9results about How to "Flexible editing" patented technology

The embodiment of the invention discloses an image editing and generating method and device, electronic equipment and a storage medium, and relates to the technical field of image generation, and the method comprises the steps: obtaining a to-be-processed image and a target instruction, constructing an image description of the to-be-processed image according to a scene in the to-be-processed image, converting the image description into a text mark, and storing the text mark in the target instruction; the method comprises the steps of obtaining a to-be-processed image, embedding a text mark into a high-dimensional space through an embedding model to obtain text embedding, obtaining an element vector of the to-be-processed image according to the to-be-processed image and the text embedding through a diffusion model, designing an editing operator according to a target instruction, updating the element vector by using the editing operator, and generating a result image according to the updated element vector through the diffusion model. According to the method, efficient, accurate and flexible editing of the image is realized by combining the diffusion model and the editing operator, and the problems that the expression of the model on a specific target category cannot be improved, the problem of long tail distribution cannot be solved and data similar to a real scene cannot be generated in the prior art are solved.

The embodiment of the invention provides a motion mechanism track generation and position calibration method, which comprises the following steps of: firstly, acquiring and recording teaching point data generated by a demonstrator-guided action executed based on a motion mechanism, constructing an initial track of a first part, and inputting the initial track into offline programming software to generate a theoretical track; then, the sensor and the movement mechanism are calibrated, and a rotation matrix and a translation vector are obtained through calculation; thirdly, collecting three-dimensional data of the first part through a sensor, and converting the three-dimensional data into a theoretical template in combination with a rotation matrix and a translation vector; and after the current part is in place, collecting the three-dimensional data of the current part, and converting the three-dimensional data into the current point cloud by combining the rotation matrix and the translation vector. The offset is calculated by matching the current point cloud with the theoretical template. And finally, based on the theoretical trajectory and the offset, calculating the operation trajectory of the current part, and sending the operation trajectory to a movement mechanism for execution. Therefore, the trajectory generation speed is improved, recalibration is not needed, different pose offsets can be coped, and the trajectory can be visually created and adjusted.

The invention provides a form production management system supporting creation of multiple service modules, and the system comprises a master control unit which is used for monitoring and controlling the overall operation of the system, and managing user accounts and permissions at the same time; the form making unit is used for creating and editing a form by a user; the business module unit is used for managing and executing business logic of the system and creating, configuring and managing various business modules according to business requirements; the data management unit is used for managing and storing all data in the system, including original data, intermediate processing results and final analysis reports, and providing data support; a notification management unit; the form production management system supporting the creation of the multiple service modules has the advantages of efficient data processing capability, relatively strict safety guarantee and flexible expansibility, and provides certain convenience for users.

This disclosure relates to a cleaning control method, apparatus, device, medium, and program product for a robotic vacuum cleaner. According to an example of this disclosure, the method includes: displaying an initial work area map in a user interface; in response to receiving a shape editing instruction for an ultrasonic carpet area, editing the shape of the ultrasonic carpet area according to the editing method indicated by the shape editing instruction to obtain a target work area map; and sending the target work area map to the robotic vacuum cleaner for cleaning based on the target work area map. This disclosure enables flexible and accurate editing of the shape of the ultrasonic carpet area in the robotic vacuum cleaner's work area map according to user-triggered shape editing instructions, improving the accuracy of the ultrasonic carpet shape and thus enhancing the subsequent cleaning effect of the robotic vacuum cleaner.

The invention discloses an instruction editor and an instruction generation method based on the instruction editor. The instruction editor comprises an instruction editing mode switching module which comprises mode identifiers of at least two instruction editing modes, and the at least two instruction editing modes comprise a real-time instruction editing mode and a repeated instruction editing mode; the instruction description module comprises a plurality of first key field key names for describing instruction contents and first setting options of first key field key values corresponding to the first key field key names; and the role requirement module comprises a plurality of second key field key names for describing the instruction execution main body information and second setting options of second key field key values corresponding to the second key field key names. According to the embodiment of the invention, the instruction can be flexibly edited based on the instruction editor, and the man-machine interaction efficiency is improved.

The present application discloses a radiation source simulation method, device and medium based on three-dimensional sorting, and relates to the field of radiation simulation technology. Applied to a radiation source simulation device, the radiation source simulation device includes a scene simulation module, a radiation source generation module, an antenna array module and a turntable module, and the method includes: the scene simulation module creates electromagnetic scene parameters according to the radiation source position and the radiation source motion parameters; the radiation source generation module performs scene solution on the electromagnetic scene parameters to obtain the radiation source signal; the radiation source signal is sorted by a three-dimensional sorting algorithm to obtain the sorting information, and is allocated to the corresponding signal channel; the antenna array module rotates the signal channel to the corresponding angle according to the sorting information. The present application implements the three-dimensional sorting algorithm to allocate the radiation source through the above method, and simulates the radiation source signal from three dimensions: time domain, frequency domain and spatial domain to make the simulated scene more realistic.

The present invention provides a method, medium and system for determining drying parameters in the production process of HIPS board, belonging to the technical field of HIPS board production, including: obtaining multiple sets of historical records of HIPS board drying process, including material parameters, process parameters and measured drying quality vectors; establishing a mathematical model, fitting with historical records, and obtaining a drying prediction model; augmenting and expanding historical data, and constructing a training data set; establishing a bidirectional neural network model, including precise and fuzzy branches, training based on the augmented data set, and obtaining a prototype of a drying parameter model; optimizing the model with historical records, and obtaining a final drying parameter model; inputting the current parameters of the HIPS board to be dried and the target drying quality, and outputting the optimal drying process parameters. The present invention solves the technical problem that the existing technology often relies on manual experience for drying parameters, and it is difficult to comprehensively consider the influence of multiple factors, resulting in the determined drying parameters often being inaccurate.

The application discloses a kind of based on triangulated mesh differentiable rendering animated face three-dimensional reconstruction method, this method takes single-view or multi-view portrait head portrait video as input, single-frame reconstruction and sequence frame reconstruction are successively carried out, finally output the portrait head portrait basic model of triangular mesh format, face main joint position information and control weight, face expression mixed shape and multiple face color map.The geometric structure of the face three-dimensional model reconstructed by the method is accurate, the color map is high in definition, and the animation can be edited by joint parameters and expression mixing, which can meet the needs of film and television, game industry for face animation model.

The invention discloses a game scene resource generation method and device, relates to the technical field of game development, and mainly aims at solving the problem that the resource consumption is relatively large when a snow falling area or a rain falling area is distinguished for game making in the prior art. Comprising the steps of baking a single-channel height map of a game scene based on a top view; obtaining an operation coordinate of an operation control in a game scene editing area, and determining height information of a target pixel point in the single-channel height map based on the operation coordinate; the height information is updated through the height color value selected by the operation control, and game scene resources to be subjected to scene rendering are generated.