The invention provides a voice recognizing method and device, equipment and a storage medium. The method includes the steps of receiving first voice sent by an intelligent voice device by a server, extracting voice features of the first voice by the server, determining the confidence coefficient of the first voice according to the voice features by the server, sending the confidence coefficient ofthe first voice to the intelligent voice device by the server, and determining whether the first voice is a voice inquiry request or not according to the confidence coefficient of the first voice bythe intelligent voice device. Through the voice recognizing method, whether the obtained voice is the voice inquiry request or noise can be essentially distinguished, and therefore the voice recognizing accuracy of the intelligent voice device can be improved.

Voice recognizing method and device, equipment and storage medium

An embodiment of the invention provides a voice interaction method, device and equipment and a storage medium. The method comprises the steps as follows: judging reception duration is overtime; if no,performing voice recognition on a to-be-detected voice signal to obtain a to-be-detected text; performing primary detection on the to-be-detected text; when a primary detection result indicates failure, returning to execute the judgment step. By adoption of the embodiment, the misrecognition rate of the voice signal in the voice interaction process can be reduced and user experience can be improved.

Voice interaction method, device and equipment as well as storage medium

The invention discloses an entity alignment method and device, and the method comprises the steps: carrying out the iterative execution of two screening steps so as to obtain a first entity pair set,wherein the two steps are: carrying out the screening of a target entity pair in two knowledge maps according to a target attribute pair, and carrying out the screening of a new target attribute pairin the two knowledge maps according to the target entity pair. Each target entity pair in the first entity pair set is obtained through the attribute information between different entities, and the attribute information of each entity can more truly and comprehensively represent the entity, so that when the attribute information of the entity is used for aligning the entity, the accuracy of an entity alignment result can be improved.

Entity alignment method and device

An embodiment of the invention provides a method for a voice assistant. The method comprises the following steps: 101, the voice assistant acquires a voice command of a user; 103, whether an interactive sub-engine corresponding to the voice command exists or not is judged according to the voice command, and if yes, the interactive sub-engine is called and the step 105 is executed, otherwise, the step 107 is executed; 105, interaction with the user is performed according to the called interactive sub-engine; and 107, the interactive sub-engine is created by the voice assistant. According to themethod, the interaction between the voice assistant and the user can be more intelligent and humanized, the interaction efficiency is improved, and the user experience is improved.

Method and device for voice assistant

The invention provides a voice interaction method. The method comprises the following steps: parsing a received first voice command; determining a second voice command based on the first voice commandin response to the inability to parse the first voice command to obtain an intention, wherein the second voice command is a voice command which can be parsed to obtain an intention; and executing thesecond voice command on the basis of the intention of the second voice command. The invention also provides a voice interaction device, a terminal and a computer readable medium.

Voice interaction method and device, terminal and computer readable medium

The application discloses a speech interaction method and speech interaction equipment. An association relationship between a to-be-distinguished speech and historical interaction data can be analyzed, and the historical interaction data include a user speech instruction before the to-be-distinguished speech and a response result for the user speech instruction; then whether the to-be-distinguished speech is an instruction-type speech can be judged according to the association relationship between the two parts; command response can be not carried out thereon when it is judged that the speechis a non-instruction-type interference speech; and thus one time of wrong human-machine interaction is avoided, and then user experience is improved.

Speech interaction method and speech interaction equipment

The invention discloses an attribute name representation method and device. The method comprises the steps of pre-building an attribute name representation model, wherein the attribute name representation model is used for enabling attribute names with the same or similar meanings to correspond to the same or similar representation vectors; and during actual use, by utilizing the attribute name representation model, carrying out vector representation on the to-be-represented target attribute names to obtain the representation vectors corresponding to the target attribute names. According to the attribute name representation method and device, the attribute names with the same or similar meanings generally correspond to the same or similar attribute values, so that when the attribute valueinformation is considered during the model building, the attribute name representation model can enable the target attribute names with the same or similar meanings to correspond to the same or similar representation vectors.

Liu Quan

Papers

Speech interaction method and speech interaction equipment

Attribute name representation method and device