image Fragments 801 Patent Drawings 802 SVG image 901 Location coordinates 902 Description 903 Write / Add / Display / Assign 1000 Patent Documents 1001 Patent Specification 1001-1 Claims 1001-2 Detailed Description of the Invention 1002 Patent Drawings 1402 Explanation of Drawing Reference Numerals 1403 Functions 1502 Highlight 1504-1, 1504-2 Exploration Window 1505 First Indicator 1506-1, 1506-2 Explanation of drawing symbols or drawing symbols 1601 Web Server 1602 User equipment 1710 Processor 1720 memory units 1720-1 Patent Document Search Database and / or Patent Drawing Search Database 1730 Communication Unit

Claims

[Claim 1] In the method for outputting explanations of drawing symbols performed by the server, At the stage when the above server recognizes the size of the patent drawing, The above server obtains the relative position coordinates of the reference numerals in the above patent drawing. The above server sets the relative position coordinates of the drawing reference description corresponding to the above drawing reference, The above server overlays a transparent image, which is the same size as the above patent drawing, onto the above patent drawing. The above server overlays the above image onto the above patent drawing and fixes the above transparent image onto the above patent drawing, and A method for outputting explanations of drawing symbols, including the step of the server outputting the explanations of the drawing symbols to the transparent image using the relative position coordinates of the explanations of the drawing symbols.

Images