48results about How to "Reduce creative costs" patented technology

The invention discloses a multi-label microblog text classification method based on semi-supervised learning, and relates to the field of natural language processing. The method comprises the following steps: firstly, preprocessing an original microblog text, and labeling a small amount of texts; generating augmented data of the annotation data set by using reverse translation, generating augmented data of the unannotated data set by using synonym replacement and random noise injection, guessing and generating a pseudo tag of the unannotated data by using a classifier, and forming a new training set together with the augmented annotation data set; converting the multi-label classification task into a plurality of dichotomy tasks, training a semi-supervised microblog text classification model, randomly extracting two samples from a new training set each time during training, generating a new sample in a text hidden space by using a sample mixing technology, calculating a loss value, and updating network parameters; and finally, classifying the microblog texts by comprehensively using a plurality of trained classifiers. The invention has an important application value for fine-grained information extraction of the microblog texts.

The invention discloses a method for realizing an embossment effect of an animation character and a background of a mobile phone. The method comprises the following steps of: 1, creating an optional route-distortion-based animation face; 2, creating chromatic embossments on an image; and 3, performing optional graying operation. In the method for realizing the embossment effect, a simple and practical digital image processing algorithm is used, great attention is paid to reducing the data volume and improving the central processing unit (CPU) operating efficiency to ensure that a user can usea mobile phone with comparatively poor computing power to DIY (do-it-yourself) a mobile phone animated cartoon work with a unique artistic style on the mobile phone, and effects of low creation cost and a quick operation can be achieved. The method for realizing the embossment effect of the animation character and the background of the mobile phone is low in data processing amount, is easy to implement and is suitable for running on the mobile phone.

The invention discloses a music model training method. The music model training method comprises the following steps: acquiring a MIDI music data set, wherein the MIDI music data set comprises a plurality of MIDI music scores; extracting the feature vector of each MIDI music score; inputting the feature vectors into a structured support vector machine for training, so that a music model is obtained, the step specifically comprises the following substeps: constructing a discrimination function f(x;w), wherein x is a feature vector, w is a parameter vector, carrying out outputting by adopting the data value (with the calculation formula shown in the description) of the maximal discrimination function f(x;w) as the predicted value, calculating the predicted value and the true value accordingto a preset loss function (shown in the description), wherein P is the probability distribution of data, which is replaced with the empirical risk (shown in the description) obtained through calculation with the trained sample data, solving the unique parameter vector omega by adopting the optimizing formula (as shown in the description) of SVM, so that the empirical risk (shown in the description) obtained through the trained sample data is 0, solving the discrimination function f(x; omega), and finally, outputting the music time sequence. The invention further provides a music creation method, devices, a terminal and a storage medium. In the technical scheme, artificial intelligence is used for music model training for the first time, for the trained music model, the feature extraction capacity of the MIDI music score can be improved.

The invention discloses a mobile phone anime character and background creation method, using any one of the following five methods to process an original image or using any one of the previous four methods and the method 5 to process the original image in a mixed mode. The methods are as follows: method 1: off-diagonal element blanking method; method 2: random fuzzification method; method 3: bead curtain effect simulation method; method 4: image color shifting method; and method 5: monochromatization and passivation method. The method provided by the invention is novel in conception, not only has strong enjoyment and is simple to realize, but also has small data volume, is easy to implement and suitable for running on a mobile phone.

The invention provides a simulation test system and method based on network data analysis, and the system comprises a module M1 which collects a network message in a production environment through a network packet capturing technology, analyzes the network message, generates structured transaction data, and stores the structured transaction data; a module M2 which is used for preprocessing the structured transaction data to obtain preprocessed transaction data; and a module M3 which is used for selecting a data set from the preprocessed transaction data according to test requirements, replaying the data set to the tested software system according to a preset proportion and a preset rate for testing, monitoring the state of the tested system and generating a test report. According to the invention, the test database is established by using full production data, the simulation degree is high, the test scene coverage is comprehensive, and the business calling proportion is consistent withthe actual scene.

The invention discloses an internet of things-based digital media creation system and a creation method. According to the system, professional digital media soft-hardware resources are open to a platform, so that the platform has the real-time material capturing capability and the massive digital media storage capability; and thus a unified creation function for various types of digital medias is realized and the creation efficiency is improved. The provided system comprises: an application layer, which is used for providing originality and design interfaces for movie-video special effects, animation a digital media material library; an intermediate layer, which is used for providing a digital cloud media platform and providing movie-video special effect and animation production software, high reality parallel rendering engine software and a massive digital media material library based on the platform; and a base layer, which is used for providing a digital media service based on the Internet of things and includes a digital media internet-of-things intelligent gateway and an internet of things-based massive media data fusion processing module.

The invention provides a subject heading classification model creation method. The method comprises the steps that multiple model training documents are obtained, and label terms of the model training documents are extracted; based on a similarity algorithm, core theme phrases corresponding to the label terms are obtained; based on a map content library, a first model training document collection corresponding to the core theme phrases is obtained; based on a machine learning algorithm, the model training documents are subjected to sort operation; based on the map content library, subject type identification of all the model training documents corresponding to the label terms is obtained, and according to the subject type identification corresponding to the label terms, a second model training document collection corresponding to the label terms is determined; repetitive model training documents in the first model training document collection and the second model training document collection corresponding to the label terms are taken as positive samples, other model training documents in the map content library are taken as negative samples, and a subject heading classification model of the label terms is created. The invention further provides a subject heading classification model creation device and a storage medium.

The invention discloses a mobile comic manufacturing method based on space-time and audio-video dynamic combination, which quickly meets novel creative demands on the basis of local modification of the prior materials to form novel mobile comic works. The mobile comic manufacturing method based on space-time and audio-video dynamic combination is characterized by comprising the following steps: firstly, acquiring the materials; secondly, the compiling the materials into divided shots; thirdly, setting the sequence of the divided shots appearing on the scene and space positions of the layout to form creation description files; and fourthly, combining the materials of the divided shots and the creation description files into a playable file for a mobile phone. By adoption of the method, the comic works which are suitable to be played on the mobile phone can be quickly and conveniently manufactured with low cost.

The embodiment of the invention provides a video creation method and device, electronic equipment and a computer program product. The video creation method comprises the steps: providing an interface used for creating a video, wherein the interface comprises a sub-mirror display area and a time axis area, the sub-mirror display area is used for displaying video sub-mirrors and video elements in the video sub-mirrors, and the time axis area is used for displaying time axis intervals of the video elements; in response to the received editing operation of the video elements corresponding to the sub-mirror display area or the time axis area, determining display positions and display time of the video elements included in the video sub-mirror; and generating a video synthesis file corresponding to the video sub-mirror according to the display position and the display time of the video element included in the video sub-mirror. According to the scheme provided by the embodiment of the invention, video creation can be realized by adopting a mode similar to PPT editing, so that the video creation efficiency is greatly improved, the video creation time is shortened, and the video creation cost is reduced.

The invention discloses a universal SPL (Show Play List) generation method and system. The method comprises the steps of: obtaining original automation commands of different playing servers in a theatre; mapping all the original automation commands into a universal automation command list; mapping all the original automation commands corresponding to the same operation to the same universal automation command in the universal automation command list; obtaining a matched feature film file according to film scheduling information; determining a matched advertising film file according to the feature film file and the advertising position of a movie hall; according to the feature film file and the advertising film file, determining the operation corresponding to a playing device; according tothe operation corresponding to the playing device, extracting the universal automation command; determining a black field file; and, combining the feature film file, the advertising film file, the universal automation command and the black field file, generating the SPL corresponding to the movie hall. By adoption of the method or the system in the invention, the SPL generation efficiency can be increased; and the workload of workers can be reduced.

The invention discloses a panoramic image distortion-based mobile phone cartoon character creating method, which comprises the following steps of: 1) designing an image distortion template; 2) setting a distortion parameter so as to adjust a distortion degree; 3) distorting an image so as to form a distorted character facial type; and 4) performing selectable graying or binaryzation operation. A simple and practical digital image processing algorithm is used, data volume is reduced and the running efficiency of a central processing unit (CPU) is improved, so that funny and interesting mobile phone cartoon works can be made on a mobile phone with relatively small computing power in a do it yourself (DIY) way, and low creation cost and quick running effect are realized.

The invention discloses a character deformation design method based on a mobile phone platform, which is characterized by comprising the following steps: (1) carrying out gray processing on an original image; (2) computing the jump degree of the gray scale; (3) and zooming the original image according to the zooming curve: if the jump degree of the gray scale alpha is greater than or equal to thethreshold value alpha T, zooming the original image according to the zooming curve by using a convolution interpolation method; and if the jump degree of the gray scale alpha is smaller than the threshold value alpha T, zooming the original image according to the zooming curve by using a linear interpolation method. By using the simple and practical digital image processing algorithm, the method tends to reduce the data size and enhance the operation efficiency of CPU, so that mobile phone animation works restricted by the screen size and the computing power of the mobile phone have low creation cost and quick operation effect.

The invention discloses a mobile phone cartoon character creating method based on boundary tracking and pseudo-coloring, which comprises the following steps: (1) carrying out automatic boundary tracking on the original image, and marking the boundary; (2) carrying out manual auxiliary definition for part of the boundary; (3) separating the region within the boundary from the original image; (4) pasting the separated image into the target image; and (5) performing pseudo-coloring. The invention uses the simple and practical digital image processing algorithm, and takes care to reduce the data bulk and enhance the CPU operating efficiency, so that the mobile phone cartoon work restricted by mobile phone screen size and computing power has the advantages of low creation cost and high operation speed.

The invention discloses an intelligent 3D fitting system based on virtual reality. The system includes a fitting terminal and a management server, wherein the fitting terminal includes a controller, a sensor, a communication module, a voice module, an image acquisition module and a display module; the controller is electrically connected with the sensor, the communication module, the voice module, the image acquisition module, and the display module; the fitting terminal is connected with the management server through the communication module. The system provided by the invention adopts a camera and the sensor to collect human body information, so that a user can visually see the fitting effect, and the tedious processes of fitting are reduced; the user can change the clothes models and colors through the touching screen in an automatic manner, and query the goods storage situation. The intelligent 3D fitting system based on virtual reality is low in cost and high in intelligence degree; the working efficiency is improved; user time is reduced; high-quality fitting experience is provided for customers; meanwhile, the management services of managers are simplified; the system is suitable for popularization in major shopping malls.

The invention discloses a point-to-point positioning system for a downhole mine tunnel. The point-to-point positioning system comprises a plurality of position indicators, transmitters installed on movable devices, and a control center arranged on the ground, wherein the position indicators are distributed in the downhole mine tunnel in a fixedly-arranged mode and are connected with the control center in a wired mode, the transmitters are worn by downhole operating personnel and carry out wireless point-to-point communication with the position indicators, so that the position indicators obtain information of angles and distances between the transmitters and the position indicators, the control center processes the information of the angles and the distances after receiving the information, sent by the position indicators, of the angles and the distances, and the transmitters are positioned. The point-to-point positioning system for the downhole mine tunnel is simple in structure and low in creation cost; a technology of wireless point-to-point positioning between the transmitters and the position indicators has high positioning accuracy, and the advancing direction of the downhole operating personnel can be determined.

The invention provides a video processing method, electronic equipment and a computer readable storage medium. The video processing method comprises the steps of: extracting a key frame from a to-be-processed video; selecting a target image region in the key frame; and performing image stylization processing on the target image region to generate a cartoon image. According to the video processingmethod of the invention, the key frame is extracted from the to-be-processed video, and the target image region in the key frame is selected for image stylization processing, so that the wonderful andmeaningful part in the video clip can be converted into the cartoon image, manual creation is not needed, the cartoon creation efficiency can be effectively improved, and the cartoon creation cost can be reduced.

The invention discloses a search-and-rescue positioning system for an underground mine disaster. The search-and-rescue positioning system for the underground mine disaster comprises a wired signal transmission network distributed underground, multiple position finders which are distributed underground and are connected with the wired signal transmission network, a transmitter installed on a movable device, a control center arranged on the ground and a signal receiving terminal used for search and rescue, wherein the control center is connected with the wired signal transmission network and receives positioning signals transmitted by the position finders, the transmitter is worn by an underground operator and moves along with the underground operator, and the signal receiving terminal is carried with a search and rescue person, moves along with the search and rescue person to be close to the underground operator trapped underground and gives a wireless signal response to the transmitter carried with the underground operator. The search-and-rescue positioning system for the underground mine disaster is simple in structure, low in establishment cost and high in positioning speed and positioning precision, and the advancing direction of the underground operator can be confirmed; the position of the trapped person can be found out rapidly when the mine disaster occurs so that rescue can be conducted in time.

The embodiment of the invention provides a script generation method and system, a computer storage medium and a computer program product. The script generation method comprises the steps of displaying a visual generation interface used for video script generation, the visual generation interface comprises a script generation option column for generating a video script and a video template recommendation column; receiving a selection input operation of a user for the script generation option field or the video template recommendation field; according to the selection input operation, displaying a script framework interface of an option corresponding to the selection input operation, displaying corresponding script framework information and operation options for the script framework information through the script framework interface, and the script framework information at least comprises one or more paragraphs and texts of all the paragraphs. According to the method of the invention, the method can effectively assist a video creator in creating a video, and greatly improves the creation and production efficiency of the video creator.

The invention belongs to the field of hand-painted animations, and provides an application method of a combined material in a hand-painted animation. The method comprises the following steps: storinga combined material configuration file which comprises a material animation and a combined form, the material animation comprising form display information and animation information, reading the formdisplay information to display static pictures, reading animation information for displaying the static pictures in an animation mode, and combining the form display information and the animation information according to the combination form so as to complete material combination. The technical effects of reducing user creation cost and improving user work creation quality are achieved.

Embodiments of the invention provide a point cloud processing method, apparatus and device, and a computer readable storage medium. The method comprises steps of constructing a first model and a second model based on obtained point cloud; wherein the first model is arranged in a space formed by the point cloud, and the second model is arranged outside the space formed by the point cloud; expandingand deforming the first model and contracting and deforming the second model; wherein a target distance from the expanded and deformed first model to the point cloud is less than or equal to a firstthreshold, or the target distance from the expanded and deformed first model to the first set is less than or equal to the first threshold; wherein the target distance from the contracted and deformedsecond model to the point cloud is less than or equal to a second threshold, or the target distance from the contracted and deformed second model to the second set is less than or equal to the secondthreshold; wherein the first set comprises point cloud and a second model, and the second set comprises the point cloud and the first model; and fitting and reconstructing a three-dimensional model of the target object based on the point cloud, the deformed first model and the deformed second model.

The invention relates to a pyrotechnic composition for calligraphy and painting creation, and a preparation method thereof, and belongs to the field of calligraphy and painting creation pyrotechnic compositions. The pyrotechnic composition for calligraphy and painting creation comprises 30-50 parts of ammonium perchlorate, 15-40 parts of metaldehyde, 15-35 parts of copper chloride and 5-10 parts of shellac. The preparation method comprises the following steps: respectively weighing certain amounts of ammonium perchlorate, metaldehyde, copper chloride and shellac according to proportions of the above formula; respectively fully grinding the weighed ammonium perchlorate, metaldehyde and copper chloride in a mortar, respectively sieving by using a 100-200 mesh sieve 3 times, and carrying out full dry mixing on all the obtained sieved reagents until uniformity; and putting weighed shellac in a beaker, adding a proper amount of 95% ethanol to dissolve shellac, pouring the above obtained dry mixed uniform medicine mixture into the beaker after shellac is completely dissolved, fully stirring, and air-drying the obtained medicine in a shady place until no liquid exists. The pyrotechnic composition has the advantages of fast combustion, low combustion temperature, few combustion residues, fire delivery cross the air, short creation time, low creation cost and high safety coefficient.

The invention discloses a red pyrotechnic composition for calligraphy and painting creation and a preparation method thereof, and belongs to the field of pyrotechnic composition preparation. The red pyrotechnic composition for calligraphy and painting creation comprises the following components in percentage by weight: 50wt%-60wt% of ammonium perchlorate, 5wt%-10wt% of metaldehyde and 30wt%-45wt% of methyl red. The red pyrotechnic composition for calligraphy and painting creation has the characteristics of low combustion temperature, few combustion residues, low creation cost, high safety coefficient and the like, red traces can be left on paper on the premise of not burning through the paper, and red artistic works can be created. The pyrotechnic composition can be widely applied to the field of calligraphy and painting creation pyrotechnic compositions.

The invention discloses a camouflage facial makeup realizing method for cell phone games. The method comprises the step that 1, a colored original image with a face pattern is acquired; 2, the face portion of the colored original image is colored with the camouflage color; 3, lip gloss application and eye shadow application are selectively carried out. The camouflage facial makeup realizing method for the cell phone games is easy to implement and high in data processing efficiency.

Embodiments of the invention provide a picture color matching method and device, and electronic equipment. The method comprises the steps of obtaining a target style data set; for the content elementpart in the target style picture, carrying out probability density estimation based on color features, wherein the color features comprise content element features of the content element part and difference comparison features of the content element part and a product part in a picture to be subjected to color matching; and forming a target scheme according to the probability density estimation result of the target style picture, and re-coloring the content element part in the picture to be subjected to color matching. According to the embodiment of the invention, the color feature-based probability density estimation is performed on the target style picture, and the color matching scheme is automatically formed in combination with the difference between the content element and the productin the picture to be subjected to color matching, so that the creation cost of the commercial picture is reduced, the time spent by a user on content color matching is reduced, and the creation efficiency of the commercial picture is greatly improved.

The invention provides an image processing method, electronic equipment and a computer readable storage medium. The image processing method comprises the steps of extracting a key frame from a to-be-processed video; selecting a target image area in the key frame, wherein the target image area comprises a face image area; and exaggeration processing is performed on the face image area, so that a cartoon image can be generated. According to the embodiment of the invention, the key frame is extracted from the to-be-processed video, the area containing the face image in the key frame is selected as the target image area, exaggeration processing is carried out on the face image area, the invention is used for cooperating with story plots, manual creation is not needed, cartoon creation efficiency can be effectively improved, and the cartoon creation cost can be reduced.