Information Search System

Abstract

Provided is an information retrieval system capable of retrieving, for a designated application, similar applications and value information for the similar applications. Provided is an information retrieval system that: receives a designated application; calculates a first degree of similarity between the specification of the designated application and respective specifications of a plurality of applications; extracts a plurality of first similar applications from the plurality of applications on the basis of the first degree of similarity; calculates, for at least one of the plurality of first similar applications, a second degree of similarity between a support drawing corresponding to the scope of the claims and at least one drawing of the designated application; on the basis of the second degree of similarity, extracts, for at least one of the plurality of first similar applications, at least one drawing similar to the support drawing from among the drawings of the designated application; and outputs value information, the support drawing, and the similar drawing, for at least one of the plurality of first similar applications. The value information may be information about related products or the like.

Description

[Technical Field]

[0001] One aspect of the present invention relates to an information retrieval system and an information retrieval method.

[0002] One embodiment of the present invention is not limited to the above technical field, and examples of the technical field of one embodiment of the present invention include semiconductor devices, display devices, light-emitting devices, power storage devices, memory devices, electronic devices, lighting devices, input devices (e.g., touch sensors), input / output devices (e.g., touch panels), driving methods thereof, and manufacturing methods thereof. [Background technology]

[0003] There has been growing attention and awareness of intellectual property rights such as patents, designs, and trademarks, and technological developments to support the effective utilization of patents are underway. In order to confirm whether other companies are using patented inventions, it is necessary to compare one's own patents with the products of other companies to determine whether the other companies' products infringe on one's own patents. In addition, whether one's own products are protected by one's own patents must be checked frequently, not only when a new product is released, but also when an existing product is improved.

[0004] Patent Document 1 discloses a system that can search for information related to inputted intellectual property information. For example, it is possible to search for patent documents, papers, or industrial products that are similar to a specified patent document. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2018-206376 Summary of the Invention [Problem to be solved by the invention]

[0006] The value of an invention that has been applied for can be measured from various perspectives. Increasing the value (which can also be called added value) of a patent held by a company is required not only at the application stage, but also after registration. For example, the fact that the company is implementing the patented invention and the fact that other companies are implementing the patented invention are each factors that contribute to a higher evaluation of the patent's value. Furthermore, even if there is no current record of implementation, if future demand is expected, the patent will be evaluated highly. Note that the value of an invention that has been applied for is diverse, and the present invention does not exclude value other than the examples given here.

[0007] It is difficult to find applications that other companies are infringing from among the many applications. First, you must decide which product to target for infringement investigation from among the many products. Next, you narrow down your company's applications to those that are likely to be related to that product. Then, you compare each of the narrowed down applications with the product in question. As you can see, finding combinations of applications and products that are in an infringing or infringed relationship is a very labor-intensive task.

[0008] Furthermore, even if it is found that a certain application is highly related to a certain product, it is not easy to find out whether the product is also related to other applications, or whether the application is also related to other products (e.g., new products). In this case, it is necessary to compare each product and application one by one.

[0009] An object of one embodiment of the present invention is to provide an information retrieval system capable of searching for information with high accuracy.An object of one embodiment of the present invention is to provide an information retrieval system capable of efficiently searching for information.An object of one embodiment of the present invention is to provide an information retrieval system capable of performing a highly accurate information retrieval using a simple input method.

[0010] An object of one aspect of the present invention is to provide an information search system that can search for similar applications and value information of the similar applications for a specified application.An object of one aspect of the present invention is to provide an information search system that can search for similar applications and information on products associated with the similar applications for a specified application.

[0011] Note that the description of these problems does not preclude the existence of other problems. One embodiment of the present invention does not necessarily have to solve all of these problems. Problems other than these can be extracted from the description in the specification, drawings, and claims. [Means for solving the problem]

[0012] One aspect of the present invention is an information retrieval system having a reception unit that receives designated applications, a processing unit that performs processing using a database, and an output unit that outputs information based on the processing results of the processing unit. The database contains at least data on specifications, drawings, and value information for multiple applications. The drawings include supporting drawings corresponding to the claims. The processing unit calculates a first similarity between the specification of the designated application and each of the specifications of the multiple applications. The processing unit extracts multiple first similar applications from the multiple applications based on the first similarity. The processing unit calculates a second similarity between the supporting drawing and each of at least one drawing included in the designated application for at least one of the multiple first similar applications. The processing unit extracts at least one similar drawing to the supporting drawing from the drawings included in the designated application for at least one of the multiple first similar applications based on the second similarity. The output unit outputs the value information, supporting drawing, and similar drawing for at least one of the multiple first similar applications. The output unit may output a second similarity between the supporting drawings and the similar drawings for at least one of the plurality of first similar applications.

[0013] One aspect of the present invention is an information retrieval system having a reception unit that receives designated applications, a processing unit that performs processing using a database, and an output unit that outputs information based on the processing results of the processing unit. The database contains at least data on specifications, drawings, and value information for multiple applications. The drawings include supporting drawings corresponding to the claims. The processing unit calculates a first similarity between the specification of the designated application and each of the specifications of the multiple applications. The processing unit extracts multiple first similar applications from the multiple applications based on the first similarity. The processing unit calculates a second similarity between the supporting drawings of each of the multiple first similar applications and at least one drawing included in the designated application. The processing unit extracts at least one second similar application by narrowing down and / or sorting the multiple first similar applications based on the second similarity. For the second similar application, the processing unit extracts at least one drawing similar to the supporting drawing from the drawings included in the designated application based on the second similarity. The output unit outputs the value information, the supporting drawings, and the similar drawings for the second similar application. The output unit may also output a second similarity between the supporting drawings and the similar drawings for the second similar application.

[0014] The information search system according to an aspect of the present invention may further include a storage unit that stores the processing results.

[0015] One aspect of the present invention is an information retrieval method that receives a designated application, calculates a first similarity between the specification of the designated application and each of multiple applications, extracts multiple first similar applications from the multiple applications based on the first similarity, calculates a second similarity between supporting drawings corresponding to the claims of at least one of the multiple first similar applications and each of at least one drawing included in the designated application, extracts at least one similar drawing to the supporting drawing from the drawings included in the designated application based on the second similarity for at least one of the multiple first similar applications, and outputs value information, supporting drawings, and similar drawings for at least one of the multiple first similar applications.Furthermore, the method may output a second similarity between the supporting drawing and the similar drawing for at least one of the multiple first similar applications.

[0016] One aspect of the present invention is an information retrieval method that receives a designated application, calculates a first similarity between the specification of the designated application and each of multiple applications, extracts multiple first similar applications from the multiple applications based on the first similarity, calculates a second similarity between the supporting drawings corresponding to the claims of each of the multiple first similar applications and at least one drawing included in the designated application, narrows down and / or sorts the multiple first similar applications based on the second similarity to extract at least one second similar application, extracts at least one drawing similar to the supporting drawings from the drawings included in the designated application based on the second similarity, and outputs value information, supporting drawings, and similar drawings for the second similar application. Furthermore, the method may output a second similarity between the supporting drawings and similar drawings for the second similar application.

[0017] The value information may include information on related products.

[0018] The designated application may be an application pending at the Patent Office, and the plurality of applications may include at least one of pre-examination applications, applications under examination, and registered applications. [Effects of the Invention]

[0019] According to one aspect of the present invention, it is possible to provide an information retrieval system that retrieves information with high accuracy. According to one aspect of the present invention, it is possible to provide an information retrieval system that retrieves information efficiently. According to one aspect of the present invention, it is possible to provide an information retrieval system that performs highly accurate information retrieval using a simple input method.

[0020] One aspect of the present invention provides an information search system that searches for similar applications and value information for a specified application. A user can consider the value of a specified application by referring to the similar applications and value information for the similar applications obtained using the information search system. Furthermore, the user can obtain an opportunity to, for example, make amendments to increase the value of the specified application.

[0021] According to one aspect of the present invention, it is possible to provide an information search system that searches for information on similar applications and products associated with the similar applications for a specified application.

[0022] Note that the description of these effects does not preclude the existence of other effects. One embodiment of the present invention does not necessarily have all of these effects. Effects other than these can be extracted from the description in the specification, drawings, and claims. [Brief explanation of the drawings]

[0023] FIG. 1 is a diagram illustrating an example of an information retrieval system. FIG. 2 is a diagram illustrating an example of an information search method. FIG. 3 is a diagram illustrating an example of an information search method. 4A and 4B are diagrams showing an example of an information search method. FIG. 5 is a diagram illustrating an example of an information search method. FIG. 6 is a diagram illustrating an example of an information search system. FIG. 7 is a diagram illustrating an example of an information retrieval system. DETAILED DESCRIPTION OF THE INVENTION

[0024] The embodiments will be described in detail with reference to the drawings. However, the present invention is not limited to the following description, and it will be readily understood by those skilled in the art that various changes can be made in form and detail without departing from the spirit and scope of the present invention. Therefore, the present invention should not be interpreted as being limited to the description of the embodiments shown below.

[0025] In the configuration of the invention described below, the same parts or parts having similar functions are denoted by the same reference numerals in different drawings, and repeated explanations thereof will be omitted. In addition, when referring to similar functions, the same hatch pattern may be used and no particular reference numeral may be assigned.

[0026] Furthermore, for ease of understanding, the position, size, range, etc. of each component shown in the drawings may not represent the actual position, size, range, etc. Therefore, the disclosed invention is not necessarily limited to the position, size, range, etc. disclosed in the drawings.

[0027] (Embodiment 1) In this embodiment, an information retrieval system and an information retrieval method according to one embodiment of the present invention will be described with reference to FIGS.

[0028] In one embodiment of the information search system of the present invention, a designated application is accepted, and multiple similar applications are extracted from the multiple applications based on a first similarity between the specification of the designated application and each of the specifications of multiple applications.

[0029] A similar application is an application that is similar to the accepted designated application and has value information. Value information is information about the value of the similar application. Examples of value information include information on related products, licenses, related technologies, related services, and evaluations by consultants.

[0030] If the database contains a mixture of applications with value information and applications without value information, only applications with value information are extracted as similar applications.

[0031] By specifying an application, users can search for applications that have value information and are similar to the specified application, thereby obtaining the information necessary to consider the value of the specified application.

[0032] In this embodiment, the case of searching for related products of an application will be mainly described as an example, but the information linked to the application is not limited to information on related products. By using a database in which applications are linked with at least one of the value information examples given above, the information search system of one embodiment of the present invention can easily obtain applications similar to the designated application and the value information of the similar applications.

[0033] If a similar application contains information on related products, users of the information search system can specify the application for which they want to search for related products, and search for applications that are linked to the related product information and are similar to the specified application. By referring to these similar applications that already have linked information on related products, users can evaluate the designated application. Furthermore, they can appropriately amend the claims of the designated application, if necessary.

[0034] However, if the similar application's similar features are different from the features related to the product, the probability that the designated application is related to the product is low. It takes a lot of time and effort to check the features related to the product one by one for the multiple similar applications found in the search, and to check whether the features are also described in the designated application. The same can be said for other valuable information.

[0035] Therefore, in one embodiment of the information search system of the present invention, similar drawings to the supporting drawings are searched for among the drawings held by the designated application based on a second similarity between the supporting drawings corresponding to the claims of the similar application and each of at least one drawing held by the designated application.

[0036] The supporting drawings corresponding to the claims of the similar application show the structure related to the product. If the designated application has drawings similar to the supporting drawings of the similar application, there is a high probability that the structure similar to the designated application corresponds to the structure related to the product in the similar application. Therefore, it can be said that there is a high probability that the designated application is also related to the related product of the similar application.

[0037] In one aspect of the present invention, the information search system can output information on related products, supporting drawings, and similar drawings in designated applications to a user's terminal for similar applications. This allows the user to easily understand the configuration related to the product in the similar application from the supporting drawings. The user can then easily determine whether the designated application contains the relevant configuration from the similar drawings. This allows the user to easily understand how the designated application is related to the product. Furthermore, the user can determine how the designated application should be amended to further enhance its relevance to the product.

[0038] In addition, the information retrieval system according to an embodiment of the present invention may output a second similarity between the supporting drawings and the similar drawings. By checking similar applications with a high second similarity, the user can efficiently obtain desired information.

[0039] In the above output, for example, similar applications can be output in descending order of first similarity. Alternatively, in an information search system according to one embodiment of the present invention, similar applications can be narrowed down and / or sorted based on the second similarity, and then output. The output order of similar applications may be determined by combining both the first similarity and the second similarity. Furthermore, both a list based on the first similarity (list of similar applications) and a list based on the second similarity (list of similar drawings) may be output. Among similar applications, cases where designated applications are highly likely to be related to related products of the similar applications are displayed at the top, allowing users to efficiently obtain desired information. Specifically, products related to designated applications can be easily found.

[0040] <Information Retrieval System 1> 1 shows a block diagram of an information retrieval system 200. The information retrieval system 200 includes a receiving unit 110, a storage unit 120, a processing unit 130, an output unit 140, and a transmission path 150.

[0041] [Reception Section 110] The reception unit 110 receives the designated application. The data supplied to the reception unit 110 is supplied to one or both of the storage unit 120 and the processing unit 130 via the transmission path 150.

[0042] [Storage section 120] The storage unit 120 has a function of storing a program executed by the processing unit 130. The storage unit 120 may also have a function of storing calculation results and inference results generated by the processing unit 130, data input to the receiving unit 110, etc.

[0043] The storage unit 120 has at least one of a volatile memory and a non-volatile memory. Examples of volatile memory include DRAM (Dynamic Random Access Memory) and SRAM (Static Random Access Memory). Examples of non-volatile memory include ReRAM (Resistive Random Access Memory, also called Resistive Memory), PRAM (Phase Change Random Access Memory), FeRAM (Ferroelectric Random Access Memory), MRAM (Magnetoresistive Random Access Memory, also called Magnetoresistive Memory), and flash memory. The storage unit 120 may also have a recording media drive. Examples of recording media drives include a hard disk drive (HDD) and a solid state drive (SSD).

[0044] The storage unit 120 may include a database containing application and / or product data. For example, the storage unit 120 may include an application database and / or a product database.

[0045] The information retrieval system 200 may also have a function to retrieve application and / or product data from a database located outside the system. For example, the information processing system may have a function to retrieve data from an application database and / or a product database located outside the system.

[0046] Furthermore, the information retrieval system 200 may have a function of retrieving data from both its own database and an external database.

[0047] The database may be configured to include, for example, text data and / or image data.

[0048] Alternatively, instead of the database, one or both of a storage and a file server may be used. For example, when using files stored in a file server, it is preferable that the database has paths to files stored in the file server.

[0049] The following description will be given taking as an example a case where the application database and the product database exist separately, but the present invention is not limited to this, and all data may exist together in one database, or may exist separately in three or more databases, or at least some of the data may exist in a storage device, or at least some of the data may exist in a file server.

[0050] The application database contains at least data on specifications, drawings, and related product information for multiple applications. The drawings include supporting drawings corresponding to the claims (also called claims). Applications include intellectual property applications such as patent applications and utility model registration applications. In the case of a patent application, the drawings include supporting drawings corresponding to the claims. In the case of a utility model registration application, the drawings include supporting drawings corresponding to the utility model registration claims. There are no restrictions on the status of each application, including whether it is published, whether it is pending at the patent office, and whether it is registered. For example, the database may contain data on at least one of pre-examination applications, applications under examination, and registered applications, or it may contain data on all of them.

[0051] It is preferable that the information on related products includes at least information that can identify the products. Specifically, it is preferable that the application database includes, as information on related products, at least one of the following: a control number (including a unique internal company number) for identifying the product, a product name, and a model number.

[0052] The information retrieval system of one aspect of the present invention can extract detailed information about a product from a product database using information that can identify the product contained in the application database. Therefore, the application database does not need to contain detailed information about the product. For example, if a product database already exists, the product database can be utilized.

[0053] The application database may also include, as related product information, one or more of the following: manufacturer name, release date, product category, and photograph data.

[0054] The product database may include one or more of the following: a control number for identifying a product, a product name, a model number, a manufacturer name, a release date, a product category, and photographic data.

[0055] For example, the application database may have image data of all drawings in each application and may also have data (such as text data or label data) indicating which drawings are supporting drawings that correspond to the claims. Alternatively, the application database may have image data of only the supporting drawings that correspond to the claims among the drawings in each application.

[0056] The application database may also contain meta-information about drawings. For example, the meta-information may include information about the meaning expressed by the drawing (also called semantic information, such as whether the drawing is a circuit diagram or a memory circuit). For example, semantic information can be tagged to drawings using artificial intelligence (AI). Alternatively, semantic information assigned by a human may be linked to the drawing. In this case, searches may be performed using this meta-information in addition to or instead of the similarity of the supporting drawings. For example, if a designated application has drawings that share meta-information with the supporting drawings of a certain application, the application may be suggested as a similar application to the designated application.

[0057] The processing unit 130 may extract information about supporting parts of claims from documents and determine supporting drawings based on the information. The documents may include documents related to applications prepared by humans (such as memos at the time of filing and memos during prosecution) and documents submitted to the Patent Office (such as petitions, explanations of circumstances for accelerated examination, and written opinions). The application database may contain these documents.

[0058] The application database contains data on specifications of multiple applications. The specifications are stored, for example, as text data.

[0059] The application database may further include at least one of the following data: an application management number (including a unique company number) for identifying an application, an application family management number for identifying an application family, an application number, a publication number, a registration number, claims, drawings, an abstract, a filing date, a priority date, a publication date, a status, a classification (such as a patent classification or a utility model classification), a category, and keywords. Each of these pieces of information may be used when searching for similar applications. Alternatively, each of these pieces of information may be used to identify an application when accepting a designated application. Alternatively, each of these pieces of information may be output together with the processing results of the processing unit 130.

[0060] The application database may also contain data on applications that do not have information on related products (such as applications for which no related products exist and applications for which the existence of related products has not been confirmed). For example, if a user specifies an application from among applications for which no related product information exists, the information retrieval system can execute processing using data in the application database. This eliminates the need for the user to input specification and drawing data, allowing for easy search execution. Furthermore, if an application database already exists, the information retrieval system of one aspect of the present invention can use the application database to execute various processes, searching only for applications that have related product information. Alternatively, a series of processes may include a process for narrowing down the search to only applications that have related product information.

[0061] The product database contains one or more pieces of data, such as a control number for identifying a product, a product name, a model number, a manufacturer name, a release date, a category, and photographic data.

[0062] The data stored in the storage unit and the database can be changed as needed depending on the value information. The information retrieval system according to one aspect of the present invention may use a database that contains at least one of license information, related technology information, related service information, and consultant evaluations.

[0063] [Processing section 130] The processing unit 130 has a function of performing processing such as calculation and inference using data supplied from one or both of the receiving unit 110 and the storage unit 120. The processing unit 130 also has a function of performing processing using various data contained in a database. The processing unit 130 can supply processing results such as calculation results and inference results to one or both of the storage unit 120 and the output unit 140.

[0064] The processing unit 130 may include, for example, an arithmetic circuit and a central processing unit (CPU).

[0065] The processing unit 130 may have a microprocessor such as a DSP (Digital Signal Processor) or a GPU (Graphics Processing Unit). The microprocessor may be implemented by a PLD (Programmable Logic Device) such as an FPGA (Field Programmable Gate Array) or an FPAA (Field Programmable Analog Array). The processing unit 130 can perform various data processing and program control by interpreting and executing instructions from various programs using the processor. Programs that can be executed by the processor are stored in at least one of a memory area of ​​the processor and the storage unit 120.

[0066] The processing unit 130 may have a main memory, which includes at least one of a volatile memory such as a random access memory (RAM) and a non-volatile memory such as a read only memory (ROM).

[0067] The RAM may be, for example, a DRAM or an SRAM, and a virtual memory space is allocated and used as a working space for the processing unit 130. The operating system, application programs, program modules, program data, lookup tables, and the like stored in the storage unit 120 are loaded into the RAM for execution. The data, programs, and program modules loaded into the RAM are each directly accessed and operated by the processing unit 130.

[0068] ROM can store BIOS (Basic Input / Output System) and firmware, which do not require rewriting. Examples of ROM include mask ROM, OTPROM (One-Time Programmable Read Only Memory), and EPROM (Erasable Programmable Read Only Memory). Examples of EPROM include UV-EPROM (Ultra-Violet Erasable Programmable Read Only Memory), which allows stored data to be erased by exposure to ultraviolet light, EEPROM (Electrically Erasable Programmable Read Only Memory), and flash memory.

[0069] It is preferable that the information retrieval system uses AI for at least some of its processing.

[0070] It is particularly preferable that the information retrieval system uses an artificial neural network (ANN, hereinafter also simply referred to as a neural network). A neural network is realized by a circuit (hardware) or a program (software).

[0071] In this specification, a neural network refers to a general model that mimics the neural circuit network of a living organism, determines the connection strength between neurons through learning, and has problem-solving capabilities. A neural network has an input layer, an intermediate layer (hidden layer), and an output layer.

[0072] In this specification and the like, when discussing neural networks, determining the connection strengths (also called weighting coefficients) between neurons from existing information may be referred to as "learning."

[0073] In this specification and the like, the act of constructing a neural network using connection strengths obtained by learning and deriving a new conclusion from it may be referred to as "inference."

[0074] [Output section 140] The output unit 140 outputs information based on the processing results of the processing unit 130. For example, one or both of the calculation results and the inference results of the processing unit 130 can be supplied to the outside of the information retrieval system 200. Furthermore, the output unit 140 can output various data contained in the database based on the processing results of the processing unit 130.

[0075] [Transmission Line 150] The transmission path 150 has a function of transmitting data. Data can be transmitted and received between the reception unit 110, the storage unit 120, the processing unit 130, and the output unit 140 via the transmission path 150.

[0076] An information search method in an information search system according to one embodiment of the present invention will be described with reference to Figures 2 to 5. Two information search methods will be described below.

[0077] <Information search method 1> The information retrieval method 1 includes the processes from step S1 to step S6 shown in FIG.

[0078] [Step S1] In step S1, a designated application is accepted. A designated application is, for example, an application for which a user wants to search for related products. There are no particular limitations on the status of the designated application. An example of a designated application is an application pending at the Patent Office. Furthermore, a designated application may be, for example, a pre-examination application, an application under examination, or a registered application.

[0079] The user can directly input text data of the specification and image data of the drawings of the designated application.

[0080] Furthermore, if the designated application is an application included in a database, etc., the user can specify the application for which information is to be searched by inputting information that identifies the application. The user may also enter information that identifies an application family. Based on the information input by the user, the information search system extracts data related to the designated application (specifically, data necessary for subsequent processing) from the application database, etc.

[0081] Information identifying an application (or application family) includes an application control number, an application family control number, an application number, a publication number, and a registration number.

[0082] [Step S2] In step S2, a first similarity between the specification of the designated application and each of the specifications of the multiple applications is calculated.

[0083] Here, as mentioned above, the data of the multiple applications is contained in a database or the like, and includes at least the data of the specification, drawings, and value information (information on related products in this case). The drawings include supporting drawings corresponding to the scope of claims.

[0084] If the database contains data on applications that do not have information on related products, the first similarity may be calculated for only applications that have information on related products in step S2, or may be narrowed down to applications that have information on related products in step S3.

[0085] The similarity between two specifications can be determined by vectorizing (quantifying) the specifications (text) and calculating either or both of the similarity and distance between the vectors. In other words, either or both of the similarity and distance between the vectors can be considered as the first similarity.

[0086] Alternatively, the frequency of occurrence of words included in the specifications may be calculated, and a word ranking may be created in descending order of frequency of occurrence. In this case, the similarity between the two specifications in the word ranking may be regarded as the first similarity.

[0087] Alternatively, the degree of agreement between two specifications may be scored using words contained in the specifications and their synonyms, and this score may be regarded as the first degree of similarity.

[0088] The first similarity calculation method can be appropriately determined depending on the language of the specification. The information retrieval system according to one aspect of the present invention can search for applications in at least one language, such as Japanese, English, German, French, Chinese, and Korean.

[0089] In languages ​​such as Japanese where words are not separated by spaces, it is preferable to perform morphological analysis and divide sentences into words. Also, when extracting only specific parts of speech and calculating similarity, it is preferable to perform morphological analysis regardless of the language.

[0090] Specifically, one or more of morphological analysis, syntactic analysis, semantic analysis, and contextual analysis can be performed on the text data of the specification. Morphological analysis divides sentences written in natural language into morphemes (the smallest units that have meaning in language) and determines the parts of speech of the morphemes. This makes it possible, for example, to extract only nouns from each specification.

[0091] For example, morphological analysis can be performed using Mecab, a morphological analysis engine. For example, syntactic analysis (dependency analysis) can be performed using CaboCha, a dependency analysis tool.

[0092] The text data of the specification may be segmented into sentences and / or extracted into character strings (words) using word segmentation (separating words with spaces) or N-gram (also known as N-character indexing or N-gram method).

[0093] There are various methods for vectorizing text.

[0094] For example, TF-IDF (Term Frequency-Inverse Document Frequency) is a method for vectorizing text based on the number of times a word appears. The TF value represents the frequency of each word in a given specification, and the IDF value represents the degree to which a word appears concentratedly in some specifications. The more frequently a word appears in a specification, the higher the TF value of that word in that specification. A word that appears in many specifications has a small IDF value, while a word that appears in only some specifications has a high IDF value. By calculating the product of the TF value and IDF value of each word, it is possible to calculate a score for whether the word is a word that characterizes the specification.

[0095] Alternatively, a sentence may be vectorized using word embeddings. Word embeddings are also called word embeddings, and word embedding vectors are vectors that represent words using quantified continuous values ​​for each feature element (dimension). Words with similar meanings will have similar vectors. For example, word embedding vectors can be generated using machine learning, such as a neural network.

[0096] Here, we will explain an example of a method for generating a distributed representation vector of a word using a neural network. Neural network learning is performed using supervised learning. Specifically, a certain word is provided to the input layer, and the surrounding words of that word are provided to the output layer, and the neural network learns the probability of the surrounding words for that word. It is preferable that the intermediate layer (hidden layer) has a relatively low-dimensional vector with 10 to 1000 dimensions. The vector obtained after learning is the distributed representation vector of the word.

[0097] Distributed representation of words can be achieved, for example, using the open-source algorithm Word2vec, which converts words into vectors, including their features and semantic structure, based on the hypothesis that words used in the same context have the same meaning.

[0098] In word vectorization, by generating distributed representation vectors of words, it is possible to calculate the similarity and distance between words by performing operations between vectors. When the similarity between two vectors is high, it can be said that the two vectors are highly related. Also, when the distance between two vectors is short, it can be said that the two vectors are highly related.

[0099] Methods for calculating the similarity between two vectors include cosine similarity, covariance, unbiased covariance, and Pearson's product-moment correlation coefficient, etc. Among these, it is particularly preferable to use cosine similarity.

[0100] Methods for calculating the distance between two vectors include Euclidean distance, standard (normalized, average) Euclidean distance, Mahalanobis distance, Manhattan distance, Chebyshev distance, and Minkowski distance.

[0101] Alternatively, words may be expressed as vectors using other methods. For example, words can be vectorized using one-hot representation (also called one hot vector). A description may be expressed as a vector of the number of times a word appears using Bag-of-Words, which uses one-hot representation.

[0102] While one-hot representation assigns one dimension to each word, distributed representation allows words to be represented as low-dimensional real-valued vectors, so even if the vocabulary size increases, it can be represented with fewer dimensions. Therefore, even if the corpus contains a large number of words, the amount of calculation does not increase much, and it is possible to process huge amounts of data in a short time.

[0103] Alternatively, methods using distributed representations of sentences, such as Doc2Vec and Sent2Vec, may be used.

[0104] As described above, there are various methods for calculating the first similarity, and the method is not particularly limited.

[0105] [Step S3] In step S3, a plurality of first similar applications are extracted from the plurality of applications based on the first similarity.

[0106] For example, an application whose first similarity is equal to or greater than a reference value, or an application whose first similarity is higher than the reference value, can be extracted as a first similar application. When the first similarity is expressed as a value between 0 and 1, the reference value can be, for example, 0.70, 0.75, 0.80, 0.85, or 0.90. The reference value can be determined appropriately, and a value less than 0.70 can be used as the reference.

[0107] Alternatively, for example, a predetermined number of applications with a high degree of first similarity may be extracted. For example, the top 100, 200, 300, 400, or 500 applications with a high degree of first similarity may be extracted. Alternatively, the top number of applications with a high degree of first similarity may be extracted in a number corresponding to 10%, 20%, 30%, 40%, or 50% of the multiple applications.

[0108] Furthermore, in step S3, when narrowing down the applications contained in the database to those that have information on related products, the narrowing down may be done before extracting the predetermined number of applications, or after extracting the predetermined number of applications. For example, if narrowing down is done before extracting the predetermined number of applications (100), 100 applications will be extracted as is, and if narrowing down is done after extracting the predetermined number of applications, the number of applications extracted will be 100 or less.

[0109] Alternatively, for example, it is possible to extract a predetermined number of applications whose first similarity is equal to or greater than a standard value, or applications whose first similarity is higher than the standard value. Specifically, if the number of applications whose first similarity is 0.70 or greater is 300 and the predetermined number is 250, the top 250 applications whose first similarity is highest are extracted as first similar applications. Also, if the number of applications whose first similarity is 0.70 or greater is 200 and the predetermined number is 250, the 200 applications whose first similarity is 0.70 or greater are extracted as first similar applications.

[0110] In step S3, by narrowing down the applications (first similar applications) to be used in subsequent processing from among the multiple applications, it is possible to reduce the amount and time of processing in subsequent steps.

[0111] By narrowing down the applications using the first similarity, it is possible to perform a more detailed search for applications that are highly similar to the designated application, thereby enabling efficient and highly accurate information searches.

[0112] By outputting multiple applications in a list based on the first similarity, applications with a high similarity to the specified application can be displayed at the top, making it easier for users to find the desired application from the search results and improving work efficiency.

[0113] At this point, information on the first similar applications may be generated as a first list based on the first similarity, and may further be output. In the first list, the first similar applications are preferably arranged in descending order of first similarity. For example, if the next step uses information input by the user to perform processing, it is preferable to generate and output the first list before proceeding to step S4. At this time, there are no particular limitations on the information to be output; for example, a number capable of identifying the first similar application (such as an application management number, application number, publication number, or registration number) may be output together with the first similarity.

[0114] In this embodiment, an example is shown in which first similar applications are extracted in step S3, but the present invention is not limited to this. It is also possible to proceed to step S4 without performing step S3. For example, if the number of applications for which the first similarity has been calculated is small, it is not necessary to narrow down the applications. All applications may be treated as first similar applications and the subsequent processing may be performed. In this case, the first similarity may be used to determine the order in which applications are output before proceeding to step S4 and / or in step S6. For example, the processing results may be output by arranging the applications in descending order of first similarity.

[0115] [Step S4] In step S4, a second similarity is calculated between the supporting drawings corresponding to the claims of at least one of the first similar applications and at least one drawing included in the designated application.

[0116] Although the first similar application is an application that is highly similar to the designated application, the configuration similar to the designated application may differ from the configuration related to the product. The supporting drawings corresponding to the claims of the first similar application show the configuration related to the product. If the designated application has drawings similar to the supporting drawings (i.e., drawings with a high second similarity), there is a high probability that the configuration similar to the designated application corresponds to the configuration related to the product. In other words, there is a high probability that the designated application is related to the product. By checking the drawings with a high second similarity, the relationship between the designated application, the first similar application, and related products can be efficiently understood. This allows products related to the designated application to be quickly found.

[0117] In step S4, the second similarity may be calculated for all of the multiple first similar applications. Alternatively, the second similarity may be calculated for at least one application designated by the user among the multiple first similar applications. Alternatively, the second similarity may be calculated for only a predetermined number of the multiple first similar applications that have the highest first similarity. Alternatively, the second similarity may be calculated for the first similar applications until the number of applications with second similarity higher than the reference value reaches a predetermined number. In this case, it is preferable to perform the processing in descending order of first similarity.

[0118] Figure 3 shows an illustration of how the second similarity is calculated. For example, if the supporting drawing of Application P, one of the first similar applications, is FIG. Q, the second similarity between FIG. Q and each drawing of the designated application is calculated. Figure 3 shows an example in which the designated application has three drawings: FIG. A, FIG. B, and FIG. C. Figure 3 shows an example in which the second similarity between FIG. Q and FIG. A is 0.80, the second similarity between FIG. Q and FIG. B is 0.90, and the second similarity between FIG. Q and FIG. C is 0.10. Note that these values ​​are not actual calculation results.

[0119] The similarity between two images is preferably calculated using a convolutional neural network (CNN), and in particular, it is preferable to use deep learning using a CNN.

[0120] The drawing data can be subjected to one or more of the following processes: blurring (also called smoothing), inversion, changing (reducing) the resolution, and binarization.

[0121] When handling data in different image formats, it is preferable to perform channel conversion and unify the number of data channels. For example, the jpg format has three channels: RGB (red, green, and blue). On the other hand, the png format has transparency information (alpha channel) in addition to RGB. Therefore, when handling both the jpg and png formats, it is preferable to unify the number of channels and unify the dimensions of the data.

[0122] For example, the second similarity can be calculated by determining how closely the values ​​of the coordinates in the two drawings match. For example, cosine similarity can be used as the second similarity.

[0123] Specifically, various image processing methods can be used to process the drawing into 64 coordinates of 8 rows and 8 columns, and the image data of each coordinate can be binarized to have a value of 0 (black) or 1 (white).The calculation result of the cosine similarity using this data (here, 64-dimensional data) can then be used as the second similarity.

[0124] In addition, if a similar description in the designated application and the similar application corresponds to one of the technical features in each application, and the meaning expressed by the drawings supporting the description in the designated application and the similar application is similar, there is a high probability that infringement of the same product will be recognized. Even if the cosine similarity between two drawings is low due to reasons such as different artists, the meaning expressed by the drawings may be similar.

[0125] Therefore, the second similarity between the supporting drawings and at least one drawing of the designated application may be calculated using information about the meaning expressed by the drawings (also called semantic information). For example, drawings with the same semantic information may be scored so that the second similarity is higher than drawings with different semantic information. The second similarity may be calculated using semantic information alone, or may be calculated in combination with cosine similarity, etc.

[0126] The second similarity can be calculated by any of a variety of methods, and is not particularly limited.

[0127] In step S4, the amount of processing and the processing time can be reduced by processing the first similar applications narrowed down in step S3. Also, in step S4, it is not necessary to process all of the first similar applications, and it is possible to perform only the necessary amount of processing based on either or both of the first similarity and the user's designation.

[0128] [Step S5] In step S5, for at least one of the plurality of first similar applications, at least one drawing similar to the supporting drawing is extracted from the drawings of the designated application based on the second similarity.

[0129] For example, for each first similar application, a second list may be generated in which the drawings in the designated application are arranged in descending order of second similarity. In this case, similar drawings may not be extracted, and all drawings in the designated application may be rearranged.

[0130] For example, drawings whose second similarity is equal to or greater than a reference value, or drawings whose second similarity is higher than the reference value, can be extracted as similar drawings to the supporting drawing. When the second similarity is expressed as a value between 0 and 1, the reference value can be, for example, 0.70, 0.75, 0.80, 0.85, or 0.90. The reference value can be determined appropriately, and a value less than 0.70 can be used as the reference value.

[0131] In addition, if a standard value is set for the second similarity, there may be applications among the first similar applications in which it is determined that none of the drawings in the designated application are similar to the supporting drawings. Although such applications are highly similar to the designated application, there is a high probability that the configuration similar to the designated application is different from the configuration related to the product. Therefore, in step S5, it is sufficient to extract drawings similar to the supporting drawings from the drawings in the designated application for at least one, but not all, of the multiple first similar applications.

[0132] Alternatively, for example, a predetermined number of drawings with a high second similarity may be extracted. For example, the top one, two, three, four, or five drawings with a high second similarity may be extracted. Alternatively, the top number of drawings with a high second similarity may be extracted, corresponding to 10%, 20%, 30%, 40%, or 50% of the drawings in the designated application.

[0133] Alternatively, for example, drawings whose second similarity is equal to or greater than a reference value, or applications whose second similarity is higher than a reference value, can be extracted within a predetermined number. Specifically, if the number of drawings whose second similarity is 0.70 or greater is three and the predetermined number is two, the top two drawings with the highest second similarity are extracted as similar drawings to the supporting drawings. Also, if the number of drawings whose second similarity is 0.70 or greater is one and the predetermined number is two, one drawing whose second similarity is 0.70 or greater is extracted as a similar drawing to the supporting drawings.

[0134] By using the second similarity to narrow down the drawings, you can easily compare the supporting drawings of the first similar application with the drawings of the designated application that are similar to those supporting drawings. This allows you to efficiently understand the relationship between the designated application, the first similar application, and related products. You can then find products related to the designated application. Furthermore, depending on the circumstances, you may consider amending the claims so that the designated application covers the product.

[0135] [Step S6] In step S6, information on related products, supporting drawings, and similar drawings are output for at least one of the first similar applications.

[0136] Furthermore, other information can also be output. For example, information can be output from either or both of the application database and the product database. For example, at least one of various pieces of information related to the first similar application (such as application management number, filing date, status, and keywords) can be output. Also, one or both of the first similarity and the second similarity calculated in the previous step can be output.

[0137] The output layout (display layout) can be determined appropriately depending on the information to be output and the amount of information to be output, etc. For example, data may be output separately to a screen on which the user can check a list of similar applications and a screen on which the user can compare supporting drawings and similar drawings.

[0138] An example of the output is shown in Figure 4A. The first similar applications are output in the order of Application X, Application Y, and Application Z. For example, the first similar applications can be output in descending order of the first similarity, the second similarity, or the overall highest first and second similarities.

[0139] Furthermore, information on the related products of each of the first similar applications is output. Application X and Application Y are both related to Product AAA, and Application Z is related to Product BBB.

[0140] The supporting drawings of the first similar application are also output. For example, it is preferable to output both the figure number and the drawing. Also, a link to the drawing may be provided so that the drawing can be viewed on a separate screen.

[0141] The supporting drawing for Application X is Figure 1 (FIG. 1), and the similar drawing in the designated application is Figure 1 (FIG. 1). The supporting drawing for Application Y is Figure 2 (FIG. 2), and the similar drawing in the designated application is Figure 1 (FIG. 1). The supporting drawing for Application Z is Figure 6 (FIG. 6), and the similar drawing in the designated application is Figure 7 (FIG. 7).

[0142] Figure 4A shows an example of extracting and outputting similar drawings to supporting drawings one by one from the drawings of the designated application based on the second similarity. As shown in Figure 4B, multiple similar drawings may be extracted, and the second similarity score may also be output.

[0143] In this embodiment, an example of extracting similar drawings in step S5 is shown, but the present invention is not limited to this. It is also possible to proceed to step S6 without performing step S5. In this case, in step S6, information on related products and supporting drawings for at least one of the multiple first similar applications are output, and a second similarity to the supporting drawings can be output for all drawings in the designated application. Alternatively, information can be output based on the second list created in step S5. Furthermore, in step S6, both the first list and the second list can be output.

[0144] As described above, by using the information search method of this embodiment, it is possible to search for applications that are similar to designated applications and that contain information on related products. By calculating the similarity between the supporting drawings of similar applications and each drawing of the designated application, it is possible to search for similar applications that have a high probability of matching structures similar to the designated application with structures related to the product. This makes it possible to efficiently find products related to similar applications that are also likely to be related to the designated application.

[0145] <Information search method 2> Information retrieval method 2 includes the processes from step S1 to step S3 shown in FIG. 2 and the processes from step S14 to step S17 shown in FIG.

[0146] The processing from step S1 to step S3 is the same as that in <Information retrieval method 1>, and therefore the explanation will be omitted.

[0147] [Step S14] In step S14, a second similarity is calculated between the supporting drawings corresponding to the claims of each of the first similar applications and at least one drawing included in the designated application.

[0148] In step S14, it is preferable to calculate the second similarity for all of the plurality of first similar applications, but other steps can be performed in the same manner as step S4.

[0149] [Step S15] In step S15, at least one second similar application is extracted by narrowing down and / or sorting the plurality of first similar applications based on the second similarity.

[0150] If the final processing results are output while multiple first similar applications are sorted based on the first similarity, an application among the first similar applications whose configuration similar to the designated application differs from the configuration related to the product may be displayed at the top.

[0151] By narrowing down similar applications based on the second similarity, applications that are highly likely to have a structure similar to that of the designated application and a structure related to the product can be displayed at the top. For example, among the first similar applications, applications that have supporting drawings whose second similarity with any drawing of the designated application is equal to or greater than a standard value can be extracted as second similar applications.

[0152] By sorting the similar applications based on the second similarity, applications that are highly likely to have a configuration similar to that of the designated application and a configuration related to the product can be displayed at the top. Alternatively, the similar applications may be sorted based on both the first similarity and the second similarity. Note that, when only sorting the similar applications, the number of first similar applications and the number of second similar applications may be the same. In other words, step S15 may be rephrased as a process of sorting multiple first similar applications based on the second similarity.

[0153] As described above, by using the second similarity, similar applications linked to products that are highly likely to be related products of the designated application can be displayed at the top of the search results.

[0154] [Step S16] In step S16, for the second similar application, at least one drawing similar to the supporting drawing is extracted from the drawings of the designated application based on the second similarity.

[0155] Step S16 can be performed in the same way as step S5, except that the subject is the second similar application. Also, steps S15 and S16 may be processed simultaneously, or it may be difficult to separate the processes.

[0156] [Step S17] In step S17, information on related products, supporting drawings, and similar drawings for the second similar application are output.

[0157] Step S17 can be performed in the same manner as step S6, except that the target is the second similar application.

[0158] As described above, the information search system of this embodiment can search for value information, such as similar applications and products associated with the similar applications, for designated applications. By searching using not only the similarity between the specifications of the designated application and the similar application, but also the similarity between the supporting drawings corresponding to the claims of the similar application and the drawings of the designated application, the system can present to the user cases in which there is a high probability that configurations similar to the designated application correspond to configurations associated with the value information. This provides useful information and assistance to the user in considering the value of the designated application. For example, the user can easily find products related to the designated application.

[0159] This embodiment mode can be combined with other embodiment modes as appropriate. In addition, in this specification, when a plurality of configuration examples are shown in one embodiment mode, the configuration examples can be combined as appropriate.

[0160] (Embodiment 2) In this embodiment, an information retrieval system according to one embodiment of the present invention will be described with reference to FIGS.

[0161] <Information Retrieval System 2> 6 shows a block diagram of the information retrieval system 210. The information retrieval system 210 includes a server 220 and a terminal 230 (such as a personal computer). Note that for the same components as those in the information retrieval system 200 shown in FIG. 1, the description of the <information retrieval system 1> in the first embodiment can also be referred to.

[0162] The server 220 includes a communication unit 161a, a transmission path 162, a storage unit 120, and a processing unit 130. Although not shown in FIG. 6, the server 220 may further include at least one of a reception unit, a database, an output unit, an input unit, and the like.

[0163] The terminal 230 has a communication unit 161b, a transmission path 164, an input unit 115, a storage unit 125, a processing unit 135, and a display unit 145. Examples of the terminal 230 include a tablet personal computer, a notebook personal computer, and various types of portable information terminals. Alternatively, the terminal 230 may be a desktop personal computer that does not have the display unit 145, and the terminal 230 may be connected to a monitor or the like that functions as the display unit 145.

[0164] A user of the information retrieval system 210 inputs information about the designated application from the input unit 115 of the terminal 230 to the server 220. The information is transmitted from the communication unit 161b to the communication unit 161a.

[0165] For example, text data of the specification and image data of the drawings of the designated application are transmitted from communication unit 161b to communication unit 161a. Also, for example, information specifying the application is transmitted from communication unit 161b to communication unit 161a.

[0166] The information received by the communication unit 161a is stored in the memory of the processing unit 130 or in the storage unit 120 via the transmission path 162. Furthermore, the information may be supplied from the communication unit 161a to the processing unit 130 via a reception unit (see the reception unit 110 shown in FIG. 1).

[0167] The various processes described in <Information retrieval method 1> and <Information retrieval method 2> of the first embodiment are performed by the processing unit 130. Since these processes require high processing power, they are preferably performed by the processing unit 130 included in the server 220. It is preferable that the processing unit 130 has higher processing power than the processing unit 135.

[0168] The processing result of processing unit 130 is stored in the memory of processing unit 130 or storage unit 120 via transmission path 162. Thereafter, the processing result is output from server 220 to display unit 145 of terminal 230. The processing result is transmitted from communication unit 161a to communication unit 161b. Furthermore, various data included in the database may be transmitted from communication unit 161a to communication unit 161b based on the processing result of processing unit 130. Furthermore, the processing result may be supplied from processing unit 130 to communication unit 161a via an output unit (output unit 140 shown in FIG. 1 ).

[0169] [Communication Unit 161a and Communication Unit 161b] Using the communication units 161a and 161b, data can be transmitted and received between the server 220 and the terminal 230. A hub, a router, a modem, or the like can be used as the communication units 161a and 161b. Data can be transmitted and received using either a wired connection or wirelessly (for example, radio waves, infrared rays, etc.).

[0170] [Transmission path 162 and transmission path 164] The transmission paths 162 and 164 have a function of transmitting data. Data can be transmitted and received between the communication unit 161a, the storage unit 120, and the processing unit 130 via the transmission path 162. Data can be transmitted and received between the communication unit 161b, the input unit 115, the storage unit 125, the processing unit 135, and the display unit 145 via the transmission path 164.

[0171] [Input section 115] The input unit 115 can be used when the user specifies an application. For example, the input unit 115 can have a function for operating the terminal 230, and specific examples thereof include a mouse, a keyboard, a touch panel, and the like.

[0172] [Storage section 125] The storage unit 125 may store one or both of data related to the designated application and data supplied from the server 220. The storage unit 125 may also store at least a portion of the data that the storage unit 120 can store.

[0173] [Processing Unit 130 and Processing Unit 135] The processing unit 135 has a function of performing calculations and the like using data supplied from the communication unit 161b, the storage unit 125, the input unit 115, etc. The processing unit 135 may have a function of executing at least a part of the processing that can be performed by the processing unit 130.

[0174] The processing unit 130 and the processing unit 135 can each include one or both of a transistor having a metal oxide in a channel formation region (OS transistor) and a transistor having silicon in a channel formation region (Si transistor).

[0175] Note that in this specification and the like, a transistor using an oxide semiconductor or a metal oxide for a channel formation region is referred to as an oxide semiconductor transistor or an OS transistor. The channel formation region of an OS transistor preferably contains metal oxide.

[0176] In this specification and the like, the term "metal oxide" refers to an oxide of a metal in a broad sense. Metal oxides are classified into oxide insulators, oxide conductors (including transparent oxide conductors), oxide semiconductors (also referred to as oxide semiconductors or simply as OSs), and the like. For example, when a metal oxide is used in a semiconductor layer of a transistor, the metal oxide may be referred to as an oxide semiconductor. In other words, when a metal oxide has at least one of an amplifying function, a rectifying function, and a switching function, the metal oxide can be referred to as a metal oxide semiconductor, or OS for short.

[0177] The metal oxide contained in the channel formation region preferably contains indium (In). When the metal oxide contained in the channel formation region contains indium, the carrier mobility (electron mobility) of the OS transistor is increased. Furthermore, the metal oxide contained in the channel formation region is preferably an oxide semiconductor containing element M. The element M is preferably at least one of aluminum (Al), gallium (Ga), and tin (Sn). Other elements applicable to element M include boron (B), silicon (Si), titanium (Ti), iron (Fe), nickel (Ni), germanium (Ge), yttrium (Y), zirconium (Zr), molybdenum (Mo), lanthanum (La), cerium (Ce), neodymium (Nd), hafnium (Hf), tantalum (Ta), and tungsten (W). However, a combination of the above elements may be used as element M. The element M is, for example, an element having a high binding energy with oxygen. For example, it is an element whose bond energy with oxygen is higher than that of indium. Furthermore, the metal oxide contained in the channel formation region is preferably a metal oxide containing zinc (Zn). Metal oxides containing zinc may be more likely to crystallize.

[0178] The metal oxide contained in the channel formation region is not limited to a metal oxide containing indium. The semiconductor layer may be, for example, a metal oxide containing zinc but not indium, such as zinc tin oxide or gallium tin oxide, a metal oxide containing gallium, or a metal oxide containing tin.

[0179] The processing unit 130 preferably includes an OS transistor. Because the off-state current of an OS transistor is extremely small, using the OS transistor as a switch for retaining charge (data) flowing into a capacitor functioning as a memory element can ensure long-term data retention. By utilizing this characteristic in at least one of the register and cache memory of the processing unit 130, the processing unit 130 can be operated only when necessary, and can be turned off at other times by saving information from the previous processing in the corresponding memory element. In other words, normally-off computing becomes possible, enabling the information retrieval system to consume less power.

[0180] [Display section 145] The display unit 145 has a function of displaying the output result. Examples of the display unit 145 include a liquid crystal display device and a light-emitting display device. Examples of light-emitting elements that can be used in a light-emitting display device include an LED (Light Emitting Diode), an OLED (Organic LED), a QLED (Quantum-dot LED), and a semiconductor laser. The display unit 145 can also be a display device using a shutter-type or optical interference-type MEMS (Micro Electro Mechanical Systems) element, or a display device using a display element that applies a microcapsule type, an electrophoresis type, an electrowetting type, or an electronic liquid powder (registered trademark) type.

[0181] FIG. 7 shows an image diagram of the information retrieval system according to this embodiment.

[0182] 7 includes a server 5100 and terminals (which can also be considered electronic devices). Communication between the server 5100 and each terminal can be performed via an internet line 5110.

[0183] The server 5100 can perform calculations using data input from a terminal via an internet line 5110. The server 5100 can transmit the results of the calculations to the terminal via the internet line 5110. This can reduce the calculation load on the terminal.

[0184] 7 shows an information terminal 5300, an information terminal 5400, and an information terminal 5500 as terminals. The information terminal 5300 is an example of a portable information terminal such as a smartphone. The information terminal 5400 is an example of a tablet terminal. The information terminal 5400 can also be used as a notebook information terminal by connecting it to a housing 5450 having a keyboard. The information terminal 5500 is an example of a desktop information terminal.

[0185] With such a configuration, a user can access the server 5100 from an information terminal 5300, an information terminal 5400, an information terminal 5500, or the like. The user can then receive a service provided by an administrator of the server 5100 through communication via an Internet line 5110. An example of such a service is a service that uses an information search method according to one embodiment of the present invention. In such a service, the server 5100 may use artificial intelligence.

[0186] This embodiment mode can be combined with other embodiment modes as appropriate. [Explanation of symbols]

[0187] 110: Reception unit, 115: Input unit, 120: Memory unit, 125: Memory unit, 130: Processing unit, 135: Processing unit, 140: Output unit, 145: Display unit, 150: Transmission path, 161a: Communication unit, 161b: Communication unit, 162: Transmission path, 164: Transmission path, 200: Information retrieval system, 210: Information retrieval system, 220: Server, 230: Terminal, 5100: Server, 5110: Internet line, 5300: Information terminal, 5400: Information terminal, 5450: Housing, 5500: Information terminal

Claims

1. A reception department that accepts designated applications; A processing unit that performs processing using a database; and an output unit that outputs information based on the processing result of the processing unit; The database includes at least data on specifications, drawings, and value information for a plurality of applications; The drawings include supporting drawings corresponding to the claims; the processing unit calculates a first similarity between the specification of the designated application and each of the specifications of the plurality of applications; the processing unit extracts a plurality of first similar applications from the plurality of applications based on the first similarity; The processing unit calculates a second similarity between the supporting drawing and each of at least one drawing included in the designated application for at least one of the first similar applications; The processing unit extracts, for at least one of the plurality of first similar applications, at least one similar drawing to the supporting drawing from among drawings included in the designated application based on the second similarity; An information search system in which the output unit outputs the value information, the supporting drawings, and the similar drawings for at least one of the plurality of first similar applications.

2. In claim 1, The output unit outputs the second similarity between the supporting drawing and the similar drawing for at least one of the plurality of first similar applications.

3. A reception department that accepts designated applications; A processing unit that performs processing using a database; and an output unit that outputs information based on the processing result of the processing unit; The database includes at least data on specifications, drawings, and value information for a plurality of applications; The drawings include supporting drawings corresponding to the claims; the processing unit calculates a first similarity between the specification of the designated application and each of the specifications of the plurality of applications; the processing unit extracts a plurality of first similar applications from the plurality of applications based on the first similarity; the processing unit calculates a second similarity between the supporting drawings of each of the plurality of first similar applications and at least one drawing of the designated application; the processing unit extracts at least one second similar application by narrowing down and / or sorting the plurality of first similar applications based on the second similarity; The processing unit extracts, for the second similar application, at least one drawing similar to the supporting drawing from among the drawings of the designated application based on the second similarity; An information search system in which the output unit outputs the value information, the supporting drawings, and the similar drawings for the second similar application.

4. In claim 3, The output unit outputs the second similarity between the supporting drawings and the similar drawings for the second similar application.

5. In any one of claims 1 to 4, The value information includes information on related products.

6. In any one of claims 1 to 5, An information retrieval system having a storage unit that stores the processing results.

7. In any one of claims 1 to 6, The designated application is an application pending at the Patent Office, an information retrieval system.

Images