206 results about "Sequence processing" patented technology

The invention provides an image restoration and super-resolution reconstruction system and method based on deep learning, and belongs to the technical field of digital image processing. The invention aims to solve the problems of high calculation complexity and resource consumption, limitation of long sequence processing, high training difficulty and texture scene deficiency when a multi-scale residual network based on a Transform architecture is used for image resolution conversion. The reconstruction system comprises: an image preprocessing module performing window division and video memory optimization on an input low-resolution image; the multi-layer fusion network dynamically adjusts the characteristics of the low-resolution image, captures channel information in different scenes, performs interactive fusion, performs comparison supervision, establishes an information communication channel, dynamically adjusts and optimizes parameters through negative feedback, and obtains a super-resolution image. And the loss function module maximizes the similarity of the super-resolution image and the high-resolution image in the segmentation feature space to obtain a final super-resolution image.

The invention belongs to the related technical field of artificial intelligence, and discloses a robot time sequence imitation learning method and system based on a Mama coding complete history, and the method comprises the steps: receiving a multi-modal observation sequence in a task execution process of a robot, the multi-modal observation sequence comprising observation data of at least one sensor; processing the multi-modal observation sequence by using a sequence processing module based on a state space model, and updating a time sequence output of complete historical information of one code up to the current time step at each time step; and predicting the next step or a series of future actions of the robot based on the time sequence output of the current time step so as to control the robot to simulate. The time sequence processing module based on the state space model is utilized to process and encode the complete observation history in the task execution process of the robot, so that a non-Markov decision-making imitation learning method is realized, and the learning efficiency and the execution success rate of the robot in a complex and state-dependent long time sequence operation task are improved.

A machine-learned system for aligning textual and image representations prior to input to a sequence processing model is described. The system includes a machine-learned image embedding model configured to receive image data and generate one or more image embeddings and a machine-learned text embedding model configured to receive text data and the one or more image embeddings and generate one or more text embeddings. The system includes a machine-learned cross-modal adapter configured to generate one or more text tokens aligned with one or more image tokens based at least in part on aligning data associated with the one or more text embeddings and the one or more image tokens. The system includes a machine-learned sequence processing model configured to generate an output based at least in part on the one or more text tokens and the one more image tokens.

The invention belongs to the field of artificial intelligence and electroencephalogram emotion recognition, and provides a double-branch electroencephalogram emotion recognition method and system based on brain region topology and time-space, and the method comprises the steps: preprocessing a to-be-recognized electroencephalogram signal to obtain a plurality of electroencephalogram fragments, and extracting a difference entropy sequence of each electroencephalogram fragment and a Spearman correlation coefficient matrix between channels; based on the Spearman correlation coefficient matrix, utilizing a bridging dynamic graph attention network module to extract topological features of a brain region; processing the differential entropy sequence by using a multi-scale space-time mixed attention module to obtain multi-scale space-time features; carrying out residual mutual cross attention fusion on the topological features of the brain region and the multi-scale spatial-temporal features to obtain fusion features; and performing classification based on the fusion features, and determining an emotion recognition result corresponding to the electroencephalogram signal. According to the method, the accuracy and robustness of emotion recognition are improved by utilizing the spatial topology characteristics and the multi-topology time dynamic characteristics of the electroencephalogram signals, and the defects of modeling spatial dependence and time dynamic are overcome.

Provided are systems and methods for enhancing the output accuracy and consistency of sequence processing models, particularly when generating text that must conform to a specific formal language. Systems and methods can integrate finite-state or push-down automata with the decoding process to ensure that the generated sequences adhere to the desired syntax or grammar rules. A system can generate or otherwise leverage a finite-state or push-down automaton that encodes constraints associated with a particular formal language or syntax. At each decoding iteration of a sequence processing model, the decoding system can use the finite-state or push-down automaton to evaluate the token validity for each of a number of possible output tokens. The output of the sequence processing model can then be limited to or otherwise guided towards tokens that are indicated as valid by the finite-state or push-down automaton.

Systems and methods for machine-learned generation of data insight summaries are provided. A computing system can obtain numerical time series data comprising a plurality of numerical values associated with a plurality of times. The computing system can identify, based on the numerical time series data, one or more first mathematical relationships in the numerical time series data. The computing system can generate, based at least in part on the mathematical relationships, a first input context comprising first natural language data indicative of the mathematical relationships. The computing system can provide the first input context to a first machine-learned sequence processing model. The first machine-learned sequence processing model can generate, based at least in part on the first input context, one or more outputs describing the one or more first mathematical relationships. The computing system can output the one or more outputs.

Provided are systems and methods for fine-tuning sequence processing models to human preferences. The approaches can account for tied preferences between pairs of sequences and, therefore, can be referred to as Tied Preference Optimization (TPO). Example sequence processing models include so-called large language models (LLMs), large multimodal models (LMMs), and other models that are configured to process inputs and / or generate outputs that are structured as a series of data elements such as tokens.

The invention relates to the technical field of education intelligent analysis, and particularly discloses a learner cognition level fine-grained tracking method and system based on a state space model. The method aims at solving the problems that an existing knowledge tracking method is low in cognitive level modeling granularity, weak in long sequence processing capacity, poor in educational interpretation and the like. According to the method, a Bloom cognitive classification system and a state space modeling technology are combined, and fine-grained and multi-level dynamic modeling and future learning performance prediction of the knowledge mastering state of the learner are achieved. The core steps of the method comprise: constructing a semantic mapping relationship between knowledge points and cognitive hierarchies (S101); collecting and encoding multi-source learning behavior features (S102); learning a cognitive state evolution trajectory based on the state space model (S103); and outputting the cognitive hierarchy classification and the answer performance prediction (S104). According to the method, by fusing the multi-dimensional learning behavior data and the state space modeling capability, the accuracy and personalized analysis depth of cognitive tracking are improved, and technical support is provided for precise teaching and intelligent decision making.

Aspects of the disclosed technology include machine-learning systems and methods for generating user interface elements that allow user control over generative content creation by machine-learned generative models. A generative user interface (UI) system is configured to generate, as output of one or more machine-learned sequence processing models, computer-executable functional code to process a user query in association with a content item. The system is configured to generate computer-executable interface code for a user interface that includes a user interface element associated with at least one parameter of the computer-executable functional code for modifying the content item. The system is configured to determine data for the at least one parameter of the computer-executable functional code based at least in part on a user input to the user interface element and generate a modified content item using the computer-executable functional code and the data for the at least one parameter.

Aspects of the disclosed technology include computer-implemented systems and methods for conversational recommendation systems, such as conversational chatbots that are configured to process user queries and generate responses. A recommendation system includes a conversational user interface configured to receive a user query and provide a recommendation response and a machine-learned sequence processing model that has been trained on training data including a plurality of triplets. Each triplet includes an example query, an example model reasoning plan associated with the example query, and an example response associated with the example query and the example model reasoning plan. The sequence processing model can be trained to provide conversational-based recommendations using a multi-stage recommendation process that includes a planning stage, a conversation stage, and a retrieval stage.

The invention belongs to the technical field of education data mining and personalized learning, discloses a learner knowledge cognition level diagnosis method and system based on cross-scale learning performance dynamic modeling, and has higher accuracy in the aspects of learner cognition state prediction and knowledge point difficulty assessment. Through a selective state space modeling mechanism and cross-scale historical learning income feature engineering, cognitive change tracks of students in various learning scenes can be accurately captured; and the robustness, convergence efficiency and long sequence processing capability of the model in learner performance prediction are improved. The method can be widely applied to a personalized education platform, a self-adaptive learning system and an intelligent teaching auxiliary tool, provides accurate student learning state analysis for teachers, optimizes learning path design, and improves the teaching effect.

The invention relates to the technical field of signal reconstruction, in particular to a complex electromagnetic environment-oriented millimeter wave signal blind source separation and reconstruction system, which comprises a frequency spectrum trend division module, a path fading construction module, an initial cluster label generation module, a multi-solution path screening module and a fusion reconstruction execution module. According to the method, power spectral density sequence processing is carried out on millimeter wave frequency domain data, a multi-dimensional feature group is formed according to a path loss factor, an angle of arrival and the like, and an initial feature cluster is screened through an Euclidean distance, so that the accuracy of signal source classification is effectively improved; after the frequency domain response and the phase contour are continuously subjected to point comparison, path screening is completed by integrating a mean square error residual value, the path misjudgment probability is reduced, time domain resampling and phase frequency offset standardization are executed in fusion reconstruction, the consistency and fidelity of signal reconstruction are enhanced, and the reconstruction precision is improved. The whole process improves the separation accuracy and reconstruction precision of mixed signals in a complex electromagnetic environment.

One example aspect is directed to a computer-implemented method for performing model decoding with reduced latency. The method includes obtaining a pre-trained sequence processing model comprising a plurality of layers. The method includes modifying the sequence processing model to contain an adapter layer that is configured to receive and process an intermediate representation generated by a particular intermediate layer of the plurality of layers to predict an output token. The method includes training the adapter layer while holding the plurality of layers of the sequence processing model frozen. The method includes deploying the sequence processing model for speculative decoding in which the adapter layer, the particular intermediate layer, and the plurality of layers that precede the particular intermediate layer perform speculative token decoding and the plurality of layers that are subsequent to the particular intermediate layer perform token verification.

The invention relates to the technical field of human resource management, in particular to a labor dispatch outsourcing management and intelligent human dispatch outsourcing system, which comprises a process disassembly module, a condition check module, a capability construction module, a connection screening module and a dispatch adaptation module. According to the method, the post task is subjected to nodal sequence processing, digital expression of the post operation process is realized in combination with action labels and operation stage mapping, deviation nodes in the operation process are identified by means of device numbers and sorting verification of operation sections, and the task process precision and the quality control capability are improved; post boundary condition constraint verification is completed by fusing post equipment permission and an operation section period table, the probability of occurrence of task matching conflicts is remarkably reduced, and the coherence consistency of personnel and post actions is improved by comparing behavior tags with a post action sequence, so that accurate matching and efficient coherence deployment of tasks and personnel are realized, and the task matching efficiency is improved. And the intelligence, the matching degree and the performability of labor dispatching are enhanced.

The invention provides a text generation method and device based on a pre-trained language model, equipment and a medium, and can be applied to the technical field of text generation. The method comprises the following steps: inputting a target question text into a pre-trained language model to generate a target path; generating a confusion value based on the conditional probability of each step in the logic step sequence; in response to determining that the confusion value is greater than the preset threshold value, correcting at least one step in the logic step sequence by utilizing a pre-trained language model to obtain a corrected logic step sequence; and processing the target question text and generating the target reply text according to the corrected logic step sequence by using the pre-trained language model, so that the correctness of each step in the logic step sequence is ensured, the reasoning efficiency is improved, the consumption of computing resources is reduced, and meanwhile, the robustness and interpretability of the target reply text are improved.

The invention belongs to the technical field of artificial intelligence and multi-modal emotion calculation, and discloses a multi-modal emotion recognition method based on a Mama state space model and cross-modal self-distillation. Through the organic combination of the efficient sequence modeling capability of the Mamba state space model and the knowledge sharing mechanism of cross-modal self-distillation, the advantages of the state space model in the aspects of time sequence modeling and calculation efficiency are fully played, and meanwhile, the limitation of a single model architecture is made up through a cross-modal attention mechanism; the technical bottlenecks of an existing multi-modal emotion recognition method in the aspects of long sequence processing efficiency, cross-modal information fusion and knowledge transfer sufficiency are effectively solved, and an efficient and reliable technical solution is provided for further development and practical application of the multi-modal emotion recognition technology.

The invention provides a multi-domain feature fusion network and a bearing fault diagnosis method and system, and relates to the technical field of deep learning. The network comprises a feature extraction module, a feature fusion module and a classification module. The feature extraction module performs feature extraction on input data by three branch lines to obtain bearing vibration time domain features, frequency domain features and time-frequency domain features; and the feature fusion module performs cross-domain fusion and dynamic adjustment fusion on the three features through the multi-head attention mechanism module and the feature calibration mechanism module to obtain accurate multi-domain fusion features, so that deep mining of input data is realized, and information of a fault state is captured more comprehensively. And a self-adaptive multi-pooling fusion structure is designed in the classification module, so that the diagnosis robustness of the model is enhanced, and the accuracy and comprehensiveness of fault classification are improved. The multi-domain feature fusion network is remarkably superior to an existing model in the aspects of noise robustness, variable working condition adaptability and short sequence processing capacity.

The invention relates to the technical field of artificial intelligence, and provides a sequence processing method, electronic equipment, a storage medium and a program product.The method comprises the steps that a preset alternative block size set is obtained, and the alternative block size set comprises a plurality of different alternative block sizes; obtaining a sequence length of a target sequence to be processed, and determining a target block size corresponding to the target sequence from the alternative block size set based on the sequence length, the target block size is the alternative block size with the minimum invalid filling data volume generated when the target sequence is subjected to blocking processing in the alternative block size set; and performing attention calculation on the target sequence based on the target block size. According to the method, the optimal block size capable of minimizing invalid calculation is dynamically matched for the sequences with different lengths, and self-adaptive optimization of the calculation load and the sequence length is realized, so that the calculation efficiency and the throughput capacity can be remarkably improved, and meanwhile, the consumption of memory resources is reduced.

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

The invention discloses a background coherent story picture book generation method based on a diffusion model, and belongs to the field of computer vision and generative artificial intelligence. The method comprises a training stage and a testing stage: in the training stage, bidirectional cross attention fusion and modal soft selection are carried out on text, background and role multi-modal conditions through a feature enhancement fusion module, model optimization is carried out by utilizing joint alignment loss, and efficient parameter fine tuning is carried out on a diffusion model by adopting an efficient parameter fine tuning method; in the test stage, a reference image input by a user and a text sequence are processed into a fusion condition, a large language model is driven to generate an image mark, the image mark is converted into a diffusion condition through a mapper, and each frame of image is generated step by step by combining an autoregression mode with a multi-condition injection diffusion network. According to the method, the problem of inconsistency of cross-frame backgrounds, styles and roles is effectively solved, and high-quality and coherent generation of the long-sequence story picture book is realized.

The invention relates to the technical field of crossing of bioinformatics, artificial intelligence and plant genomics, and discloses a plant single cell gene expression prediction method, system, device and medium. A plant single cell gene expression prediction model realizes dynamic feature fusion of a DNA sequence and chromatin accessibility signals through a gated cross attention mechanism; the problem that a traditional single-mode model cannot model regulation and control dynamic association is effectively solved, and the result interpretability is enhanced; a hybrid expert system and a load balancing design are adopted to significantly improve the recognition capability of the model for rare cell types, and a decoupling prediction head design supports efficient transfer learning; a DNA long sequence processing mechanism and nucleosome scale feature coding ensure cross-species compatibility; an end-to-end automatic process and a dynamic parameter optimization framework greatly improve the practicability; a'prediction-verification 'closed-loop support system can be constructed for molecular breeding, and high-precision and interpretable prediction of plant single-cell gene expression is realized.

The invention provides a voice synthesis method, system and device, a storage medium and a program product, and relates to the technical field of artificial intelligence and voice processing, and the method comprises the steps: obtaining Mel spectrum data corresponding to to-be-synthesized voice text data; inputting the Mel spectrum data into a neural vocoder based on a selective state space model; and performing long sequence processing on the Mel spectrum data by using the selective state space model based on the neural vocoder to obtain synthesized audio data corresponding to the to-be-synthesized voice text data. According to the invention, the neural vocoder can be constructed based on the state space model for speech synthesis, the high-frequency reconstruction capability is improved, the loss of high-frequency details is avoided, and better synthetic tone quality is obtained.

Provided are analytical expressions for multi-sample preference sampling distributions. A distillation training approach can be framed as a distribution matching problem with respect to one of these analytical expressions. The distribution matching problem can be solved using various algorithms. For example, a student model can be finetuned via policy distillation techniques. The resulting student model is therefore able to provide the benefits of the multi-sample preference sampling process, including its robustness and ability to align with human preferences, while significantly reducing the computational overhead at inference time.

The invention relates to the technical field of data processing, in particular to a small phased array radar data real-time processing system which comprises a jump positioning module, a frame sequence reconstruction module, a window mapping module, a branch binding module and a path synchronization module. In the invention, in the processing of a received frame sampling point sequence, a starting frame site is extracted through a hopping identification threshold value, accurate calibration of a channel and a time intersection point is realized, time base alignment and sequence adjustment are carried out on an out-of-order frame sequence in combination with an index, and a frame recording structure with traceability is constructed; the hopping frequency distribution characteristics of a sliding area are judged through a mapping mechanism, the dynamic response capability to a locking window is enhanced, a resolution threshold limit is introduced to effectively recognize a multi-target state and complete task branch binding, and path synchronization offset is recognized based on real-time sampling difference between locking frames. The timeliness of monitoring of the concurrent path state and tolerance judgment is improved, and stable synchronization of target information extraction and a dynamic path in a data processing link is effectively guaranteed.

The invention relates to the field of artificial intelligence, the technical scheme can be applied to the field of financial science and technology / medical health, and discloses a long context key value cache optimization method, device, equipment and medium, and the method comprises the steps: carrying out the global analysis of the hidden state of an input sequence through embedding a lightweight attention gating module in each layer of a Transform architecture, and carrying out the global analysis of the hidden state of the input sequence; outputting a binary decision signal to dynamically select a key token key value state needing to be reserved; a key value cache pool is managed according to the signal, and a corresponding attention mask is constructed to ensure that the self-attention calculation is only focused on the retained context. According to the method, the problems of high key value cache memory occupation and large reasoning delay in long sequence processing are effectively solved, the reasoning efficiency is remarkably improved, the resource consumption is reduced, and meanwhile, the original performance and the output accuracy of the model in the long text understanding task are guaranteed.

An example method includes inputting a first segment of a sequence into a machine-learned sequence processing model, wherein the first segment comprises data associated with a sequence generation request. The example method includes generating, in parallel, a plurality of candidate second segments. The example method includes generating a plurality of scores respectively for the plurality of candidate second segments using a segment quality model to generate a first component score and a response quality model to generate a second component score. The example method includes selecting, based on the plurality of scores, a second segment based on the plurality of candidate second segments. The example method includes processing the first segment and the selected second segment using the machine-learned sequence processing model to generate a third segment. The example method includes returning the selected second segment and the third segment in response to the sequence generation request.

Computer-implemented methods and systems provide a persistent fixed-size recurrent memory that supports long or unbounded sequence processing with substantially constant compute and bounded memory. A recurrent model maintains a matrix state updated per chunk from key, value, gate, and optional control signals; a gated error between value and a key-weighted state yields a rank-1 proposal. Chunk proposals are reconciled coordinate-wise by an order-invariant convex combiner; solitary proposals pass unchanged. Queries can be answered from proposals without materializing a full updated state. Multiple asynchronous agents emit sparse updates with overwrite strengths that are merged using sparse convex or max selection and optional optimizer preprocessing. A feedback projection writes higher layer activations into lower layer state to consolidate durable skills and reduce forgetting. The approach enables durable retention, parallel inference-time adaptation, scalable linear-attention approximation, and persistent fixed memory use over arbitrarily long sequences.

Provided are systems and methods for fine-tuning sequence processing models (e.g., Large Language Models (LLMs) or Large Multimodal Models (LMMs)) to human preferences. Specifically, provided are systems and methods for application of matching losses, including asymmetric matching losses, at various stages of aligning sequence processing models to reward or preference labels that capture human preferences.

The invention provides a test case generation method and device, equipment, a medium and a program product, and can be applied to the field of artificial intelligence and the field of financial science and technology. The method comprises the steps that the difference between first version core data and second version core data is analyzed, and changed metadata is obtained; on the basis of the change metadata, semantic modeling is conducted on the old-version case data through a test case generation model, and a first test case is generated; wherein the test case generation model is constructed based on a recurrent neural network and an attention mechanism; scheduling and executing the first test case, and collecting multi-modal data in the execution process; processing the test execution data through the exception recognition model to obtain a recognition result; wherein the test execution data comprises multi-modal data, and the anomaly recognition model is constructed based on a sequence processing neural network; and according to the identification result, modifying the first test case based on an exception repair strategy to obtain a second test case.

The invention discloses a traffic information prediction method, device and equipment, a storage medium and a product, and relates to the technical fields of artificial intelligence, big data analysis, Internet of Things data application, intelligent transportation, location service, wireless communication data processing and the like. The method comprises the steps that spatial features of a to-be-predicted road section are obtained, a road network diagram is processed by a model for processing diagram structure data and then output, the road network diagram comprises nodes and edges used for representing the road section, the weight of the edges is determined according to historical data corresponding to the road network diagram, the spatial-temporal features of the to-be-predicted road section are obtained, and the spatial-temporal features of the to-be-predicted road section are obtained; according to the method, an event sequence determined according to historical data is processed by a sequence processing model and then output, event elements in the event sequence comprise time coding information and event information of a preset type of event, and road section features of a road section to be predicted are constructed according to spatial features and spatial-temporal features. The traffic information of the to-be-predicted road section in the future time period is predicted based on the road section features, and low-cost accurate prediction of the traffic information can be realized.