53results about How to "No need for manual labeling" patented technology

The invention relates to the technical field of computers, in particular to an integrated circuit repair algorithm determination method and device, a storage medium and electronic equipment. The method comprises the steps of obtaining failure test unit data of a to-be-repaired integrated circuit; acquiring a failure unit distribution type of the to-be-repaired integrated circuit according to the failure test unit data in combination with a type analysis model constructed by a deep learning network; According to the failure unit distribution type, obtaining a repair performance index of each candidate repair algorithm for the failure unit distribution type in a repair algorithm library, and determining the candidate repair algorithm with the optimal repair performance index as a target repair algorithm. According to the invention, the repair of each to-be-repaired integrated circuit can reach the highest repair rate, the minimum use number of the repair circuits, the shortest repair analysis time and the like, the repair efficiency and accuracy are improved, and the repair cost is reduced.

The invention relates to the technical field of image processing, and particularly discloses a certificate photo matting method based on an end-to-end convolutional neural network, which comprises thefollowing steps: synthesizing a foreground image in a matting mask of a certificate portrait photo with an Internet photo to obtain a training image; generating a coarse segmentation Trimap network according to the lightweight semantic segmentation network model; performing refined matting on the coarsely segmented Trimap network according to the encoding and decoding network to obtain a refinedmatting network; cascading the coarsely segmented Trimap network and the refined matting network to obtain an end-to-end network model; and inputting the training image into the end-to-end network model for fine adjustment to obtain a trained end-to-end network model. The invention further discloses a certificate photo matting system based on the end-to-end convolutional neural network, a storagemedium and a processor. According to the certificate photo matting method based on the end-to-end convolutional neural network, the corresponding matting prospect can be automatically obtained for thecertificate photo, manual annotation is not needed, and the matting efficiency is improved.

A technical scheme of the invention discloses a method for obtaining a text classifier used for automatic corpus tagging, and the text classifier. The method comprises: determining a concept set, using a concept keyword corresponding to each concept to match a non-tagging corpus text and perform automatic tagging processing, the concept keyword being in a concept keyword set; for each concept, when the number of texts in a tagging corpus text set corresponding to the concept meets a threshold condition, training a corresponding text classification model for the concept, to obtain a corresponding text classifier, and finally a text classifier set corresponding to the concept is obtained, all text numbers meeting the threshold condition. The invention provides an algorithm structure having universality, and a classification system is flexibly changed, calculation time and resources are saved. The text classifier just needs few initial corpus texts, and the text classifier automatically tags without manual tagging, so as to further save time and cost.

The invention discloses a video abstract generation method and a related device, which are applied to a machine learning technology of artificial intelligence. The method comprises: acquiring a targetvideo; extracting image features of each video frame to generate an image feature sequence; dividing a video frame sequence into a plurality of target segment sequences to generate a paragraph feature sequence; fusing the image feature sequence and the paragraph feature sequence to obtain fused features; and carrying out reinforcement learning training based on the fusion features to generate a video abstract. According to the invention, an unsupervised video abstract generation process is realized, the video abstract generation quality is ensured by combining the image features of the picture level and the paragraph features of the depth level, and the unsupervised video abstract generation process does not need manual annotation, so that the video abstract generation efficiency and accuracy are improved.

The embodiment of the invention discloses a training and auditing method and device of a content auditing model, equipment and a storage medium. The training method of the content auditing model comprises the following steps: receiving a sample video file; extracting partial image data in the sample video file as sample image data; if the content of the sample image data is illegal, positioning the time point of the sample image data in the sample video file; extracting image region data with significance from the image data surrounding the time point; and training a content auditing model according to the image region data and the sample image data. Sample image data of content violation is positioned in time, image area data with significance is positioned in space, features representingcontent violation can be rapidly sampled from a sample video file, and the quality of the features is improved in time and space dimensions, so that a content auditing model is trained, and the performance of the content auditing model can be ensured.

The invention discloses an object 6D posture prediction method based on RGB image and coordinate system transformation. The method includes decoupling 6D posture parameters of the object, and realizing 6D posture prediction of the object by solving six parameter solving problems. The 3D translation of the object is predicted by positioning the center of the object in the image and estimating the distance between the object and the camera. 3D rotation of a predicted object is converted into a pose of a predicted camera through coordinate system transformation, pose parameters of the camera aredecoupled into an azimuth angle, an elevation angle and a rotation angle around a main optical axis, and the three parameters are predicted, so that 3D rotation prediction of the object is indirectlyrealized. The invention provides a universal frame for object 6D posture prediction, 2D target detection and 6D posture prediction can be carried out in one RGB image at the same time, and the methodhas good robustness for the conditions of complex illumination conditions, disordered placement, mutual shielding between objects and the like.

Embodiments of the present invention provide a road structure information extraction method, unmanned aerial vehicle, and automatic driving system. The method includes: obtaining at least one frame ofimage data of the road (S201); determining a semantic map of the road based on the at least one frame of image data (S202), and determining road structure information of the road according to the semantic map and the road structure model, wherein the road structure information includes lane grouping information (S203), which realizes the automatic extraction of road structure information withoutmanual annotation, and can extract road structure information in real time, which improves the extraction efficiency of road structure information and the road structure information includes not onlylane information but also lane grouping information, and description of the road structure is more specific. .

The invention discloses a new energy lithium battery surface defect detection method based on adaptive deep learning. The method comprises the following steps: carrying out nonlinear mapping on a lithium battery surface grayscale image; transforming the decoupled irradiation component and reflection component to a frequency domain; performing filtering, inverse Fourier transform and exponential transform on the frequency domain data to obtain a reconstructed lithium battery image; based on morphological processing and background differencing, enhancing gray scale response at the defect; carrying out image segmentation and connected domain analysis and screening processing, and taking a result as a labeled image; designing an operator to simulate illumination details, and carrying out sample enhancement operation on the surface grayscale image of the lithium battery; training a deep convolutional neural network based on the enhanced sample image set and the labeled image; and achievinglithium battery surface defect detection based on the trained network. By utilizing the method, the detection efficiency can be improved and the false detection rate can be reduced in a lithium battery surface defect detection scene.

The invention discloses an extraction type document automatic abstracting method based on context semantic perception. The extraction type document automatic abstracting method mainly solves the problem that a traditional algorithm lacks the recognition degree of sentences in different contexts. The method comprises: firstly, using an LDA topic model for calculating topic probability distributionin a document, and then determining the similarity between each sentence and a topic word; extracting semantic features of sentences by using a CNN model, further calculating the similarity between each sentence and the features, finally adding values of topic similarity and feature similarity of each sentence to obtain a final sentence score, and taking a proper number of sentences as abstracts according to score ranking. According to the method, a topic model and a deep learning model are introduced, a topic abstracting method is determined, sentence meanings in different contexts can be analyzed more accurately, and a calculation reference method is provided for other automatic document abstracting methods.

The invention provides a video data processing method and device, equipment and a storage medium. The method comprises the steps that: video information is determined, wherein the video information isselected from preset video information, wherein the preset video information is obtained after video and audio separation is carried out on video data; subtitle content displayed by video frames in the video information is determined; the video frames in the video information are classified at least based on the subtitle content to obtain a video frame sequence, wherein the subtitle content displayed by each video frame in the video frame sequence is associated; and time information corresponding to the video frame sequence is determined to obtain the time information of the subtitle contentcorresponding to the video frame sequence so as to determine target audio information matched with the subtitle content corresponding to the video frame sequence from the audio information of the video data.

One embodiment of the invention provides an audio data processing method. The audio data processing method includes the steps: acquiring a spectrum corresponding to audio data; dividing the spectrum corresponding to the audio data into a homophonic tone spectrum and a non-homophonic tone spectrum, wherein the frequency in the homophonic tone spectrum is an integer multiple of the frequency of thefundamental tone; and determining the emotional information expressed by the audio data according to the characteristic information of the homophonic tone spectrum and the characteristic information of the non-homophonic tone spectrum. The audio data processing method can accurately identify the emotion expressed by the audio so as to enable a user to search the related audio of expressing the corresponding emotion according to the emotion dimension so as to bring a better experience for the user, by dividing the spectrum corresponding to the audio data into the homophonic tone spectrum and the non-homophonic tone spectrum, and determining the emotion information expressed by the audio data according to the characteristic information of the homophonic tone spectrum and the characteristic information of the non-homophonic tone spectrum. Besides, the embodiment of the invention provides an audio data processing device, a medium and a computing device.

The invention provides a gang fraud phone recognition method based on suspicion measurement, which adopts an unsupervised mode, utilizes call record information between phone numbers to define suspicion measurement for each phone number, and adopts a risk level quantification mode to recognize a gang fraud phone. According to the method, a subjective marking result of a user does not need to be introduced, defects caused by subjective judgment can be avoided, model training and online use can be completed within a short time, a simple and practical recognition method is provided for the user to suffer from group fraud, and the problem caused by lagging is effectively relieved.

The embodiment of the invention discloses an image set establishing method and device and a storage medium. The method comprises the steps of obtaining a single-label image set and a multi-label imageset; converting the contents of the tags into word identifiers according to a semantic network to obtain a word identifier set, a converted single-tag image set and a converted multi-tag image set; constructing a hierarchical semantic structure according to the word identifier set and the semantic network; carrying out label supplement on the images in the converted single-label image set according to the semantic relationship between the word identifiers in the hierarchical semantic structure to obtain a supplemented single-label image set; based on the co-occurrence probability between theword identifier in the supplemented single-label image set and the word identifier in the converted multi-label image set, carrying out label supplementing on the images in the supplemented single-label image set to obtain a final supplemented image set; and establishing a target multi-label image set according to the finally supplemented image set and the converted multi-label image set. According to the scheme, the establishment efficiency of the large-scale multi-label image set and the label labeling quality can be improved.

The invention discloses a retrieval method of color images based on quaternion Harmonic-Fourier moments. The method includes expanding Harmonic-Fourier moments according to the principle that quaternions contain color information, expanding the Harmonic-Fourier moments to quaternion level, acquiring a new image-describing feature vector according to the character that the Harmonic-Fourier moments can describe shape features of images, and designing a new retrieval method of color images based on quaternion Harmonic-Fourier moments. Experimental results show that the system has such features that the system can effectively represent the colors and shape features of the images, the design is simple, implementing is easy, and image feature extraction needs no manual annotation; the manual annotation process tedious and error prone is avoided, and retrieval precision and efficiency is greatly improved.

The invention discloses a high-generalization cross-domain road scene semantic segmentation method. The method comprises the following steps: generating a virtual image and a corresponding label through a game engine; generating a global/local texture migration image by using the virtual image; sending the virtual image and the global/local texture migration image to a neural network for training; performing consistency constraint on the global/local texture migration image trained by the neural network; calculating loss values of the virtual image trained by the neural network and the local texture migration image and the local texture migration image subjected to consistency constraint with the labels respectively, and training a semantic segmentation model according to the loss values; and performing semantic segmentation by using the trained semantic segmentation model. According to the method, data enhancement is realized through global texture migration and local texture migration of a virtual image, a neural network is attacked, and a model is forced to learn cross-domain invariant shape information; moreover, the method only carries out network training in the source domain, achieves a reliable cross-domain segmentation effect, and has very high generalization performance.

The embodiment of the invention relates to the technical field of computer vision, and discloses a data acquisition method, electronic equipment and a storage medium. The data acquisition method comprises the following steps: selecting a target person from a plurality of stored person models, and/or selecting a target scene from a plurality of stored scene models; controlling the target person tomove in the target scene; acquiring motion data of the target person at different acquisition moments, wherein each piece of motion data comprises an acquired image of the target person and position information of each joint of the target person in the image. By adopting the implementation mode, the data for human body posture estimation can be quickly generated, the data acquisition efficiency isimproved, and the data acquisition cost is reduced.

The invention discloses an intelligent speech recognition method and device based on classification identification and related equipment, and the method comprises the steps: carrying out the endpoint detection and feature extraction of original speech data, so as to obtain speech feature data; identifying the industry attribute of the original voice data through the attached industry attribute identifier when the original voice data is input; recognizing the voice feature data through a trained universal voice recognition model to obtain a recognition result; judging whether the confidence coefficient in the recognition result is lower than a preset value or not; inputting the corresponding text of which the confidence coefficient is lower than a preset value into the corresponding industry vertical module for optimization identification; and selecting the text corresponding to the maximum confidence coefficient as a final recognition result according to the confidence coefficient in the recognition result and the optimized confidence coefficient. The industry attribute identifier is attached when the original voice data is input, so that a corresponding industry vertical module can be conveniently called subsequently to carry out optimization identification; manual labeling is not needed, and high accuracy is maintained through secondary verification, recognition and correction.