Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

166 results about "Lexical analysis" patented technology

In computer science, lexical analysis, lexing or tokenization is the process of converting a sequence of characters (such as in a computer program or web page) into a sequence of tokens (strings with an assigned and thus identified meaning). A program that performs lexical analysis may be termed a lexer, tokenizer, or scanner, though scanner is also a term for the first stage of a lexer. A lexer is generally combined with a parser, which together analyze the syntax of programming languages, web pages, and so forth.

Zero-illusion large language model output method and system

The invention relates to the technical field of large language models, and discloses a zero-illusion large language model output method and system, and the method comprises the steps: sequentially carrying out the deterministic lexical analysis and standardized mapping of a received original query, and generating a standard term set; locking to-be-reasoned items through hierarchical matching to form a deterministic retrieval result set; executing five rounds of progressive verification processing on the result set to obtain an integrated result set with an LLM verification mark; and outputting a layered zero illusion result through multiple verification and auditing of structure compliance, semantic consistency and knowledge base double recheck. According to the method, probabilistic reasoning is replaced by full-link deterministic operation, so that each code can be traced back to a credible knowledge source, illusion is thoroughly eliminated, absolute reliability and complete traceability of an output result in a professional field are realized by a verifiable deterministic path, and a foundation is laid for zero-illusion application.
Owner:YUANYUANZHIJI ARTIFICIAL INTELLIGENCE TECHNOLOGY (CHONGQING) CO LTD

ANTLR4-based multi-manufacturer network equipment configuration analysis method and system

The invention discloses an ANTLR4-based multi-manufacturer network equipment configuration analysis method and system, and the method comprises the steps: carrying out the preprocessing of a configuration file; based on a machine learning algorithm of multi-dimensional feature analysis, automatic identification of configuration file manufacturer types is realized; based on the identification result of the manufacturer type, loading an ANTLR4 grammar parser corresponding to the manufacturer type; a lexical analyzer in ANTLR4 realizes lexical analysis on the configuration file through lexical rule definition, a Token classification system and an optimized analysis algorithm; a syntactic analyzer in ANTLR4 constructs an abstract syntax tree according to a lexical analysis result and a syntactic rule defined based on a context-independent grammar; traversing the abstract syntax tree, and extracting key configuration information; and converting the specific configuration format of each manufacturer into a unified standard model. According to the method and the system, network equipment configuration files of different manufacturers can be automatically identified and analyzed, and key configuration information is extracted and converted into a unified model.
Owner:CHINA UNITECHS

Transverse mixed attention mechanism model training method, medium, device and program product

The invention provides a model training method for a transverse mixed attention mechanism, a medium, equipment and a program product, and the method comprises the steps: obtaining a data set containing a plurality of sample sequences, each sample sequence in the data set being formed by arranging a plurality of Token sequences obtained through word segmentation; constructing a to-be-trained model based on the pre-trained full attention model, and adding newly added parameters for linear attention calculation; in the same transverse mixed attention layer, executing total attention calculation on a Token set in a preset total attention calculation range, executing linear attention calculation on all Tokens, and fusing results of the total attention calculation and the linear attention calculation to obtain transverse mixed attention output used for forward reasoning and loss calculation; and based on the output and prediction result, only updating the newly added parameters to optimize the to-be-trained model until the to-be-trained model converges. According to the method, the calculation complexity and video memory occupation of long text sequence processing are reduced, and the reasoning speed and the resource utilization rate are improved.
Owner:BEIJING JIBU QIANLI TECHNOLOGY CO LTD

Hybrid recommendation system using Team Frequency-Inverse Document Frequency (TF-IDF) for film recommendations

A hybrid recommendation system for generating personalized film recommendations, the system comprising the following: a processing unit for receiving metadata, configured to receive descriptive data related to films, the descriptive data including plot summaries, genre identifiers, cast lists and director names; a text preprocessing module that is communicatively coupled with the metadata ingestion processing unit and is configured to perform tokenization, stopword removal, stemming, and lemmatization on the descriptive data to obtain a processed corpus; a TF-IDF vectorization unit configured to encode the processed corpus into high-dimensional semantic feature vectors by calculating TF-IDF inverse document frequency values ​​over the entire film dataset, with the semantic feature vectors representing the contextual meaning of terms for individual films; a collaborative filter engine comprising a user-element interaction matrix, wherein the engine is configured to compute latent preference signals using one or more techniques selected from the group consisting of cosine similarity, k-nearest neighbor similarity, and matrix factorization; a score fusion controller coupled to both the TF-IDF vectorization unit and the collaborative filter engine, wherein the module is configured to normalize the semantic feature vectors and the collaborative preference scores and dynamically combine them according to an adaptive weighting coefficient, the coefficient being determined as a function of data density, interaction sparsity, and user history length; and a recommendation output module configured to evaluate candidate films for each user based on the combined score and generate a top-N recommendation list.
Owner:NITTE MEENAKSHI INSTITUTE OF TECHNOLOGY (DEEMED TO BE UNIVERSITY) BENGALURU +3

Method and system for analyzing and editing view in real time based on streaming data

The invention discloses a real-time analysis and view editing method and system based on streaming data, and the method comprises the steps: receiving streaming data which comes from a large language model and is organized in an editing protocol format, carrying out the real-time lexical analysis of the streaming data, and decomposing the streaming data into a semantic unit sequence through a semantic pattern recognition technology; performing grammar analysis on the semantic unit sequence, and converting the semantic unit into a structured editing instruction for modifying an existing rendering tree node according to an instruction pattern recognition mechanism and a target object analysis mechanism; converting the structured editing instruction into an atomic instruction sequence executable by a rendering tree editing interface; and modifying the rendering tree in real time according to the atomic instruction sequence and triggering update rendering of the view. According to the method, the content generated by the AI is analyzed in real time by adopting a streaming output mechanism, so that a user can observe the generation process of the view in real time, local redrawing of the view is realized by using an editing protocol, and the view editing efficiency is greatly improved.
Owner:HANGZHOU DIMENG TECHNOLOGY CO LTD

Nuclear power equipment operation defect grading method and device, electronic equipment and storage medium

The invention relates to the technical field of nuclear power plants, in particular to a nuclear power equipment operation defect grading method and device, electronic equipment and a storage medium. The invention provides a nuclear power equipment operation defect grading method, and aims to realize grading of nuclear power equipment operation defects through a systematic and multi-level fusion decision-making mechanism. The problems that rule grading lacks flexibility, graph grading is influenced by keyword sensitivity, large model grading field knowledge is insufficient, and precision and adaptability are limited due to the fact that a traditional fusion strategy is single in the prior art are effectively solved. The core of the method is that lexical meta processing and a value matrix mechanism are introduced, dynamic and fine-grained fusion of multi-base classifier output is achieved, and therefore the overall performance of a grading system is improved. Through lexical element processing, value matrix construction and dynamic updating and multi-classifier fusion decision making, the nuclear power equipment defect grading method with high precision, high adaptability and high reliability is realized, and many limitations in related technologies are effectively solved.
Owner:CHINA NUCLEAR POWER ENGINEERING COMPANY LTD +1

Code similarity detection method and system based on large language model

The invention discloses a code similarity detection method and system based on a large language model, and the method comprises the steps: obtaining a to-be-detected source code pair, and marking the to-be-detected source code pair as a source code A and a source code B; performing code cleaning and format standardization on the source code A and the source code B, and mapping a variable name and a function name which are customized by a user into a uniform placeholder; analyzing the source codes A and B based on the abstract syntax tree, respectively replacing variable names and function names in the source codes A and B with unified serialized placeholders, and maintaining a mapping table; meanwhile, expanding a lexical dictionary of the pre-training large language model, and inserting a special identifier; splicing the replaced code snippets with special identifiers, and constructing a structure sensing input sequence; inputting the structure perception input sequence into a pre-trained large language model backbone network for feature coding to obtain a high-dimensional semantic feature vector containing global context information; connecting a multi-task prediction head behind the large language model backbone network, inputting the feature vector into the multi-task prediction head, outputting probability distribution of code clone types through a classification task head, and respectively outputting a row level similarity score and a lexical element level similarity score through a regression task head; and according to the classification probability and the regression score, performing comprehensive judgment by combining a preset threshold, and generating a detection report. According to the method, similar codes after variable renaming, statement rearrangement or control flow transformation can be accurately recognized, and the accuracy and robustness of code similarity detection are improved.
Owner:NANJING UNIV OF SCI & TECH

General data exchange system based on configurable label structure

The invention discloses a general data exchange system based on a configurable label structure, which relates to the technical field of data processing and information integration, and comprises a parameter module used for establishing an identity authentication mechanism of two exchange parties; the business document module is used for establishing a data structure definition based on a preset exchange demand; the receipt logic module is used for carrying out logic analysis and code decoupling on the data structure definition, generating a marked language script code and an execution instruction, constructing an execution matrix and realizing mapping between a database physical field and a memory logic variable; and the standard adaptation module is used for comparing and checking the content of the generated data and feeding back a checking result to the parameter module to correct the exchange rule and parameter configuration. A more intelligent logic separation strategy is implemented through structural insight, data reading, writing and transmission are cooperatively controlled, complete decoupling of service logic and program codes is achieved through a nested tag structure, and flexibility, universality and maintenance efficiency of data exchange are optimized.
Owner:BEIJING LIGONGDAXUE PRESS CO LTD

Language specification and conversion method and system fused with multi-database dialects

The invention provides a multi-database dialect fused language specification, a multi-database dialect fused language conversion method and a multi-database dialect fused language conversion system, and relates to the technical field of databases. A user inputs a unified SQL statement and selects the type of a target database, lexical analysis and grammatical analysis are performed on the unified SQL statement, an abstract syntax tree is constructed, semantic analysis is performed, dialect characteristics in the unified SQL statement are identified, the support condition of the dialect characteristics in the target database is verified, and a dialect conversion strategy is provided. And selecting a corresponding conversion rule in the unified SQL specification library, converting the grammar of the unified SQL statement into the dialect grammar of the target database, and generating the SQL statement. According to the method, one set of SQL and multi-database support is realized through unified SQL specification formulation, intelligent dialect adaptation and configuration driving, a complete technical solution is provided for cross-database application development, and technical challenges caused by database dialect differences are solved.
Owner:DIGITAL CHINA FINANCIAL SOFTWARE LTD

General SQL grammar conversion method and device, equipment and medium

The invention relates to the technical field of SQL (Structured Query Language) grammar conversion, and provides a general SQL grammar conversion method, device and equipment and a medium, the method comprises the following steps: performing lexical analysis on a source end SQL statement to obtain a lexical unit set; based on the type features and semantic attributes of the lexical unit set, determining parser combiners, and constructing a specific parser by infinitely combining the parser combiners; the specific resolver is used for conducting grammar analysis on the lexical unit set, a general abstract syntax tree is constructed through a mapping assembly, and nodes of the general abstract syntax tree correspond to the specific resolver one to one; and traversing the general abstract syntax tree, and generating a target end SQL statement according to an SQL syntax rule of a target end database. Through the technical scheme, any complex source end SQL can be accurately converted into the target end SQL.
Owner:CSC FINANCIAL CO LTD

Compilation method for compiling C language source code into RISC-V assembly code

The invention discloses a compiling method for compiling a C language source code into an RISC-V assembly code. The method comprises the following steps: acquiring a C language source code; performing lexical analysis on the C language source code to generate a mark flow; performing syntactic analysis on the mark flow, and constructing an abstract syntax tree; performing semantic analysis on the abstract syntax tree to generate a target abstract syntax tree; constructing a runtime environment of the RISC-V assembly code; generating an intermediate code and a control flow diagram corresponding to the intermediate code according to a rule in the runtime environment and the target abstract syntax tree; generating a target code by using the intermediate code and the control flow diagram corresponding to the intermediate code; according to the technical scheme, the intermediate representation more adaptive to RISC-V custom instruction mapping can be generated, so that the execution efficiency of assembly codes is improved; and meanwhile, by designing a lightweight runtime environment, the performance overhead is further reduced.
Owner:CHINA SOUTHERN POWER GRID COMPANY

Large language model operator compiling method and system oriented to GPU (Graphics Processing Unit) platform

The invention provides a large language model operator compiling method oriented to a GPU platform, and belongs to the field of GPU operator compilation. A large language model operator is compiled through a Python interface to obtain a Python code; performing lexical analysis and grammatical analysis on the Python code to generate an abstract syntax tree; mapping the abstract syntax tree into an MMIR extension intermediate representation; tensor layout in the MLIR extension intermediate representation is uniformly converted into a binary linear mapping matrix, and optimization problems of global memory layout, shared memory layout and register block layout are analyzed based on the binary linear mapping matrix; automatically deducing a non-key tensor layout based on a program control flow diagram, generating a global optimal layout scheme, and obtaining an optimized MMIR extension intermediate representation; enabling the optimized MLIR extension intermediate representation to pass through a GGPU (Graphics Graphics Processing Unit) target code generator of the MLIR, and generating a PTX code adaptive to the NVIDIA GPU; the PTX code is loaded to a GPU, and an operator calculation result is output; the invention further provides a compiling system. The problem that the current large language model operator compiling efficiency is low is solved.
Owner:江淮前沿技术协同创新中心

Method and system for dynamic weighted metrics-based evaluation and tokenization of large language models

The embodiments of the present disclosure herein address unresolved problems of evaluation of LLM response quality and overall LLM models. Existing approaches for LLM evaluation and LLM response evaluation can be broadly categorized into automatic evaluation metrics, human evaluation, and adversarial testing. Embodiments herein provides a method and system for dynamically weighted selection of performance metrics for generation of LLM response score. Further, the system is configured method and system for generation of LLM maturity gap analysis and associated recommendation for improvement of LLM response score. Finally, the system generates a compliance certificate for every model (version) with a (threshold) level score and generates an NFT using a smart contract based blockchain, using metadata associated with the model and the evaluation metrics and results.
Owner:TATA CONSULTANCY SERVICES LTD

Method and system for detecting unauthorized URL (Uniform Resource Locator) of website based on automatic operation of common user

The invention provides a method and system for detecting an unauthorized URL of a website based on automatic operation of a common user, belongs to the technical field of network security, and can at least partially solve the problems of low detection efficiency, poor accuracy and excessive dependence on manual operation in the prior art. Automatically logging in a website by using the registration information, processing a verification link, and obtaining session information; obtaining a JS file through a web crawler in a normal user login state; analyzing the JS file, extracting static, dynamic and relative URLs in combination with lexical analysis, grammatical analysis and sandbox simulation execution, and unifying the static, dynamic and relative URLs as absolute URLs; de-duplicating and normalizing the URL; accessing the URL through a common user session by using a network test tool, obtaining response data, comparing the response data with a high-authority user reference response, and judging an unauthorized URL; the method has the beneficial effects that automatic and comprehensive detection of the unauthorized URL is realized, and the detection efficiency and accuracy are remarkably improved.
Owner:HUANENG POWER INT INC +1

Fault-tolerant processing method and system for long text in large model service, and storage medium

The application relates to the technical field of large language model application, in particular to a fault-tolerant processing method and system for super-long text in a large model service and a storage medium. The method comprises the following steps: obtaining a to-be-processed super-long text and a maximum Token threshold of a large model context window, completing Tokenization and judging whether the Token is out of limit; starting a multi-level alternative solution containing fast compression, dynamic compression and chat history compression; starting an error recovery mechanism containing hierarchical exception processing, intelligent degradation and parameter verification; outputting a target text with a compliant Token number; the system comprises a text acquisition module, a multi-level alternative solution execution module, an error recovery module and an output module; the storage medium stores a computer program, and the computer program realizes the above method when executed, can be adapted to multiple models, meets the industrial super-long text processing demand, and solves the problems of the absence of a fault-tolerant mechanism, Token out-of-limit errors caused by insufficient boundary processing and unstable reasoning service in the prior art.
Owner:POWERCHINA BEIJING ENG CORP

Cybersecurity event handling and enrichment system

A Cybersecurity Event Handling Processor (CEHP) and method for processing security alerts includes: a File System containing a Universal Target Schema (UTS) of target language representations (UTS JSONs); a Normalizer running Feature Extraction and Word Embeddings algorithms; a Tree Converter; and a Transformer running linguistic and structural matching algorithms. The CEHP: (a) captures threat events in one or more native formats generated by cybersecurity tools; (b) runs Feature Extraction and Word Embeddings algorithms for tokenization and categorization of the captured events to create normalized events; (c) converts the normalized events into trees and then translates the trees into event representations in JSON (or XML) format (Event JSONs); and (d) runs nearest neighbor and / or linguistic and structural matching algorithms to compare the Event JSONs to the UTS JSONs to generate output JSONs (Translation JSONs) from the UTS corresponding to the captured events.
Owner:NUHARBOR SECURITY INC

Method and system for cobol to java program conversion based on syntax tree

PendingCN122411953APathPingSource code file
The application discloses a COBOL-to-Java program conversion method and system based on a syntax tree, belongs to the technical field of computer program language conversion, and comprises the following steps: obtaining a COBOL source program file to be converted and configuration rules; performing lexical analysis and syntax analysis to generate an abstract syntax tree; converting COBOL syntax elements into corresponding Java semantic representations according to pre-defined semantic mapping rules; establishing an accurate access chain of a main program and COPYBOOK internal variables through variable path tracking; detecting and solving naming conflicts of COBOL different-level same-name variables based on a scope tree, and renaming variables by adding a parent class name prefix; and generating the converted Java semantic representations into a Java source code file. The application realizes high-fidelity and high-automation COBOL-to-Java conversion, significantly reduces the migration cost of a legacy system, and generates code with strong readability and excellent performance.
Owner:SHANDONG CITY COMMERCIAL BANK COOP ALLIANCE CO LTD

Mathematical expression diagnosis method and device based on abstract syntax tree and semantic network

The application discloses a mathematical expression diagnosis method and device based on an abstract syntax tree and a semantic network, and belongs to the technical field of mathematical expression processing. The method comprises the following steps: establishing formal grammar rules of a mathematical expression based on an extended Backus-Naur form; performing lexical analysis on an input mathematical expression to generate a token stream; performing syntax analysis on the token stream based on the formal grammar rules to construct an abstract syntax tree; in the process of constructing the abstract syntax tree, running a structural diagnosis process, wherein the structural diagnosis process comprises constructing a semantic network based on a mathematical knowledge base, and performing graph matching on nodes in the abstract syntax tree and the semantic network to identify structural errors in the mathematical expression; and generating error correction suggestions based on the identified structural errors. The application can realize deep analysis from syntax correctness checking to mathematical rationality, and improve the accuracy of mathematical expression processing.
Owner:OCEAN UNIV OF CHINA

A digital signal processor (DSP) assembler transplantation method based on processor architecture description

ActiveCN115293200BLexical analysisEngineering
This invention discloses a method for porting a digital signal processor (DSP) assembler based on a processor architecture description, comprising the following steps: S1. Based on the processor architecture description, a lexical analysis and syntax analysis part of the assembler is constructed to realize the parsing of special assembly instructions; S2. Taking the parsed instruction data or instruction binary code as input, dynamic encoding and decoding of instructions are implemented according to the instruction definition, thereby realizing the conversion between the object file and the assembly file. This DSP assembler porting method further improves the performance of the assembler and automates the porting process, adapting it to the digital signal processor architecture. It also provides support for single instruction multiple data, very long instruction words, and instruction validity checks. While ensuring that the program execution result meets expectations, it greatly reduces the number of clock cycles required for execution, possesses universality, and meets the needs of rapid processor architecture updates.
Owner:合肥乾芯科技有限公司

A fluid simulation method and system based on adaptive mesh optimization

The application discloses a fluid simulation method and system based on adaptive grid optimization, and belongs to the technical field of computational fluid dynamics, and comprises the following contents: receiving fluid state data at a current moment, state data at a historical moment and global physical parameters, performing scale alignment and normalization processing on the data and encapsulating the data as structured input; performing initial blocking on the whole calculation domain, converting original regular grid expression into a candidate unit set with hierarchical relationship; calculating physical indexes of each candidate unit based on fluid physical properties, judging whether each candidate unit needs to be refined, reserved or discarded; performing word tokenization and position coding on a multi-scale unit sequence, inputting the sequence into a neural solver to establish a long-range dependence relationship across regions, and outputting state word tokens at a next moment; and mapping the state word tokens back to an original regular grid space to generate a flow field simulation result. By using the method, accurate identification of a key region of a flow field and efficient modeling of multi-scale flow characteristics are realized.
Owner:FEIJIE COSI INTELLIGENT TECHNOLOGY (SHANGHAI) CO LTD

AI-driven structured data migration method and system

The application discloses an AI driving-based structured data migration method and system, belongs to the technical field of big data migration, and aims to solve the technical problem of how to improve the efficiency of large-scale data migration and reduce resource waste. The method comprises the following steps: forming a private large language model with field adaptation capability; performing lexical analysis and syntax analysis on non-standard structured data in a source database based on an AST analysis method, generating an abstract syntax tree AST, traversing and optimizing AST nodes, and converting the AST nodes into standard structured data supported by a target database; calling the large language model, and converting unstructured data into structured data supported by the target database through instruction fine-tuning, thought chain reasoning and step-by-step analysis; generating a migration script by the large language model; monitoring the migration process in real time, recording abnormal events, automatically retrying or repairing the abnormal events by the large model, and optimizing the large language model configuration strategy and data conversion rules in combination with feedback data.
Owner:INSPUR TIANYUAN COMM INFORMATION SYST CO LTD

High-availability and high-performance formula execution method based on analysis-free

The invention belongs to the technical field of industrial dynamic formula execution, and discloses an analysis-free high-availability and high-performance formula execution method. The method comprises the following steps: S1, formula extraction and function body construction: receiving a calculation formula input by a user, and taking the calculation formula as a function body core calculation logic; s2, function packaging: adding a function head and a return value statement for a function body, and constructing a complete function definition character string; wherein the function head comprises a function name and a parameter list; and S3, function persistence and dynamic import execution: writing a function character string into an independent Python module file, and calling and executing through a dynamic import mechanism. According to the method, function packaging is adopted, the repeated lexical analysis and grammar analysis process which must be carried out when a traditional event () method is executed each time is eliminated, and the problems that a formula is forcibly required to only comprise functions of input parameters, calculation expressions and return values, and the bottleneck of industrial real-time application and the fragility of a whole framework are solved.
Owner:HUANENG POWER INT INC DALIAN POWER PLANT

Method and system for quickly configuring and generating index library based on domain-specific language

The invention provides a method and system for generating an index library in a rapid configuration mode based on a domain-specific language, and relates to the technical field of computer software. Index configuration information, input by a user in a configuration interaction interface, of a target index is received; performing lexical analysis, grammatical analysis and semantic verification on the index configuration information to obtain target configuration information; according to the target configuration information, generating an executable code which can be identified by the target calculation engine, wherein the executable code is an SQL query statement; scheduling the executable code to a target calculation engine for execution, extracting data from the associated data source and completing calculation to obtain a target index, and storing the target index to a preset index library; the target index is registered to the index library center for metadata management, and an index query and data service interface is provided externally, so that efficient configuration generation and flexible iteration of the index library can be realized while the accuracy and controllability of the generation result are ensured, and the technical threshold is reduced and the existing data assets are reused.
Owner:SUNSHINE PROPERTY & CASUALTY INSURANCE CO

Magnitude invariant multimodal agent for efficient image-text interface automation

A system for magnitude-invariant image-text agentic interface automation is disclosed. A bit vectorization logic is configured to convert image patches in a plurality of image patches into magnitude-invariant bit vectors, and generate a plurality of lines of magnitude-invariant bit vectors. A tokenization logic is configured to translate the input text sequence into a sequence of input text tokens, and to translate the successive lines of magnitude-invariant bit vectors interleaved with a newline character into a sequence of input magnitude-invariant bit vector tokens. A linear projection logic is configured to linearly project a single token stream of the sequence of input text tokens and the sequence of input magnitude-invariant bit vector tokens into a decoder-only Transformer logic, wherein the linear projection of the single token stream bypasses any embedding lookup.
Owner:ANTHROPIC PBC

Real-time compiling method and device, equipment and storage medium

The invention discloses a real-time compiling method and device, equipment and a storage medium, belongs to the field of data processing, and can solve the problem that a program cannot be compiled on a target platform in real time. The method comprises the following steps: converting source codes in a character stream into a symbol set through a lexical analysis state machine; processing the grammar symbols in the symbol set through an analysis engine to generate corresponding intermediate representations; the intermediate representation is processed through an assembly generator and a node distributor, a binary file corresponding to a target platform is obtained, and the binary file at least comprises a first machine instruction corresponding to the target platform; and compiling the dynamic code through a real-time compiling engine to obtain a second machine instruction corresponding to the target platform, and putting the second machine instruction into a dynamic loading library to load and run the second machine instruction.
Owner:CHINA TELECOM CLOUD TECH CO LTD

Determining semantic and grammatical correctness of user-expanded sentence using integrated programmatic and specialized guided and constrained artificial intelligence

A system and method guide an Artificial Intelligence engine to determine the semantic and grammatical correctness of a user-expanded sentence in real-time. The sentence validation process involves receiving input from the user, the input includes sentence fragment that the user wishes to expand and user-expanded sentence that the user constructs on the fragment provided. The inputs are broken down into tokens. The word-level tokenization algorithm is used, which identifies tokens by splitting the text into spaces, punctuation marks, and other delimiters. Further, a token comparison algorithm is used to assess the relationship between the sentence fragment and the user-expanded sentence to analyze order and placement. Once the token comparison is complete, a prompt is generated using prompt generator to evaluate grammatical and semantic evaluation of the user-expanded sentence. Real-time feedback is provided to the user based on grammatical and semantic evaluation.
Owner:2HR LEARNING INC

Continuous pre-training method for Chinese medical entity recognition

The invention relates to the technical field of natural language data processing, and provides a continuous pre-training method for Chinese medical entity recognition, which comprises the following steps: S1, word segmentation labeling: performing text cleaning and word segmentation processing on a medical professional text data source, and labeling proper nouns and terms; s2, inserting a boundary mark: inserting the boundary mark at the inter-word position of the segmented word in the sentence; s3, adding dynamic shielding; s4, adjusting the shielding probability according to the stages; s5, performing dynamic mask operation; and S6, performing fine adjustment training. According to the method, the context understanding capability of the model is enhanced by using a relatively high shielding rate at the initial stage of training, and then the shielding rate is gradually reduced to adapt to real data distribution, so that the learning efficiency and the final performance of the model are effectively improved, and the learning efficiency and the final performance of the model are effectively improved through innovatively continuing pre-training and refining a training strategy. The key challenge of NLP processing in the Chinese medical field is effectively solved, and a new technical approach is provided for improving the accuracy and efficiency of Chinese medical text analysis.
Owner:WUHAN CHILDRENS HOSPITAL

AI support device, AI support method, and program

To provide devices, methods, and programs that assist users in using AI. [Solution] The AI ​​support device of the present invention comprises: a morphological analysis unit that performs morphological analysis on text information representing a command to be performed by the AI; keyword master data that stores pre-registered words, processing attribute codes corresponding to pre-determined processing attributes for each word, and pre-specified scores associated with the processing attribute codes; a keyword extraction unit that extracts words obtained by morphological analysis from the words stored in the keyword master data as keywords; a score calculation unit that calculates a total score by summing the scores for each processing attribute code; and a first decision unit that determines to proceed to the execution of the processing attribute corresponding to the processing attribute code with the highest total score obtained by the score calculation unit.
Owner:WORKVISION CO LTD

A power plant DCS data acquisition interface automatic configuration method and system

The application provides a power plant DCS data acquisition interface automatic configuration method and system. The method comprises the following steps: obtaining a production process diagram file from a DCS host computer, analyzing and extracting measuring point information based on a DCS type; generating a structured dictionary sequence through lexical analysis, and generating a measuring point list according to a preset rule to screen target measuring points; comparing the measuring point list state by using a Myers difference algorithm to dynamically update the interface program acquisition range; transmitting the measuring point list, the process diagram and real-time data to a management information layer (MIS) across a safety zone, and synchronously checking the consistency based on a digital twin model. The application realizes automatic extraction of measuring points by using regular expressions and DOM analysis technology, solves the problems of low efficiency of manual configuration, lagging update and cross-zone data island by combining dynamic key encryption and incremental update mechanism, significantly improves the accuracy of measuring point configuration and synchronization real-time performance, and provides safe and reliable digital support for power plant production monitoring and information management.
Owner:HUADIAN ZOUXIAN POWER GENERATION CO LTD +2

Agent ontology pollution isolation method based on memory layering and tokenization access control

This invention discloses a method and apparatus for isolating agent ontology pollution based on memory layering and tokenized access control, belonging to the field of large language model agent technology. This invention establishes a three-layer logically isolated architecture within the MCP service cluster: a dialogue text layer, an ontology structure layer, and an execution protocol layer. It employs a differentiated update strategy of cumulative appending, complete replacement in each round, and constant updates. Each round generates a unique token strongly bound to the current round's ontology subgraph's TTL, atomically invalidating historical tokens and completing atomic switching of the ontology version. The business service entry point performs triple mandatory checks on existence, state validity, and version currentity in a fixed order through a token verification interceptor. The agent is configured in a zero-memory, stateless mode, with context and ontology data obtained through external services. Simultaneously, dynamic memory compression and summary condensation are implemented in the dialogue text layer.
Owner:BEIJING ZHONGSHURUIZHI TECH CO LTD