Disclosed is a system for determining a temporal citation count for a document associated with an author, wherein the system comprises a database arrangement storing metadata related to the document, and a server arrangement communicably coupled to the database arrangement, wherein the server arrangement receives the metadata associated and employs dimensionality reduction techniques on the metadata to obtain a state data; designates the author of the document as a source node in the entity network comprising information related to a plurality of authors and citation history between the plurality of authors, wherein the remaining authors in the plurality of authors are designated as destination nodes determines an edge weight for edge between any of the source node and the destination nodes based on the state data; and aggregates the edge weight for the edges to obtain the temporal citation count.

Systems, methods, and computer program products may be configured to generate a set of related document objects for a predictive entity and/or to generate an optimal document sequence for a set of related document objects. In one embodiment, for example, a set of related document objects for a predictive entity is generated by processing entity metadata features associated with the predictive entity using an entity-document correlation machine learning model, and an optimal document sequence is generated for the set of related document objects by processing the set of related document objects using a document sequence optimization machine learning model.

A computing system may identify a first reference citation within a technical document, wherein the first reference citation is identified based at least in part a length of a first block of text that is included in the first reference citation and an inclusion of at least one numeric character in the first block of text. The computing system may determine, based on querying at least one datastore, whether the first reference citation matches a matching stored reference citation. The computing system may determine, based at least in part on whether the first reference citation matches the matching stored reference citation, an error review prioritization status for the first reference citation. The error review prioritization status may also be determined based, in part, on a specified revision number for the first reference citation. The computing system may provide visual feedback indicating the error review prioritization status.

Systems and methods of the present technology generally provide computer implemented assistance for data summary, including organizing and generating a summary of data selected form source documents. In accordance with the present technology, a user identifies a subset of information from one or more source documents, assigns an identifier to the user-identified information, and may add custom information. The user can repeat the identification and assignment steps using multiple source documents, as many times as desired. The system then analyzes and prioritizes the user-identified information and any custom information, and generates a formatted summary.

The present invention relates to a reference organizing and indexing system for research papers. The system can be used by students, universities, researchers, and companies for saving time to correctly include citations and references in their research papers. The system offers a software application that is configured to identify the source and metadata including author, page numbers, and dates of references to be used as citations. The system eliminates the need of a researcher to manually search and collect the citation information. A plurality of citations is indexed which can then be retrieved in a proper format for inclusion in research papers. The citations can be added as footnotes, bibliographies, and/or in-text citations.

Systems and methods are configured to generate a set of related document objects for a predictive entity and/or to generate an optimal document sequence for a set of related document objects. In one embodiment, a set of related document objects for a predictive entity is generated by processing entity metadata features associated with the predictive entity using an entity-document correlation machine learning model, and an optimal document sequence is generated for the set of related document objects by processing the set of related document objects using a document sequence optimization machine learning model.

An information processing apparatus including processing circuitry configured to acquire a base group that is a set of documents concerning a prescribed intellectual property right based on a prescribed search query and evaluate, for each document included in the base group, a value that is calculated based on a parameter concerning the document and a first weight linked to patenting of the document, as a first index indicating a relative strength of right of the document in the base group.

Systems and methods are provided for analyzing documents. In one implementation, a computer implemented method is provided for analyzing a patent application and providing a visual representation. According to the method, a selection is received from a user to view claims of the patent application in a claim tree hierarchy and a computer displays the claims in the claim tree hierarchy on a display. The claim tree hierarchy visually depicts relationships between the claims. The method identifies one or more words of at least one of the claims that constitutes an element and displays, in the claim tree hierarchy, the words constituting the element in association with the claim.

Methods, systems, and techniques for facilitating searching for patent related literature are provided. Some examples provide a Patent Related Publication Search Engine (“PRPSE”), which enables users and or programs through the use of an application programming interface (“API”) to iteratively find patent related publications such as issued patents and patent application publications. In typical operation, based upon input text, the PRPSE determines predominant keywords found in the text and locates a set of patent related publications most closely related to these determined keywords as search results. In some examples, the PRPSE determines the set of patent related publications most closely related to these determined keywords both by full text searching of a corpus of patent related publications for all of the patent related publications that contain the predominant keywords and by finding all correlated patent related publications through citation analysis.

Methods, systems, and techniques for managing and using search snapshot histories are provided. Some examples provide a Search Snapshot Management Engine (“SSME”), which enables users and or programs through the use of an application programming interface (“API”) to define and manipulate search snapshots. In typical operation, an iteration of a search result is associated with a search snapshot history. A rendering of the search snapshot history may be provided to assist in navigation to other potentially related search iterations and to define new search states for performing searches. In some examples, the SSME may be used to provide search histories to teams for reviewing patent related publications and other types of literature.