68 results about "Expert group" patented technology

The invention relates to the technical field of electric power task adjustment, and provides an electric power task model fine tuning method and system, terminal equipment and a storage medium, and the method comprises the steps: inserting a shared low-rank expert module in a pre-training model trunk, dynamically calculating the activation weight of each expert according to the input characteristics through a gating network, and carrying out the fine tuning of an electric power task model; and a sparse regularization constraint activation number is introduced. During training, expert output is subjected to weighted fusion to generate fine adjustment parameters, multi-task joint training is adopted, balance optimization is achieved by dynamically adjusting task weights, and during reasoning, only part of experts with the highest weights are activated, and sparse calculation is achieved. According to the method, a plurality of low-rank expert modules are inserted into a large model trunk, a trainable gating routing mechanism is introduced, the optimal expert combination weight is dynamically calculated according to semantic features of input task samples, and knowledge fusion, parameter multiplexing and reasoning sparse activation among multiple tasks are achieved.

According to the time sequence risk control method and system based on the multi-level mixed experts, heterogeneous data in the medical field is fused and mapped to the unified representation space through multi-modal representation learning, and therefore data information is utilized more comprehensively. The system adopts a multi-level hybrid expert (MoE) architecture, tasks can be accurately routed to a more professional expert group according to patient characteristics through a hierarchical gating network, and the accuracy and resource utilization efficiency of the model are greatly improved. Meanwhile, through bidirectional interpretability and a causal inference mechanism, not only can the reason of a risk prediction result be explained, but also anti-fact analysis and specific intervention measure guidance can be provided, so that the model is converted from a pure prediction tool to an intelligent partner for auxiliary decision making.

The invention relates to the technical field of image data processing, in particular to an automatic driving model based on a mixed low-rank expert and a multi-domain adaptive fine tuning method, and the model comprises a general model base in a frozen state and a multi-domain adaptive component in a trainable state; the universal model base comprises an image encoder, a measurement information encoder and a trajectory planner; the multi-domain adaptation component comprises a mixed low-rank expert group and a domain sensing router; the mixed low-rank expert group is used for calculating a difference correction signal according to the input characteristics; and the domain sensing router is used for receiving the shared image features extracted by the image encoder, outputting probability vectors and dynamically activating corresponding experts in the mixed low-rank expert group according to feature distribution of input data. According to the method, plug-and-play type efficient adaptation of a single universal model to multiple downstream domains is achieved with extremely low calculation and storage cost, and the pain point of a traditional multi-domain adaptation method is perfectly solved.

The invention relates to an intelligent bid evaluation expert extraction method and system in the technical field of bidding and tendering information management. The method comprises the following steps: S1, constructing an expert multi-dimensional portrait; s2, receiving review project information, analyzing and calculating relevancy between a project demand vector and each expert capability vector, and screening candidate experts; s3, performing intelligent scheduling and priority ranking according to the historical response rate, attendance rate and evaluation of the candidate experts; s4, carrying out credible evidence storage on key data of the extraction process by utilizing a block chain, and ensuring tampering prevention and traceability of the extraction process and expert information; s5, at the appointed time and place before bid opening, decrypting and reviewing expert sensitive information under supervision, and completing confirmation and notification of a final expert group; the system comprises an expert database management module, a semantic matching module, an intelligent scheduling module, a block chain evidence storage module, a security decryption module and a visual interface. According to the extraction method and the system thereof, the precision, the intelligence and the security of expert extraction can be realized.

The invention discloses an MoE expert deployment system and method based on a wafer-level chip, and the system comprises a statistical module which is used for carrying out the statistics of expert co-activation probability distribution reflecting the cross-layer cooperative activation relation between experts in MoE and the communication demands of a calculation core on the wafer-level chip; and the clustering module is used for performing clustering based on the expert co-activation probability distribution and communication requirements by taking the minimization of communication traffic across physical regions and the minimization of intra-group communication load difference of expert groups borne by the physical regions as targets to obtain an expert grouping scheme of MoE and a physical region layout mapping scheme corresponding to wafer-level chips. According to the method, clustering can be carried out according to the cross-layer co-occurrence rule of the experts, and the experts subjected to high-frequency cooperative activation are constrained in the same physical region, so that a large amount of global communication is converted into local exchange, and the overhead of long-distance and high-delay cross-region communication is remarkably reduced. Meanwhile, load distribution is optimized in combination with communication requirements, and local hotspots are effectively avoided.

The invention discloses an intelligent design system and method for a building structure. The method comprises the following steps: S1, constructing a building database and a rule database; s2, inputting a construction area and a construction target; s3, generating multiple groups of building designs; s4, generating a simulated building structure, and performing a simulated building structure test; s5, submitting an architectural design result passing the test to an expert group appraisal platform, and scoring by an expert group according to an assessment condition; and S6, outputting a final building design result. Model simulation and testing are carried out after the building scheme is generated according to the construction target, unqualified building design schemes can be filtered and processed through the testing step, the follow-up expert review data volume is reduced, scoring is carried out after expert review, and the efficiency is improved. And some basic qualified design schemes can be optimized according to suggestions of expert appraisal, so that the finally obtained design schemes can be enabled to be richer, and the efficiency of generating the construction design schemes of the scheme is further ensured.

The invention discloses a multi-task intensive prediction method based on mixed single-rank experts. The method comprises the following steps: collecting and arranging a multi-task intensive data set; dividing the data set into a training set, a verification set and a test set, and performing preprocessing; constructing a multi-task intensive prediction model; training the model by using a training set, and regularly evaluating the performance of the model in the training process by using a verification set; carrying out loss calculation and parameter optimization on the model in the training process; and performing final performance evaluation on the trained model by using the test set, and applying the trained model to a to-be-reasoned image to obtain an output result of the image under each dense prediction task. According to the method, a model comprising a shared feature extraction module, a task feature enhancement module and a task prediction module is constructed, and a mixed single-rank expert group is adopted to dynamically enhance task features in space and channel dimensions, so that a unified learning framework for performing multi-task intensive prediction on images is realized.

The invention discloses an expert review componentization system and a review method, belongs to the technical field of software systems, and aims to solve the technical problems of poor universality, insufficient intelligence and rigid process in the process of business declaration and qualification affirmation. Comprises: a component library configuration module for constructing a standardized review component and constructing a component library based on the review component; the expert database configuration module is used for collecting review experts to construct an expert database according to the review requirements of each business scene; the review rule configuration module is used for pulling related review components from the component library according to review rules and constructing a review process based on the pulled review components; the expert extraction module is used for pulling related reviews from an expert database to construct a review expert group and setting expert review rules; the review analysis module executes a review task based on a review process, and summarizes review suggestions of review experts to form a review result; and the data storage module is used for storing the review rule, the review expert group and the review result.

The invention provides a question and answer method and system based on a large model expert group and a knowledge graph and a storage medium, the question and answer method comprehensively utilizes the knowledge graph, the expert model group and a generative large model, and introduces the steps of multi-stage filtering and cue word optimization into the expert model group, so that accurate understanding of user questions and efficient answer generation are realized, and the user experience is improved. And the accuracy and the user satisfaction degree of the question-answering system are remarkably improved. Query is carried out through the unified knowledge graph before the expert model group, and the unified knowledge graph module adopts consistent input and maintenance standards, so that the consistency and normalization of all knowledge entries are ensured, and the problems of standard differentiation and variation caused by decentralized management are avoided. And moreover, a consistent query interface is provided, so that the knowledge graph method can be more universal and efficient.

The invention provides a same-type expert aggregation federation hybrid expert learning method based on VSMC filtering, and relates to the technical field of expert model learning, and a framework of the method comprises a client local weight calculation module, a server same-type expert grouping module and a server VSMC aggregation module. The client calculates a local weight reflecting real-time credibility based on expert historical performance data and preprocesses broken data; a server side groups cross-client experts of the same type according to task labels, introduces a variational sequential Monte Carlo filtering mechanism for each group of experts, dynamically approaches posterior distribution of expert weights through particle sampling and resampling, calculates an optimal aggregation weight, integrates intra-group prediction results and broken data, and updates a global model. According to the method, high-dimensional approximation and strong anti-noise capability of VSMC filtering are utilized, accurate and adaptive aggregation of weights of experts of the same type in a federated dynamic scene is realized, and the convergence speed, prediction precision and communication efficiency of a global model are effectively improved.

The invention discloses a high-precision hybrid expert large model and a fine tuning method thereof. The hybrid expert large model is composed of a domain expert group and a shared expert group. A high-precision data transmission fine tuning module based on each linear network LN in the shared expert, wherein the fine tuning module comprises an extended linear network, a numerical value alignment network, a blocking controller and a precision converter; the extended linear network is of a replicated linear network (LN) structure and converts an input vector into a first data flow vector; the numerical value alignment network performs numerical value coding on the output data flow vector of the extended linear network to generate a second data flow vector; the blocking controller controls whether the extended linear network and the numerical alignment network participate in domain expert group reasoning or not according to binary data signals; the precision converter adjusts the precision of the data stream output by the numerical alignment network and the precision of the data of the shared expert linear network to be consistent; according to the invention, the flexibility and intelligent control capability of the high-precision hybrid expert large model can be enhanced.

This application relates to the field of image data processing technology, and particularly to an autonomous driving model based on hybrid low-rank experts and a multi-domain adaptation fine-tuning method. The model includes: a general model base in a frozen state and a multi-domain adaptation component in a trainable state. The general model base includes: an image encoder, a measurement information encoder, and a trajectory planner. The multi-domain adaptation component includes: a hybrid low-rank expert group and a domain-aware router. The hybrid low-rank expert group is used to calculate differential correction signals based on input features. The domain-aware router is used to receive shared image features extracted by the image encoder, output probability vectors, and dynamically activate the corresponding experts in the hybrid low-rank expert group according to the feature distribution of the input data. This application achieves highly efficient "plug-and-play" adaptation of a single general model to multiple downstream domains with extremely low computational and storage costs, perfectly solving the pain points of traditional multi-domain adaptation methods.

The invention relates to the technical field of construction risk management of constructional engineering, in particular to a subway station deep foundation pit construction risk assessment method based on bilateral probability language, which comprises the following steps: step 1, constructing an evaluation set in a bilateral probability language term set form; 2, performing objective standardization processing on evaluation information; 3, determining a combination weight of subjective and objective combination; step 4, hierarchical information aggregation based on a weighted average operator; and step 5, risk quantification and grade determination. According to the method, a bilateral probability language term set (DPLTS) is introduced to completely describe expert group opinion distribution, and an LCM objective standardization method and a fuzzy entropy-cross entropy-BWM combined weighting model are combined to construct a risk assessment system which is complete in information, scientific in weight and robust in decision making; the defects of the prior art in the aspects of expressing complex uncertainty and fusing subjective and objective information are effectively overcome, and the reliability, the distinction degree and the practical value of a risk assessment result are remarkably improved.

The present invention relates to a marketing method, and more specifically, to a multi-industry synergy sales method involving a broker with applied CPA, wherein when a user utilizes a service through a CPA link, the CPA is paid to the broker to support the broker's sales activities, and objective information from a group of experts stored in a review database is provided to the user to enhance trust between the contracting parties. The present invention for this purpose proposes a multi-industry synergy sales method involving a broker with applied CPA, characterized by comprising: a web server that generates a CPA (Cost Per Action) link including detailed information of multiple expert groups and a unique identification code of a broker; a management database that manages user information, broker information, and expert group information separately in independent DBs; a callback server that transmits the CPA (Cost Per Action) link to the user after a phone call between the user and the broker; and an expert group including one or more of a moving company, a curtain / blind company, a cleaning company, an interior design company, a CCTV company, and an internet subscription company, wherein when a user uses the service through the CPA link, the CPA (Cost Per Action) is paid to the broker. Therefore, the multi-industry synergy sales method involving a broker applying CPA according to the present invention has the effect of increasing user satisfaction by transmitting a CPA link containing expert information to a registered user and paying a certain percentage of revenue for service usage, and improving trust between contracting parties by providing the user with objective information from the expert group stored in the review DB.

The application provides a same-type expert aggregation federal hybrid expert learning method based on VSMC filtering, and relates to the technical field of expert model learning, and the framework of the method comprises a client local weight calculation module, a same-type expert grouping module of a server and a VSMC aggregation module of the server. The client calculates local weights reflecting real-time reliability based on expert historical performance data and preprocesses broken data; the server groups same-type experts across clients according to task labels, and introduces a variation sequential Monte Carlo filtering mechanism for each group of experts, dynamically approximates the posterior distribution of expert weights through particle sampling and resampling, calculates optimal aggregation weights, integrates group prediction results and broken data, and updates a global model. The application utilizes the high-dimensional approximation and strong anti-noise ability of VSMC filtering, realizes accurate and adaptive aggregation of same-type expert weights in a federal dynamic scene, and effectively improves the convergence speed, prediction accuracy and communication efficiency of the global model.

Moving Picture Experts Group (MPEG) media transport protocol (MMTP) data indicating fragmented MP4 media content is received from a source of content such as an ATSC 3.0 source. The MMTP data is used to create HTTP Live Streaming (HLS) files, and the receiving HLS media player then plays the associated media content using the HLS files.

This invention discloses a training method, inference method, apparatus, and device for a hybrid expert model. The method includes: determining the number of expert groups and task positioning of the target hybrid expert model based on the required scenario; determining the expert quantity configuration information of each expert group based on the multidimensional evaluation parameters of each expert group; training the routing module of the target hybrid expert model based on routing training sample data to obtain a trained routing module; the routing module includes expert group routing modules and intra-group expert routing modules for each expert group; and training each expert group based on expert group training sample data until the global loss function of the target hybrid expert model converges. This invention can accurately differentiate and define the functions and boundaries of each expert in the hybrid expert model, clarify the task adaptability and task positioning of each expert, reduce the ineffective consumption of computing resources, and improve the training convergence rate.

The invention discloses a large language model multi-dimensional preference alignment method based on multi-attribute collaborative optimization, and the method comprises the steps: generating a multi-candidate response based on reference strategy sampling, constructing a preference data set containing main and auxiliary attributes through an attribute scoring mechanism, and precisely capturing human implicit multi-dimensional preferences; a learnable prompt pool and an expert group are constructed, after expert groups are divided through attribute combination, multi-dimensional features of samples are fused through a routing gating network, accurate matching of the samples and the experts is achieved, and different attribute combination modeling requirements are met; constructing a self-normalization importance sampling weight based on the log-likelihood difference of the current model and the reference model, and estimating and maximizing the joint expectation score of the primary and secondary attributes; and meanwhile, flexible control is carried out on the expected constraint violation condition of the secondary attribute, so that collaborative optimization of the primary and secondary attributes is realized. According to the method, the large language model better fits human multi-dimensional real preferences, performance does not need to be sacrificed in any attribute dimension, and the model output quality and scene adaptation capability are remarkably improved.

This invention relates to a method and apparatus for predicting and analyzing health intervention factors based on the Eight Principles of Traditional Chinese Medicine (TCM) diagnostic methods. The method includes: constructing a deep learning model, denoted as the first prediction model, for predicting TCM interventions based on the four diagnostic methods of TCM; constructing a first dataset through volunteer data collection and expert group classification; training the first prediction model based on the first dataset; after model training, feeding the user-input four diagnostic vector X into the first prediction model for prediction, and performing health intervention factor analysis based on the model's output prediction vector Y and an intervention factor library to obtain a corresponding health intervention report, which is then fed back to the current user. This invention can improve the personalized prediction level of health intervention factors and enhance the accuracy and completeness of health intervention factor analysis.

Method, apparatus, and system for haptic signal processing are provided. The process may include receiving a media stream comprising at least one haptic track and at least one video track. The process may include obtaining, from the media stream, one or more moving picture experts group (MPEG) immersive haptics stream (MIHS) units and obtaining, from the media stream, timing information associated with one or more haptic effects, the timing information comprises at least one temporal position of the one or more haptic effects. Then the process may include rendering the media stream based on the obtained timing information.

The present application relates to the technical field of industrial boiler, in particular to a kind of multi-objective prediction method and system coupled with biomass gas.The method collects multi-source operation data, carries out time alignment and resampling to generate mode characterization vector;Based on historical characterization vector clustering, divide K operation modes, and train corresponding expert model to constitute multi-objective prediction expert group respectively;Current characterization vector is input into gate network to obtain basic gate weight, and mode migration jitter is inhibited by double threshold hysteresis judgment and shortest residence time constraint, and final gate weight is generated by weight smoothing;The final gate weight is used to weight and fuse the multi-objective results output by each expert, to obtain continuous and stable prediction results.The method can improve the prediction accuracy and stability under complex working conditions, enhance the adaptability to working condition change and mode evolution, and has good engineering application value.

The application discloses a kind of robust preference aggregation method and system of multi-expert group decision-making, take the expert condition preference matrix of multiple experts to multiple candidate scheme, execute tailing robustness processing and normalization processing with numerical protection according to expert line, obtain robust initial opinion matrix;Similarity trust matrix and uniform trust matrix with diagonal line as zero and non-diagonal uniform distribution are constructed based on the matrix, and the final trust matrix is obtained by convex combination fusion of the two through shrinkage coefficient;Robust initial opinion matrix and final trust matrix are input Friedkin-Johnsen opinion evolution model to solve balanced opinion matrix, and the group score is obtained by weighting aggregation according to preset expert aggregation weight, and the sorting result is output.

The invention discloses a power grid control method and device based on a hybrid expert network and a medium, and belongs to the technical field of power grid optimization, and the method comprises the steps: obtaining power grid data which comprises node voltage, load demands, generator output and energy storage charging and discharging data; based on the power grid data, an intelligent scheduling model driven by multi-modal data is constructed, and the intelligent scheduling model comprises a plurality of expert sub-networks composed of a steady-state regulation and control model, a deep reinforcement learning model, a model prediction control model, a new energy consumption model and dynamic safety evaluation, and dynamically allocating expert weights through the gating network to realize self-adaptive decision making. Through the combination of the dynamic expert network and the lightweight gating mechanism, the multi-modal data of the power grid can be analyzed in real time, the optimal expert combination is activated in a self-adaptive manner, and dynamic spatial-temporal characteristic capture is realized. Compared with a traditional deep reinforcement learning method, the method is remarkably improved, and excellent self-adaptability and real-time performance are shown.

A method includes establishing a primary bounding area corresponding to a first geographic broadcast area of a traffic message, the primary bounding area associated with a first set of road classes; establishing a first sub-bounding area nested within the primary bounding area, the first sub-bounding area corresponding to a second geographic area smaller than the first geographic broadcast area, and being associated with a second set of road classes different than the first set of road classes. A traffic message associated with a road having an assigned road class is received, and the traffic message is inserted into a Transport Protocol Experts Group frame transmitted within the first sub-bounding area in response to determining that the road and the assigned road class are associated with either the first sub-bounding area or the primary bounding area.

The invention relates to the technical field of artificial intelligence and automatic driving, in particular to an automatic driving mixed expert multi-task learning method based on feature contrast learning, and the method comprises the following steps: firstly, constructing a multi-task mixed expert architecture, and obtaining a training data set; the multi-task hybrid expert architecture comprises a feature encoder, a multi-task expert group and a task router; then, dividing the training data set based on the driving task; thirdly, applying intermediate feature comparative learning loss to the output of the feature encoder, performing intermediate feature comparative learning, and remodeling a feature space; task routing loss is introduced, a task router is trained for distribution, and an upstream feature encoder is forced to learn task distinguishable feature representation; and finally, updating and reasoning parameters. According to the method, feature learning and routing distribution are decoupled, intermediate features are introduced to compare learning loss, and while the router is trained, an upstream feature encoder is forced to learn task-distinguishable feature representation.

The invention provides a business resource prediction method and device, electronic equipment and a readable storage medium. The method comprises the steps of inputting to-be-processed data into a trained classification model, and obtaining a target index output by the trained classification model; obtaining a target business expert group model according to the target index, inputting the to-be-processed data into the target business expert group model, and obtaining a resource prediction result output by the target business expert group model; the trained classification model is used for determining a corresponding target business scene category according to the to-be-processed data, and determining and outputting a target index according to the target scene category; the target business expert group model is used for predicting the resource demand of the to-be-processed data by using each trained expert model, and determining and outputting a resource prediction result by using the trained output network according to the resource demand output by each trained expert model. The resource quantity required by the to-be-processed data can be accurately predicted, and the resource saving degree is improved.

The application discloses an artificial intelligence-based key problem fusion method and system and a storage medium, and belongs to the technical field of artificial intelligence.The method comprises the following steps: extracting a plurality of first key problems from a plurality of prediction mask words by an initial training language model; clustering the plurality of first key problems, distributing the clustering results to each member of an expert group, and correcting the clustered key problems by each member of the expert group to obtain a plurality of second key problems; taking the corrected plurality of second key problems as training sentences; generating the encoding features of the training sentences based on a first mask for randomly masking the unrecorded words in the fixed word table contained in the training sentences; generating prediction mask words based on the encoding features; and repeating the above steps until a key problem fusion model is obtained by converging the first key problems.The initial training model is trained by taking the key problems modified by each expert as the training sentences, so that the summarization efficiency and accuracy are improved.

The application discloses a side information fusion recommendation method based on a double-end multi-expert network and group balanced routing, and relates to the technical field of recommendation systems. In view of the problem that existing side information fusion methods ignore semantic space, feature scale and dynamic importance difference, and have high computational complexity and are difficult to balance extensibility and efficiency, the application carries out professional and differentiated fine-grained feature extraction by parallelly deploying multiple expert networks at the user end and the item end, introduces a group balanced routing mechanism to divide experts into expert groups and implement in-group balanced constraints and group-level sparse activation to reduce computational overhead, combines multi-layer graph convolution to iteratively aggregate neighborhood information and fuse the representation of each layer, adopts a joint loss function for end-to-end training, and finally generates a Top-K recommendation list based on inner product scoring. The application can improve recommendation accuracy, extensibility and actual running efficiency.

The application discloses a radio fuze anti-interference efficiency evaluation method and device, relates to the technical field of radar signal processing, and comprises the following steps: collecting a first anti-interference index matrix and a second anti-interference index matrix used for evaluating the performance of a radio fuze; performing capacity expansion processing and feature compression processing on the first anti-interference matrix and the second anti-interference matrix; obtaining a first optimization matrix and a second optimization matrix respectively; obtaining a first score vector and a second score vector corresponding to the first optimization matrix and the second optimization matrix respectively by using the score results of an expert group; and obtaining radio fuze anti-interference efficiency evaluation results by processing newly obtained anti-interference indexes by using a weighted first anti-interference capability evaluation neural network model and / or a second anti-interference capability evaluation neural network model. The method can take into account the independence and completeness characteristics of the evaluation index system, and can realize radio fuze anti-interference efficiency evaluation model training and evaluation under a small sample condition.

The invention discloses a vehicle voice assistant quality evaluation method and system, electronic equipment and a storage medium, and relates to the field of vehicle voice interaction, and the method comprises the steps: collecting interaction data of a user and a voice assistant, carrying out the preprocessing of the interaction data, generating a basic data set, formulating a scoring standard, and recruiting an expert group, performing expert consistency analysis through pre-labeling to generate a consistency analysis data set; obtaining a consistency score according to the consistency analysis data set; the experts with the consistency scores reaching a specific threshold value are screened, and formal labeling is carried out; taking a score mean value of a plurality of experts as a sample label, marking, inspecting samples with filtering variance exceeding a threshold value, and obtaining a training sample set with the score label; according to the training sample set, constructing an instruction quality evaluation model; obtaining a semantic similarity score through the instruction quality evaluation model; and according to the semantic similarity score, evaluating the instruction quality, and generating a final overall instruction quality score.