49results about "Patent retrieval" patented technology

The invention relates to the technical field of electrical digital data processing, and discloses a system conflict point intelligent review system based on a knowledge graph and a large language model, which comprises the following steps: constructing a dual-mode storage space containing an unstructured index and a structured logic graph, analyzing target text extraction features and triggering graph-based generation logic; converting the topological structure of the associated sub-atlas into a natural language instruction sequence to construct a forced logic constraint template, filling the template with a text, and inputting a pre-training language model to generate a verification result; according to the method, the discrete atlas topology is mapped into the linear logic constraint, random divergence of the generative model is restrained on the calculation principle, and precise decoupling and dynamic evolution of unstructured semantics and structured logic are achieved.

A patent drawing code recognition method according to one embodiment of the present invention may include the steps of: learning a plurality of patent drawing samples to construct a drawing code position recognition model and a drawing code recognition model; inputting a patent drawing to be recognized as a drawing code; recognizing the position of the drawing code included in the patent drawing using the drawing code position recognition model; cutting out the drawing code at the recognized position from the patent drawing as an image fragment; and recognizing the drawing code included in the image fragment using the drawing code recognition model.

The application discloses an intelligent matching method and system for an intelligent supply chain platform, and the method comprises the following steps: receiving user demand data and performing multi-modal semantic analysis to generate a semantic network comprising a technical field label, a technical problem vector and a technical means correlation graph; generating a first matching list and a second matching list through collaborative operation of a knowledge graph matching model and a natural language processing model; performing adaptive cross-validation and generating a candidate set; uniformly sorting the candidate set according to a sorting rule and outputting a matching result. Through the semantic network of the technical field label, the problem vector and the technical correlation graph, the limitation of traditional keyword matching is broken through, and multi-dimensional accurate mapping of demand and supply is realized; the double-model cooperation of the knowledge graph model and the natural language processing model solves the problem of semantic deviation of a traditional single model; and the adaptive cross-validation mechanism dynamically switches a fusion strategy through a deviation rate, thereby effectively improving the robustness in a complex scene.

The invention provides a patent document database construction method and device based on technical description. The method comprises the following steps: identifying a main body tag and a description tag of each patent document based on a named entity identification model; carrying out punctuation mark-based feature statement division on the technical description part, and combining all main body tags and / or all description tags belonging to the same feature statement to obtain a technical description combination; and associating the patent number of the patent file with all the technical description combinations to form a patent file database based on the technical description. The patent document is subjected to entity recognition, the feature statements are used as the combination range of the main tags and the description tags, and the technical description of the patent document is combined by using more simplified main information, so that complete coverage of the feature information is realized; and the problem that the retrieval precision is influenced by redundant descriptions or interference words in traditional independent keywords or key sentences is avoided.

A target IP search method for a target item according to one embodiment is performed by a computer device. The target IP search method for the target item includes the steps of: obtaining a designating query for the target item; and, based on the query, searching for a plurality of target IPs used in at least one of the research, development and production of the target item. Here, the plurality of target IPs include IP relating to each of at least two components of the components of the target item and / or IP relating to the combined technology of the at least two components used for the performance, operation, production and use of the target item.

An information processing apparatus includes an analysis section that analyzes text data representing a claim included in patent literature data to determine a constituent element of an invention for each claim included in the claim, and a display control section that divides text representing each claim of the claim into each of the constituent elements and displays on a display device.

The present disclosure relates to a document comparison system (100) for comparing a first document (D1) with a second document (D2). The first document (D1) includes at least a first section having at least one first section entity (CEn), and the second document (D2) includes at least one second document entity (CEn). The document comparison system includes a processor (110) and a memory device (120). The processor is configured to identify the at least one first section entity (CEn ) in the first section of the first document (D1). The processor conducts a search of the second document (D2) to identify the presence or absence of one or more second document entity (CEn) corresponding to or equivalent to each first section entity (CEn) identified in the first section. The present disclosure also relates to a dictionary generating system; a document comparison method; a dictionary populating method; and non-transitory computer-readable medium.

A novel data processing system that is highly convenient, useful, or reliable is provided. The data processing system is composed of three components. A component 1 receives identification data, transmits the identification data to a component 3, and provides an annotated document. A component 2 extracts a special technical feature and generates the annotated document with the use of a large language model. The component 3 receives and shares the identification data and the special technical feature, and creates and shares a table. The component 3 includes two subcomponents. A subcomponent 1 manages a patent application document and an examination record with the use of a database and a management system. A subcomponent 2 creates a prompt to extract the special technical feature and generate the annotated document.

The present invention, a machine for inventing, hereinafter referred to as "Inventor," relates to a holistic computing system and method for evaluating and using existing technical and scientific disclosures in all kinds of documents, including patentable and non-patentable existing art and prior art known in patentability, to create and provide useful new solutions in the form of methods and devices, including but not limited to patentable subject matter, and for carrying out solutions / inventions.

Disclosed are a method for constructing a database, a method for labeling an association degree of biological sequences, a method for retrieving a document, and a computer device. In the solution of this application, a biological sequence and attribute information are extracted from a target document, and an entry in a database is constructed based on the extracted biological sequence and the attribute information. When a user conducts retrieval based on the database, a server can match an entry for the user by means of the biological sequence and the attribute information in the entry or a combination of the two. Therefore, when applied to a retrieval platform, the database of this application can provide the user with various types of retrieval support, such as biological sequence retrieval, biological sequence attribute retrieval, and comprehensive biological sequence and biological sequence attribute retrieval, and the like.

The invention belongs to the technical field of data processing. The embodiment of the invention provides an interface control method based on data analysis and terminal equipment. According to the interface control method based on data analysis, the first retrieval operation sequence formed based on the first retrieval process of the user can be matched with the user template, then the user is recognized, and a corresponding interface display mode is provided for the user. Under the condition that the first retrieval operation sequence is not matched with the user template, a second sequence label value is calculated in combination with the second retrieval operation sequence, and then the user template is matched based on the second sequence label value. And when the second sequence tag value is matched with the user template, providing a corresponding personalized customized retrieval interface layout for the user.

Proposed is a method for searching target intellectual properties (IPs) for a target item performed by a computer device. The method may include acquiring a query designating the target item; and on the basis of the query. The method may also include searching a plurality of target IPs for a use in at least one selected from the group consisting of research on or the development and production of the target item. Here, the plurality of target IPs may include IPs for at least two elements among elements of the target item and / or IPs for a technology combining the at least two elements for a use in the performance, operation, production, and utilization of the target item.

A system and computer implemented method of patent mapping are provided. The method comprises maintaining a database of patent portfolios and a database of patents, each patent stored in the database of patents associated with one or more patent portfolios stored in the database of patent portfolios; maintaining a database of ontologies, the ontologies including one or more patent concepts in defined groups; receiving a search query associated with a first patent portfolio; searching the first portfolio as a function of the search query; generating search results, the search results including one or more patent claims associated with the search query; and mapping the one or more patent claims to a patent concept in a defined group.

The invention provides a semantic retrieval method and device based on a patent document database, and the method comprises the steps: carrying out the preset processing of a retrieval text inputted by a user, so as to obtain a preset tag of the retrieval text; each preset label is correspondingly converted into a label word vector, each label word vector is used as a target word vector in sequence, m patent numbers with the highest similarity with the target word vector are determined in the patent file database, and scores of the patent numbers are determined according to the similarity between the patent numbers and the target word vector; constructing a score dictionary of each patent number, and determining a total score of each patent number; and feeding the k patent numbers with the highest total score back to the user as a retrieval result of the retrieval text. According to the patent document database retrieval method and device, the retrieval text is subjected to structural splitting, and in the retrieval process based on the patent document database, the retrieval result most meeting the user requirement is obtained by combining the score conditions of the retrieval result under different preset tags through finer-grained and more accurate retrieval information.

The invention relates to a method and a computer-implemented method for splitting text accurately into semantically correctly separated parts in an infrastructure or hardware for artificial intelligence, the splitting of the text being performed by a trained large language model on one or more graphics processors or graphics processor servers understanding natural language understanding and the processing of the natural language by stored rules being used for improving the splitting of the individual text parts and the individual text parts being transmitted in a machine-readable format to a management program for storing and / or displaying the split text parts and / or the relationship to the assigned text source. Here, the steps of high computing power are optimally distributed between different hardware components or servers in order to be able to guarantee fast processing.

Various embodiments of the present disclosure include systems and methods for analyzing patents and prior art in a patent management system. In an example embodiment, a computer-implemented method of determining a potential point of novelty for an identified patent comprises retrieving at least one independent claim of the patent in the claim form as issued; retrieving at least one independent claim of the patent in the claim form as published; and automatically comparing the issued claim to the published claim by identifying unique keywords present in the issued claim but not present in the published claim and flagging the unique keywords to a user.

The present disclosure relates to a document comparison system (100) for comparing a first document (D1) with a second document (D2). The first document (D1) includes at least a first section having at least one first section entity (CEn), and the second document (D2) includes at least one second document entity (CEn). The document comparison system includes a processor (110) and a memory device (120). The processor is configured to identify the at least one first section entity (CEn ) in the first section of the first document (D1). The processor conducts a search of the second document (D2) to identify the presence or absence of one or more second document entity (CEn) corresponding to or equivalent to each first section entity (CEn) identified in the first section. The present disclosure also relates to a dictionary generating system; a document comparison method; a dictionary populating method; and non-transitory computer-readable medium.

The invention discloses an intellectual property database searchable encryption method supporting dynamic updating, and aims to solve the problems of high index reconstruction overhead and low updating efficiency in a data addition scene in an existing scheme. The core of the method is to construct a layered and merged dynamic index structure: for newly added data, a client generates an independent lightweight incremental index fragment (L0) and uploads the fragment, so that low-delay updating is realized; and when the incremental index fragments are accumulated to a threshold value, triggering a background hierarchical merging mechanism to merge a plurality of low-level index fragments into high-level index fragments so as to maintain the retrieval efficiency. By storing the index entries in the confusion bucket located by trap door hash, the association between the index entries is cut off, and the access mode privacy is enhanced. In the searching stage, the server side performs intelligent filtering through a bloom filter, the minimum target ciphertext set is determined, and network transmission and client side decryption expenses are greatly reduced. According to the method, the data confidentiality and the retrieval privacy are ensured, and meanwhile, the system performance in a dynamic environment is remarkably improved.

The application relates to the technical field of electric digital data processing, and discloses a system for intelligently examining system conflict points based on a knowledge graph and a large language model, which comprises the following steps: constructing a dual-mode storage space containing an unstructured index and a structured logical graph, analyzing a target text to extract features and triggering generation logic based on the graph; converting the topological structure of an associated subgraph into a natural language instruction sequence to construct a mandatory logical constraint template, filling the template with the text and inputting the pre-trained language model to generate a verification result; and writing the result back to the graph. According to the application, the discrete graph topological mapping is converted into linear logical constraints, the random divergence of the generative model is inhibited in the calculation principle, and the precise decoupling and dynamic evolution of unstructured semantics and structured logic are realized.

A text recognition method, a text recognition apparatus, a computer-readable storage medium, and an electronic device are provided. In the text recognition method, adjacent character strings in a plurality of character strings partially overlap, so that the plurality of character strings may reflect the relationship between the contexts of a text to be recognized, then word vector conversion is performed on the plurality of character strings to obtain a plurality of word vectors, word vector recognition results respectively corresponding to the plurality of word vectors are generated on the basis of the plurality of word vectors to determine whether a text corresponding to the word vectors is an effect text or a non-effect text, and the plurality of word vector recognition results are synthesized to determine a text recognition result of the text to be recognized.

A data processing system including three components is provided. A first component receives a scope of claims, a notice of reasons for refusal, an argument draft, and a forecast. A second component receives a prompt, receives and transmits the forecast to a third component, and performs processing using a large language model. The third component receives the scope of claims, the notice of reasons for refusal, and the argument draft, and shares them. The third component including two subcomponents receives and transmits the forecast to the first component. A first subcomponent performs processing using a database including an examination record and a search engine. The search engine extracts an examination record list in accordance with a query. The system has a function of creating a forecast of an examination result and an argument draft in view of the scope of claims, an examiner, a technical field, and the like.

The present disclosure relates to a document comparison system (100) for comparing a first document (D1) with a second document (D2). The first document (D1) includes at least a first section having at least one first section entity (CEn), and the second document (D2) includes at least one second document entity (CEn). The document comparison system includes a processor (110) and a memory device (120). The processor is configured to identify the at least one first section entity (CEn) in the first section of the first document (D1). The processor conducts a search of the second document (D2) to identify the presence or absence of one or more second document entity (CEn) corresponding to or equivalent to each first section entity (CEn) identified in the first section. The present disclosure also relates to a dictionary generating system; a document comparison method; a dictionary populating method; and non-transitory computer-readable medium.

A method for searching target IPs for a target item according to one embodiment is performed by a computer device. The method for searching target IPs for a target item includes the steps of: acquiring a query designating the target item; and on the basis of the query, searching a plurality of target IPs for a use in at least one selected from the group consisting of research on or the development and production of the target item. Here, the plurality of target IPs include IPs for at least two elements among elements of the target item and / or IPs for a technology combining the at least two elements for a use in the performance, operation, production, and utilization of the target item.

The invention discloses a core literature identification method and device and electronic equipment, and relates to the technical field of big data and data mining, and the method comprises the steps: obtaining a literature quotation network in response to a received core literature identification instruction; different nodes in the literature quotation network are combined; removing each node group from the literature quotation network, and determining first network degradation quantization information of degradation of the literature quotation network caused by removal of each node group; respectively removing each node in each node group from the literature quotation network, and determining second network degradation quantization information of degradation generated by the literature quotation network due to removal of the corresponding node; determining the importance of the node based on the first network degradation quantization information corresponding to the node group to which the node belongs and the second network degradation quantization information corresponding to the node; and identifying the core literature based on the importance degree of each node. According to the method, a node dynamic failure simulation mechanism is introduced, so that the accuracy of core literature identification is effectively improved.

To provide a novel information processing system that is superior in convenience, usefulness, or reliability. [Solution] This information processing system consists of three components. Component 1 receives identification information, transmits it to component 3, and provides annotated documents. Component 2 extracts special technical features using a large-scale language model and generates annotated documents. Component 3 receives and shares identification information and special technical features, and creates and shares tables. Component 3 has two subcomponents. Subcomponent 1 manages patent application documents and examination records using a database and management system. Subcomponent 2 creates instructional statements and extracts special technical features and generates annotated documents.

The invention relates to a cross-modal patent image retrieval method and device, equipment and a storage medium. The method comprises the steps of obtaining a query instruction and updated patent data; obtaining patent fusion feature data according to the updated patent data; obtaining integrated database fusion feature data according to the patent fusion feature data and fusion feature data pre-stored in a preset database; wherein the preset database fusion feature data is obtained by fusing image features and character features in patent data; according to the query instruction, the type of the query instruction is judged, and query feature data is obtained through calculation; and according to the query feature data and the integrated database fusion feature data, performing Hamming calculation to obtain a query result.

To provide an information processing system and an information processing method excellent in convenience, usefulness or reliability for predicting an examination result and preparing an opinion draft.SOLUTION: In the system composed of three components, a component 120 receives a range PC of a patent request, a notice NRFR of reasons for rejection, a draft DArg1 and a predicted Fcst. The component 130 receives the instruction statement Pt1, transmits the prediction to the component 110, and performs processing using the large language model LLM. The component 110 receives and shares the range of the patent request, the notification of reasons for rejection, and the draft of the opinion, receives the prediction, and transmits it to the component 120. Component 120 comprises two subcomponents. The first sub-component performs processing using a database and a search engine. The database includes audit records, and the search engine extracts a list of audit records in response to the query.SELECTED DRAWING: Figure 1

Systems, computer program products, and methods are described herein for automatically correlating data of unstructured datasets from disparate disclosure sources. The present disclosure is configured to identify application metadata associated with at least one application; access at least one database comprising a plurality of unstructured datasets; input the application metadata and the plurality of unstructured datasets to a graph synthesizer; generate, by the graph synthesizer, a correlation score between the application metadata and the plurality of unstructured datasets; and determine, based on the correlation score, the at least one application is highly correlated to at least one unstructured dataset of the plurality of unstructured datasets or is low correlated to the plurality of unstructured datasets.

An advanced system and method for conducting automated patent infringement analysis and prior art review are disclosed. The system utilizes artificial intelligence (AI) technologies, including machine learning, natural language processing, and computer vision, to evaluate target products against existing patents and prior art references. The invention features a data ingestion module capable of processing patent documents, including design patent drawings and utility claim texts, and a machine learning model trained to identify patterns indicative of patent infringement. Additionally, the system includes a novelty detection module that benchmarks product attributes against prior art to assess innovation. Users interact with the system through a secure interface to input product data and receive comprehensive analysis reports, which detail infringement risks, similarity scores, and novelty assessments. By automating traditionally manual processes, the invention reduces the time and cost of intellectual property analysis while increasing accuracy and scalability.

The present invention, a machine to invent, in the following "Inventer", relates to a holistic computing system and methods for evaluating and using existing technical and scientific disclosures in documents of all kinds, including patentable and non-patentable existing art, also prior art as known in patenting, for making and providing useful new solutions in form of methods and devices - including but not limited to patentable subject matter - and inventions, and for carrying out the solutions / inventions.