Abstract:
Methods and systems are described for responding to natural language queries. Specifically a natural language query is received and a query template that corresponds to the natural language query is determined. One or more search results corresponding to the natural language query are retrieved. One or more attributes associated with the user equipment device are identified and based on those attributes a first response template associated with an audio-only response to the natural language query, a second response template associated with a visual-only response to the natural language query, or a third response template associated with an audio-visual response to the natural language query is selected. A response to the natural language query is generated based on the selected response template and the retrieved one or more search results.
Abstract:
Systems and methods are provided herein for using a trained knowledge graph to accurately determine whether two phrases are conversationally connected. To this end, three phrases are received. The phrases are translated to strings of word types by determining what type of word each word of each phrase represents, and replacing each word of the first phrase with its respective type. A knowledge graph is then accessed to determine strengths of association between a combinations of each string of word types and any conversational category of a plurality of conversational categories. If any of the strengths of association exceed a threshold, the corresponding strings may be determined to be part of a conversation.
Abstract:
Systems and methods provided herein for a determining a meaning of an ambiguous term in a text segment based on a context term, a static knowledge graph and a temporal knowledge graph. These systems and methods access a first knowledge graph associated with the context term to determine a potential term that is the meaning of the unknown term. Upon determining that there are multiple potential terms in the first knowledge graph that could be the meaning of the unknown term, the systems and methods take into account the temporal dimension of relationships between entities for disambiguating the meaning of the unknown term. The systems and methods achieve this by determining a time stamp of the text segment and accessing a second knowledge graph associated with the first context term and related to the time stamp to determine the potential term that is the meaning of the first unknown term.
Abstract:
Systems and methods provide a media guidance application that recognizes a plurality of natural language search queries for identifying a set of search results. For example, a user may want to determine when the Yankees are playing their next baseball game. The user may structure their query in multiple ways, such as, “When are the Yankees playing?” “What time is the Yankees game?” “When is the next Yankees baseball game?” The user would expect the same result, a description of when the Yankees are playing, regardless of how the query is structured. The systems and methods enable a user to use a plurality of search queries when searching for items or information to get desired results.
Abstract:
Methods and systems are provided for generating a response to a natural language query. Specifically, the natural language query is received and a query template that corresponds to the natural language query is determined. One or more search results corresponding to the natural language query are retrieved. One or more attributes associated with a user are selected based on selection criteria. Based on those attributes, a response template previously assigned to the query template is identified. A response to the natural language query is generated based on the identified response template and the retrieved one or more search results.
Abstract:
Methods and systems for determining an error value based on comparing an expected media asset similarity value corresponding to a first media asset and a second media asset, as determined using a model, to a media asset similarity value determined from user preference information associated with multiple data spaces. User preference information is received from two data spaces that are managed by different content providers. User preference information from the two data spaces is normalized and an indication of similarity between two media assets is determined. The indication of similarity is compared to an expected similarity value received from a model and an error value is determined based on the comparison of the expected similarity value and the similarity value.
Abstract:
Methods and systems for determining an error value based on the user's expected level of enjoyment with respect to a specific media asset based on the user's level of enjoyment of other media assets, as determined using a model. User preference information is received from two data spaces that are managed by different content providers. User preference information from the two data spaces is normalized and an indication of similarity between two media assets is determined. The user's level of enjoyment with respect to a media asset is compared to an expected user's level of enjoyment with respect to the media asset received from a model and an error value is determined based on the comparison.
Abstract:
Systems and methods for searching for a media asset are described. In some aspects, the system includes control circuitry that receives a first search query from a user. The control circuitry identifies media assets related to the first search query from a content database. The control circuitry receives a second search query following the first search query. The control circuitry determines whether a media asset from the media assets is related to the second search query. In response to determining that less than a threshold number of media assets from the media assets are related to the second search query, the control circuitry transmits an instruction requesting the user to repeat the second search query. The control circuitry receives a third search query related to the first search query. The control circuitry determines a media asset from the media assets that is related to the third search query.