64 results about "Similitude" patented technology

Method and system for analyzing at least one computing system for supply chain vulnerabilities of at least one machine learning model include configuring machine learning model and optionally additional data; decomposing operations of the machine learning model's computational graph into smaller decomposed components; associating properties of each decomposed component with properties of the original operations and associating additional data; detecting the semantic similarity of decomposed component and previously encountered decomposed components; converting decomposed components into a standardized representation; calculating signature of decomposed components; evaluating whether portions of the machine learning model are similar to previously calculated signature; testing for supply chain and model vulnerabilities that exist based on previous signatures; identifying vulnerabilities that persist and correlating defenses; storing the generated signatures, identified vulnerabilities, and identified defenses; and generating report detailing the machine learning model's supply chain, vulnerabilities, and defenses.

The invention belongs to the technical field of artificial intelligence and natural language processing, and discloses an NL2SQL model training and storing method and device based on a GRPO reward function. According to the method, a high-quality training data set is constructed, and the training effect and the generation performance of the model are effectively improved in combination with grammar verification, execution verification and semantic consistency screening; according to the method, the GRPO is adopted as a basic framework, and a combined reward function with multiple dimensions of coverage execution accuracy, grammar legality, semantic similarity, mode link and the like is designed; according to the method, a staged course learning strategy is designed, the sub-reward functions are activated and adjusted in a staged mode, the model is guided to be gradually transited to semantic understanding and execution optimization from structure specifications, and the generalization ability is improved; meanwhile, a reward weight dynamic adjustment mechanism is introduced, the weight of a reward function is automatically adjusted when SQL query execution fails, and the stability and sensitivity of training feedback are enhanced.

The invention discloses a multi-dimensional example selection method and system applied to a numerical reasoning task, and relates to the technical field of natural language processing, and the method comprises the steps: employing a plurality of demonstration problems and corresponding demonstration code thinking chains to form a plurality of training demonstration examples; dividing an ordered positive example group and an ordered negative example group by adopting a large language model based on the prompt answer accuracy determined by each training demonstration example; performing model training based on the training query problem, the ordered positive example group and the ordered negative example group through a to-be-trained example scoring model according to similarity, uncertainty and complexity, and determining a trained example scoring model; when the target query problem is determined, candidate demonstration scores of candidate demonstration examples corresponding to the target query problem are determined through the trained example scoring model, and a target demonstration example is selected. On the basis of the scheme, the programmed thinking is introduced to generate examples to perform multi-dimensional collaborative evaluation on the examples, and the example scoring model is optimized through inter-group differences, so that the reliability of example selection is improved.

The invention discloses a similarity comparison-based large model supply chain automatic restoration method and device, and the method comprises the steps: firstly carrying out the semantic coding of an original vulnerability code through a pre-training model, and constructing a semantic and structure parallel dual-channel representation in combination with an abstract syntax tree and other program structures; cWE type intelligent classification is performed on vulnerabilities by using a locally deployed large language model subjected to LoRA fine tuning, and meanwhile, a zero sample semantic matching mechanism is introduced, so that the recognition capability of unknown vulnerability types is improved. And searching the closest historical case from the knowledge base through similarity vector comparison, and extracting a repair abstract to construct a model to generate a prompt. Patch codes and repair instructions are generated through a large model, automatic filing and knowledge base updating are supported, and the continuously-enhanced automatic repair capacity is achieved. The method can be widely applied to automatic vulnerability repair scenes of supply chain components such as large model plug-ins, code interfaces and dependent packages, and the safety, functionality and interpretability of code repair patches are greatly improved.

The invention discloses a code review comment generation method and system based on reinforcement learning, belongs to the technical field of crossing of software engineering and artificial intelligence, and aims to solve the technical problem of how to improve the accuracy, efficiency and expandability of code review and overcome the defects that an existing tool is low in comment quality and poor in practicability. According to the technical scheme, the method comprises the steps of collecting and preprocessing data of code differences, human comments and real correction codes, and constructing a data set; code review comments are generated, specifically, a pre-trained large language model LLM is finely adjusted through the data set, code difference data are collected, and the review comments are obtained; semantic similarity reward: calculating the semantic similarity between the generated comment and the real comment, and generating a reward signal Rsematic; the generated comment and code difference is input into a code optimization model, a corrected code patch is generated, the similarity between the generated patch and a real patch is evaluated, and a reward signal Rtask is generated; performing reinforcement learning and fine tuning on the large language model LLM; and deploying and generating comments.

The invention relates to the technical field of intelligent education systems, in particular to a subjective question automatic correction method based on multi-technology fusion, which comprises the following steps of: firstly, identifying whether a question is a strong proposition or not through a regular expression, and then performing knowledge point extraction, off-question judgment and double similarity evaluation on the strong proposition question; plagiarism detection, cosine similarity calculation and user-defined rounding are carried out on all the questions, and finally personalized comments are generated and correction results are output. According to the method, through double similarity evaluation, semantic relevance between answers and standard answers as well as questions is comprehensively considered, the misjudgment rate is remarkably reduced, meanwhile, through strong proposition recognition, knowledge point extraction and double similarity evaluation, the pertinence and accuracy of correction are remarkably improved, whether the answers of students meet the requirements of the questions or not can be deeply analyzed, and the correctness of the questions is improved. Misjudgment caused by insufficient semantic understanding in the prior art is avoided, and the method is particularly suitable for accurate scoring of strong proposition questions in subjective questions.

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 invention provides an active man-machine cooperation method driven by process knowledge and interactive semantics, and the method comprises the steps: carrying out the step-by-step optimization and updating of a general task description text and a dynamic assembly task interaction description text in the manufacturing field, and obtaining an initial generation result; performing evaluation according to a semantic similarity classification standard and a real label to obtain a final generation result, performing observation sampling on a posture sequence when an operator implements an assembly behavior according to the generation result to obtain observation postures and dynamic scene semantic information, and extracting features to obtain a diffusion matrix; further processing to obtain an inherent matrix and a weight matrix to form point matrix features, mapping the point matrix features to a Gaussian distribution coding set feature map, sampling potential coding factors, mapping the sampling potential coding factors to a posture sequence to obtain a current posture sequence, predicting to obtain an operator assembly behavior prediction result, and combining an assembly environment state and an assembly task state to obtain an operator assembly behavior prediction result. Intelligent agent actions and operator assembly behaviors are evaluated, current state and reward function feedback are provided for the intelligent agents, and the robot is controlled to move.

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.

The invention provides a code similarity review method based on artificial intelligence, and belongs to the field of artificial intelligence and software engineering.The code similarity review method comprises the steps that semantic features of codes are extracted through a deep learning model, code similarity classification is conducted through a machine learning model, the semantic features of the codes can be automatically learned, and the similarity of the codes is detected; the problems of potential code plagiarism, code reuse, code vulnerabilities and the like are identified, and the accuracy, efficiency and expandability of code similarity review are improved.

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.

A large language model-oriented multi-sample attack detection and defense method relates to the field of artificial intelligence security. A multi-level text screening and intervention mechanism is constructed to reduce the impact of multi-sample attacks through input content deduplication, format adjustment and context disturbance. Similarity analysis is performed on the text to identify highly repetitive examples, which are screened using an efficient matching strategy. The semantic features of the text are mapped using a pre-trained model, and historical data are compared to determine whether there is a potential inducement risk. The multi-round dialogue structure is analyzed, and the user and system interaction mode is extracted and analyzed to dynamically adjust the detection rules and improve the adaptability to different format inducement attacks. For high-risk text, deletion and truncation strategies are adopted, and for some medium-risk text, the order is adjusted or interference information is inserted to reduce its impact. The safety of LLM in complex interactive environments is improved, and the generation of non-compliant content is reduced, which is efficient, low in false positives and scalable.

The invention relates to a computer-implemented method for inspecting or operating a first product (TD1), the following steps being carried out: a) transmitting a provided global model (GM) of the first product (TD1) or the operation thereof from the server (S) to the first client (C1) and second client (C2), b) capturing a first data set (DS1) of the first product (TD1) or the operation thereof with first product parameters of the first product (TD1) as respective first subsets (C1.1-C1.3), and generating and training respective first local models (LM1.1-LM1.3) with the respective first subsets (C1.1-C1.3), c) capturing a respective second data set (DS2) of the respective second product (TD2) or the operation thereof with respective second product parameters of the respective second product (TD2) as respective second subsets (C2.1-C2.3), and generating and training respective second local models (LM2.1-LM2.3) with the respective second subsets (C2.1-C2.3), d) performing a similarity analysis between models of the first and the second local models (LM1.1-LM1.3, LM2.1-LM2.3), and assigning these similar models to a common model group (G1-G3), e) training a global detail model (M1) on the basis of the model of the common model group (G1-G3) and transmitting same to the first client (C1), f) applying the detail model (M1) to the first product (D1) for inspection or operation thereof, by the first client (C1).

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).

This invention relates to a method and system for decompiling optimized code based on deep learning. The method includes the following steps: obtaining a low-level intermediate language (LIR) and a high-level intermediate language (HIR) using a low-level programming language (LPL) and a high-level programming language (HPL) as training datasets; training a deep learning model using the training datasets to learn the mapping rules between LIRs and HIRs; using the trained deep learning model to translate the LIR of the LPL to be decompiled into the HIR; performing data flow recovery and control structure recovery on the HIR obtained by the deep learning model to generate HPL code; and using a similarity matching algorithm to find source code similar to the generated HPL code, transferring the semantic information from the source code to the generated HPL code. This invention can automatically convert LPL to HPL and has high accuracy for both optimized and non-optimized binary decompilation.

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.

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.

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.