Abstract:
A touch region adjustment method includes: determining a region on a touch display of a terminal device and in which a sensing parameter changes to determine a grasping gesture of a user for the terminal device; and adjusting a location of a touch response region on the touch display based on the grasping gesture of the user for the electronic device to avoid an accidental touch caused by the grasping gesture of the user for the screen of the terminal device.
Abstract:
A method and neural network system for human-computer interaction, and user equipment are disclosed. According to the method for human-computer interaction, a natural language question and a knowledge base are vectorized, and an intermediate result vector that is based on the knowledge base and that represents a similarity between a natural language question and a knowledge base answer is obtained by means of vector calculation, and then a fact-based correct natural language answer is obtained by means of calculation according to the question vector and the intermediate result vector. By means of this method, a dialog and knowledge base-based question-answering are combined by means of vector calculation, so that natural language interaction can be performed with a user, and a fact-based correct natural language answer can be given according to the knowledge base.
Abstract:
A touchscreen of an electronic device includes a first region and a second region, which each correspond to a baseline, and the baseline corresponds to a capacitance value when a region corresponding to the baseline is not touched. A method for controlling the touchscreen includes that the electronic device receives a first touch signal in a first region on the touchscreen, and the electronic device maintains a baseline corresponding to the first region unchanged in response to the first touch signal in the first region.
Abstract:
A multi-document summary generation method includes obtaining a candidate sentence set, training each candidate sentence in the candidate sentence set using a cascaded attention mechanism and an unsupervised learning model in a preset network model, to obtain importance of each candidate sentence, selecting, based on the importance of each candidate sentence, a phrase that meets a preset condition from the candidate sentence set as a summary phrase set, and obtaining a summary of a plurality of candidate documents based on the summary phrase set.
Abstract:
An address search method and device, includes acquiring address search request information, determining to-be-found destination address information included in the address search request information, splitting the destination address information into at least one piece of sub-address information, where the destination address information is formed by multiple pieces of sub-address information, and the multiple pieces of sub-address information respectively correspond to different address types, matching the at least one piece of sub-address information or the at least one piece of sub-address information and the destination address information with different address information included in an address database, where each piece of address information stored in the address database includes different sub-address information that forms the address information, and setting address information that is obtained by matching and whose match degree is greater than a set threshold as found destination address information for output.
Abstract:
A paraphrase sentence generation method and apparatus relating to the research field of natural language processing include generating m second sentences based on a first sentence and a paraphrase generation model, determining a matching degree between each of the m second sentences and the first sentence based on a paraphrase matching model, and determining n second sentences from the m second sentences based on matching degrees among the m second sentences and the first sentence, where the paraphrase generation model is obtained through reinforcement learning-based training based on a reward of the paraphrase matching model.
Abstract:
An information displaying method and a terminal are provided. The method includes: obtaining audio data to be played in a chronological order; determining, based on attribute information at any moment of a sound represented by the audio data, a shape of a graph corresponding to the any moment, where the graph corresponding to the any moment including a closed curve with a bump, and a maximum distance in distances from points on the bump to a center of the graph is positively correlated to a value indicated by the attribute information at the any moment; and displaying the graph corresponding to the any moment. The bump in the graph changes with the value indicated by the attribute information of the sound, and such graph is presented to a user, to enhance perception of the user on the attribute information of the audio data and improve user experience.
Abstract:
Embodiments of the present invention provide a weighing method of a touchscreen terminal, and a touchscreen terminal. When a to-be-weighed object is placed in a preset area of a touchscreen of a touchscreen terminal, a reported first capacitance value and reported coordinates of a compensation point are obtained. The first capacitance value is compensated according to a compensation relationship, the coordinates of the compensation point, and the first capacitance value to obtain a second capacitance value. In this way, no additional external structure is needed for the touchscreen terminal, making the touchscreen terminal convenient to carry.
Abstract:
A reply information recommendation method and apparatus provides recommended reply information suitable for a context that can be quickly and accurately calculated when a user replies to information. A specific solution is: acquiring information to be replied to received by a user and pre-reply information that is input by the user and corresponding to the information to be replied to; performing segmentation processing on the information to be replied to, to obtain a segmentation processing result; learning a stored text interaction history set of the user to obtain a reply model; obtaining candidate reply information with reference to the segmentation processing result of the information to be replied to and the reply model; and calculating a set of recommended reply information with reference to the candidate reply information and the pre-reply information. The embodiments of present invention are used for reply information recommendation.
Abstract:
The present disclosure includes acquiring a keyword of information to be replied to, as a first feature, and acquiring a keyword of a pending reply in a pending reply set as a second feature, calculating, according to a correlation between the first feature and the second feature, a match between the information to be replied to and the pending reply, where the correlation between the first feature and the second feature is obtained through multiple trainings according to an original text and a reply to the original text that are acquired from a corpus environment, where the corpus environment includes a microblog, a forum, and a post bar, repeating the foregoing steps, until matches between the information to be replied to and all pending replies are obtained, and selecting a best matched pending reply as a reply to the information to be replied to.