113 results about "Expert group" patented technology

The invention relates to the field of intelligent automatic driving, in particular to a knowledge-driven end-to-end automatic driving method based on a sparse expert mechanism and a diffusion model. Comprising the following steps: S1, sensing information processing and state coding; s2, sparse expert module construction and multi-task training; constructing a sparse expert module composed of a plurality of experts, and obtaining a reusable driving skill through multi-task behavior cloning training; s3, generating a diffusion strategy network and an action sequence; and on the basis of a diffusion model, a future multi-step control action sequence is generated from the current state condition, and a continuous and stable driving decision is formed. And S4, a continuous learning and task migration mechanism. According to the method, a combinable and explainable modular driving knowledge structure is constructed, so that the strategy modeling capability is remarkably improved; a diffusion generation mechanism effectively improves the smoothness and stability of the decision process; and a continuous learning and task migration mechanism of structural decoupling improves the long-term adaptability and deployment efficiency of the system.

The invention relates to an optimization method of a hybrid expert system, computer equipment, a readable storage medium and a program product. A plurality of experts contained in the MOE are deployed in a plurality of artificial intelligence chips in groups, and the method comprises the following steps: carrying out routing calculation on an original input tensor to obtain a routing calculation result; determining input element grouping information corresponding to each expert based on expert index information and expert weight information in the routing calculation result; taking the expert dimension as a parallel dimension, executing rearrangement operation for the original input tensor in parallel based on the input element grouping information, taking a rearrangement result as input information of an expert, executing matrix multiplication and accumulation operation, and taking the expert dimension as the parallel dimension, and based on the input element grouping information, executing anti-rearrangement operation of the matrix multiplication and accumulation operation result in parallel to obtain a final operation result. By adopting the method, the MOE reasoning performance can be improved.

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.

The invention provides a multi-agent collaborative decision-making method, system and device, a medium and a product, and belongs to the field of business support, and the method comprises the steps: carrying out the registration and role distribution of multiple agents based on a member registration and election algorithm, and determining a round table member and a round table chairman; acquiring an external decision demand based on the round table chairman, selecting a round table member corresponding to the external decision demand as an expert group member, sending the external decision demand to the expert group member, and generating a proposal corresponding to the external decision demand by the expert group member; summarizing proposals fed back by the members of the expert group based on the round table chairman, distributing the summarized proposals to the members of the expert group, and voting the summarized proposals by the members of the expert group to obtain a voting result; voting results fed back by the members of each expert group are obtained based on the round table chairman, an optimal proposal is determined according to the voting results, and the optimal proposal is used as a decision scheme. The democratic votes are processed in parallel through multiple agents, the advantages of multi-agent decision making are exerted, and the decision making risk is reduced.

The embodiment of the invention provides a data processing method based on a grouped hybrid expert model, electronic equipment and a medium. According to the method, multiple pieces of input feature data are acquired, and for each piece of input feature data in the multiple pieces of input feature data, at least one target expert group matched with the input feature data is determined from multiple routing expert groups through a group routing unit; and determining at least one activation expert matched with the input feature data from each target expert group through an expert routing unit, and performing data processing on the input feature data through the sharing expert and the at least one activation expert to obtain a corresponding processing result. According to the method, the routing experts with the high adaptation degree with the input feature data are determined as the activated experts, distribution of the routing experts according to needs is achieved, the method only needs to carry out weight calculation on the routing experts in the target expert group, the calculation amount in the data processing process is reduced, the calculation cost is reduced, and the calculation efficiency is improved.

The invention discloses a hybrid expert model training optimization method based on expert calculation load balancing scheduling, and the method comprises the steps: firstly predicting current iteration global expert load data, and obtaining sampling data; and secondly, designing a multi-dimensional performance perception expert placement evaluation method, and realizing quantitative comparison and decision in a stage of searching an expert placement scheme by converting multi-dimensional communication and calculation into a unified time delay index. And then designing an expert placement strategy by adopting an expert grouping search algorithm of dynamic load feature perception and a matching algorithm of expert grouping and resource perception based on the sampling data and an expert placement evaluation method. Finally, on the basis of an expert placement strategy, an asynchronous communication strategy is adopted to implement expert and optimizer parameter scheduling, and training optimization is completed. According to the method, by improving the computing load balance and asynchronous communication concealment between the devices, synchronous waiting is reduced, and the training efficiency and the overall performance of the hybrid expert model are effectively enhanced.

The invention relates to a task execution method and device based on a hybrid expert model, equipment, a storage medium and a program product, and relates to the technical field of artificial intelligence. The calculation utilization rate and the calculation efficiency of the equipment can be improved. The method comprises the steps that the number of lexical units distributed to each expert in equipment is determined, the number of lexical units of each expert group in the equipment is obtained according to the number of lexical units of each expert, the expert group comprises one or more experts in the equipment, and an execution sequence corresponding to each expert group is determined according to the relative size of the number of lexical units of each expert group in the equipment, different devices are configured with the same number of expert groups, each expert group comprises the same number of experts, the expert groups in the same execution sequence in the different devices have the same relative size in the respective devices, and the communication task and the calculation task of each expert group are sequentially executed according to the execution sequence. The computing task of each expert group in the device is parallel to the communication task of another expert group in the device.

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 remote sensing image ship target detection method based on a geographic information hybrid expert model. The method depends on a hybrid expert model and a Mask-RCNN network in deep learning, and is a visible light remote sensing image ship target deep learning detection method suitable for a multi-spatial resolution and complex geographical environment. In a Mask-RCNN feature extraction link, two expert groups are introduced, and two feature extraction expert groups guided by resolution and latitude and longitude geographic information respectively are constructed. In this way, detection of the ship target in the multi-resolution complex background visible light remote sensing image is achieved. The method not only has an accurate multi-scale target position sensing capability, but also can effectively eliminate ground feature interference in various geographic areas and complex background environments, and makes up for the deficiency of a current deep learning ship detection method in the aspect of multi-resolution complex background image research.

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.

The present disclosure relates to an information processing apparatus and method capable of suppressing an increase in a load of a reproduction process.A scene description file that describes a scene of 3D object content is generated, the scene description file including information associated with Media Presentation Description (MPD) that stores metadata of the 3D object content distributed by using Moving Picture Experts Group Dynamic Adaptive Streaming over HTTP (MPEG DASH) and information regarding encoding of Representation included in Adaptation Set in the MPD. Furthermore, the scene description file is analyzed, the 3D object content to be decoded is selected on the basis of the information regarding the encoding of the Representation, and the encoded data of the selected 3D content is decoded. The present disclosure can be applied to, for example, an information processing apparatus, an information processing method, or the like.

A method for processing media content in Network-Based Media Processing (NBMP) of Moving Picture Experts Group (MPEG) includes obtaining at least one function from a function repository storing one or more functions for processing media content, each of the at least one function including a function descriptor; based on the obtained at least one function, obtaining a task for processing the media content, the task including a task descriptor, the function descriptor and each of the task descriptors including a flag indicating whether the descriptor describes a function group, the function group including multiple functions of the one or more functions; and using the obtained task to process the media content based on the task descriptor.

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 application relates to the field of intelligent automatic driving, and particularly relates to a knowledge-driven end-to-end automatic driving method based on a sparse expert mechanism and a diffusion model. The method comprises the following steps: S1: perception information processing and state coding; S2: sparse expert module construction and multi-task training; a sparse expert module composed of multiple experts is constructed, and reusable driving skills are obtained through multi-task behavior cloning training; S3: diffusion strategy network and action sequence generation; based on the diffusion model, a future multi-step control action sequence is generated from the current state condition, and a continuous and stable driving decision is formed; and S4: continuous learning and task migration mechanism. The present application constructs a modular driving knowledge structure that is combinable and interpretable, significantly improves the strategy modeling capability; the diffusion generation mechanism effectively improves the smoothness and stability of the decision-making process; the continuous learning and task migration mechanism with structural decoupling improves the long-term adaptability and deployment efficiency of the system.

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.

The embodiment of the invention provides a data processing method and device suitable for a large language model, and the method comprises the steps: carrying out the grouping of each first expert network in a conventional mixed expert model architecture replacing a feedforward network, and adding a second expert network for each obtained expert group. In the data processing process, the activation condition of the second expert group depends on whether the first expert group in the corresponding expert groups is activated or not. When any first expert group in the respective expert groups is activated, the respective second expert group is activated. In this way, differentiated and adaptive feature data processing can be provided for various business scene data, and the adaptive capacity of a large language model in various scenes is improved.

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.

A method for parsing a scene description document, including: determining an index value of a target haptic object description module; obtaining the target haptic object description module from a moving picture experts group (MPEG) haptic description module in the scene description document according to the index value of the target haptic object description module; and obtaining description information of a haptic media accessor according to the target haptic object description module, where the haptic media accessor is an accessor configured to access haptic rendering data of a haptic media file declared in an MPEG media description module.

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.