37results about How to "Correct answer" patented technology

This invention provides a method for realizing the question and answer function for electronic documents, an assist art writing method by computers, a method for browsing electronic documents, an assistant writing device, a browser capable of providing question and answer functions, a service method and system by computers. The method includes: when an author writes an electronic document, it generates information of its function, the author guarantees its reliability, such information corresponding to the document is stored and the function is provided by the information.

The invention discloses a keyword-based question and answer method and device and a medium, and the method comprises the steps: obtaining an online corpus, extracting keywords in the online corpus, screening out a target keyword matched with a training corpus from the obtained keywords, inputting the target keyword and the training corpus into a corpus training model together, and adjusting parameters of the model based on an output result of the model to obtain a semantic understanding model; after the semantic understanding model is obtained, obtaining a standard question corresponding to auser question according to the user question, thereby outputting an answer corresponding to the standard question, and completing a question and answer mode. Therefore, because the target keyword is used as an auxiliary and is used as an input sample together with the training corpus, the weight of the information matched with the keywords in the training corpus is improved, the attention of the semantic comprehension model to the keywords is actively improved, and the similar user questions are accurately recognized, so that more accurate answers can be output, and the user experience is improved.

A social CAPTCHA is presented for authenticating members of a social network. The social CAPTCHA includes one or more challenge questions based on information available in the social network, such as the user's activities and / or connections in the social network. The social information selected for a social CAPTCHA may be determined based on affinity scores associated with connections to members, such that the challenge questions relate to information that is more likely to be familiar to the user. The difficulty of asking questions can be determined based on suspiciousness and used to select a CAPTCHA.

The present invention belongs to the technical field of computer intelligent dialogue, and provides a method and system for unstructured text intelligent question answering, including: S1, the encoding layer encodes the acquired text and questions respectively, to obtain text hidden vectors and question hidden vectors; S2, the information fusion layer fuses the text hidden vector and the question hidden vector, and obtains a fused association vector group; S3, the decoding layer decodes the text according to the association vector group, and obtains the question , and output said answer. The present invention can directly give answers to questions about unstructured texts, and does not need to establish a question-and-answer library in advance; there is no limit to the type of questions; the returned answers are relatively accurate; data-driven, effectively utilizing big data.

The invention discloses a method for responding to a user registration state request. The method includes the following steps: setting a user registration state priority table for saving user registration state priority in the HSS in advance; the HSS according to the first user identifier and Pre-saved correspondence between the first user ID and the second user ID and the user registration status, obtaining all user registration statuses corresponding to the first user ID, and obtaining the acquired user registration status according to the user registration status priority table The user registration status with the highest priority in the status, and send the user registration status with the highest priority to the AS through a UDA message. The invention also provides a system for responding to user registration status requests. When the first user ID corresponds to a plurality of second user IDs, the invention can correctly respond to the UDR message and return the appropriate user registration status to the AS, thereby making up for the deficiency of the existing protocol.

The invention belongs to the field of video question and answer, and in particular relates to a method for multi-modal video question and answer using frame-subtitle self-supervision. It includes the following steps: extracting video frame features, question and answer features, subtitle features, and subtitle suggestion features; obtaining frame features with attention and subtitle features with attention, and obtaining fusion features; calculating temporal attention scores based on fusion features; using temporal attention The time boundary of the question is calculated by the score calculation; the answer to the question is calculated by using the fusion feature and time attention score; the neural network is trained by using the time boundary of the question and the question answer; the network parameters of the neural network are optimized, and the optimal neural network is used for video question and answer and planning set time boundaries. Instead of using expensive time annotations, the present invention generates problem-related time boundaries based on self-designed time attention scores. In addition, the present invention obtains a more accurate answer by mining the relationship between the subtitle and the corresponding video content.