66 results about "Input design" patented technology

The invention proposes systems and methods for testing on-device machine learning models such as network models of a device based on an access to normal input and output channels, wherein a structure of a model is designed through training such that the model produces distinctive outputs to a given set of test inputs only so long as its internal structure remains in a desired state. Models may be rendered susceptible to such testing via model pre-training with training inputs designed to train the model into an appropriate structure and / or to cause the model to produce a distinctive output if later presented with a certain set of test inputs. If the structure of the model remains within allowable limits, the device will produce a predictable output when tested. If not, the device may be enforced to return to a pre-trained model.

The invention discloses an SQL statement structure verification system based on large model and knowledge graph fusion enhancement. The SQL statement structure verification system comprises a knowledge graph construction module, an input design module, a verifier design module and an output design module. According to the method, a knowledge graph is introduced as a structured semantic support, and a closed-loop enhancement processing flow of SQL statements from generation, verification to optimization is realized in combination with a structure perception cue word design, a rule verification mechanism and a Function Call feedback interface; the defects that an existing Text2SQL method is insufficient in structural understanding, lack of semantic reasoning, weak in generalization ability, dependent on computing power and the like are overcome. According to the method, triple guarantee of semantic perception, rule driving and model assistance is realized, the accuracy, robustness and interpretability of SQL generation are remarkably improved, and the cognitive load and operation risk of non-professional users in database interaction are effectively reduced.

The invention belongs to the technical field of automobile structure design, and particularly relates to a large-model-based automobile body structure generative design method and system, and the method comprises the steps: building a multi-source database containing automobile body structure pictures, design variables and mechanical properties; training a vehicle body structure performance evaluation model and generating an evaluation model according to the database; on the basis of the generated evaluation model, the general text graph large model is finely adjusted, and a vehicle body structure generative design large model is obtained; generating a structure picture by using the obtained large model, and establishing a structure size evaluation model in combination with a database; inputting design requirements and constraint conditions, generating a vehicle body structure, evaluating the performance and size of the vehicle body structure, and outputting a final result. According to the method, the problems of low efficiency and strong dependence on experience of engineers in an existing automobile concept design stage are solved, the efficiency and creativity of automobile body structure design are improved, the design period is shortened, manual intervention is reduced, and automation and intelligence of automobile body structure design are promoted.

The invention discloses an online moment compensation and control method for an elastic joint, belongs to the technical field of robot joint precision control, and aims at performing online moment error compensation for the elastic joint based on adaptive filtering and a neural network and realizing accurate moment control based on compensated moment measurement information. Specifically, the method comprises the following steps: respectively collecting angle information of double encoders, carrying out noise reduction processing, converting a time domain signal of an angle into a frequency domain signal through discrete Fourier transform, and carrying out adaptive filtering based on a recursive least square algorithm (RLS); taking the obtained angle error information as input, performing adaptive prediction and compensation on a nonlinear error of an encoder angle based on an RBF neural network, solving the rigidity of an elastic element, and verifying the accuracy of torque identification through a torque sensor; finally, the solved torque value serves as reference input, an elastic joint torque control algorithm is designed, and high-precision torque control is achieved.

The invention discloses a design information generation method and device of an intellectual property core, electronic equipment and a medium. The method comprises the steps that input design associated information of the intellectual property core is acquired; determining a current design direction type according to the design association information; according to the design direction type and a port signal naming rule of a preset template library, a standardized top-layer code is generated, and the standardized top-layer code comprises standardized signal code information, a standardized time sequence constraint file and a standardized power domain constraint file. According to the embodiment of the invention, based on a design direction type and a port signal naming rule of a preset template library, port naming standardization is automatically carried out on top-layer codes: signal code information, a time sequence constraint file and a power domain constraint file, so that the problem that design information such as top-layer HDL codes, instantiation codes and SDC, UPF and the like of a current digital IP needs to be written manually is solved; time and labor are consumed, efficiency is low, and errors are prone to occurring.

The invention provides a rapid design model reconstruction method and system based on parameterized feature decoupling, and relates to the technical field of data processing, and the method comprises the steps: selecting a product template from a parameterized product template library constructed according to a feature decoupling idea; on the basis of the selected product template, a new design scheme is obtained through saving operation; based on the new design scheme, determining a process type selection calculation book through project requirements, inputting main body parameters of the design scheme according to the process type selection calculation book, and storing the main body parameters to obtain a parameterized design scheme; on the basis of a parameterized design scheme, parameters of key parts are sequentially input and stored according to predefined part types in a product template, and complete parameter configuration is obtained. Normalization and standardization of product design are achieved, and finally the purposes of shortening the development period and reducing the product cost are achieved.

To provide a method, a device, a system, and an article for utilizing an artificial intelligence (AI)-based model to update a product design on the basis of an execution result of a generated verification code.SOLUTION: A device including a programmable circuit instantiates: generating, using a first trained artificial intelligence (AI)-based model, on the basis of an input design, a verification code; performing the verification code to generate a verifiability score for the input design; and adjusting, using a second trained AI-based model, on the basis of the verifiability score, the input design.SELECTED DRAWING: Figure 7

Disclosed herein is a platform comprising a hardware compiler framework to directly instrument an RTL representation of an input design with a fault injection processor enabling the execution of arbitrary error injection requests from the user and communication with the design under test to target specific design sections for fault injection.

A method for designing a unit cell may include receiving input data via a user interface, the input data including one or more input design parameters for a unit cell, rendering a virtual three-dimensional (3D) representation of the unit cell within the user interface, based on the input design parameters, receiving, via the user interface, at least one modification command modifying the virtual 3D representation of the unit cell, altering the input data based on the received modification command, resulting in modified design parameters for the unit cell differing from the input design parameters, and outputting the modified design parameters for the unit cell.

The invention relates to the technical field of highway engineering digital management and artificial intelligence, and provides a highway engineering drawing, quantity and price integrated cost compilation method and system based on AI enhancement. The method comprises the steps of obtaining a to-be-processed design drawing; based on AI multi-modal recognition capability, processing the input design drawing, and performing automatic extraction, calculation and cleaning to form a multi-level engineering quantity combination data set based on standard EBS classification and coding; automatically associating the project amount combination data set to a budget cost project, a list sub-item or a quota sub-item based on a rule engine, and generating cost data of each stage according to different compilation depths and data category requirements of cost of different stages; performing penetration or backtracking on data of each link from input to output, and generating a graph, quantity and price integrated management framework; and when the design drawing is changed, updating the related engineering quantity combination data set and the cost number based on the drawing, quantity and price integrated management framework so as to generate standardized cost data and reports.

Process control parameters are predicted to fabricate an object using deposition. An input design geometry is provided for the object. A training data set includes past post-build physical inspection data for a plurality of objects that comprise at least one object that is different from the object to be physically fabricated; and training data generated through a repetitive process of randomly choosing values for each of multiple process control parameters and scoring adjustments to the multiple process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments. A machine learning algorithm is trained using the provided training data set and a predicted optimal set of the multiple process control parameters is generated for initiating and performing the deposition process to fabricate the object.

Systems and methods for valve mounting kit design automation. Valve mounting kit (VMK) design systems and methods are presented that implement: a graphical user interface (GUI) configured to receive input from a user, the input defining at least one parameter for a VMK; and a computer-implemented rule engine configured to receive input from the GUI, apply a set of rules to the input, where the set of rules includes a rule-based relationship between the at least one parameter and a design of the VMK and a predefined case-based inference rule, and design a geometric parameter of the VMK based on applying the set of rules to the input, and generating a VMK design output via the automated design tool, the output including at least one of a master model, a manufacturing drawing, a computational report, or a bill of materials corresponding to the design of the VMK.

The invention relates to a software function point identification method fusing a large model and multiple clustering analysis, and solves the problems of subjective deviation, inconsistent naming and low auditing efficiency caused by function disassembly depending on artificial experience in traditional function point measurement and calculation. The method comprises the following steps: inputting a design scheme, and constructing a document level semantic tree; obtaining feature information described by corresponding function points in the semantic tree, and analyzing the feature information to determine candidate function points; fusing the candidate function points according to semantic tree hierarchy alignment; and carrying out differentiation processing on the candidate function points, and carrying out duplicate removal on the similarity frequency according to the candidate function points to obtain the function points. According to the method, based on construction and analysis of a document hierarchy semantic tree, feature positions and large model reasoning ability are combined, and accurate extraction and auditing of function points are achieved. And differentiation is formed by adopting multiple clustering, and a co-cooperation relation matrix is constructed through clustering cross validation, so that the function point de-duplication accuracy is greatly improved.

The invention discloses a GPU program soft error elasticity prediction method based on an error propagation knowledge graph. The method comprises the steps that static and dynamic information of a program is acquired; single-particle bit flipping fault injection is carried out at the register or memory level, and the occurrence rate of different types of error results after bit flipping occurs at each fault point of the program is obtained; preprocessing data obtained by fault injection, and encoding heuristic features; the method comprises the following steps: pre-training a Word2Vec model based on a program SASS assembly code, and mining semantic knowledge of an instruction to obtain a semantic embedding feature of the instruction; constructing an error propagation knowledge graph by combining the execution condition and the data dependency relationship between the program instructions; and fusing the two heterogeneous feature representations as input, and designing a GPU program soft error elasticity prediction model based on the graph convolutional network. According to the method, heterogeneous feature mining and error propagation relation modeling are carried out on the program, the soft error elasticity of the GPU program fault point can be identified more accurately, and the method has higher soft error prediction rate and lower space-time overhead.

The invention provides an online identification and input design method and device for a wireless power transmission system, and the method comprises the steps: carrying out the online estimation of a transfer function parameter of a target system, and building an initial small signal model; constructing a full-order model corresponding to the target system, and performing order adaptive order reduction processing; determining a loss function of the target system by taking minimization of disturbance of the excitation signal to the target system as a target; on the basis of defining the loss function, constructing an optimization problem of the target system under disturbance constraint, and performing optimal excitation input design; and constructing a robust controller of the target system by adopting a robust control method in combination with the initial small signal model. According to the method, the system modal change can be tracked in real time under the closed-loop working condition, the modeling precision and the real-time performance are improved, and the problem that the identification precision is poor in the prior art is solved.

The invention provides a micro-service creation method and device. The method comprises the following steps: acquiring an input design document associated with a first business processing system; creating a plurality of initial micro-services in the first business processing system according to the input design document; wherein each initial micro-service comprises a code engineering framework and an interface implementation code; and in response to completion of creation of the interface implementation code of each initial micro-service, performing unit testing on each initial micro-service, and synchronously filling a code engineering framework of each initial micro-service with the business processing code matched with the corresponding system requirement to obtain the first micro-service, thereby greatly shortening the development period and improving the development efficiency. Therefore, the system can respond to business changes more quickly, and the accuracy and applicability of the system are improved at the same time.

The invention relates to the technical field of material information matching, and discloses a material information matching method based on an attention mechanism, which comprises the following steps: collecting material description information provided by each design institute and material description information maintained in an enterprise material database as original data, carrying out data matching, labeling and data cleaning, and making a basic data set, dividing the basic data set into a training set, a verification set and a test set; preliminarily training a preset information matching model by using the training set to obtain a basic model, adjusting the basic model by using the verification set, and testing the accuracy of the model by using the test set to establish a target model; and inputting the material description information provided by the design institute into the target model, and outputting the existing material information in the material database with matched semantics. The method relates to text semantic comparison, intelligently matches the design institute material description information with the material description information in the enterprise database, and reduces the labor cost and time cost of material information matching.

The application belongs to the technical field of transformer three-dimensional design, and discloses a transformer three-dimensional parameterized design method based on Autodesk Inventor, which is realized based on an iLogic programming platform embedded in Autodesk Inventor, and the design steps are as follows: step one, establishing a standard component template; step two, parameterized design; step three, three-dimensional model generation; step four, two-dimensional drawing generation; and step five, version management and updating. The sub-modules are set as the standard component template, and the parameterized mode is used, so that the designer only needs to input design data in the input interface of the parameterized standard component template during design, then calls the program to calculate, and the transformer three-dimensional model and two-dimensional drawing can be obtained, thereby greatly reducing the workload and shortening the design cycle, and more importantly, the algorithm of the parameterized standard component template eliminates the quality problems caused by human factors and controls the design quality at a high level.

The present invention relates to a cross-language and cross-target stance detection method based on collaborative guidance of dual expert models, and belongs to the field of natural language processing technology. The present invention includes: constructing a cross-language and cross-target training dataset to generate the input required for model training; designing a cross-language expert model, and optimizing the adaptability of the mBERT model in cross-language tasks by using prompt fine-tuning and consistency learning; constructing a cross-target expert model, and generating high-quality target representations by mining target category information and an optimization method based on contrastive learning; optimizing the representation capability of the collaborative module by using unlabeled data in the target language; jointly guiding the collaborative module to train the cross-language expert model and the cross-target expert model, integrating the losses of the cross-language expert model and the cross-target expert model and the contrastive learning loss, and improving the overall performance of the model by optimizing the total loss. The present invention improves the accuracy, robustness and generalization ability of the cross-language stance detection task.

To automatically generate a drawing including at least one of process information and sequence information.SOLUTION: The drawing generation system 1 includes a drawing generation unit 10 that receives an input of input data including a design specification that is a book in which design information of a plurality of devices is described and outputs output data including drawing data. The drawing generation unit 10 includes a device information generation unit 11 that generates device information on the devices based on the input design specification, and a connection information generation unit 12 that generates connection information indicating a connection relationship between the devices based on the input design specification, and the drawing generation unit 10 generates drawing data in which a plurality of figures including symbols representing the devices and lines connecting the devices are drawn in a frame of the drawing based on the device information and the connection information generated by the device information generation unit 11 and the connection information generation unit 12, and output the generated drawing data.SELECTED DRAWING: Figure 2

The present disclosure relates to a design generation device including a design generator configured to generate at least one design from design data when design data is input, a simulator configured to simulate the at least one design and evaluate a result of the simulating, and an optimization engine configured to derive an optimization parameter for the at least one design by inputting the evaluation result obtained from the simulator into a parameter optimization model provided in advance, wherein the design generator modifies the at least one design according to the optimization parameter. By doing so, an optimized design may be automatically generated by reflecting industry-specific characteristics and user needs.

Provided are: an insole manufacturing system and manufacturing method which enable anyone in any area to manufacture a desired insole according to their needs; and an insole manufactured by the same. This manufacturing system for manufacturing a desired insole composed of a plurality of parts from thousands of patterns or more, preferably hundreds of thousands of patterns or more, even more preferably hundreds of billions of patterns or more, includes a design unit which is configured by a computer, and which selects a plurality of parts from a predetermined part list according to an input design specification and designs the insole by arranging the plurality of selected parts.

The present invention discloses a human-machine collaborative conceptual design generation method based on FBS theory, comprising the following steps: obtaining a conceptual design case and extracting keywords based on design requirements and the functions, behaviors and structures in the FBS theory to construct a functional space, a behavioral space and a structural space; embedding the functional space, the behavioral space and the structural space into a large language model framework in sequence based on the logical order of the conceptual design process to construct a conceptual design auxiliary model; inputting the design requirements into the conceptual design auxiliary model to obtain a function-structure mind map. The present invention also provides a human-machine collaborative conceptual design generation system. The method provided by the present invention provides guidance for the designer's thinking process in a structured manner, thereby expanding the design ideas and improving the quality of the final generated design solution.

The invention relates to the technical field of integrated circuit design, in particular to a solder ball management system and method. The solder ball management system comprises an information acquisition module used for acquiring a solder ball layer and a port layer from an input design layout, wherein the port layer comprises a plurality of ports; the solder ball creating module is used for creating solder balls on the solder ball layer based on a preset creating mode; and the solder ball connecting module is used for connecting the solder balls with the ports, and / or connecting the solder balls of different solder ball layers. According to the solder ball management system, automatic creation, arrangement and connection of the solder balls are realized through cooperation of a plurality of functional modules, and the problem that the existing solder ball layout management efficiency and yield are low is solved.

The application discloses a kind of flow meter abnormal behavior monitoring method and system, method includes flow meter abnormal state description, preliminary control input, unknown dynamic approximation, adaptive parameter update law, final control input and flow meter abnormal behavior monitoring.The application belongs to the field of data processing, specifically refers to a kind of flow meter abnormal behavior monitoring method and system, the scheme is compensated unknown disturbance by using adaptive switching control gain through preliminary control input design, unknown nonlinear dynamics caused by temperature change and medium fluctuation factor to flow meter are approximated using logic system, to further improve the precision of abnormal monitoring;Adopting online adaptive updating fuzzy approximator parameter, set fusion updating mechanism in combination with fusion coefficient, realize the continuous learning of dynamic characteristics under normal and abnormal state of flow meter;Adaptive dynamic abnormal threshold mechanism is introduced, dynamically adjusts abnormal threshold, avoids false alarm and miss problem caused by fixed threshold.

We provide the system. [Solution] An input means for the user to input design instructions to the system in natural language, A natural language processing means that analyzes natural language instructions input through an input means, An instruction interpretation means interprets specific design requirements and placement conditions based on instructions analyzed by a natural language processing means, An image generation means that automatically generates design drawings based on the design requirements obtained by the instruction interpretation means, A means for verifying the results, which includes checking the quality of the generated design drawings and verifying their consistency with the instructions, An output means for providing the user with the final confirmed design drawings, A system that includes this.

To further easily create a space for exhibiting objects in a virtual space.SOLUTION: An information processing device for providing a virtual exhibition space in which a plurality of objects is exhibited in a virtual space comprises: an acquisition unit which acquires arrangement instructions for a plurality of objects in the virtual exhibition space, the arrangement instructions transmitted from a communication terminal of each of a plurality of working users who inputs design instructions for the virtual exhibition space; an arrangement unit which arranges the plurality of objects in the virtual exhibition space in accordance with the arrangement instructions; a generation unit which generates display data for displaying the virtual exhibition space updated in accordance with the arrangement instructions; and a transmission unit which transmits the display data to the communication terminals of the plurality of working users. A list of the plurality of objects present in the virtual exhibition space and a map of the virtual exhibition space indicative of the arrangement positions of the plurality of objects are displayed in display units of the communication terminals. The arrangement instructions are transmitted to the information processing device in response to operations for moving the arrangement positions of the plurality of objects on the map by the working users.SELECTED DRAWING: Figure 2

The present invention makes it possible to more easily create a space for exhibiting objects in a virtual space. This information processing device for providing a virtual exhibition space where a plurality of objects are exhibited in a virtual space comprises: an acquisition unit that acquires instructions for arranging a plurality of objects in a virtual exhibition space, said instructions being transmitted from respective communication terminals of a plurality of working users who input design instructions for the virtual exhibition space; an arrangement unit that arranges the plurality of objects in the virtual exhibition space in accordance with the arrangement instructions; a generation unit that generates display data for displaying the virtual exhibition space updated in accordance with the arrangement instructions; and a transmission unit that transmits the display data to the communication terminals of the plurality of working users. A display unit of each communication terminal displays a list of the plurality of objects present in the virtual exhibition space and a virtual exhibition space map showing the arrangement positions of the plurality of objects. The arrangement instruction is transmitted to the information processing device in response to each operation performed by a working user to move the arrangement positions of the plurality of objects on the map.

The present application relates to the field of integrated circuit computer-aided design, and particularly relates to a via cell automatic generation method, system, device, medium and product. The via cell automatic generation method comprises the following steps: inputting a design rule file, identifying and extracting constraint parameters of a via and metal interconnection, and dividing the constraint parameters into size type and surrounding amount type constraint rules; traversing and obtaining values of the surrounding amount constraint parameters of the surrounding amount type constraint rules in the design rule file, arranging and combining all the values, defining each combination generated as a candidate via cell configuration, and generating a via cell configuration list. The via cell configuration list is traversed, and it is judged whether the candidate via cell configuration conforms to the size type constraint rule. If not, it is modified or deleted. If the rule is met, a via cell library is output. The system, computer device, computer readable storage medium and computer program product of the present application have the same beneficial effects as the via cell automatic generation method.

Process control parameters are predicted to fabricate an object using deposition. An input design geometry is provided for the object. A training data set includes past post-build physical inspection data for a plurality of objects that comprise at least one object that is different from the object to be physically fabricated; and training data generated through a repetitive process of randomly choosing values for each of multiple process control parameters and scoring adjustments to the multiple process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments. A machine learning algorithm is trained using the provided training data set and a predicted optimal set of the multiple process control parameters is generated for initiating and performing the deposition process to fabricate the object.