44 results about "Similitude" patented technology

Methods and systems for generating output content using a generative artificial intelligence (AI) model based on an input. A similarity-assessment layer at the output of the generative AI model determines a similarity measure for the output content vis-à-vis pre-existing items in a repository. The similarity measure is compared to a threshold value and, responsive to the comparison indicating excessive similarity, one or both of the input and the generative AI model are adjusted, and the generative AI model is re-run to generate new output content.

The invention discloses a method and system for evaluating and improving paragraph similarity judgment precision of a large model, and belongs to the technical field of artificial intelligence and natural language process.The method comprises the steps that a scoring standard and an evaluation process are formulated, the scores account for 50% of the overall score; scoring by experts in the three fields of business, algorithm and test according to indexes; automatically scoring the paragraphs of the test set by adopting the trained large model, comparing with manual comprehensive scoring, considering that the model is accurate when the difference does not exceed 0.5, and calculating the accuracy rate of the model according to the result; model optimization and promotion: constructing a training set; carrying out model training and iteration; preparing a test set and accurately evaluating the test set; and performing cyclic feedback optimization. According to the method, the accuracy and practicability of the large model in paragraph similarity judgment can be improved, and the method is more reliable and efficient in practical application.

Methods and systems for generating output content using a generative artificial intelligence (AI) model based on an input. A similarity-assessment layer at the output of the generative AI model determines a similarity measure for the output content vis-à-vis pre-existing items in a repository. The similarity measure is compared to a threshold value and, responsive to the comparison indicating excessive similarity, one or both of the input and the generative AI model are adjusted, and the generative AI model is re-run to generate new output content.

THE WAY IN WHICH THE ESSENTIAL ASPECT OF THE STRATEGE "FROM NOTHING - SOMETHING" IS IMPLEMENTED IN INFORMATION TECHNOLOGIES. The initial essence "Nothing" (0, Zero) of the method is the abstract essence. The mathematical model of the Projected Object Entity (PEO) is embodied in material, software, and mixed entity objects from various disciplines—the "something" of the method. The methodology of comparative cause-and-effect analysis is applied in the creation of the PEO, and the methodology of essential synthesis is used in its design: subject-specific and essential interdisciplinary properties of similarity, universal mathematical models in the form of orgraphs and their matrices, graphs with algorithms of nodes and their matrices, as well as essential identities, equations, and differential equations that reflect the balance of actions and counteractions.And since the professional and interdisciplinary properties of similarity for individual objects of different disciplines continue to apply, the transfer of the parental properties, qualities and the collective image of "nothing" and its "something" takes place "according to the image and likeness" of the essence.

The application discloses a small sample face recognition method based on prototype calibration and adaptive fine-tuning, comprising the following steps: 1) pre-training the encoder on a large-scale face database, capturing rich semantic information and class distribution, constructing an evaluation set, and ensuring that the training identity information does not overlap with the constructed evaluation set; 2) initializing the classifier weight through the weight imprint method, ensuring smooth transition, and inducing the discriminative structure of the encoder; 3) calculating the cosine similarity between the fine-tuning class prototype and the pre-training prototype, fusing the pre-training class information through weighted average, and calibrating the biased fine-tuning class prototype; 4) introducing an adaptive margin loss function, adjusting the sample penalty strength, and selectively fine-tuning the BatchNorm layer and the classifier weight; and 5) using the field-aware similarity NAC to calibrate the unknown class rejection, enhancing the similarity relationship with the field sample, and obtaining the final matching score. The method can improve the recognition accuracy and rejection ability of the model in the small sample learning scene.

Comprising a method and apparatus including computer code configured to cause one or more processors to construct a similarity score between a plurality of words, initialize a similarity structure that depends on a task and is based on the similarity score, and initialize the similarity structure based on the similarity score by implementing a bilayer optimization. And performing machine learning on the task dependency of the similarity structure, the double-layer optimization comprising: a search stage comprising learning a model weight by estimating a model parameter corresponding to a first entry of the similarity structure, learning a parameter of a second entry of the similarity structure by applying the model parameter to the second entry; and a fine tuning stage: updating the model parameters under the condition of keeping the similarity structure unchanged.

Systems, methods, devices, and computer readable storage media described herein provide techniques for prioritizing software development using a trained model. In an aspect, model features are determined based on analysis of user behavior with respect to a software application. A software development prioritization (SDP) system determines data associated with the model features and utilizes a generative artificial intelligence (AI) model to summarize the model features based on the determined data. The SDP system determines, based on the summaries, a similarity between software development items and the model features and prioritizes one of the software development items over another based on the determined similarities. In a further embodiment, the SDP system causes a software development task corresponding to the prioritized software development item to be performed before another software development task corresponding to a different software development item. In an aspect, model features are determined utilizing a trained machine learning model.

Methods and systems for obtaining contextual information about a machine learning model are provided. The method includes: receiving raw data that is usable for training a model; training the by using the raw data; computing a set of common background data based on the raw data; computing a first explanation based on an output of the model and the set of common background data; computing, based on an output of the model, an agnostic model representation of the model; computing, based on the first explanation and the agnostic model representation, a deep, compact, and dense explanation-driven representation of the model; and determining, based on the explanation-driven representation, contextual information that relates to the model.

The application relates to the technical field of mechanical fault diagnosis and machine learning, and particularly relates to a bearing incremental fault diagnosis method and system based on causal distillation and a dynamic threshold. In the incremental learning process, firstly, a causal loss function is used to reserve potential causal features; secondly, the causal similarity between samples and category prototypes is quantified through a causal feature classification loss, and a dynamic threshold is calculated, so that the aggregation of samples of the same category and the separation of samples of different categories are adaptively constrained in the feature space; finally, a difference loss is used to estimate the relationship between feature distribution mapping drift and loss function change, so that the causal features are reserved and the change of confused features is allowed in the model updating process. The application realizes the balanced optimization of the stability and plasticity of the bearing fault diagnosis model, has high diagnosis accuracy, has strong ability to overcome catastrophic forgetting, and is suitable for the incremental fault diagnosis task of continuously emerging new fault categories.

The invention relates to the technical field of software engineering, in particular to an automatic code review method based on retrieval enhancement generation (RAG), and relates to the technical field of software engineering, in particular to an automatic code review method based on RAG. The method comprises the steps that a vector database containing historical code repair examples is constructed, after code change fragments are encoded, similar examples are retrieved, and a retrieval result is fused to guide a generation model to complete a review task; by introducing a contrast learning mechanism, the representation capability of an encoder is optimized, so that code snippets with similar semantics are more closely distributed in a vector space, and the retrieval accuracy is improved; furthermore, retrieval data is organized by adopting a graph structure, a graph is constructed according to meta-information such as defect types, project affiliation and semantic similarity, graph-guided retrieval is performed based on the graph, and a GraphRAG method is realized. According to the method, four tasks of code problem detection, problem positioning, problem type identification and optimized code generation are automatically completed, the accuracy, consistency and interpretability of a review result are remarkably improved, and the method is suitable for intelligent auxiliary development and quality guarantee scenes in a large-scale software project.

The invention relates to a method for performing a simulation (12) for the generation of a geometric component (14), comprising the steps of: providing a first simulation file (16) of the geometric component (14); comparing the first simulation file (16) with a plurality of simulation files (18); determining a similarity between the first simulation file (16) and the plurality of simulation files (18); specifying a simulation parameter (26) for the simulation (12); selecting at least one simulation file (18) by evaluating the simulation files (18) depending on the specified simulation parameter (26) and depending on the determined similarity; identifying a change made in the selected simulation file (18) depending on the simulation parameter (26);and adapting the first simulation file (16) depending on the identified change and performing the simulation (12) with the adapted first simulation file (16) depending on the simulation parameter (26). Furthermore, the invention relates to a computer program product and an electronic computing device (10).

A computing system (100) for identifying an illusion in a generative artificial intelligence (AI) output includes processing circuitry (12) configured to receive a text output (14) generated by a generative large language model (LLM) (16) in response to an input prompt (18) including original source text data (20), and extracts entities (28A, 28B) from the text output (4) and from the original source text data (20) using an entity extraction model (26). The processing circuitry (12) forms a first semantic pair (32A) from the entities (28A) of the text output (14) and a second semantic pair (32B) from the entities (28B) of the original source text data (20) using the semantic pairing model (30), and semantically compares the first semantic pair (32A) to the second semantic pair (32B) using the semantic similarity model (38). The processing circuitry (12) classifies, based at least on the comparison (40), whether any of the first semantic pairs (32A) are illusion and outputs an indication (52, 56, 58, 60) of the classification (44).

This invention provides a software defect localization method based on enhanced embedding vector semantic representation, belonging to the field of computer technology, and solves the technical problem of insufficient semantic information representation of multimodal embedding vectors. The technical solution includes the following steps: S1: Data augmentation of the source code; S2: Constructing positive and negative sample pairs between and within modalities; S3: Text preprocessing of the defect report to obtain a text sequence; S4: Inputting the text sequence into a CodeBert pre-trained model to obtain embedding vector representations; S5: Learning the similarity within and between modalities; S6: Fine-tuning the pre-trained model by jointly performing retrieval and binary classification tasks; S7: Sorting the source code files to obtain prediction results. The beneficial effects of this invention are: through comparative learning, better embedding vector representations are obtained; and by jointly sorting the source code files using the retrieval and classification models, the effectiveness of defect localization is further improved.

A non-transitory, machine-readable storage medium containing instructions that, when executed, cause a system (400) to: Generating a training dataset (122) based on features of example workloads, wherein the training dataset (122) includes labels associated with the features of the example workloads, the labels being based on load indicators generated in a computing environment and relating to load conditions of the computing environment resulting from the execution of the example workloads; Grouping (502) selected workloads (106) into a plurality of workload clusters (118) based on features of the selected workloads (106), wherein a workload cluster (118) of the plurality of workload clusters (118) includes workloads (106) that are similar to each other according to a similarity criterion; Computation (506) of parameters (124) representing the contributions of each workload cluster (118) of the plurality of workload clusters (118) to a load condition in the computing environment, using a model (120) trained on the basis of the training data set (122), wherein the parameters (124) include a first parameter (124) representing a contribution of a first workload cluster (118) to the load condition and a second parameter (124) representing a contribution of a second workload cluster (118) to the load condition, wherein the first and second workload clusters (118) are part of the plurality of workload clusters (118); Selection of a workload cluster (118) from the multitude of workload clusters (118) based on different values ​​of the calculated parameters (124), wherein a value of a parameter (124) calculated for a selected workload cluster (118) indicates that the selected workload cluster (118) has a workload (106) that negatively affects the work performance of a workload (106) in another workload cluster (118); and Perform workload management (508) in the computer environment based on the calculated parameters (124), wherein workload management (508) includes: Determining a relative priority of the identified workload (106) over other workloads (106), and Restricting the resource utilization of the identified workload (106) in the selected workload cluster (118) in response to the determined relative priority.

Systems and methods for multi-agent artificial intelligence with shared experience repositories are disclosed. A system can obtain a set of actions generated by one or more language models based on a set of input data. The system can generate, using at least one reward model, a respective score for each action representing a degree to which the action satisfied a corresponding objective. The system can generate and store data records comprising the action data, corresponding input data, outcome data, and respective scores in a repository accessible to the language models. The system can generate a query according to an input context, select data records based on respective scores and similarity between the query and the records, and execute the language model using the selected record to generate an output action corresponding to the input context.

The invention discloses a ship field-oriented intelligent meta-model construction and dynamic adaptation method and system. The method comprises the following steps: constructing a ship field system meta-model library comprising concept, interaction and behavior meta-models; performing semantic understanding and intention recognition on natural language requirements of a user by using a large language model of an integrated domain dictionary, and extracting structured modeling elements; word vector cosine similarity and semantic distance calculation based on domain ontology are fused to generate a candidate set; a multi-objective decision model is adopted, semantic fitting degree, coupling degree and multiplexing frequency are comprehensively considered to optimize and screen the candidate set, and an optimal meta-model adaptation sequence is output; instantiating the meta-model and constructing an incidence relation; performing consistency verification including static grammar, dynamic semantics and cross-view logic on the instance set; and performing version persistent storage on the verified model. According to the method, automation and intelligence of ship domain model construction are realized, and the modeling efficiency and the model accuracy and reliability are remarkably improved.

A query is received which is to be input into a machine learning model (or other artificial intelligence model). Thereafter, a plurality of historical queries of the machine learning model meeting first criteria relative to the query is determined using a first distance-based similarity analysis technique. Each of the historical queries have a known output by the machine learning model. An output of the machine learning model responsive to query is received. Next, it is determined, using a second distance-based similarity analysis technique, whether the output meets second criteria relative to each of the known outputs corresponding to the historical queries. This determination characterizes whether the query is likely to cause the machine learning model to behave in an undesired manner and can be provided to a consuming application or process. Related apparatus, systems, and techniques are also described.

The invention discloses a dynamic language type inference method and system based on a large language model, and the method comprises the steps: obtaining a cross-function context dependency relationship of unlabeled variables through constructing a structured knowledge base containing a user definition type and a third-party library type in combination with an inter-process code slicing technology; based on structure information implied in the slices, candidate data types with similar structures are retrieved and screened from a knowledge base, the candidate data types and code contexts are jointly constructed into natural language prompts, the natural language prompts are input into a large language model, and multiple types of prediction results are generated; and determining a final type inference result by performing frequency sorting on prediction results and combining a name similarity matching and structure mapping mechanism. According to the method, the context understanding capability of the large language model is enhanced through static analysis, and the accuracy and robustness of type inference in the dynamic language are effectively improved.

The present invention relates to a system and method for automatically generating a complete and precise bill of materials by learning the structural and logical relationships between design components using a graph neural network (GNN) from heterogeneous design data sources such as 2D CAD drawings, 3D BIM models, and specifications, and by predicting and interpolating the actual quantities to be input at the time of final completion from incomplete initial design data using a generative adversarial interpolation neural network (GAIN). The effects according to the present invention are as follows. First, the present invention precisely interpolates missing attributes using a Generative Adversarial Interpolation Network (GAIN) even in incomplete situations where input data, such as drawings, BIM, and specifications, is heterogeneous and some information (thickness, material, specifications, etc.) is missing. Through this, the reliability and integrity of input data, which forms the basis of quantity calculation, can be dramatically improved even in the initial design stage where data quality is low. Second, active risk management and design quality improvement through learning design change trajectories. Unlike existing methods that simply sum dimensions on drawings or predict only the final result, this invention predicts future change risks in advance by learning the trajectory of design changes through LSTM-based time-series historical analysis. By providing real-time feedback to the designer regarding warnings and alternatives for potential change-inducing factors, it fundamentally prevents unnecessary design changes, maximizes the accuracy of completion predictions, and minimizes the risk of increased construction costs and project delays. Third, it structurally learns the physical support, connectivity, inclusion, and spatial adjacency relationships of a building through a Graph Neural Network (GNN). This enables the automatic generation of a consistent bill of materials that aligns with the structural hierarchy and engineering correlations of the entire building (e.g., the relationship between column load and foundation reinforcement quantity), rather than merely calculating the fragmentary quantities of individual objects. Fourth, by utilizing a Large Language Model (LLM), the generated bill of materials items are double-checked to ensure they logically align with text-based specifications and building codes. By comprehensively evaluating semantic similarity and logical validity, legal and technical risks are minimized by preventing errors in advance where the quantity is correct but the specifications are incorrect (e.g., standard gypsum board vs. fire-resistant gypsum board). Fifth, by applying X-ray Influence Analysis (XAI) technology to the results generated by AI, it explains, using 3D heatmaps and causal text, which object (node) on the drawing is the origin of a specific volume increase. This resolves the 'black box' problem of AI and provides a reliable environment where users can clearly trace the basis of calculations. Sixth, regarding scalability, it enables risk-based estimation by providing multiple scenarios in the form of 'average value + range of variation (confidence interval)' rather than a single predicted value. Furthermore, by linking the calculated quantity data with cost and schedule data, it provides full-cycle project management efficiency that allows for the immediate simulation of the impact of design changes on total construction costs (5D) and construction duration (4D).

The invention discloses a dialogue type recommendation method and system based on multi-source collaborative enhancement, and relates to the technical field of artificial intelligence and recommendation systems, and the method comprises the following steps: S1, multi-source feedback collection and matrix construction: extracting hidden feedback data from a dialogue context and extracting dominant feedback data from an external platform, a user and project interaction matrix is constructed based on implicit feedback, a user scoring matrix is constructed based on dominant feedback, and normalization processing is performed on the dominant feedback to improve cross-user comparability; s2, multi-source collaborative weight learning: respectively taking the user and item interaction matrix and the user scoring matrix as collaborative data input, and executing EASE learning in parallel to obtain an implicit weight matrix and an explicit weight matrix to represent an item similarity structure; according to the method, multi-source collaborative enhancement of the dialogue type recommendation candidate set is realized through EASE parallel learning of correlation weights of multi-source items, density statistics-based adaptive weighted fusion and combination of dialogue context dynamic popularity adjustment.

The invention provides a method for detecting similar vulnerabilities in firmware based on a large model. The invention provides the method for detecting the similar vulnerabilities in the firmware based on the large model. The invention provides a method for detecting similar vulnerabilities in firmware based on a large model, aiming at the problems of high false alarm rate, high manual checking cost and the like generally existing in the practical application of a binary code similarity detection technology based on deep learning due to the black box characteristic of a deep learning model. According to the method, the data dependency relationship of the variables in the key statement is analyzed, and the core instruction for triggering the vulnerability is filtered out, so that the accuracy of vulnerability semantic comparison is improved. The method comprises the steps of extracting potential vulnerability trigger statements and semantic features of known vulnerabilities, performing semantic matching on potential vulnerability signatures and known vulnerability signatures, and realizing positioning of similar vulnerabilities and tracing of vulnerability causes. According to the method, true positive samples can be accurately discriminated, vulnerability cause analysis is synchronously generated, and the complexity of manual verification is remarkably reduced.

The application discloses a large model BUG repair method based on RAG, and relates to the technical field of artificial intelligence, and comprises the following steps: constructing a basic model with target task input and output capability through an original prompt; based on a RAG knowledge base with distinguishing training sample pairs, carrying out self-distinguishing training on the basic model through a preset guide language to obtain a target model with input difference recognition capability; receiving instruction information, carrying out similarity retrieval in the RAG knowledge base according to the instruction information, and obtaining a retrieval result; generating a dynamic prompt spliced in a preset format according to the retrieval result; inputting the dynamic prompt and the instruction information into the target model, and outputting a result after defect repair. The method can dynamically correct and generalize repair errors, shorten the repair cycle, reduce the model update frequency and the calculation cost.

The invention discloses a multi-modal emotion recognition method based on a dynamic variance perception mechanism (DVAM) and truncation penalty, and belongs to the technical field of artificial intelligence and multi-modal emotion calculation. According to the method, through five core steps of multi-modal feature extraction and alignment, DVAM, graph modeling and cross-modal interaction, an index truncation similarity penalty mechanism (ECSP) and feature fusion and sentiment classification, the problems of insufficient dynamics, noise redundancy, obvious modal dominant effect and insufficient cross-modal difference modeling in the prior art are solved. DVAM realizes time sequence variance dynamic perception and weighted modulation of multi-modal features, ECSP realizes adaptive constraint of cross-modal feature similarity, and graph modeling and multi-granularity feature fusion are combined to significantly improve robustness, modal balance and emotion recognition accuracy of multi-modal fusion. And on IEMOCAP and MELD data sets, weighted average F1 values respectively reach 75.42% and 68.35% and are averagely improved by about 2.7% compared with a mainstream fusion model, so that the method has a good engineering application value.

The invention relates to a zero sample industrial fault diagnosis method based on prototype prediction, and belongs to the field of industrial fault diagnosis. Comprising the steps of performing multi-scale adaptive sparse coding feature extraction on a visible fault sample, and constructing a visible fault prototype; a variable contribution degree is quantitatively calculated by adopting a variational auto-encoder in combination with SHAP value analysis, and a variable correlation matrix is obtained based on normalized mutual information; constructing a contribution-weighted fault similarity matrix, and quantifying the similarity between visible faults and non-visible faults; using the similarity matrix and the visible prototype to predict an unseen fault prototype, and determining the fault category of the test sample through clustering and cosine similarity. According to the method, the average accuracy rate of TE process diagnosis tasks is high, high-precision unseen fault diagnosis can be achieved only by depending on simple fault description, the problems that an existing method excessively depends on domain knowledge and is insufficient in generalization ability under complex working conditions are solved, accurate diagnosis of unseen fault samples and detailed semantic attributes is not needed, and an effective solution is provided for industrial fault diagnosis.

The invention discloses a model interpretation-based binary code similarity detection robustness evaluation method, which comprises the following steps of: training a mixed regression model as a locally interpretable agent model, and introducing a fusion lasso regularization item to approximate a local decision boundary of a target model; according to the method, the internal structure and parameter information of the target model do not need to be obtained, black box evaluation is achieved, and the limitation of an existing gradient-based method in a real black box scene is solved. According to the method, the proxy model is used for obtaining the feature importance weight, the instruction feature mapping module is innovatively introduced, the module can process basic block or graph node features of different granularities and accurately map the basic block or graph node features to specific instructions, direct positioning from model decision making to key instructions is achieved, and the method is high in practicability and easy to popularize. According to the method, the evaluation result is quantified through multi-dimensional indexes such as the attack success rate and the disturbance efficiency, so that the evaluation conclusion is more scientific and reliable.

System for analyzing technical intellectual property documents using AI, comprising: a) input of a technical description, b) generation of a semantic representation, c) comparison with existing intellectual property rights, d) evaluation and output of the similarity.

This invention discloses an intelligent review method based on AI grouping of text similarity, belonging to the field of review and analysis technology. The method includes the following steps: obtaining the scale text of a power engineering project and extracting features to generate scale semantics; aligning the scale semantics with entities in a technical specification knowledge graph to obtain a technical specification text set and extracting material quantity requirement names; determining the similarity between the material quantity requirement names and the names of materials to be reviewed, and establishing a candidate matching set; obtaining the material category inclination rate of the names of materials to be reviewed by analyzing the category characteristics of material quantity requirements; reconstructing the candidate matching set based on the material category inclination rate and adding material usage for approval review. This invention aims to solve the problems of review difficulties and low accuracy caused by non-standard semantic expression in engineering documents during intelligent review of power materials.

The invention relates to the field of artificial intelligence testing, in particular to an automatic testing method and system for a multi-modal large model.The method comprises the steps that a reference multi-modal sample is obtained, the reference multi-modal sample comprises first modal data and second modal data, and the first modal data comprises a core semantic entity; generating a corresponding causal intervention problem based on the core semantic entity; automatic editing is executed on the first modal data to remove the core semantic entity, an anti-fact multi-modal sample is generated, and the image structure similarity of the anti-fact sample and the reference sample beyond the area where the core semantic entity is located is higher than a preset threshold value; respectively inputting the reference sample and the anti-fact sample into a multi-modal large model, and obtaining two output answers of the multi-modal large model to the causal intervention problem; quantifying the causal sensitivity of the multi-modal large model to the core semantic entity by calculating the difference degree between the two output answers; and generating a robustness evaluation report of the multi-modal large model based on the causal sensitivity.

Systems, software, and computer implemented methods for building a terminology dictionary are disclosed. A process including providing one or more documents to a generative artificial intelligence (AI) model for analysis; obtaining, using the generative AI model, a set of terms extracted from the one or more provided documents; generating, using the generative AI model, a definition for each term of the set of terms; identifying, using the generative AI model, two or more similar terms from the set of terms based on identifying semantic similarity between respective definitions of the two or more similar terms; generating, using the generative AI model, a consensus term, the definition being generated based on the respective definitions of the two or more similar terms; and providing the consensus term and the definition for the generated consensus term to store in the terminology dictionary.