52 results about "Semantic change" patented technology

The invention provides a text segmentation method and related equipment. The method comprises the steps of obtaining a to-be-processed text; segmenting the to-be-processed text into ordered statement sequences to obtain an initial statement set of the to-be-processed text; wherein the ordered statement sequence comprises a plurality of statements; the semantic variation, the confusion degree variation and the information entropy variation of a first target text block are calculated when a to-be-decided statement in an initial statement set of the to-be-processed text is added into the first target text block, and the first target text block is a set of multiple statements meeting a merging condition; determining the collaboration degree of the statement to be decided and the first target text block based on the semantic variable quantity, the confusion variable quantity and the information entropy variable quantity; and partitioning the to-be-processed text based on the collaboration degree of the to-be-decided statement and the first target text block to obtain a target partitioned text of the to-be-processed text. The text segmentation quality can be improved.

The invention discloses a remote sensing image semantic change detection method based on semantic enhancement Transform and three-dimensional convolution, and aims to solve the problems of insufficient semantic and change information fusion and difficult narrow and long ground feature feature extraction in the existing method. According to the method, an SET-3DC network is constructed, 'feature extraction-feature interaction-semantic enhancement-change information fusion 'is taken as a core link, multi-scale dual-time-phase features are extracted through a dual-branch feature extractor (DFE), cross-branch feature interaction is realized through a channel feature exchange module (CFE), and multi-scale dual-time-phase features are extracted through a multi-scale dual-time-phase feature extraction module. A semantic branch decoder (SEAA-SD) based on semantic enhancement and axial attention strengthens local details, global semantics and narrow and long ground feature features, a change information extraction module (CIE) based on three-dimensional convolution fuses multi-source change information and aligns time-space correlation, and a network is optimized in combination with a joint loss function. Through multi-module cooperation and innovative structural design, the precision and internal consistency of semantic segmentation and change detection are improved, and the method is suitable for a high-precision remote sensing image semantic change detection scene.

The invention relates to a business data processing method and system, equipment and a medium. The method comprises the following steps: preprocessing multi-source heterogeneous cross-domain economic data to generate a standardized data stream; semantic drift in the standardized data flow is detected in real time, and a detection result is generated; semantic alignment judgment is carried out based on the detection result, and a dynamic alignment signal is generated; performing incremental training of a mapping model by using the dynamic alignment signal to generate an updated cross-domain mapping model; and finally, performing mapping conversion on the data stream based on the updating model, and outputting service data with unified semantics. By adopting the method, the semantic change in the economic data can be responded in real time, the problems of semantic drift detection lag, long model updating period and high maintenance cost in the traditional technology are effectively solved, and the accuracy and timeliness of cross-domain economic data processing are remarkably improved.

The invention provides a sensitive data discovery method based on complex semantic analysis, which innovatively introduces high-dimensional sparse Fourier transform (HSFT), maps semantic characteristics to a frequency domain space, captures semantic change frequency characteristics (such as high-frequency mutation characteristics of sensitive information) which are difficult to recognize by traditional deep learning, and improves the recognition accuracy of the sensitive data. Sensitive information and non-sensitive information in similar contexts are effectively distinguished, and the problems of high misjudgment rate, lack of dynamic adaptability and unreliable risk assessment in complex contexts in the prior art are solved.

The invention relates to the technical field of image processing and computer vision, in particular to a remote sensing image semantic change detection method based on comparative learning of pseudo tag guidance, which comprises the following steps: constructing and training a remote sensing image semantic change detection model, and inputting an image to be processed into the trained remote sensing image semantic change detection model to obtain a detection result; the remote sensing image semantic change detection model comprises a double-branch encoder module, a semantic consistency feature enhancement module, a double-branch semantic decoder module, a binary change classifier, a category condition false label generation module and a cross-time phase comparison learning module. According to the method, the precision of semantic change detection is improved, and the dependence on large-scale manual annotation data is reduced.

The invention provides a semantic communication method and system based on multi-modal perception, and the method comprises the steps: obtaining multi-modal information, carrying out the semantic extraction of the multi-modal information, and generating a corresponding current semantic representation; performing semantic association on the current semantic representation and historical semantic information to obtain context enhanced semantic information; determining a semantic difference degree or a semantic change trend between the current semantic representation and historical semantic information based on the context enhanced semantic information to generate a key frame semantic description; semantic processing and semantic completion are carried out on the semantic description of the key frame; and according to a set context constraint condition, performing conditional semantic restoration on the complemented semantic description of the key frame by using a multi-modal model, and outputting auxiliary decision information or prompt information based on a restoration result. According to the method, the multi-modal data transmission bandwidth requirement is reduced, and meanwhile, the robustness and continuity of semantic communication in a complex channel environment are improved.

The invention relates to a semantic change detection method based on text assistance and comparative learning. The method comprises the following steps: 1, acquiring remote sensing images acquired in different time phases in the same area, and inputting a twin multi-scale encoder with shared parameters to extract multi-stage features; 2, a pre-training vision-language model and a text encoder are introduced in the training stage, a text describing changes is generated, high-level visual features are injected, migration features are obtained, and reconstruction constraints based on comparative learning are constructed; 3, constructing a context and channel perception fusion module to carry out adaptive fusion on the multi-scale features; 4, designing a multi-scale decoder to recover the spatial resolution and outputting a semantic change graph; and 5, performing end-to-end optimization on the network by adopting a joint training target consisting of spatial mask supervision loss and reconstruction loss. The method is suitable for scenes such as remote sensing monitoring, disaster assessment and urban dynamic analysis.

The invention discloses a software testing method and system based on a data analysis platform, and particularly relates to the technical field of software testing, and the method comprises the following steps: tracking business semantic change by constructing a semantic evolution perception map, and establishing a semantic-driven data label linkage mechanism to maintain the consistency of training samples of a defect recognition model; semantic consistency drifting is monitored, model output is controlled, a map-enhanced test case generation mechanism is introduced to achieve semantic synchronous generation, meanwhile, a semantic regression verification process is set to ensure alignment of a test case and evolution semantics, and a closed-loop test process covering a full path is formed; according to the method, semantic-driven label linkage and model synchronous updating are realized by constructing the semantic evolution perception map, and a map-enhanced test case generation and regression verification process is introduced, so that the test process is ensured to be consistent with the service semantic dynamic state, the defect identification accuracy and the test coverage integrity are improved, and the test efficiency is improved. The method is suitable for software quality guarantee in a continuous delivery environment.

The application provides a sensitive data discovery method based on complex semantic analysis, which innovatively introduces high-dimensional sparse Fourier transform (HSFT), maps semantic features to a frequency domain space, captures semantic change frequency characteristics (such as high-frequency mutation characteristics of sensitive information) that are difficult to identify by traditional deep learning, effectively distinguishes sensitive and non-sensitive information in similar contexts, and solves the problems of high misjudgment rate, lack of dynamic adaptability and unreliable risk assessment in the prior art in complex contexts.

This invention relates to a method for constructing a disaster-bearing entity based on a structure-function-behavior model, comprising the following steps: S1 entity structural semantic modeling; S2 entity functional semantic modeling; S3 behavioral semantic modeling; S4 constructing a semantic fusion module and building urban natural disaster risk factor data and knowledge data, and using the risk factor data and knowledge data to fuse the semantics formed in the models built in steps S1-S3 to realize the construction of the disaster-bearing entity. The method also includes a data and mechanism-driven twin model update method, specifically including: updating the twin model using a change detection model, and update management, wherein the change detection model includes the detection of structural and semantic changes. The method also includes a disaster risk prediction method, which uses a hybrid approach consisting of decision trees and node data formed by urban natural disaster risk factor data and knowledge data. This achieves data analysis and prediction of urban entity disaster situations with visualization of the sum of structure-function-behavior factors.

The invention provides a key frame generation method and device based on a semantic change degree and a semantic communication system, and the method comprises the steps: obtaining multi-modal perception data at a current moment, and carrying out the semantic coding of the multi-modal perception data, so as to generate a current semantic representation; determining a semantic change degree according to the current semantic representation and pre-acquired historical semantic information, wherein the semantic change degree is used for quantifying the change degree of the current semantic state relative to the historical semantic state; and comparing the semantic change degree with a preset change threshold value, judging that the current moment is a key frame according to a comparison result, triggering to generate a key frame semantic description, performing semantic coding based on the generated key frame semantic description, and sending the semantic coding result to a receiving end through a communication channel. According to the method, generation and sending of the semantic description of the key frame can be triggered in a self-adaptive manner, so that the communication overhead is effectively reduced on the premise of ensuring the integrity of the key semantic information, and the stability and the real-time performance of a semantic communication system in a complex environment are improved.

This invention relates to the field of semantic processing technology, specifically to a large-scale adaptive training method and system based on task semantic awareness. The method includes the following steps: acquiring text structure information, extracting batch semantic vectors to determine consistency, tracking semantic differences across steps to form a trajectory, merging stage boundaries, locating abnormal nodes and verifying loss gradients, and mapping parameter tuning instructions into an adaptive training control structure. In this invention, through structured semantic expression and a real-time feedback mechanism, the training process can be dynamically adjusted to adapt to changes in task semantics, avoiding semantic shift and inconsistency issues. Precise labeling of semantic states and monitoring of change trajectories enable the model to adjust training strategies in a timely manner at different semantic stages, thereby improving training efficiency and stability. Accurate location of key nodes allows training to focus on training steps with significant impact, avoiding ineffective training. Through semantic-driven parameter adjustment and training control, the model's adaptability to complex tasks and resource utilization are improved.

The application discloses a medical dialogue understanding and generation method based on a Transformer model, and comprises the following steps: medical text, structured medical record data and historical dialogue content are extracted, and unified semantic representation is generated through embedding mapping; various embedding representations are input into a Perceiver structure containing a cross-attention mechanism to perform cross-source information fusion, and unified latent semantic vectors are obtained; a semantic state evolution path function is constructed based on a neural ordinary differential equation; a dialogue round is introduced as a time variable to model the dynamic evolution process of the semantic change with the round; a context control semantic vector is constructed in combination with the current semantic state and the historical context, and the natural language generation model is guided to generate initial reply text; and finally, the final medical dialogue response text is output through semantic trajectory consistency and medical entity reference consistency verification. The application has strong context modeling capability.

The invention provides a universal remote sensing image change detection method for binary change detection and semantic change detection, and the method comprises the steps: employing a dynamic rare category perception sampling module, evaluating the rare degree of each semantic category, carrying out the weighted sampling of a dual-time-phase image pair, and forming a training set; inputting the double-time-phase image pair into a multi-scale attention enhancement encoder sharing a weight, carrying out feature extraction, and constructing a low-level difference feature and a high-level difference feature; splicing the two to obtain a comprehensive change representation, respectively inputting the comprehensive change representation to a change detection solution head and a contrast learning module, outputting a change detection result by the change detection solution head, and establishing a contrast learning loss by the contrast learning module; based on the semantic change detection loss, the binary change detection loss and the contrast learning loss, establishing an overall loss function for training; and inputting the to-be-detected dual-time-phase image pair into the general change detection model to obtain a corresponding change detection result.

The invention discloses a policy graph dynamic updating method and device, and the method comprises the steps: obtaining a policy document, obtaining a historical related document according to the policy document, and judging whether the policy document forms an updated document of the historical related document or not based on the matching of a preset updating keyword rule base and / or based on the similarity calculation of a semantic vector; if it is determined that the updated documents are formed, extracting second knowledge of the updated documents through the first semantic model, collecting the updated documents, and accumulating vocabularies or semantic variations based on the updated documents; when the accumulated vocabulary or semantic variation meets a preset model training trigger condition, performing incremental training on the first semantic model based on the gathered update document and historical document to obtain a second semantic model, and replacing the first semantic model; and based on the second knowledge, updating the historical policy atlas to generate a target policy atlas, and replacing the historical policy atlas with the target policy atlas. According to the invention, automatic and intelligent dynamic updating of the policy knowledge graph is realized.

This invention discloses a remote sensing change detection method based on spatial-frequency difference modeling and bidirectional semantic consistency coupling. First, multi-temporal remote sensing images are preprocessed, and the preprocessed images are input into a shared encoder to extract a multi-scale feature pyramid. Then, cross-temporal difference features are constructed, obtaining frequency-guided enhancement features in the frequency domain and spatial structure enhancement features in the spatial domain, which are fused to form a joint spatial-frequency difference feature. Next, boundary difference cues are constructed, and a structure confidence map is generated through Gaussian-edge guidance, which is used to perform gated interaction on the cross-temporal features. Finally, a bidirectional semantic consistency coupling decoding mechanism is used to achieve collaborative inference between the change detection branch and the semantic segmentation branch, ultimately outputting the semantic change detection result. This invention can reliably extract and represent changed regions and their semantic change information under complex conditions such as imaging differences, texture perturbations, and slight registration errors in multi-temporal remote sensing images.

The embodiment of the application relates to the technical field of multi-agent communication, and specifically discloses a communication method and system based on multi-agent semantic cooperative evolution. The embodiment of the application initializes semantic states for multiple agents; locally updates the semantic states; when a communication triggering condition is met, corresponding agents generate communication messages according to semantic change amounts; cooperatively updates the semantic states; and dynamically adjusts the communication triggering condition, communication frequency and communication content selection strategy of subsequent time steps. Through semantic state modeling and a cooperative evolution mechanism, the embodiment of the application can depict semantic interaction relationships between agents, enable semantic information to continuously evolve at a group level along with a cooperation process, combine communication strategies with semantic cooperative evolution states, realize adaptive adjustment of communication parameters, thereby reducing communication redundancy, improving semantic consistency, and enhancing the cooperation efficiency and operation stability of multi-agents in a complex dynamic environment.

The application provides a pedestrian re-identification method and equipment based on a mixed attention decoupling re-identification network, so as to enhance the discrimination ability of field-invariant pedestrian features, thereby forming reliable class boundaries and learning the in-class semantic diversity. The design of the mixed attention module in the method is to strengthen the field-invariant feature expression in the form of attention weight decoupling from the spatial and channel perspectives, which forces the network to automatically use the image regions and attribute clues conducive to cross-domain re-identification. In addition, based on the enhanced field-invariant feature expression, a multi-difficult sample memory learning strategy is proposed to improve the in-class diversity of target domain samples. The application optimizes the feature learning process by updating the reliable sample memory library and multiple difficult sample memory libraries, and by considering the relationship between samples in the same class, the application can be used to capture significant in-class semantic changes, and can positively affect the accuracy of pseudo labels.

This invention discloses a method and system for image comparison and retrieval of power equipment based on semantic object relationships. The method first acquires images of the power equipment and uses cosine similarity to obtain normal images for comparison from a standard library. An instance segmentation model is used to obtain an object mask set. This mask set is then mapped to a two-dimensional space to obtain an attention affinity matrix and calculate a semantic alignment score. The mask set is processed to construct an attribute graph, and a rotation-invariant spatial consistency score is calculated. Visual features and text embedding features are acquired, projected, added, and input into a Transformer architecture to obtain fused features. Text attributes are obtained through an encoder, and attribute similarity is calculated. Finally, a comparison score is calculated for intelligent fault diagnosis. This invention improves robustness to geometric transformations and semantic changes, making it suitable for scenarios such as intelligent operation and maintenance of power equipment, and significantly improving the accuracy and robustness of retrieval.

The application discloses a contract compliance review method and system based on multi-agent cooperation, and relates to the technical field of intelligent review, comprising the following steps: collecting contract text and corresponding context information, establishing a continuous semantic trajectory in chronological order, which is used to provide a basic semantic reference for subsequent semantic analysis and compressed difference comparison; based on the continuous semantic trajectory, the change range of expression strength and responsibility expression is analyzed, semantic change points are extracted and a semantic difference anchor point list is generated, and the semantic change trend is recorded, which establishes a reference basis for semantic consistency detection of compressed content. Through multi-agent collaborative semantic analysis and dynamic compression adjustment, the application realizes semantic continuity and logical consistency of contract text in high-concurrent compressed transmission. Through semantic trajectory and anchor point tracking, the application avoids clause mismatch caused by compression aliasing, and realizes real-time semantic compensation by combining compressed deviation distribution and rhythmic compression, thereby guaranteeing stable, accurate and traceable review results.

This application relates to a method for constructing a deeply coupled end-to-end urban 3D semantic change detection strategy. The method includes: firstly, constructing an encoder semantic change method to add a semantic decoder to existing 3D change detection methods to obtain land cover category information, while simultaneously decoding change and semantic information; secondly, constructing a decoder semantic change method based on Siamese networks to extract semantic change features and assist in the implementation of 3D semantic change detection; thirdly, fusing the encoder and decoder semantic change methods to construct a fused semantic change method; and fourthly, discussing the principles and mechanisms of each semantic change method, and based on the discussion results, forming an efficient end-to-end urban 3D semantic change detection strategy. This solves the problems of existing 3D semantic change detection methods being unable to detect "from-to" semantic changes and the difficulty in effectively coupling semantic segmentation and change detection at the model mechanism level.

The invention discloses a remote sensing semantic change detection method based on language-guided comparative learning and difference enhancement, and relates to the technical field of remote sensing image processing, computer vision and deep learning. Comprising the following steps: step 1, inputting and preprocessing a dual-time-phase remote sensing image; step 2, multi-scale feature extraction of the hybrid image encoder; 3, the change structure characteristics of the difference enhancement module are enhanced; 4, change category language prompt construction and text feature coding are carried out; step 5, performing comparative learning optimization of vision-language feature alignment; step 6, carrying out joint loss and end-to-end training; according to the method, the semantic change detection precision superior to that of an existing method is obtained on various public data sets, and particularly, better robustness and generalization ability are shown in complex scenes such as more false changes and fuzzy category boundaries.

The invention belongs to the technical field of software security and program analysis, and particularly discloses a function semantic abstract increment updating method based on call chain influence analysis, which comprises the following steps of: constructing a function call graph of an initial code, determining a processing sequence according to a topological sequence of the function call graph, generating and storing initial semantic abstracts corresponding to all functions, constructing an initial semantic abstract library; analyzing the code difference between the new code and the initial code, and identifying changed and newly added functions to determine an affected function set and obtain an update processing sequence; generating a new semantic abstract of each influenced function based on the updating processing sequence, performing semantic comparison on the new semantic abstract and historical abstracts in a semantic abstract library, and updating the semantic abstract library when semantic change is determined; and updating version information of the semantic abstract library, and outputting a latest function semantic abstract set and an abstract change report. According to the method and the device, increment updating can be quickly carried out while the accuracy of generating the abstract is ensured to be improved.

The application discloses an engineering construction site real-time three-dimensional modeling method based on unmanned aerial vehicle aerial image, relates to the technical field of computer vision, and comprises the following steps: collecting oblique image data and high-frequency pose data, acquiring sparse key point features, deep semantic features and high-frequency time sequence features, generating a three-dimensional space point cloud model, identifying a low-confidence area, comparing the three-dimensional space point cloud model with a dynamic semantic three-dimensional model of the last period as a reference model to identify a semantic change area and a semantic state conversion conforming to a preset construction logic, constructing a dynamic semantic three-dimensional model of the current period, and generating an unmanned aerial vehicle flight parameter adjustment instruction. The application improves the three-dimensional modeling quality through cross-view semantic consistency verification, interprets progress changes based on the construction logic, combines a building information model and time sequence prediction, solves a multi-objective optimization function, decides unmanned aerial vehicle collection work, and provides high-confidence data support for construction site management.

The application discloses a crowd-sourcing mode point cloud semantic generation method, medium, equipment and product, relates to the field of map semantic generation, and comprises the following steps: acquiring point cloud, image, IMU and positioning data from crowd-sourcing data, and constructing a plurality of local maps of collection sources; in an absolute world coordinate system, optimizing the local map pose and splicing into a global map; mapping pixel semantic labels to corresponding single-frame point cloud, projecting semantic information of the single-frame point cloud to the local map, and projecting the local semantic map to the global map; when the observation times and angles of target point semantics in the global map meet preset conditions, the target point is given a semantic initial value; if the point with the semantic initial value is observed again, the observation angle, times and semantics are updated, the semantic change and update times are recorded, the semantic confidence of the point is calculated, the stable semantic region is judged, the point cloud semantics of new crowd-sourcing data are directly assigned in the stable semantic region, and the automatic generation of the point cloud semantics is realized.

The invention discloses an intelligent processing method for logistics operation logs of medical institutions, and relates to the technical field of operation log processing. The method comprises the following steps: collecting multi-source log data, and carrying out time serialization and semantic coding processing to generate a log semantic vector; establishing a semantic rheology matrix of time and tasks, calculating a semantic change rate and correlation intensity, and generating a multilayer fractal logic map; logic similar task pairs are identified, a task symmetry layer is constructed, and a semantic coupling channel is established; based on the semantic rheology matrix and the task symmetry layer, generating a time sequence reflection rule, comparing a prediction path with an actual execution path, and calculating a path deviation residual value; and triggering a self-evolution residual error correction mechanism to obtain a path correction result, and executing semantic feedback resonance operation. According to the method, intelligent analysis and self-learning optimization of logistics operation logs of medical institutions are realized, and task execution consistency, semantic understanding depth and operation management efficiency are improved.

The invention mainly relates to the technical field of semantic recognition, and provides a semantic risk assessment and restoration method based on a multi-modal semantic fingerprint in order to carry out real-time dynamic monitoring and verification on a prompt injection attack semantic intention, the core of the method is that the multi-modal semantic fingerprint is acquired based on a text input by a user, and the semantic risk assessment and restoration method is applied to the text judged to be semantic anomaly. Constructing a semantic change track based on the multi-text modal features of the text and the historical text modal features, and calculating the semantic drift degree of the current text relative to the historical text based on the semantic change track; performing intention consistency verification, and calculating an intention consistency score; obtaining a long-term semantic behavior difference between the current semantic text and the user based on the multi-modal semantic fingerprint of the current text; and calculating the semantic risk of the current text based on the semantic drift degree, the consistency score and the semantic behavior difference, and outputting or repairing the texts of different risk levels according to a formulated repairing strategy to realize real-time risk adjustment for different users under different contexts.

The application discloses a kind of social media network slang semantic change automatic detection and interpretation method and system, two stages of entire scheme, through two stages automatic detection and understanding social media comment in network slang semantic change phenomenon, in the first stage, by the distance of the corresponding vector representation of word in different corpus, can find the word that occurs changes in semantics (i.e. Network slang);Second stage, use multi-modal information can generate network slang explanation text, so as to accurately translate the real meaning of network slang.

This invention discloses a semantically aware KV Cache management method. It constructs a semantically aware KV Cache management model for the reasoning process of large-scale Transformer architecture models. Based on deepest-layer attention drift detection, it determines the segmentation point and synchronizes across all layers after triggering semantic segmentation. Combined with four-region caching, it performs cache compression, transforming the cache management process from fixed-position truncation to a dynamic process based on semantic changes. Through the collaborative updating of initial blocks, Top-K blocks, temporary blocks, and active blocks, this method can balance the preservation of historical key information, maintenance of current semantic continuity, and cache occupancy control during long-context reasoning, thereby improving cache management efficiency and reasoning stability. It solves the problems of rapid growth in KV Cache memory usage with increasing sequence length during long-context reasoning of large language models, the tendency of existing compression methods to truncate the context at fixed physical positions and cause semantic fragmentation, and the impact of inconsistent multi-layer cache updates on reasoning stability.

Methods, systems, and devices for data management are described. A data management system may generate, at a first time, an ontology defining a structure and one or more relationships between one or more columns across a set of tables included in a database of a data management system. In some examples, the data management system may receive, at a second time that is later than the first time, an input to access at least one column of the one or more columns of the database in the data management system, where accessing the at least one column may correspond to a semantic change to the metadata of the database. The data management system may determine whether the ontology is updated to reflect the semantic change to the metadata of the database. The data management system may then generate a validation result based on determining whether the ontology is updated.