30results about How to "Fully express" patented technology

Embodiments of the invention provide a word vector learning model training method and a server. The method comprises the following steps of: obtaining a word meaning vector and a primitive vector corresponding to a word in a training sample text; expressing a word vector in the training sample text according to the word meaning vector or the primitive vector; and substituting the word vector expressed by the word meaning vector or the primitive vector into an existing word vector learning model and carrying out model training. The server is used for executing above method. According to the word vector learning model training method and the server provided by the invention, the word vector is expressed through the primitive vector or the word meaning vector, and the word vector learning model corresponding to the word vector expressed by the word meaning vector or the primitive vector is trained, so that the semantic information of the word can be sufficiently expressed.

The invention discloses a random projection fern based real-time target tracking algorithm, and relates to machine vision and pattern recognition technologies. The target tracking algorithm comprises four steps of: step 1: an algorithm initialization module; step 2: a random projection fern training module; step 3: a random projection fern classification module; and step 4: a training set updating module. According to the target tracking algorithm provided by the invention, random projection is introduced in addition to random fern, and the target tracking algorithm has the advantages of having the fast calculation speed, few memory demands, being accurate in tracking and easy for transplanting of an embedded system, and therefore can be widely applied in the field of visual navigation, man-machine interaction and monitoring systems and the like.

The invention discloses an audio file cutting method and device and terminal equipment. The method comprises a step of determining an invalid audio in an audio file and a file fragment where the invalid audio is located, a step of cutting the file fragment where the invalid audio in the audio file is located, and generating a cut audio file. In the invention, the file fragment where the invalid audio in the audio file is located can be automatically determined and cut, which is equivalent to a condition that the invalid audio in the audio file is filtered. Thus under the condition of preserving a valid audio in the audio file, the storage space occupied by the audio file is reduced, and the utilization efficiency level of the storage space of equipment which stores the audio file is improved. When the audio file is played, the time of playing the invalid audio in the audio file is saved, the time and energy of listening to the invalid audio by a user are saved, the playing efficiency of the audio file is improved, and a user experience is improved.

A multi-feature fusion-based polarimetric SAR image classification method disclosed by the present invention comprises the steps of firstly extracting the polarimetric feature vectors of a to-be-classified polarimetric SAR image to obtain a high-dimension polarimetric feature set; extracting the morphological profile feature vectors of the SPAN processing results of the image to obtain a high-dimension morphological feature set; carrying out the dimension reduction processing of the locality preserving discrimination analysis on the two kinds of high-dimension features separately, and then selecting the image pixel points of the known category labels to form a training sample set, and then selecting the rest pixel points of the whole image as a classification sample set; using a maximum posterior probability-based support vector machine (SVM) to process the two kinds of low-dimension features separately to obtain the category labels and the corresponding posterior probabilities of the pixel points on the respective conditions; adopting a summation criterion or an adaptive weighted summation criterion to combine the posterior probability vectors of each pixel point on the two conditions, and according to the maximum posterior probability principle, obtaining a final classification result of the high-resolution polarimetric SAR image. According to the present invention, the classification accuracy and the efficiency of the resolution polarimetric SAR image are helpful to be improved.

The invention discloses an ontology construction methodology for complex product design. The ontology construction methodology comprises the steps that requirements of knowledge needed by the design are analyzed, and the ontology using object, application background and achieving function are determined; according to the requirements and the function-behavior-structure combination, the complex product design knowledge is classified; a semantic relation framework for product design ontology construction is constructed, and the semantic relation in the complex product design is determined, wherein the semantic relation framework refers to the relation in a suggested upper merged ontology (SUMO) and the relation defined by a user according to product characteristics; UML modeling is carried out on a concept ontology and a design ontology; the concept ontology and the design ontology of a complex product are constructed; the ontology modification or improvement is carried out by adopting an ontology inspection and evaluation method. By means of the ontology construction methodology for complex product design, ontology construction is achieved in the field of complex product design, and a support is provided for design knowledge share and reusing.

The invention provides a method for constructing dual-promoter DNA anti-caries vaccine plasmid pCN-SSIE, and a preparation method of the anti-caries vaccine by the plasmid pCN-SSIE. Antigen gene SBR is inserted in the vector pCMVnir by the molecular cloning technology, green fluorescent protein reporter gene is added in the downstream of the SBR, and the SBR and the reporter gene pass through the interior of the ribosome and enter the site gene for connection so as to prevent the fusion expression thereof; and finally, a section of signal peptide sequence is fused at the 5' end of the SBR. The anti-caries vaccine improves the immunogenicity of the anti-caries vaccine, enhances the immune effect, has simple and convenient, effective and economical immune method with long duration, and can carry out immunity repeatedly with little side effects.

The invention relates to an image scene classification method based on a converter model and a convolutional neural network. The method comprises the steps that two convolutional neural networks and a converter model are used in the scene classification process of an image, the converter model is used for establishing interrelation between global elements at the bottom layer of the scene image, the defects of the convolutional neural networks in scene image feature extraction are effectively overcome. Therefore, the network can pay attention to the key area in the scene from the beginning, so that the scene classification effect is improved. Features extracted by the convolutional neural network are used as additional input of a converter model to guide a coding unit to focus on an area which can form good supplementation with depth features, and a relation between a network bottom layer and a network high layer is established from the other aspect, so that model expression is more comprehensive and sufficient.

The embodiment of the invention provides a method and a device for extracting a key frame. The method for extracting the key frame comprises the following steps: acquiring a target video; and taking the target video as the input of a key frame extraction model, and obtaining the key frame of the target video through the prediction of the key frame extraction model, wherein the key frame extractionmodel is obtained by training a neural network model according to a first loss corresponding to a sample video and a second loss corresponding to the sample video, the first loss represents the difference between the annotation key frame of the sample video and a prediction key frame predicted by the neural network model for the sample video, and the second loss represents the difference betweenthe annotation type of the sample video and the prediction type predicted by the neural network model for the sample video. The extracted key frame is effectively ensured to be related to the contentof the target video.

The invention discloses an adjuvant of a rabbit plague oral vaccine IL-2 and application. The adjuvant of the rabbit plague oral vaccine IL-2 is prepared by mixing recombinant bacteria SL7207-PVAX1-IL-2 and the recombinant bacteria SL7207-PVAX1-VP60. The presented recombinant strains SL7207-PVAX1-IL2 and SL7207-PVAX1-VP60 of attenuated salmonella typhimurium SL7207 were constructed correspondingly and the two recombinant bacteria are immunized in rabbits together, and IL-2 could exert the immune stimulating effect to enhance the immune effect of the oral vaccine. The adjuvant has high safety, high biosafety, simple and efficient immunization method, simple vaccine preparation and double adjuvant effects.

The invention discloses a rapid photo chatting method. The method comprises the following steps: opening a photo chatting mode interface; displaying a real-time picture in a camera shooting mode; character chat content is input in the character input area; respectively sending the picture content and the text content; and displaying the characters and the pictures shot in real time on a chat interface together. According to the invention, through a mode of combining a real situation and characters, words wanting to be spoken for a scene in front of eyes are vividly and accurately reproduced and sent out, so that emotion expression and reception are smoother and more direct, information transmission and reception are faster and more accurate, and the form is more interesting; and compared with the traditional chat software, a better effect is achieved on social attributes.

The invention provides a graph remark information generation method and device, electronic equipment and a storage medium, and relates to the field of data statistics. The graph remark information generation method comprises the following steps: responding to a received remark instruction, and extracting a statistical object name and a scalar value of each statistical object in a graph; sorting the statistical object names according to the scalar value of each statistical object to obtain a sorting result; and finally, generating remark information of the graph according to the sorting result, wherein the remark information comprises character information used for representing the sorting result, so that the remark information of the content in the graph can be automatically generated in detail and normatively, and the remark information can be fully expressed, and a target graph can be efficiently and accurately found from a large number of graphs through the remark information or description when a subsequent worker needs to use the graph.

The invention provides a thermodynamic diagram-based network structure for quickly counting stephanitis chinensis drakes. The network structure comprises a backbone network, a first feature fusion network and a second feature fusion network, wherein the backbone network comprises a convolution layer in a VGG16 network structure. Through the fusion of the backbone network and the first feature fusion network, shallow features are fused to deep features, and the spatial information and the detail information of the deep features are supplemented and enriched. In addition, through the fusion of the backbone network and the second feature fusion network, the deep features are reversely fused to the shallow features, so that the situation that the spatial information and the detail informationof the shallow features cannot be fully expressed after the deep feature information is enriched is avoided. Through the bidirectional feature fusion structure, the spatial information and the detailinformation of the shallow features and the deep features can be fully expressed, so that the stephanitis chinensis drakes can be identified and counted timely, quickly and accurately, and interference is avoided.

The invention provides the construction of plasmid pCN-SSISG of bivalent dual-promoter DNA anti-caries vaccine and the preparation of anti-caries vaccine by plasmid pCN-SSISG. The construction method comprises the following steps: inserting an antigen gene SBR and an antigen gene GBR into a vector pCMVnir by using molecular cloning technology; connecting the antigen gene SBR and the antigen gene GBR through IRES to prevent fusion expression of the antigen gene SBR and the antigen gene GBR; and fusing a signal peptide gene on the 5' end of each antigen gene. The construction method increases the immunogenicity of the anti-caries vaccine and improves immunity effects. Moreover, the immunity method is simple, effective and economical, has long-lasting effect and can realize immunity repeatedly with insignificant side effects.

The invention discloses a photo chatting method and device and a storage medium. The method comprises the following steps: opening a photo chatting mode interface; displaying a real-time picture in a camera shooting mode; inputting characters displayed on the photo in the character input area; sending the chat content; and displaying the characters and the pictures shot in real time on a chat interface together. According to the invention, through a mode of combining a real situation and characters, words wanting to say for a scene in front of eyes are vividly and accurately reproduced and sent out, so that emotion expression and reception are smoother and more direct, information transmission and reception are more accurate, and the form is more interesting; and compared with the traditional chat software, a better effect is achieved on social attributes.