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 provides a method and system for training a machine learning-based patent search or novelty evaluation system. The method comprises providing a plurality of patent documents each having a computer-identifiable claim block and specification block, the specification block including at least part of the description of the patent document. The method also comprises providing a machine learning model and training the machine learning model using a training data set comprising data from said patent documents for forming a trained machine learning model. According to the invention, the training comprises using pairs of claim blocks and specification blocks originating from the same patent document as training cases of said training data set.

An intellectual property (IP) recommending method and an IP recommending system are provided. In the method, a plurality of IP portfolios respectively designated for a plurality of product designs are retrieved and usage data of a plurality of IPs included in each of the plurality of IP portfolios are extracted. A machine learning (ML) model is trained by using a portion of the retrieved IP portfolios and the extracted usage data. In response to receiving at least one criterion for a desired product design from a user, a plurality of IPs adapted for the desired product design are predicted based on the ML model and recommended for the user.

Systems may evaluate a claim or patent with respect to a related set of claims or patent documents. The systems may perform linguistic analyses of claims included in the patent and the related set of patent documents. Based on the linguistic analyses, the systems may identify claim limitations, and/or claim elements. The systems may generate a claim profile for each claim being evaluated. The claim profile may include ratings or scores for various metrics related to the claims being evaluated. The systems may also generate a peer group profile that provides an overall measure of metrics for claims included in a peer group of patent documents.

Systems may perform analyses of claims included in a patent document. The systems may generate one or more search strings from the patent document and provide the one or more search strings to a third-party searching authority. The third-party searching authority may return a collection of documents responsive to the one or more search strings. In particular situations, the systems may re-rank the documents of the collection to provide a patent centric ranking. The systems may also analyze the documents of the collection with respect to the elements of the claims to generate various types of patent infringement and/or invalidity reports.

The present invention is a patent search and analytics software tool (Zuse) that finds prior art for each claim limitation/element. The software automatically breaks up every claim into individual claim limitations. For example, our software can automatically break up a claim into about five (5) separate, different claim limitations/elements. Then, it can find the best prior art for each of the five (5) separate, different claim limitations/elements. This is very helpful when you cannot find a prior art reference for only part of a claim. Also, the software finds the best prior art for the entire claims. Our software also includes non-patent literature (NPL) searching. ZUSE identifies relevant prior art by taking into account the limitations of the claim under consideration (query claim of query patent), the text of the art, the link structure of the citation network, and the patent classification. The present invention constructs a network that consists of two types of nodes: (i) the art (patents and non-patent literature) and the (ii) classes of the patent classification. Each art node is linked to all the art nodes that it cites and is linked to all the classification nodes that it belongs to.

Qscore is the most advanced tool available for ranking the potential commercial value of a patent or a portfolio of patents. Other ranking methods typically rely heavily on a patent's reference graph (citations to/from other patents). Qscore is far more sophisticated: using data mining tokenization techniques, Qscore takes into account multiple factors correlated with patent value. This document generally describes the method used to assign a quality score to each patent, which is used to bias the ranking of the results returned from the keyword-based searching in the analytics embodiment of the present invention. This quality score, denoted by Qscore, is designed to identify the patents that are not only relevant to the user's query but also possess some additional, query independent, quality characteristics. Consequently, Qscore can be considered as an information filtering aid—designed to identify the “good” information from a “sea” of information.

A method for information retrieval in an encrypted corpus stored on a server, from a digital request calculated on a customer device, containing a sequence of terms, includes the following steps: encryption of the request on a customer computer device and transmission of same to a database management server; and homomorphic calculation, on the server, of the encrypted response to the encrypted request recorded on the server. The method further comprises an additional requesting step performed on the customer device; and presentation of the result in an ordered form of the documents, in application of the processing of the previous step. The present disclosure also relates to a method for preparing a requestable base and to a method for information retrieval in an encrypted corpus.

Embodiments of the present disclosure provides a method and a system for labeling and retrieving the protection scope of claims and for labeling information of a gene sequence, wherein the method includes: recognizing a gene sequence from the claims of the current patent application; extracting descriptive texts of the gene sequence from the claims based on a preset keyword; determining similarity information of the gene sequence based on the extracted descriptive texts, and labeling the scope of the claims of the gene sequence based on the similarity information. In the technical solutions provide in the embodiments of the present disclosure, a sequence retrieval can be performed in a patent library, and the accuracy of the gene sequence retrieval can be improved.

Methods and systems for receiving docketing data are disclosed. The methods and systems perform operations comprising: obtaining, by a first party, a patent file wrapper from a publicly accessible database of patent records, the patent file wrapper including a plurality of patent documents; receiving, from the first party, user input that tags a patent document of the plurality of patent documents in the patent file wrapper, wherein the patent document that is tagged is associated with a patent activity that occurred within a threshold period of time; and transmitting, to a second party by the first party, a communication that includes the tagged patent document.