6258 results about "Programming language" patented technology

Systems and methods for processing input data using a generic large language model (LLM) and a secondary LLM, whereby the secondary LLM is configured to process structured data. An application is provided, including a semantic kernel, a manager module, and a plurality of workers. An input is received via the semantic kernel. The manager module invokes the plurality of workers comprising a first worker and a second worker. The first worker invokes the generic LLM and the second worker invokes the secondary LLM.

Some embodiments determine machine configuration intentions from a natural language description of a target machine configuration. Intentions are refined to remove ambiguity, and mapped to pre-approved configuration functions and tasks. A machine configuration task list which invokes the pre-approved configuration functions and tasks is generated by a stabilized language model, and is executed to configure a target machine. The requested target machine is produced without requiring a user or admin to spend substantial effort and time customizing the machine and confirming its security and policy compliance.

A computer-implemented method for performing natural language-based data integration includes causing execution of a data integration application on a remote device via a network and causing surfacing of a GUI corresponding to the data integration application on a display of the remote device. The method includes receiving, via the GUI, a natural language input representing a data integration task, generating, via an LLM, a set of ordered activities corresponding to the data integration task represented by the natural language input, and selecting, via the LLM, one or more APIs for performing each activity within the set of ordered activities. The method also includes generating a data pipeline based on the set of ordered activities and the API(s) for performing each activity, as well as back-translating the data pipeline to a desired data format for execution by the data integration application.

A method and system for generating a privilege based segmented instruction prompt has been developed. Trusted instructions defining the trusted instructions as having a first privilege level, program instructions as having a second privilege level, and data instructions as having a third privilege level are received. The program instructions to implement tasks associated with the data instructions are received. The data instructions are received. The generated privilege based segmented instruction prompt includes the trusted instructions, the program instructions, and the data instructions. The privilege based segmented instruction prompt enables a generative LLM to determine whether the privilege based segmented instruction prompt is an instruction injection attack based on whether there is a conflict between the trusted instructions, the program instructions, and the data instructions in violation of the first, second, and third privilege levels.

A communications session with a user may be automated using a language model. The language model may be instructed to select a next action to be performed where the next action may include transmitting a responsive communication to the user or performing an API call. The prompt used to query the language model may include one or more of the following: a representation of text of the communications session, a list of available API calls, instructions to select a next action, a representation of API calls performed, or a representation of API call responses received. The language model may be sequentially queried to continue the communications session by transmitting responsive communications or performing API calls. In some implementations, a prompt template may be used to generate the prompt and a prompt template may be selected using text of the communications session.

The invention discloses a report chart automatic generation method based on natural language analysis and data query, which comprises the following steps: acquiring a natural language text, and constructing a slot set and an initial semantic fragment; executing consistency verification and ambiguity identification, and constructing a semantic framework; executing field standardization and mode alignment, generating a data query statement and establishing a traceability chain identifier; querying a target database to obtain an original data set, completing data quality self-correction, and generating a cleaned data set; calling an improved Mamba model to construct a constraint judgment matrix and outputting a target chart subset; generating a chart description grammar and an image annotation template, and executing image rendering, feature point recognition and image sidebar construction; and performing layout optimization and double compilation, and outputting a structured report file. According to the method, the chart generation automation level and the report compiling efficiency are improved, and the accuracy, traceability and specialty of the output content are ensured.

The description relates to automated binary code summarization. In one example, a binary code summarization tool receives binary code and combines the received binary code with natural language in a prompt for a large language model (LLM). The binary code summarization tool receives a semantic summarization from the LLM relating to the received binary code and evaluates the new semantic summarization for malicious functionality in the received binary code.

Systems and methods herein provide a processor; and a non-transitory, processor readable storage medium communicatively coupled to the processor. The non-transitory, processor readable storage medium may include one or more instructions stored thereon that, when executed, cause the processor to: input one or more queries into a large language model; generate, based on the one or more queries, a plurality of natural language queries, wherein each of the plurality of natural language queries are distinct queries and associated with the one or more queries; perform vector searches for the one or more queries and plurality of natural language queries; compile the plurality of natural language queries into a search result based on the vector searches; and generate a summary based on the search result.

A database query processing service is provided for efficiently processing query workloads with natural language statements and native database commands. The database query processing service may receive some database queries that do not contain a natural language marker and process these database queries without using large language models to generate replacement query content. The database query processing service may also receive other database queries that do contain the natural language marker and process the other database queries using large language model(s) to generate replacement query content or leverage replacement query content already generated by the large language model(s). The replacement query content is checked to ensure the content is natively valid for the content to retrieve data from database structures referenced in the content. The database query processing service may use the natively valid replacement query content to cause execution of operations responsive to the other database queries.

The invention discloses a vehicle-mounted streaming language dialogue interaction system and method based on a large language model, and the system comprises the large language model disposed at a vehicle-mounted end, and the large language model is used for carrying out the local processing and cloud processing of information inputted by a user, so as to obtain a processing result. Wherein the large language model is connected with the edge calculation and privacy protection module, the edge calculation and privacy protection module is used for carrying out edge calculation on a processing task in local equipment and distributing a data processing reasoning process to local and cloud service for processing, and the proportion of a local processing part is larger than that of the cloud service. The advantages of the LLMs are fully utilized, the special requirements of the vehicle-mounted environment can be met, and the method has important significance for improving the intelligent level of vehicle-mounted man-machine interaction and the user experience.

Techniques for generating an executable API call for an LLM-generated request, where the executable API call is usable to cause a component to generate a potential response to a user input, are described. In some embodiments, the system receives a user input and uses a language model to generate a request for a component to provide a potential response to the user input. The system uses the request, an API description corresponding to the component, and other information not available to the language model during processing to generate an executable API call corresponding to the request. The system can execute the executable API calls (in a system-determined order or concurrently) to cause the corresponding components to generate potential responses to the user input.

Systems, apparatus, articles of manufacture, and methods to self-guardrail large language model responses are disclosed. An example apparatus includes interface circuitry, instructions, and programmable circuitry to at least one of execute or instantiate the instructions to access a first response message provided by a first large language model, the first response message generated based on an initial prompt, cause a second large language model to determine the first response message is inappropriate, modify the initial prompt to create a modified prompt, and provide the modified prompt to the first large language model to trigger generation of a second response message.

The invention discloses an MCP generation and calling method and device in a low-code platform, equipment and a medium, and relates to the field of artificial intelligence low-code, and the method comprises the steps: carrying out the semantic analysis and structure standardization of initial metadata generated in the application development process of the low-code platform, and obtaining target metadata; converting the target metadata into an MCP description file, converting a business description corresponding to the MCP service in the initial metadata into a natural language description which can be understood by a large model, and integrating the natural language description into the MCP description file to obtain a target MCP description file; constructing a standardized MCP warehouse, and managing the MCP service corresponding to the target MCP description file by using the MCP warehouse; and acquiring a user request by utilizing the large model, and performing MCP calling on the MCP service by utilizing the large model based on the current running state data in the application running process, so that the large model responds to the user request. According to the method, deep fusion of low codes and large models is promoted.

The invention relates to a federal knowledge retrieval and large language model enhancement system and method. The system comprises a server and a hardware accelerator. The server preprocesses an input query and extracts a head word of the query; the server retrieves the head word in the caching process through a cache module of the server, and if the cache of the cache module is not hit, the server sends a retrieval instruction to the hardware accelerator so as to retrieve in a local cache of the hardware accelerator; if the local cache is still not hit, the hardware accelerator generates parallel subtasks associated with the head word in a mode of segmenting a local knowledge graph, so that deep search is carried out, and noise is added into knowledge items retrieved by the parallel subtasks to protect sensitive information; and the hardware accelerator integrates the knowledge items added with the noise, performs reasoning through a large language model and generates an enhanced answer. According to the method, a two-stage dynamic cache system is constructed, the cross-device communication frequency can be effectively reduced, the query request is responded preferentially through the local high-frequency cache, and the overall network load of the system is reduced.

The present application provides a code testing method, applied to a code testing system. When a test code is generated, context information of a code under test is extracted, and the test code is generated on the basis of the context information of the code under test. The context information often has a service meaning and can embody a test scenario, so that the prior knowledge of the service and the test scenario is achieved in the generation process of test codes, thereby generating test codes having higher quality.

A device includes a processor, and a memory storing executable instructions which, when executed by the processor, cause the processor alone or in combination with other processors to perform the following functions: receive textual user input from a user describing a design to be generated; implement a first prompt generator to generate a first prompt for a Large Language Model (LLM) to restructure the user input; and implement a second prompt generator to generate a second prompt for a text-to-image model using output of the LLM to produce, the second prompt to prompt the text-to-image model to produce a proposed design based on the user input. The proposed design is provided to the user via an application comprising controls for further editing the proposed design.

A multimodal, large language model (LLM)-powered smart service specifically tailored for manufacturing quality G-Code is described. This LLM can be considered as an information encoder that compiles the information from input data of various modalities into a shared numerical representation (or embedding). The various modalities in an example database used by the LLM and / or used to train the LLM, correspond to different representations of the part under consideration, such as design specifications, G-code, and CAD models. This embedding can then be used for different downstream tasks, such as verifying, debugging, indexing, etc., of a potentially vast set of G-Code files.

Methods and systems for prompting a large language model (LLM) to generate token-efficient output are described. A task prompt is provided to the LLM for performing a natural language task and generating token-efficient output based on the task prompt. Output is received from the LLM based on the task prompt, where the output includes text related to the task and at least a portion of the text is in a token-efficient language. The text in the token-efficient language is tokenized by a tokenizer of the LLM into fewer tokens than would correspond to a tokenization of corresponding text in a different constructed language, such as a programming language.

The invention discloses an intelligent question answering method and device, equipment, a storage medium and a program product, and relates to the technical field of business intelligence, and the intelligent question answering method comprises the steps: receiving a question input by a user; according to the problem, prompt words are generated through a preset multi-scene knowledge base, and the multi-scene knowledge base is generated based on a preset knowledge configuration file; inputting the cue word into a preset large language model to obtain a query code output by the large language model; and according to the query code, performing data query on a target database to obtain an answer of the question. According to the method, intelligent question answering of the configurable multi-scene knowledge base is realized, the problem that the existing intelligent question answering cannot effectively adapt to different scenes is solved, and the adaptive capacity of the intelligent question answering to different scenes is improved.

Embodiments of the disclosed technologies are capable of generating natural language queries. The embodiments describe generating a training natural language query of a training structured search query using a first LLM and a first prompt. The embodiments further describe fine-tuning a second LLM using the training natural language query of the training structured search query and the training structured search query. The fine-tuned second LLM generates a structured version of a natural language query. The embodiments further describe generating the structured version of a received natural language query using the fine-tuned second LLM and a second prompt.

A sample data generation method executed by an electronic device, comprising: acquiring a first prompt text, and calling a first large language model to perform question instruction prediction on the basis of the first prompt text, to generate an initial question instruction (201); on the basis of the initial question instruction, determining a question instruction of a first turn of dialogue to carry out multiple turns of dialogues, wherein in each turn of dialogue, a second large language model is called to generate an answer text of the current turn of dialogue on the basis of a question instruction of the current turn of dialogue, and starting from a second turn of dialogue, a third large language model is called to generate the question instruction of the current turn of dialogue on the basis of an answer text of a previous turn of dialogue (202); and constructing sample data on the basis of the question instructions in the multiple turns of dialogues and the answer texts in the multiple turns of dialogues (203).

One embodiment of a method for generating program code to control a robot includes receiving user input specifying a task to be performed by the robot, processing the user input via a first machine learning model to generate a plurality of subtasks for performing the task, and for each subtask included in the plurality of subtasks, processing the subtask via a second machine learning model to generate program code for controlling the robot to perform the subtask.

A structured query language statement generation method, executed by an electronic device, and comprising: determining a natural language text representing a query task, and determining a preset database, the preset database comprising at least one data table, and each data table comprising at least one field (101); on the basis of the natural language text, determining, from the preset database, at least one task-associated field and at least one task-associated data table which are associated with the natural language text (102); rewriting the natural language text on the basis of the task-associated field to obtain a rewritten natural language text (103); acquiring prompt information for the rewritten natural language text, the prompt information being used for guiding a query statement generation model in generating a structured query language statement (104); performing question classification on the rewritten natural language text to obtain question type information of the rewritten natural language text (105); and generating the structured query language statement of the rewritten natural language text by means of the query statement generation model on the basis of the task-associated field, the task-associated data table, the prompt information, and the question type information (106).

A technique sends a first prompt to a language model that specifies selector information. The selector information provides a summary of a group of functions that are capable of being invoked. The language model responds by choosing one or more functions from the group of functions. The technique then sends a second prompt to the language model that specifies more detailed information regarding just the function(s) that have been identified by the language model. The language model responds by providing invocation information for each of the functions, such as properly formatted API messages. The technique then invokes the function(s) based on the invocation information. The technique reduces the size of each prompt sent to the language model, which makes efficient use of resources and improves the quality of the language model's output results.

The invention provides an open vocabulary task guiding grabbing method and device, a medium and a program product. The open vocabulary task guiding grabbing method comprises the steps that a user language instruction and a complex scene image are input into a preset visual language model; identifying a target task corresponding to the user language instruction through a preset visual language model, matching a target object associated with the target task in the complex scene image, and determining an optimal grabbing component of the target object based on a plurality of functional components of the target object; constructing a plurality of capture candidate schemes by adopting the optimal capture component and the complex scene image; and performing optimization solution on each grabbing candidate scheme to determine the optimal grabbing pose, so as to solve the problem that the existing method is poor in effect when dealing with an unseen object and a new task in a scene with open vocabularies due to the limited scale of an operability memory bank in the related technology. The invention aims at solving the problem that the existing method is poor in effect when dealing with the unseen object and the new task in the scene with the open vocabularies.

The present disclosure relates to a message segmented parsing method, apparatus, and device, and a storage medium. In the present disclosure, an n-stage parsing result is obtained by, according to parsing configuration information, performing n-stage parsing on a header comprised in a message; when a next-level header type to be parsed that is comprised in the n-stage parsing result is not the header type of n+1-stage parsing, the n+1-stage parsing of the header is skipped and n+2-stage parsing is entered; when the next-level header type to be parsed is the header type of n+1-stage parsing, the header undergoes n+1-stage parsing according to the offset address of the next stage comprised in the n-stage parsing result; and when N-stage parsing is completed or previous N-1 layer protocol parsing determines to skip N-stage parsing, the current segmented parsing of the header is stopped.

Methods, apparatus, and processor-readable storage media for automatically generating context-based responses to natural language queries using knowledge graphs are provided herein. An example computer-implemented method includes generating at least one query in a predetermined query language by processing at least one natural language query of at least one user of an enterprise; generating a first set of results by processing the at least one query in the predetermined query language using one or more data sources including at least one enterprise-related knowledge graph; generating a second set of results by processing the at least one natural language query using one or more artificial intelligence techniques; generating a third set of results by incorporating at least a portion of the first set into at least a portion of the second set; and performing automated actions based on the third set of results.

A technique accelerates the generative production of tokens using a target language model that operates in cooperation with a smaller draft language model. In operation, the target language model (1) verifies the accuracy of a first set of draft tokens produced by the draft language model, (2) predicts a new token to follow the last-verified draft token, and (3) generates plural instances of guidance information. The draft language model produces a second set of draft tokens in parallel based on the target output token(s) produced by the target language model and the instances of guidance information. The technique expedites the generation of tokens because the draft language model, due to its size, is able to produce tokens faster than the target language model. The draft language model produces its draft tokens in parallel (at the same time), rather than auto-regressively, which further speeds up token generation.

In various examples, a language model may be trained and used as part of an interface for a simulation system. For instance, user inputs may be applied to the language model and the language model may be trained to generate code, make API calls, or perform any other operations to interact with and / or control various aspects of the simulation. In some examples, the language model may generate code for, among other things, creating and / or customizing a virtual environment associated with the simulation. For instance, the generated code may include, but is not limited to, code for rendering the virtual environment, code for rendering and simulating behaviors of virtual agents (e.g., pedestrians, vehicles, animals, etc.) and / or any other objects (e.g., road signs, buildings, trees, etc.) within the virtual environment, code for recreating and simulating real-world events from recorded sensor data, etc.