508 results about "Reference modeling" patented technology

The invention relates to the field of chip verification, and provides a chip verification method, device and equipment, a medium and a chip. The method comprises the following steps: establishing a dynamic simulation verification environment of a to-be-verified design, and generating a plurality of test scenes and corresponding test excitation according to a design specification definition; sending the test excitation to a driver through a sequencer, converting the test excitation into a signal conforming to a to-be-verified design interface protocol by the driver, and transmitting the signal to the to-be-verified design; the monitor collects an input signal and an output signal of a to-be-verified design in real time, converts the input signal and the output signal into transactions, and transmits the transactions to the scoreboard; comparing the reference model with an output signal of the to-be-verified design to generate a dynamic simulation verification result; according to the dynamic simulation result, the state space is reduced, state space traversal is carried out on a design part which is not covered by dynamic simulation in the design to be verified, and a formal verification analysis result is generated; and evaluating the to-be-verified design according to the formal verification analysis result.

There are provided a method for designing a spectacle lens and a related technique thereof, the method including: a modeling step of dividing a pattern into multiple models with a deviation from a normally worn state of the spectacle lens as decentering, in which a reference model, a decenter model, and a tilt model are prepared as the multiple model; a sensitivity calculation step of calculating a decenter sensitivity and a tilt sensitivity; and a design step of using a base curve value in the vicinity of a balance solution as a base curve of the spectacle lens, wherein a base curve value c [unit: diopter (D)] which is a curvature of a surface in a region H where the on-retinal non-convergence region is not provided on an object-side surface is taken as x-axis, and the decenter sensitivity and the tilt sensitivity [unit: diopter (D)] are taken as y-axis, and an intersection of a plot of the decenter sensitivity and a plot of the tilt sensitivity is taken as the balance solution.

The invention discloses a nondestructive testing method and system and a data processing method, and relates to the technical field of nondestructive testing. Comprising the steps of obtaining initial detection data of a detected component; establishing at least one reference model according to the initial detection data, and obtaining simulation data corresponding to each reference model; determining target data according to the initial detection data and simulation data; and obtaining subsequent detection data, and comparing the subsequent detection data with the target data to form an evaluation result. According to the invention, high and low frequency mixed excitation signals are adopted, so that the penetrating power and resolution of detection are improved, surface defects and buried defects can be detected at the same time, and the comprehensiveness and accuracy of detection are remarkably enhanced; a picked complex response signal is decoupled by using an orthogonal phase locking method, a magnetic field signal and an electric field signal are effectively separated, the signal-to-noise ratio and the detection precision are improved, and accurate discrimination of defect types, depths and orientations is realized by establishing a reference model and acquiring analog data.

The invention discloses an intelligent event studying and judging method based on machine learning, which comprises the following steps of: extracting features from multi-source event data, constructing an event fragment set with a uniform structure according to a preset time window, identifying fragments with stable features in the event fragment set as normal samples, constructing a reference model through an MCD algorithm, and analyzing the normal samples. The method comprises the following steps: extracting feature distribution in a normal state, comparing a to-be-analyzed event with a reference model, calculating feature offset, forming a behavior trajectory, determining an anomaly judgment range by adopting an elliptical envelope algorithm, and finally evaluating an event risk level and dynamically adjusting reference sample composition according to a continuous anomaly condition to realize intelligent identification and risk judgment of the event. According to the invention, dynamic perception and intelligent identification of complex events can be realized.

The invention discloses a cue word compression method and system based on TF-IDF and cross entropy, belongs to the technical field of large model cue word compression, and aims to solve the problems that redundant information is introduced into long cue words, the model efficiency is reduced and the cost is increased. To-be-compressed content is divided into sentences at the sentence level and then converted into embedded vectors, and the Euclidean distance is calculated in combination with problem vectors so as to screen related sentences; calculating a TF-IDF value at the word level through a word frequency and an inverse document frequency to extract keywords and recombine sentences; and selecting a reference model and a basic model at the Token level, identifying the key Token based on a cross entropy loss difference value, and splicing the key Token in sequence to generate a compressed cue word. According to the method, a complex calculation structure is avoided, the inference efficiency is improved while the semantic integrity is maintained, and the resource consumption is reduced.

The invention relates to a motor energy-saving control method for adaptive parameter adjustment. The method comprises the following steps: constructing an operation parameter sequence and comparing the operation parameter sequence with a preset reference model by collecting the rotating speed, the torque and the current signal of a motor in real time to generate a parameter deviation vector; based on a deviation threshold comparison result, carrying out noise processing on the overrun deviation to obtain a filtered sequence, and calculating a time delay degree in combination with historical parameters; calculating a compensation gain according to the time delay, fusing the compensation gain with the filtered deviation to generate a control instruction sequence, correcting the compensation gain through fuzzy control to obtain a stabilization parameter, and further generating a correction control instruction sequence; and finally, acquiring load data, fusing the load data with the correction instruction to obtain a system operation characteristic value, and generating an optimization state identifier when a judgment standard is met. By adopting the method, adaptive adjustment of the control parameters can be realized, the dynamic working condition is accurately responded, and the energy-saving efficiency of the motor under the variable-load working condition is improved.

The invention relates to a text-to-SQL (Structured Query Language) generation method and system based on large language model fine tuning. The method comprises the following steps: collecting a triple data set; generating a reasoning path for the triple data set, and obtaining an optimized data set comprising the triple data set and the corresponding reasoning path; selecting a basic model, and performing supervised fine tuning training on the basic model through the optimized data set to obtain a reference model; executing feedback through a database corresponding to an output result of the reference model, and performing direct preference optimization training on the reference model to obtain a generative model; and performing SQL generation on a to-be-generated text through the generation model to obtain a generation result. The method utilizes the advantages of the model language reasoning ability and the preference learning algorithm to improve the accuracy of the model in the aspect of text-to-SQL (Structured Query Language) generation tasks.

The invention discloses a 3D art model intelligent generation system and method based on multi-source data fusion, and relates to the technical field of computer aided design and graph generation, and the system comprises a multi-source data input module which is used for receiving a conceptual design drawing, text description and a reference 3D model; the feature extraction module comprises an image feature extraction unit used for extracting a style feature vector and a structure contour vector of the conceptual design drawing; and the text semantic analysis unit is used for outputting a key attribute tag vector described by the text. According to the 3D art model intelligent generation system and method provided by the invention, through multi-source data input including the concept design drawing, the text description and the reference 3D model, the design intention is comprehensively fused, the limitation of a single data source generation model is solved, and the dynamic weight distribution strategy and the closed-loop optimization mechanism of the 3D art model intelligent generation system and method are high in practicability. The geometric shape and style characteristics of the generated model are highly consistent with the design intention, and the workload of manual later correction is reduced.

The invention provides a preference alignment optimization method based on reward-driven selective punishment, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining intelligent question and answer training data, and constructing an intelligent question and answer training sample set which comprises a plurality of intelligent question and answer training samples; taking a to-be-optimized large language model as a strategy model and a reference model; and training the strategy model by using the intelligent question and answer training sample set, and measuring the offset amplitude of the strategy model before and after training by using the reference model to obtain an optimized large language model. According to the method, implicit reward signals in the model are introduced, preference data are divided into multiple categories according to implicit reward distribution generated by the model, a dynamic weight function is designed, differential weighted optimization is carried out on different categories of samples, reinforcement learning of high-quality samples and suppression of low-quality samples are achieved, and the method has the advantages of being high in robustness and high in robustness. Weight of low-quality or conflict samples is reduced while high-quality sample learning is enhanced, noise interference is suppressed, and overfitting is prevented.

A method for designing a spectacle lens and a related technique thereof, including: a modeling step of dividing a pattern into multiple models with a deviation from a normally worn state of the spectacle lens as decentering, wherein a reference model, decenter model, and tilt model are prepared as the multiple model; a sensitivity calculation step of calculating a decenter and a tilt sensitivity; and a design step of using a base curve value in the vicinity of a balance solution as a base curve of the spectacle lens, wherein a base curve value which is a curvature of a surface in a region where the on-retinal non-convergence region is not provided on an object-side surface is taken as x-axis, and the decenter and tilt sensitivities are taken as y-axis, and an intersection of a plot of the decenter sensitivity and the tilt sensitivity is taken as the balance solution.

The invention provides a chip verification method and device, equipment, a medium and a program product, and the method comprises the steps: receiving a first operation instruction of a to-be-verified module and a second operation instruction of a reference model in parallel, the reference model being a function model used for simulating the expected behavior of the to-be-verified module; searching a first instruction record matched with the first operation instruction from a request queue of the reference model, and searching a second instruction record matched with the second operation instruction from a request queue of the to-be-verified module; and determining a verification result of the to-be-verified module according to a comparison result of the first operation instruction and the first instruction record and / or a comparison result of the second operation instruction and the second instruction record. According to the invention, a structured and reusable universal chip verification method is realized, so that a tedious customized scoreboard design is replaced, and the efficiency and accuracy of verification work are greatly improved.

The invention discloses a construction product style migration method based on a diffusion model and structure control, and belongs to the field of computer-aided industrial design. Obtaining a structure reference STEP model and a target style image, and respectively extracting feature token sequences of the structure and the style; splicing the structure and style feature token sequence as a mixed condition vector of the conditional diffusion model; when the model diffuses in a submerged space, decoupled double-path attention layers are used for calculating cross attention output of structure and style features respectively, time-varying weights are added to serve as cross attention output of hybrid conditions for decoupling coding, and a 2D rendering graph conforming to a target structure and style is generated through gradual de-noising. The conditional diffusion model is run a plurality of times to generate a batch of candidate 2D renders. And screening out a qualified 2D rendering graph based on NURBS curved surface reconstruction. According to the invention, a structure-style dual-condition control mechanism is adopted to realize accurate balance between high-fidelity style migration and engineering constraint.

The present disclosure provides a model training method and device, and a data processing method and device. The method of the present disclosure uses a reference model to screen an existing instruction dataset for an instruction whose model fitting difficulty meets a preset condition, and the method can screen the instruction dataset for a challenging instruction having high model fitting difficulty as a seed instruction. A plurality of similar instruction samples are generated by means of expansion on the basis of the seed instruction, thereby obtaining more challenging instruction samples, a training set comprising the instruction samples and reference responses for the instruction samples is constructed, and knowledge distillation can be achieved by using the reference model on the basis of the existing instruction dataset, thereby obtaining a training set containing higher-quality instruction data. Furthermore, using the training set to train a deep learning model enhances the capability of the deep learning model to handle more complex and challenging tasks, and improves the performance of a trained target model.

The invention relates to a verification method and device of a DMA controller, computer equipment, a readable storage medium and a program product. The method comprises the following steps: in response to a starting instruction of a verification script, extracting a test case of a to-be-verified DMA controller based on a pre-constructed verification environment, sending the test case to the to-be-verified DMA controller and a corresponding reference model according to a target path of the test case, and obtaining a first running result of running the test case by the to-be-verified DMA controller, and obtaining a second running result of running the test case by the reference model, comparing the first running result with the second running result, and generating a verification result of the DMA controller to be verified. The test case is automatically generated, so that the workload of manual writing is reduced, and the efficiency and quality of the verification process are remarkably improved.

The invention discloses a power industry large model continuous pre-training method and system based on dynamic self-constraint, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining industry pre-training corpora and instruction training corpora, dynamically adjusting the mixing ratio of the industry pre-training corpora and the instruction training corpora through a curriculum-type strategy, and obtaining an industry pre-training corpora and an instruction training corpora; obtaining a dynamic mixed data set; configuring a reference model based on the dynamic mixed data set, and training a target power industry large model by adopting a differential loss function and the reference model for different types of data in the dynamic mixed data set; according to the differential loss function, self-adaptive KL divergence is calculated according to inter-partition optimization logic, and the self-adaptive KL divergence is adopted to construct a loss function; and obtaining the probability of the reference model through an online reasoning framework, and enabling the training to be continuously carried out based on the probability of the reference model. According to the method, the knowledge conflict problem in professional field training is effectively solved, and the generality of the model is kept while the professional property of the power field is improved.

The invention discloses a photovoltaic module construction quality identification method based on computer vision and three-dimensional modeling. The method comprises the following steps: S1, collecting an original image sequence of a photovoltaic construction site and carrying out image preprocessing; s2, outputting a semantic tag graph and a two-dimensional space boundary graph through an improved BiSeNet network; s3, using a mask constraint SIFT algorithm to extract cross-view key point features, generating a dense three-dimensional point cloud according to multi-view stereo reconstruction, and outputting a structure three-dimensional geometric model; s4, mapping the semantic tag graph and the two-dimensional space boundary to the structure three-dimensional geometric model to obtain a semantic three-dimensional model; s5, performing spatial registration on the semantic three-dimensional model and the reference model, and calculating spatial error parameters of the photovoltaic module; s6, performing compliance discrimination on the spatial error parameters, and outputting a quality discrimination result; and S7, generating a construction quality evaluation report. According to the invention, automatic identification and accurate evaluation of the photovoltaic construction quality are realized, and the detection efficiency and the discrimination accuracy are improved.

The invention discloses a VPSC model construction method based on an ABAQUS sub-model, and belongs to the field of computational material science and engineering.The VPSC model construction method comprises the steps that a global model is established according to the size of a part, and an ABAQUS input file is generated; selecting a local area of a part in the global model, determining a unit number of the area, constructing a crystal plasticity constitutive model through UMAT, and adding a plurality of randomly oriented crystal grains to the local area in an ABAQUS input file to form a reference model; grain nodes and orientation information in the reference model are read through an ABAQUS script, a grain model is created, corresponding orientation is given to sub-models, sub-model boundary conditions consistent with global model deformation are applied to grain geometric boundaries, and a VPSC model is constructed. According to the method, the grain orientation is locally refined through the sub-model technology, and the VPSC sub-model is automatically generated in combination with the script, so that the calculation complexity is remarkably reduced.

The invention discloses a deep neural network model freezing training optimization method based on tensor similarity. According to the method, a reference model generation module regularly generates a single-layer reference model to support real-time tensor similarity evaluation; the tensor similarity calculation module generates a normalized Gram matrix by using the activation output, and accurately evaluates the stability of the active layer; the freezing decision module can smooth instantaneous fluctuation in an evaluation process based on a moving average value of tensor similarity so as to make a steady freezing decision; the tensor I / O module caches the forward propagation result of the freezing layer, and repeated calculation is avoided. According to the method, the calculation amount of back propagation and forward propagation in the deep neural network training process can be effectively reduced, and the calculation resource utilization rate in the training process is improved. The method is remarkably superior to an existing freezing method in deep neural network model training tasks such as image classification, target detection and image segmentation, and the training stability and efficiency are improved while the final precision of the model is not sacrificed.

The invention relates to the field of function verification of digital integrated circuits, and discloses an atomic-scale computing chip verification method based on a UVM. The method comprises the following steps: firstly, building a UVM simulation verification platform comprising each core component; then, a software program is used for generating test excitation with physical significance, wherein the test excitation comprises information such as configuration, functional, pseudo potential and track files; then respectively inputting the test excitation into the established UVM verification platform and the software reference model; the UVM verification platform applies the test excitation to the to-be-tested design and outputs a calculation result; the reference model also correspondingly generates a reference result; and finally, comparing the output of the to-be-tested design with the output of the reference model, and verifying the correctness of the function of the atomic calculation chip through visual auxiliary analysis and quantitative error analysis. Through excitation generation based on physical constraints and an effective error evaluation method, the function verification problem of the atomic-scale computing chip can be solved.

The invention discloses a large model-based safety production hidden danger identification method, which comprises the following steps of: acquiring to-be-queried data, and identifying safety production hidden dangers by utilizing an identification model; wherein the recognition model carries out reinforcement learning through the following steps: carrying out multiple sampling on to-be-queried data by utilizing a reference model, and generating a response group; calculating an advantage value of each element in the response group; and optimizing the identification model based on each advantage value. According to the method, the accuracy, the compliance and the interpretability of object recognition and hidden danger analysis in a professional scene by the model can be effectively improved on the premise of not depending on large-scale labeled data.

The invention discloses a chip verification method and device based on simulation result comparison, equipment and a medium, and relates to the field of chip verification, and the method comprises the steps: obtaining a simulation result and an expected result generated by a to-be-tested chip and a reference model based on the same input excitation; the reference model is a pre-constructed model consistent with the function of the to-be-tested chip; partitioning the simulation result and the expected result, and performing Hash calculation based on each simulation data block and each expected data block obtained by partitioning to obtain Hash values corresponding to each simulation data block and each expected data block; and verifying the to-be-tested chip by comparing the consistency of the hash values of the simulation data blocks and the corresponding expected data blocks. According to the method, the partitioning technology and the Hash algorithm are combined, the Hash value of each simulation data block and the Hash value of the corresponding expected data block can be compared in parallel, the chip verification efficiency is improved, when the chip verification goes wrong, which data block goes wrong can be accurately positioned, and the chip verification accuracy is improved.

The invention discloses a direct preference optimization-based large model post-alignment training method and system. The method comprises the following steps of: (1) constructing a static reference model and a strategy model; (2) optimizing preference data by using an implicit reference model, and (3) adjusting a strategy model by optimizing an objective function so that the strategy model better fits the user preference. According to the method, the limitation of the existing DPO and SimPO methods is solved by introducing a new reference model expression, for example, the method depends on a suboptimal reference model or uses a fixed reward margin. By adjusting the balance between the strategy model and the reference model, personalized reference model setting for each pair of responses is realized, and meanwhile, a theoretical guarantee is provided and the KL divergence is effectively controlled. And the alignment performance and the winning rate of the model are remarkably improved, and the method is a robust LLM fine tuning method.

The invention relates to the technical field of intelligent production, and discloses an intelligent tool reference model construction method for complex product assembly and an engineering implementation method thereof.The model construction method comprises the following specific steps that geometric features, tool parameters and external load working condition data of parts needing to be assembled are collected; establishing a database of the structured assembly scene; based on the database, constructing a multi-dimensional time sequence correlation model comprising an in-position-measurement-attitude adjustment-docking model, a dimension chain precision mapping model reflecting a mapping relation between a load condition and dimension chain precision, and a tool function module library of a standardized tool; and performing multi-model coupling on the time sequence correlation model, the precision mapping model and the tool function module library to form a tool reference model. The problem that an existing intelligent assembling technology is insufficient in application range is solved, and the beneficial effect that the assembling efficiency and flexibility can be improved is achieved.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a generative machine learning model using multi-turn training examples that include sequences of example inputs and example outputs. In one aspect, a method comprises, at each of a sequence of training iterations: obtaining a plurality of example interactions, wherein each example interaction includes example model inputs and example model outputs for a plurality of time steps; obtaining one or more reference interactions for each example interaction, wherein each reference interaction includes reference model inputs and reference model outputs for a plurality of time steps; determining a preference measure for each example interaction based on a comparison between the example interaction and the reference interactions for the example interaction; and updating the target generative machine learning model to optimize an objective function that includes the preference measures for the plurality of example interactions.

The invention relates to the technical field of manufacturing optimization, and discloses a manufacturing process optimization decision-making method, device and equipment based on big data analysis, and the method comprises the steps: collecting data and quality evaluation information of each link of a target product manufacturing process, forming reference data, continuously recording the reference data through a big data platform, and aligning the reference data with key characteristics; according to the method, a plurality of manufacturing reference models are obtained, key factor analysis is performed on the models, optimization factors are extracted, an objective function containing quality, efficiency and cost constraints is constructed, iterative optimization solution is performed, and an optimization result is verified through a big data platform until an optimal decision scheme is obtained. The production efficiency is improved, the cost is reduced, the stability of the product quality is ensured, and the problem that in the prior art, multi-target optimization is difficult to carry out on the multi-link manufacturing process is solved.

The invention relates to a mechanical arm self-adaption compliance control method and system based on model reference self-adaption and impedance parameter online identification, and belongs to the field of robots. The method comprises the steps that a mechanical arm task space dynamics model is established; designing a reference model; a recursive least square method is adopted, and an equivalent stiffness matrix and a damping matrix of the interaction environment are identified online; designing a composite adaptive law; the expected rigidity of the reference model is dynamically adjusted according to the environment rigidity obtained through identification; and according to sensor data collected in real time, the mechanical arm task space dynamics model, the robot parameter self-adaption law, the environment rigidity, the environment damping and the environment parameter identification robust item, control force is generated, and the mechanical arm is driven through the control force. According to the method and the system, the environment characteristics can be sensed online, and the compliant behaviors can be adaptively adjusted, so that safe, efficient and high-robustness interaction of the mechanical arm in a complex and unknown environment is realized.

The invention discloses a federal forgetting method and system based on projection gradient rise, and belongs to the technical field of machine learning, and the method comprises the steps: obtaining information of N clients and a central server in a federal, and carrying out the T-round training of the federal through a federal weighted aggregation learning algorithm; performing data distillation on each client to obtain a distillation data set; acquiring a federal global model and a local model of the forgotten client in T-1 rounds, and solving a reference model on the forgotten client; the client optimizes parameters in an l2 norm ball with the radius of delta around the reference model; sending the federal global model to all clients, and performing opposite training strategies on the forgotten clients and the remaining clients; re-aggregating the local models of the forgotten client and the remaining clients; and obtaining a final federal forgetting model until E rounds of training are completed. The problems that a non-distributed machine forgetting method caused by distributed knowledge penetration is difficult to be used for federal learning and disastrous forgetting is caused by gradient rise of federal forgetting are solved.

The invention provides a text-to-structured query statement method based on a large language model and reinforcement learning, and relates to the technical field of information, the method comprises the following steps: integrating a natural language problem and a database mode into a unified prompt template to obtain a candidate structured query, and generating a reference structured query by a reference model; constructing a multi-dimensional reward framework, and performing weighted aggregation on multi-dimensional rewards to obtain corresponding final reward scores; calculating a KL penalty value between the output of the strategy model and the output of the reference model based on the candidate structured query and the reference structured query to obtain a constraint of stable strategy update; updating the strategy model parameters through back propagation iteration to obtain an updated strategy model; and analyzing the prompt template by using the updated strategy model to obtain a text-to-structured query statement processing result, and completing the process from the text to the structured query statement. The problems that existing structured query generation is low in accuracy and semantic consistency is difficult to guarantee are solved.

Systems and methods are disclosed for implementing entity-relationship privacy for machine learning models. Raw data may be used to fine-tune a large language model that has been pre-trained with publicly available data. Raw data is first modified to generate training data that provides privacy for sensitive relationships between entities. The raw data is first analyzed to identify sensitive entity relationships, where each of the sensitive entity relationships include a first entity and a second entity. Then, for each sensitive entity relationship, at least one of the first and second entities is replaced with a non-sensitive entity generated by the reference model. Then the resulting training data may be used to further train, or fine-tune, a large language model that has been pre-trained with publicly available data.

The invention relates to the technical field of electronic design, and discloses a bit stream verification method and device, equipment, a storage medium and a program product.The bit stream verification method comprises the steps that an execution file corresponding to a target test case is executed, and a bit stream file and a routing file of the target test case are obtained; determining configuration information of the target test case based on the bit stream file and the routing file, and configuring a test file of the target test case based on the configuration information; based on the routing file, configuring an input signal and a reference model corresponding to the target test case; and based on the input signal, respectively testing the test file and the reference model, and determining a bit stream verification result of the target test case. Thus, simulation verification of the bit stream file of the target integrated circuit is deconstructed, simulation verification of the bit stream file is performed on each test unit in the target integrated circuit, simulation verification of the bit stream file is realized through the reference model, simulation of the bit stream file is simplified, simulation efficiency of the bit stream file is further improved, and simulation time is shortened.