20 results about "Probabilistic generative model" patented technology

The invention discloses a storm surge water increase prediction method and device, electronic equipment and a storage medium, and relates to the technical field of seawater monitoring, and the method comprises the steps: obtaining multi-source observation data of a target sea area, the multi-source observation data comprising satellite remote sensing data, near-shore monitoring data, meteorological mode data and drainage basin data; performing space-time alignment and exception processing on the multi-source observation data to generate standardized space-time grid data; performing hybrid prediction modeling on the standardized space-time grid data through a physical data dual-drive modeling layer to obtain a target probability water increasing field; and dynamically correcting the target probability water increasing field by using real-time observation data to obtain a storm surge water increasing predicted value. A physical mechanism model and a probability generation model are combined, limitation of a single model is overcome, and the nonlinear evolution process of the storm surge is effectively captured; the time-space dual-drive architecture is adapted to complex coast terrains and changeable meteorological conditions, and the risk of missing report or false report is reduced.

A computerized method is disclosed including obtaining an electronic message, performing a cyberthreat detection process thereon, which includes a first sub-analysis of the body and subject line information of deploying a probabilistic generative model resulting in determination of a likelihood that the electronic message is directed to one of a predefined set of topics, and when the likelihood that the electronic message is directed to one of the predefined set of topics meets or exceeds a first threshold, deploying one or more artificial intelligence models to determine or classify a semantics of the email body or subject, and a second sub-analysis of the header information of performing a heuristic analysis thereof, and performing a determination operation by either a relationship compiler resulting in a determination as to whether the electronic message is malicious or benign, and generating a display that provides the maliciousness determination.

The invention discloses an oil pipeline monitoring method and system based on spatio-temporal modeling and multi-dimensional analysis, and belongs to the technical field of oil and gas pipeline safety monitoring, data processing and intelligent prediction.The method comprises the steps that multi-source spatio-temporal data is collected to construct a probability generation model; performing inversion on the model by using the observation value to reconstruct four-dimensional posterior probability distribution; performing causal inference on the posterior probability distribution to generate a dynamic causal information flow map; and analyzing topological evolution of the atlas to generate a stability monitoring report. According to the method, a technical path of combining probability modeling based on an information field theory and causal dynamics inversion is adopted, and accurate prediction of a systematic risk critical transition precursor can be realized by reconstructing a pipeline holographic state field and analyzing topological evolution of a causal network of the pipeline holographic state field; and the operation safety and the intelligent monitoring level of the long-distance oil pipeline are obviously improved.

The invention discloses a network security uncertainty quantitative detection method based on generative AI, and belongs to the technical field of network security detection, and the method comprises the steps: collecting security event data from a plurality of heterogeneous data sources, and forming a standardized to-be-detected event sequence; constructing a dynamic baseline model based on the historical event sequence of the normal behavior by using a probability generation model, and generating at least one anomaly indication feature for the to-be-detected event sequence; inputting the anomaly indication features into a Bayesian deep learning model, and obtaining a mean value representing an anomaly probability and a variance representing prediction confidence in the event sequence to be detected through multiple forward propagation sampling; and carrying out risk grading on the security events, and carrying out retraining on the probability generation model and / or the Bayesian deep learning model based on feedback annotation of a grading result to realize closed-loop optimization. According to the invention, the decision-making efficiency is improved in a leap-over manner, and the gray attack behavior is effectively detected and the precision is improved.

Disclosed are an apparatus and method for providing a speech video. The apparatus for generating a speech video according to an embodiment comprises: an encoder for encoding a person image to generate an identity latent vector; a voice emotion recognition model for recognizing emotion from speech audio; a motion latent vector generation model which is a probabilistic generative model for generating a motion latent vector on the basis of the speech audio and the emotion; and a decoder for generating a speech video of speech spoken by the corresponding person on the basis of the identity latent vector and the motion latent vector.

A computerized method is disclosed including obtaining an electronic message, performing a cyberthreat detection process thereon, which includes a first sub-analysis of the body and subject line information of deploying a probabilistic generative model resulting in determination of a likelihood that the electronic message is directed to one of a predefined set of topics, and when the likelihood that the electronic message is directed to one of the predefined set of topics meets or exceeds a first threshold, deploying one or more artificial intelligence models to determine or classify a semantics of the email body or subject, and a second sub-analysis of the header information of performing a heuristic analysis thereof, and performing a determination operation by either a relationship compiler resulting in a determination as to whether the electronic message is malicious or benign, and generating a display that provides the maliciousness determination.

Methods, systems, and techniques for generating one or more conditionally dependent data entries using a probabilistic generative model, and for training that model. The probabilistic generative model is trained using a plurality of data generation tasks respectively corresponding to a plurality of vectors each having a sequence of differently indexed data entries that are conditionally dependent on each other. Each of the data generation tasks involves generating at least one latent data entry selected from the sequence of data entries in response to being provided at least one index for each of the at least one latent data entry. Training can be performed by minimizing an expected value of a denoising loss over all training stages.

The invention relates to a service quantity prediction method fusing multi-scale decomposition and adaptive probability modeling. The method comprises the following steps: acquiring a historical service quantity time sequence, and decomposing the historical service quantity time sequence into historical sub-sequence components with fluctuation characteristics and dependency modes of different time scales by utilizing multi-scale decomposition; respectively extracting historical time sequence characteristics of each component, performing independent modeling by using a probability generation model, and training the model to generate a plurality of groups of probability distribution parameters to fit probability distribution corresponding to each component; obtaining time sequence characteristics of a to-be-predicted moment, and inputting the time sequence characteristics into the trained model to obtain probability distribution of each prediction component; and adopting Monte Carlo sampling to generate a prediction sample, performing adaptive dynamic fusion according to the time-varying weight, and outputting a fused service quantity prediction result. By adopting the method, the precision and reliability of service quantity prediction can be remarkably improved through multi-scale collaborative modeling and adaptive probability fusion.

Disclosed are an apparatus and a method for generating a speech video. The apparatus for generating a speech video, according to one embodiment, comprises: an encoder for encoding a person image so as to generate an identity latent vector; a motion latent vector generation model which is a flow matching-based probabilistic generative model for generating a motion latent vector on the basis of a speech audio; and a decoder for generating a speech video of the corresponding person uttering, on the basis of the identity latent vector and the motion latent vector.

Disclosed herein are methods, compositions, and devices for use in diagnosis and treatment of cancer. The methods include a generative probabilistic accounting for the characteristics of methylation data, which includes random silencing and in possesses sparsity as a result. Here, the technique finds application in subtyping, determining disease transition and formation, among other oncology applications.

A computerized method is disclosed including operations of obtaining and parsing an electronic message into components including body and subject line information and determining a likelihood that the electronic message is directed to one of a predefined set of topics by deploying a probabilistic generative model, wherein the electronic message has a likelihood of being directed to a first topic of at least a first threshold. The operations may also include generating a prompt for a language model based on the first topic, providing the prompt and the body and subject line information of the electronic message to the language model, and generating a semantic result based on a response to the prompt from the language model. The electronic message may be classified by a relationship compiler or a neural network as malicious or benign based on the semantic result.

The invention discloses a voxel robot form optimization method based on a hierarchical Bayesian probability model, and the method comprises the steps: constructing a form generation model: constructing a hierarchical Bayesian probability generation model which comprises a task-individual-organ-voxel four-layer logic structure and is used for describing the relevance of tasks, individuals, organs and voxels; optimization of parameters of the generative model: estimating the parameters of the generative model by using the labeled data; performing form-control collaborative optimization: generating a robot form by using the generative model in a task environment, and performing fitness evaluation; screening a dominant form from fitness evaluation to update the generation model, and meanwhile, retaining a random generation form to maintain design diversity; introducing bionic priori: constructing a label-free natural biological form data set, and generating bionic priori through dimension reduction or feature learning; bionic prior and task label information are combined for optimization of the generative model. The method has high efficiency, interpretability and diversity.

A computerized method is disclosed analyzing maliciousness of an electronic message including operations of analyzing header information of the electronic message including a heuristic analysis and a name entity recognition analysis, determining a probability that the electronic message is directed to one of a predefined set of topics by deploying a probabilistic generative model, generating a prompt for a language model based on a first topic, providing the prompt to the language model and generating a semantic result based on a response thereto. Additional operations include classifying the electronic message as malicious or benign based on a semantic result based on the response to the prompt from the language model, and semantics of the header information, and generating a graphical user interface display that indicates whether the electronic message has been classified as malicious or benign.

The invention discloses a voxel robot structure optimization design method based on morphological statistical modeling, and the method comprises the steps: constructing and training a depth probability generation model which is based on a multi-level representation mode and comprises a task embedding layer, a morphological latent variable generation layer and a voxel distribution generation layer; performing morphological design on the target task by using the generative model, including inputting a task code, generating a morphological latent variable, and generating a voxel robot form based on the morphological latent variable; in the generation process, the morphological pool is used for storing morphological samples of intergenerational sampling and the fitness of the morphological samples, the morphological samples are screened and optimized based on the continuous natural selection sampling technology, and the optimization result is fed back to the generation model; for different task targets, a model and a sample selection strategy are generated through iterative optimization, and multi-task adaptability design is achieved. According to the method, the morphological samples are generated through the generative model, the morphological pool is introduced to store the samples and the fitness thereof, the wide applicability of description is kept, and the sample utilization rate is effectively improved.

A computerized method is disclosed including operations of obtaining and parsing an electronic message into components including body and subject line information and determining a likelihood that the electronic message is directed to one of a predefined set of topics by deploying a probabilistic generative model, wherein the electronic message has a likelihood of being directed to a first topic of at least a first threshold. The operations may also include generating a prompt for a language model based on the first topic, providing the prompt and the body and subject line information of the electronic message to the language model, and generating a semantic result based on a response to the prompt from the language model. The electronic message may be classified by a relationship compiler or a neural network as malicious or benign based on the semantic result.

A computerized method is disclosed including obtaining an electronic message, performing a cyberthreat detection process thereon, which includes a first sub-analysis of the body and subject line information of deploying a probabilistic generative model resulting in determination of a likelihood that the electronic message is directed to one of a predefined set of topics, and when the likelihood that the electronic message is directed to one of the predefined set of topics meets or exceeds a first threshold, deploying one or more artificial intelligence models to determine or classify a semantics of the email body or subject, and a second sub-analysis of the header information of performing a heuristic analysis thereof, and performing a determination operation by either a relationship compiler resulting in a determination as to whether the electronic message is malicious or benign, and generating a display that provides the maliciousness determination.

The embodiment of the invention discloses a model training method, a prediction probability information generation method, a prediction probability information generation device and electronic equipment. A specific embodiment of the method comprises the steps of obtaining a training data set; inputting the variable data set into an initial feature data vector representation model to output an initial variable vector set; performing model training on each initial discrimination model in an initial discrimination model set included in the initial target value payment mode probability generation model to obtain a discrimination model set; and according to the initial variable vector set, the actual value reduction information set and the actual value payment mode information set, performing model training on an initial generative model set and an initial feature data vector representation model included in the trained target value payment mode probability generation model to obtain the target value payment mode probability generation model. The implementation mode is related to artificial intelligence, and the target value payment mode prediction probability information can be accurately generated by using the trained target value payment mode probability generation model.

The invention particularly relates to a tissue multi-chromophore in-vivo quantitative imaging method based on a probability generation model. The tissue multi-chromophore in-vivo quantitative imaging method comprises the following steps: acquiring a multi-wavelength photoacoustic initial sound pressure reconstruction diagram of a target biological tissue area; blind unmixing processing is carried out on the multi-wavelength photoacoustic initial sound pressure reconstruction diagram, and spectral characteristics and concentration distribution of all chromophores in the target biological tissue are initialized; converting the multi-wavelength photoacoustic initial sound pressure reconstruction diagram into a logarithmic multi-wavelength photoacoustic initial sound pressure reconstruction diagram through an LOG logarithmic decoupling method; constructing a probability generation model based on a variational auto-encoder, inputting the logarithmic multi-wavelength photoacoustic initial sound pressure reconstruction diagram and the initialized spectral characteristics and concentration distribution into the probability generation model based on the variational auto-encoder, solving a new light absorption coefficient matrix, reconstructing a logarithmic multi-wavelength photoacoustic initial sound pressure reconstruction diagram by the light absorption coefficient matrix, and obtaining a logarithmic multi-wavelength photoacoustic initial sound pressure reconstruction diagram. And thus, the chromophore in-vivo spectrum and concentration image output by the model are constrained. And the precision and robustness of structure distinguishing in the complex biological tissue are improved.

A computerized method is disclosed that includes operations of obtaining and parsing a copy of an email into components including body and subject line information, performing a plurality of analyses on the copy of the email including deploying a probabilistic generative model resulting in a determination of a likelihood that the email is directed to one of a predefined set of topics, classifying semantics extracted from the body or subject based on results generated by the probabilistic generative model, and performing a determination operation by a relationship compiler or a neural network resulting in a maliciousness determination as to whether the email is malicious. Responsive to the maliciousness determination being malicious, generating a graphical user interface display indicating that the email has been classified as malicious and performing a mail retrieval attempt that causes the email to be removed from an inbox of the mail client of the intended recipient.

Embodiments of the present disclosure disclose a model training method, a prediction probability information generation method, an apparatus and an electronic device. A specific implementation of the method comprises: obtaining a training data set; inputting a variable data set into an initial feature data vector representation model to output an initial variable vector set; performing model training on each initial discriminant model in an initial discriminant model set included in an initial target value payment method probability generation model to obtain a discriminant model set; and performing model training on an initial generative model set and the initial feature data vector representation model included in the trained target value payment method probability generation model according to the initial variable vector set, an actual value reduction information set and an actual value payment method information set to obtain the target value payment method probability generation model. The implementation is related to artificial intelligence, and the trained target value payment method probability generation model can accurately generate target value payment method prediction probability information.