RELATIVITY ODA LLC

Systems and methods for opening documents and incrementally loading document fragments are provided. Upon generating a user interface associated with the document, a client device may generate a document fragment model of a portion of the document for display via the user interface. As the user navigates through the document, document fragment models of additional portions of the document are predictively generated for low-latency display via the user interface.

A system may obtain background documents and a case context extraction prompt and generate case context data by analyzing the background documents via a case context machine learning model. The case context prompt is input into the case context machine learning model with the background documents to cause the case context machine learning model to output the case context data and controls how the case context machine learning model analyzes the background documents to identify key concepts therein. The case context data includes the identified key concepts. The system may generate search queries based on the key concepts, query, via a document search engine, a corpus of documents using the search queries to produce sets of ranked documents for the search queries, compile a seed set of documents from the sets of ranked documents, and provide the seed set of documents to a document review application executing within a workspace.

A computer system may obtain a fact extraction prompt. The fact extraction prompt is configured to control how a fact generating machine learning model extracts or summarizes content of reference documents included in a corpus of documents. The computer system may input, into the fact generating machine learning model, the fact extraction prompt and one or more reference documents from the corpus of documents to identify one or more facts included in the one or more reference documents, populate respective data fields of one or more fact objects based upon the one or more facts identified by the fact generating machine learning model and generate one or more fact summaries for the matter based on the one or more fact objects. The one or more fact summaries include structured presentations of at least some of the one or more fact objects according to contents of the data fields.

Techniques for dynamically allocating RAM among a plurality of SQL server instances are provided. A method includes analyzing, for a first SQL server instance of the plurality of SQL server instances, one or more first instance performance metrics; and responsive to determining, based upon the analysis of the one or more first instance performance metrics, that the first SQL server instance requires additional RAM: determine, based upon the analysis of the one or more first instance performance metrics, a first amount of RAM required by the first SQL server instance, and responsive to determining that the first amount of RAM is available in a memory pool, allocate the first amount of RAM for the first SQL server instance from the memory pool.

Systems, methods, and computer readable media for intelligent generation of a privilege log are provided. These techniques may include accessing a corpus of documents and applying an unsupervised machine learning model thereto to identify a plurality of topics. Using the identified topics, the techniques include associating a plurality of categories with the identified topics and executing a classifier training model to train classifiers corresponding to the categories. These classifiers are then applied to the corpus of documents to label the documents. Subsequently, the techniques automatically generate a privilege log based upon the labels applied to the documents by the classifiers.

The following relates generally to: (i) converting conversation logs to composite message files; (ii) ingesting the composite message files into a review workspace; and/or (iii) classify component messages of a composite message file using generative AI. In some embodiments, one or more processors: obtain a conversation log indicative of a series of user interactions with a generative AI platform; process the conversation log to convert the conversation log into a composite message file, the composite message file including component messages representative of the series of user interactions; associate the composite message file with conversation metadata derived from the conversation log, wherein the conversation metadata includes one or more of conversation entities or contextual embeddings generated by the generative AI platform; associate the component messages with respective message metadata derived from the component message file; ingest the composite message file into the review workspace.

Techniques for birth time-based first in, first out (FIFO) cache reaping are provided. A method includes obtaining an object from a long-term storage (LTS) system; storing the object in a local cache such that the object is associated with a birth time for the object at which the storage at the local cache occurred; calculating a local cache storage time for the object based on the birth time for the object at which the storage at the local cache occurred; and flagging the object for deletion from the local cache responsive to the local cache storage time exceeding a maximum cache storage threshold.

A non-transitory computer readable medium containing program instructions that when executed, cause a computer to: generate a graphical user interface; process object model(s) to generate document model(s); and process the document model(s) to generate rendered document(s). A computing system comprising one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to: generate a graphical user interface; process object model(s) to generate document model(s); and process the document model(s) to generate rendered document(s). A computer-implemented method for improving rendering of multiple documents via one or more document models, the method comprising: generating a graphical user interface; processing object model(s) to generate document model(s); and processing the document model(s) to generate rendered document(s).

Systems and methods for previewing documents associated with a headless object are provided. A client device may generate a primary user interface having a first viewport with a first object focus. In response to a first event, the first object focus may be set to a document model corresponding to the object. The document model may be loaded into a data memory of the client device, and the first object focus may be set to display a rendering of the document model. In response to a second event, a secondary interface of the client device may display the rendering of the document model that was loaded into the data memory.

A method for identifying and ranking potentially privileged documents using a machine learning topic model may include receiving a set of documents. The method may also include, for each of two or more documents in the set of documents, extracting a set of spans from the document, generating, using a machine learning topic model, a set of topics and a subset of legal topics for the set of spans, generating a vector of probabilities for each span with a probability being assigned to each topic in the set of topics for the span, assigning a score to one or more spans in the set of spans by summing the probabilities in the vector that are assigned to a topic in the subset of legal topics, and assigning a score to the document. The method may further include ranking the two or more documents by their assigned scores.