1126results about How to "Improve labeling efficiency" patented technology

The invention provides a sample marking method and device based on artificial intelligence prosody prediction. The method comprises steps that a first text sequence of unmarked prosodies corresponding to a first sample audio file is acquired; text characteristics and pronunciation duration of each character of the first text sequence are acquired; a pre-trained prosody marking model is applied to the text characteristics and the pronunciation duration of each character of the first text sequence to acquire an output mark of each character of the first text sequence; prosodic hierarchy marking for the first text sequence is carried out according to the output mark of each character of the first text sequence. The method is advantaged in that text marking cost is reduced, text marking efficiency and accuracy are improved, more training samples required for prosodic hierarchy marking can be provided, prosodic marking model performance is improved, and the voice synthesis effect is more natural.

The embodiment of the application discloses a training method, a matting method, a device, a medium and a terminal of an image processing model. The training method of the image processing model includes obtaining a trichotomy of the original image; Generating a training sample set according to the original image and the trichotomy; The preset depth learning network is trained based on the training sample set to obtain an image processing model, wherein, the image processing model is used for labeling the original image to obtain a trichotomy. By adopting the technical proposal, the input original image can be automatically annotated to obtain a trichotomy, and a large amount of hairline level data annotation can be carried out without manual annotation, the annotation workload can be reduced, and the image annotation efficiency can be improved. In addition, the matting effect can be optimized by using image processing model to label the original image, avoiding the error that may be introduced by manual labeling.

The invention discloses a POI (Point Of Interest) labeling method and device. The method comprises the steps of receiving multiple POI data uploaded by multiple users; carrying out primary clustering on the multiple POI data according to position information by employing a clustering algorithm to generate multiple clustering areas; carrying out secondary clustering on the multiple clustering areas respectively according to names of POIs to generate multiple clustering result sets; and labeling position areas in which the POIs exist according to the multiple clustering result sets. According to the method, by employing mass POI position and attribute information uploaded by the users, the POIs are dug out quickly and accurately, so the cost of manpower and material resources is saved, the POI update speed is improved, and the POI labeling efficiency is improved.

Embodiments of the invention provide a voice processing method. The method comprises the following steps: acquiring to-be-processed audio data; extracting voiceprint information of the to-be-processed audio data; matching a target identity from a preset audio database according to the voiceprint information, wherein the preset audio database comprises a plurality of pieces of voiceprint information, each of which corresponds to an identity; and marking the to-be-processed audio data according to the target identity. The embodiments of the invention furthermore provide a terminal. Through the voice processing method and the terminal, the audio marking frequency can be improved.

The invention discloses an enzyme immunoassay of testing the bice green residues in animal derived food, which comprises an enzyme label plate covering bice green antigen, enzyme label bice green antibody working solution, bice green standard solution, substrate solution, substrate buffer solution, reaction termination solution, concentration washing liquid and sample dilute solution. The invention further discloses a method for using the immunoassay to test bice green residues, which comprises sample pretreatment, testing via the immunoassay, processing and analyzing result. The inventive immunoassay of bice green test uses direct competition enzyme-linked immunoassay adsorption analysis technique, with high sensitivity, high stability, simplified operation, reduced reaction time, reduced error caused by complex operation, reduced cost, wide application for testing samples and high practicality.

The invention provides a vehicle following distance automatic recording system and method. The vehicle following distance automatic recording system comprises multiple vehicle following distance recording units. All the vehicle following distance recording units are distributed at a monitored road according to preset distance. Each vehicle following distance recording unit comprises a supporting vertical rod. A supporting transverse rod is fixedly installed at the top end of the supporting vertical rod. The supporting transverse rod is provided with radar, at least one video camera, a light supplementing lamp and a controller. The vehicle following distance automatic recording system and method have the following advantages that (1) the monitoring recording system of combination of radar and the video cameras is adopted so that illegal vehicle position information and corresponding vehicle speed information and other driving information can be automatically recorded, the illegal vehicle position information and the corresponding vehicle speed information and other driving information can be marked on the snapshot images, and thus the vehicle illegal state can be visually and accurately reflected and sufficient legal basis can be provided for evidence obtaining and punishment of illegal vehicles.

The invention relates to a point cloud labeling method and device, computer equipment and a storage medium. The method comprises the steps of obtaining first annotation information of a first object in first frame point cloud data, wherein the first annotation information comprises size information and direction information of an annotation box and the type and number of the first object; Obtaining a second object in the to-be-labeled second frame point cloud data; And when the type of the second object is the same as that of the first object, configuring the first annotation information to the second object. According to the method, the marking efficiency of point cloud marking can be improved.

The invention provides a digital pathological image annotation method and system. The method comprises the steps that a standard graphic annotation tool based on a pathological term base is adopted to annotate a to-be-annotated digital pathological image; format management is performed on pathological annotation information on the annotated digital pathological image based on an XML format; and the annotated digital pathological image is allocated to at least three persons for review, the annotated digital pathological image passing review is stored in an annotation database, and data in the annotation database is transmitted to a machine learning sample base for machine learning. A professional, normalized and systematic digital pathological image annotation solution is provided, a user can utilize various terminal devices to perform annotation, retrieval, uploading and downloading, annotation efficiency can be improved, and formation of a uniform and collaborative pathological image annotation mechanism is promoted.

The invention provides a transfer printing plate, a display screen, a display device and a display device manufacturing method. The transfer printing plate comprises a printing region and a non-printing region, wherein the printing region comprises multiple sub-printing units corresponding to multiple unit display screens on a mother plate in one-to-one mode, different mark zones are arranged on each sub-printing unit respectively and used for forming marks for identifying the unit display screens on the mother plate on the unit display screens while forming alignment films on the unit display screens on the mother plate. By means of the scheme, the mark zones are set in the printing region of the transfer printing plate through improvement on the transfer printing plate structure, the unit display screens can be simultaneously marked on the same mother plate when the alignment films are formed on the mother plate, and the unit display screen marking efficiency of a current production line is improved.

The invention relates to a video playing method and apparatus, a computer readable storage medium and a computer device. The method comprises the steps of obtaining a target video; determining a videokey segment in the target video; playing the target video; when the video key fragment is played, playing the video key fragment at a first playing speed; when a non-key segment in the target video is played, playing the key video segment at a second playing speed; wherein the second playing speed is greater than the first playing speed. According to the scheme provided by the invention, a largeamount of unnecessary playing time consumed in the video playing process can be avoided.

The embodiment of the invention discloses a laser point cloud data labeling method and device. The method comprises the steps of obtaining laser point cloud data and a reference image which are collected at the same time and aim at the surrounding environment of the laser radar; obtaining a first labeling operation input for the displayed laser point cloud data; according to a predetermined firstmapping relation between an image coordinate system and a three-dimensional coordinate system, mapping the determined bounding box corresponding to the first labeling operation into the reference image to obtain an image bounding box in the reference image; displaying the image bounding box in an interface for displaying a reference image; and according to the bounding box and attribute information input by aiming at a reference image in the displayed image bounding box, determining marking information corresponding to the laser point cloud data. By applying the scheme provided by the embodiment of the invention, the accuracy of information labeling when the laser point cloud data is labeled can be improved.

Training sample generation is disclosed, Text data, A method for classify public opinion events and relate equipment, in a training sample generation method provided by an embodiment of the present application, At first, that text data is cluster, Because text data is clustered, When a clustering result corresponding to a target category is found, The training samples of the target category can beobtained only by selecting the text data that meet the target category conditions in the corresponding clustering results and then labeling the target category, without analyzing whether the text data in other clusters meet the target category conditions or not. Therefore, the selection range of text data is greatly narrowed, the efficiency of annotation and the accuracy of samples are improved,and the time of annotation text data is shortened. At the same time, it improves the efficiency and accuracy of text data classification and public opinion event classification process.

The embodiment of the invention provides an image annotation method and a device thereof. The image annotation method comprises the steps that an initial label set comprising a plurality of labels is obtained for an input image; the label set based similarity degree between the label set of the input image and a label set of a comparison image stored in a data base is calculated; the label set based similarity degree and the vision based similarity degree are subjected to consolidation, so as to obtain the consolidated similarity degree between the input image and the comparison image; and the label set of the input image is updated based on the consolidated similarity degree. According to the embodiment of the invention, low level characteristics and high level semantics of the image can be considered at the same time; the precision of image annotation can be improved; the automatic label annotation is realized; and the annotation efficiency is improved.

The invention discloses a face sample picture labeling method and device, a computer device and a storage medium. The method comprises: identifying the to-be-labeled picture by using a preset emotionidentification model, the identification result is used as annotation information to be annotated into a to-be-annotated picture; obtaining an error data set in the to-be-labeled picture and outputting the error data set to the client; storing the corrected error data set sent by the client and the correct data set in the to-be-labeled picture as standard samples in a standard sample library; andtraining the emotion recognition model by using the standard sample to update the emotion recognition model, and returning to the step of identifying and labeling the to-be-labeled picture by using the preset emotion recognition model until the error data set in the to-be-labeled picture is empty. According to the technical scheme, the annotation information can be automatically generated for theface image, the annotation efficiency of the face image is improved, and therefore the generation efficiency of the standard sample library used for model training and testing is improved.