73 results about "Snippet" patented technology

A vulnerability detection and repair system utilize a classifier model to detect a software vulnerability in a source code snippet and the tokens in the source code snippet attributable to the vulnerability. A large language model is then given the vulnerable source code snippet, its vulnerability type, the vulnerability tokens, and a few-shot examples to determine whether or not the source code snippet includes the identified vulnerability. The few-shot examples include positive and negative samples of the type of vulnerability to guide the large language model towards the correct output.

A vulnerability detection and repair system utilizes a classifier model to detect software vulnerabilities in source code fragments and lexical elements attributable to the vulnerabilities in the source code fragments. The vulnerable source code fragment, its vulnerability type, vulnerability lexical elements, and few sample examples are then given to a large language model to determine whether the source code fragment includes the identified vulnerability. The few sample examples include positive and negative samples of vulnerability types to direct the large language model towards correct outputs.

An assert statement generator employs a neural transformer model with attention to generate candidate assert statements for a unit test method that tests a focal method. The neural transformer model is pre-trained with source code programs and natural language text and fine-tuned with test-assert triplets. A test-assert triplet includes a source code snippet that includes: (1) a unit test method with an assert placeholder; (2) the focal method; and (3) a corresponding assert statement. In this manner, the neural transformer model is trained to learn the semantics and statistical properties of a natural language, the syntax of a programming language, and the relationships between the code elements of the programming language and the syntax of an assert statement.

Systems and methods are disclosed for automatically extracting relevant information from various source document that include tabular data. The tabular data in various forms can be received as mixed with other dissimilar data. Tabular data can appear in different orientations, document types, and can be fragmented horizontally or vertically. The proposed technique automatically detects table header data in certain regions of the received source document and associates values to the extracted headers. The proposed system is capable of combining different snippets of smaller tables into a single cohesive and monolithic table with headers designated by a set of keywords and all the values in the various columns (and / or rows) included under or along proper headers.

One or more new coding instructions are generated using a language model (LM) prompted to perform one or more genetic operations on one or more seed coding instructions of an initial set of coding instruction-snippet pairs. One or more respective coding snippets are generated to implement the one or more new coding instructions using a LM prompted to generate coding snippets for the one or more new coding instructions. A generational set of coding instruction-snippet pairs comprising the initial set of coding instruction-snippet pairs and a new set of coding instruction-snippet pairs comprising the one or more new coding instructions and the one or more respective coding snippets is created.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating answers to medical questions using neural networks and other components. In one aspect, a method includes: obtaining question data representing a medical question; obtaining a plurality of document snippets from a medical database that stores medical documents; for each document snippet in the plurality of document snippets, determining a relevance score for the document snippet by using a ranking neural network based on the document snippet and the medical question; selecting, based at least in part on the relevance scores, a subset of the plurality of document snippets; generating a prompt that includes (i) the medical question and (ii) the subset of the plurality of document snippets; and generating an answer to the medical question based on processing the prompt using a generative neural network.

A computer-implemented system is disclosed which enhances legal research by utilizing a first user interface (UI) to receive search criteria as text prompts from users, which are then processed by an application program interface (API) across an electronic connection. The system includes an instruction base for expanding the prompts into snippets for a machine learning network, which defines the legal database searches. The process further refines the prompts through a transformation module, breaking down and tagging the text for compatibility with the machine learning network. Coupled with non-transitory computer memory, the system efficiently outputs results in response to the applied search criteria. A second interactive UI displays these results and allows for user interaction to delve into detailed information, optimizing the legal information retrieval process. Also disclosed is a method for processing legal research queries enhanced by a machine learning network.

Embodiments described herein relate to systems and methods for automatically generating content for a generative answer interface of a collaboration platform. The system receives a natural language user input identifying corresponding blocks of text or snippets using a content extraction service. A prompt is generated using the blocks of text and is used to obtain a generative response. The generative response and links to corresponding content are displayed in the generative answer interface and can be inserted into content of the collaboration platform. The systems and methods described use a network architecture that includes a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and / or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

The present invention relates to the technical field of text layout. Disclosed are a text format adjustment method and system based on large language model code generation. The method comprises: constructing an API vector knowledge base on the basis of a development document of target software, the API vector knowledge base comprising vector representations of text format adjustment attributes and knowledge snippets of the text format adjustment attributes; acquiring a user format adjustment requirement; vectorizing the user format adjustment requirement, and by matching a vector representation of the user format adjustment requirement with the vector representations of the text format adjustment attributes, obtaining the knowledge snippet and an input / output example of the corresponding text format adjustment attribute; and embedding the user format adjustment requirement and the knowledge snippet and input / output example of the corresponding text format adjustment attribute into a code generation prompt word template, and generating a text format adjustment result on the basis of a large language model. The present invention can reduce the workload of developing and designing text format templates, and can more flexibly accommodate various format requirements.

A computing system comprising one or more computing devices can access a file comprising documentation that includes a textual description and a source code snippet written to comply with a programming language syntax. The computing system can identify the source code snippet. The computing system can generate an executable based on the source code snippet. The computing system can initiate a test process that accesses the executable, the test process causing the executable to cause an event. The computing system can determine that the event is a valid event or an invalid event.

Some embodiments find locations of targets which are related to a symbol in a source code snippet, when the snippet is external to a project codebase. Finding a target's location allows user-directed or proactive automatic navigation from the symbol into the codebase, display of data type, signature, and other semantic information of the symbol, proactive automatic creation of an import statement for a definition of the symbol, and other utilizations of the target location in an enhanced editor or enhanced debugger or another tool. In some scenarios, the external snippet is generated by an artificial intelligence agent, using part of the codebase as context. Some embodiments find a target of an external snippet's symbol in another external snippet, allowing a tool utilization that is informed by the project codebase even when both snippets are outside the project codebase.

Example methods for providing natural-language replies are disclosed herein. An example method includes receiving a natural-language input; providing, via the display generation component, a set of candidate snippets based on the natural-language input, wherein each candidate snippet of the set of candidate snippets corresponds to a respective response to the natural-language input; receiving, via the one or more input devices, an input corresponding to a selection of a candidate snippet of the set of candidate snippets; and providing, via the display generation component, a response to the natural-language input corresponding to the selected candidate snippet.

A system generates synthetic documents from source documents. The system receives a source document and generates prompts for generating sections of a synthetic document from the source document. The system receives sections of the synthetic document based on execution of the machine learning based language model. For each of one or more portions of the synthetic document, the system determines a snippet of the source document that provides support for the portion of the synthetic document. The system sends the synthetic document for display via a user interface. The system receives a request via the user interface to inspect a portion of the synthetic document. The system identifies a snippet of the source document corresponding to the portion of the synthetic document and sends the snippet of the source document for display via the user interface.

Technology is disclosed for programmatically generating a summary by a language model of search results based on the corresponding relevance of the search results to an input search query to a search engine. A user inputs a search query into a search engine and the search engine determines and ranks a set of search results based on the relevance of each of the search results. A snippet of information is determined for the most relevant search results to the input search query. The snippets of information are used to generate an input prompt to a language model with an instruction to generate a summary of the snippets of information based on the input search query. The generated summary is provided in response to the user to the search query and / or is cached in order to provide the generated summary in response to similar search queries.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating answers to medical questions using neural networks and other components. In one aspect, a method includes: obtaining question data representing a medical question; obtaining a plurality of document snippets from a medical database that stores medical documents; for each document snippet in the plurality of document snippets, determining a relevance score for the document snippet by using a ranking neural network based on the document snippet and the medical question; selecting, based at least in part on the relevance scores, a subset of the plurality of document snippets; generating a prompt that includes (i) the medical question and (ii) the subset of the plurality of document snippets; and generating an answer to the medical question based on processing the prompt using a generative neural network.

There is provided an offloading data interfacing method between a DBMS storage engine and a computational storage device. In a query offloading method according to an embodiment of the disclosure, a DBMS may generate an offloading code which is a code for offloading a part of query computations, based on a received query, when a query execution request is received from a client, and may deliver the offloading code to a storage in which a DB is established in a CSD. Accordingly, in a DB system using a CSD, a snippet for offloading a part of query computations may be defined, and a DBMS and a storage are interfaced by using the offloading snippet, so that a guideline for execution of a query by interworking between the CSD-based storage and the DBMS is provided.

Technology is disclosed for programmatically generate answers for a user that are responsive to aspects of a conversation. In one implementation, a conversation record is processed to determine a message embedding of a most recent message received. The message embedding is used to determine a semantically similar question embedding of a conversational snippet from a knowledge base. An answer-generation input instruction for a language model is generated based on the most recent message, the conversational snippet, and an answer-format instruction. The language model is directed to produce an answer output, which is presented via a user interface. An answer-augmentation instruction for the language model is generated based on the answer output, similar messages sent by the user based on string similarity with the answer output, and an augmented-answer format instruction. The language model is directed to produce an augmented-answer output, which is presented via the user interface.

Techniques are disclosed for intelligently prompting LLM to reconstruct code. A code snippet is accessed. The code is identified as potentially including a reference to a non-compliance library. A context is generated for the code snippets. Then, an LLM prompt is constructed. The hint is to be fed to the LLM, and the hint instructs the LLM to reconstruct the code snippets into modified code, the modified code invoking the compliance library. And displaying the output of the LLM. The output operates based on the LLM in response to the LLM cue. The output includes a proposed rewritten version of the code snippet.

A system and method is presented that extracts snippets form web pages according to specially designed logic. The extracted snippets might be made relevant to, i.e., indexed by, a location and time / day applicability. Such snippets may be thought of as apps or services that are defined only when a mobile terminal is in a pre-defined geographical area at a certain time and day (e.g., as defined by a calendar of events). Extracted snippets are stored and made searchable. Methods and a system are described to control the display of snippet search results. Snippets may be selected by user or by programmed logic and executed on the mobile terminal or in remote servers without the need to download the app or source code associated with the snippet.

Systems and methods for presenting an interface for additional content suggestions can include obtaining data describing displayed content and determining additional content associated with the displayed content. An interface displaying data associated with the displayed content and the additional content can then be provided. The interface can include a first viewing window for displaying a portion of the displayed content and a second viewing window for displaying a snippet associated with the additional content.

A text-to-speech engine creates audio output that includes synthesized speech and one or more media content item snippets. The input text is obtained and partitioned into text sets. A track having lyrics that match a part of one of the text sets is identified. The location of the track's audio that contains the lyric is extracted based on forced alignment data. The extracted audio is combined with synthesized speech corresponding to the remainder of the input text to form audio output.

Computer implemented systems and methods for annotating and linking electronic documents. In accordance with some embodiments, annotations assigned to source electronic documents are received and snippets are generated from the received annotations. The generated snippets are aggregated into clusters, which are used to generate an electronic document. Links between the snippets and their respective source documents may be generated and embedded in the generated electronic document.

An intelligent question and answering method, comprising: performing retrieval on the basis of a first user query in a current conversational turn, so as to obtain first retrieved knowledge required in the current conversational turn; processing the first retrieved knowledge and the first user query to obtain response text; on the basis of the first retrieved knowledge, the response text, and user feedback to the response text, performing a reflective evaluation on the first retrieved knowledge, so as to obtain a reflective evaluation conclusion, the reflective evaluation conclusion being used for indicating quality of a cited snippet in the first retrieved knowledge, and the cited snippet being a snippet referenced by the response text; when the quality of the cited snippet does not satisfy a requirement, optimizing, on the basis of the cited snippet, second retrieved knowledge required in a next conversational turn, the second retrieved knowledge being obtained by performing retrieval on the basis of a first cited snippet and a second user query in the next conversational turn. The method allows for erroneous knowledge in retrieved knowledge to be corrected in a timely manner, thereby reducing the probability of introducing erroneous knowledge, and improving answer quality of neural network models.

A method of responding to questions about documents by a computing system includes: (a) initially sending queries to a large language model (LLM), each query including a request for any snippets within a corresponding document that provide evidence in response to a question, the LLM returning a respective response to each query; (b) in response to a heuristic based on the responses returned by the LLM indicating a readiness for optimization, training a new model on the queries and respective responses, the new model being more computationally efficient than the LLM; (c) performing a validation operation on additional responses returned by the new model; and (d) in response to the validation operation indicating that the new model has satisfied a condition, sending future queries to the new model instead of the LLM.

A method includes obtaining descriptive information for a first machine learning project, identifying, based on the descriptive information, a plurality of past machine learning projects which are similar to the first machine learning project, retrieving digital documents that describe the bias evaluation pipelines that were used to evaluate the plurality of past machine learning projects, detecting a common bias evaluation pipeline step among at least a subset of the digital documents, extracting, from the subset, a snippet of machine-executable code that corresponds to the common bias evaluation pipeline step, modifying the snippet of machine-executable code with use case data that is specific to the first machine learning project to generate modified machine-executable code, and generating a proposed bias evaluation pipeline for evaluating the first machine learning project, wherein the proposed bias evaluation pipeline includes the modified machine-executable code.

The invention relates to a domain-specific retrieval language model. Various examples, systems, and methods are disclosed that relate to domain-specific document retrieval that combines custom vocabulary integration and embedded model update. A computing system may extract a plurality of segments from a collection of documents and generate a query corresponding to at least one segment. The computing system may identify terms that meet uniqueness criteria, and input these terms into a markup machine to create a vocabulary dataset. The vocabulary datasets, document segments, and queries can be used to update the embedding model to support retrieval and semantic alignment within private documents.

A computer-implemented system is disclosed which enhances legal research by utilizing a first user interface (UI) to receive search criteria as text prompts from users, which are then processed by an application program interface (API) across an electronic connection. The system includes an instruction base for expanding the prompts into snippets for a machine learning network, which defines the legal database searches. The process further refines the prompts through a transformation module, breaking down and tagging the text for compatibility with the machine learning network. Coupled with non-transitory computer memory, the system efficiently outputs results in response to the applied search criteria. A second interactive UI displays these results and allows for user interaction to delve into detailed information, optimizing the legal information retrieval process. Also disclosed is a method for processing legal research queries enhanced by a machine learning network.

Systems and methods for presenting an interface for additional content suggestion can include obtaining data descriptive of the displayed content and determining additional content associated with the displayed content. An interface can then be provided that displays data associated with the displayed content and the additional content. The interface can include a first viewing window for displaying a portion of the displayed content and a second viewing window for displaying a snippet associated with the additional content.

The invention relates to a method for acoustic interaction between a vehicle and a user, wherein the vehicle, in response to an action (1) performed by the user, outputs a sound response (2) via acoustic output means, wherein the sound response (2) is artificially generated from the musical patterns inherent in a piece of music (3), which are identified by an analysis of the piece of music (3) using artificial intelligence. The method according to the invention is characterized in that - the piece of music (3) is analyzed by a processing cascade (4), comprising at least one interacting digital signal processor algorithm and a suitable pre-trained machine learning model, which divides the piece of music (3) into music snippets (5) corresponding to individual temporal sections of the piece of music (3), and assigns metadata (6) to the music snippets (5), describing music-characterizing properties of the respective music snippet (5); - the music snippets (5) are stored in a snippet database (7); - for various actions (1) that can be performed by the user, at least one sound response blueprint (8) is provided, containing a metadata specification; - the sound response blueprints (8) are applied to the music snippets (5) stored in the snippet database (7), whereby for each sound response (2) at least one music scheme is generated from at least one music snippet (5) depending on the metadata specification in order to generate the sound response (2) for the respective action (1); and - a corresponding sound response (2) is emitted when performing a respective action (1).

Embodiments described herein relate to systems and methods for automatically generating content for a generative answer interface of a collaboration platform. The system receives a natural language user input identifying corresponding blocks of text or snippets using a content extraction service. A prompt is generated using the blocks of text and is used to obtain a generative response. The generative response and links to corresponding content are displayed in the generative answer interface and can be inserted into content of the collaboration platform. The systems and methods described use a network architecture that includes a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and / or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.