Techniques are described herein for enabling autonomous agents to generate conclusive answers. An example of a conclusive answer is text that addresses concerns of a user who is interacting with an autonomous agent. For example, an autonomous agent interacts with a user device, answering user utterances, for example questions or concerns. Based on the interactions, the autonomous agent determines that a conclusive answer is appropriate. The autonomous agent formulates the conclusive answer, which addresses multiple user utterances. The conclusive answer provided to the user device.

Techniques are described herein for enabling autonomous agents to generate conclusive answers. An example of a conclusive answer is text that addresses concerns of a user who is interacting with an autonomous agent. For example, an autonomous agent interacts with a user device, answering user utterances, for example questions or concerns. Based on the interactions, the autonomous agent determines that a conclusive answer is appropriate. The autonomous agent formulates the conclusive answer, which addresses multiple user utterances. The conclusive answer provided to the user device.

A system and method for integrating a widget in a third-party application. Initially, a widget software code related to insurance payment capture and verification may be received. Further, the widget software code may be integrated into an application code of a third-party application. The widget software code may be executed to invoke an insurance payment widget. The insurance payment widget is configured to capture insurance card images, and extract insurance information based on an analysis of the insurance card images. Furthermore, the extracted insurance information may be validated using an insurance database and plans curated by an application provider. Subsequently, an insurance eligibility status and insurance coverage benefits of the insurance subscriber may be received and used to enable an insurance payment mode on the third party application in real-time, thereby integrating the widget in the third party application.

A system and method for integrating a widget in a third-party application. Initially, a widget software code related to insurance payment capture and verification may be received. Further, the widget software code may be integrated into an application code of a third-party application. The widget software code may be executed to invoke an insurance payment widget. The insurance payment widget is configured to capture insurance card images, and extract insurance information based on an analysis of the insurance card images. Furthermore, the extracted insurance information may be validated using an insurance database and plans curated by an application provider. Subsequently, an insurance eligibility status and insurance coverage benefits of the insurance subscriber may be received and used to enable an insurance payment mode on the third party application in real-time, thereby integrating the widget in the third party application.

Embodiments of the present disclosure provide a method and apparatus for outputting information. A specific embodiment of the method includes: in response to receiving a query, detecting whether there is an entity slot in the query; in response to there being an entity slot in the query, adding the detected entity slot to a candidate slot; detecting, in the query, a relationship-determinative word of an entity; searching in a preset knowledge graph for a peripheral knowledge graph of the candidate slot; and inferring on the basis of the peripheral knowledge graph according to the relationship-determinative word, and outputting an entity word matching the relationship-determinative word.

A hybrid entity recognition system and accompanying method identify composite entities based on machine learning. An input sentence is received and is preprocessed to remove extraneous information, perform spelling correction, and perform grammar correction to generate a cleaned input sentence. A POS tagger tags parts of speech of the cleaned input sentence. A rules based entity recognizer module identifies first level entities in the cleaned input sentence. The cleaned input sentence is converted and translated into numeric vectors. Basic and composite entities are extracted from the cleaned input sentence using the numeric vectors.

A hybrid entity recognition system and accompanying method identify composite entities based on machine learning. An input sentence is received and is preprocessed to remove extraneous information, perform spelling correction, and perform grammar correction to generate a cleaned input sentence. A POS tagger tags parts of speech of the cleaned input sentence. A rules based entity recognizer module identifies first level entities in the cleaned input sentence. The cleaned input sentence is converted and translated into numeric vectors. Basic and composite entities are extracted from the cleaned input sentence using the numeric vectors.

This disclosure describes a system that enables a user to efficiently view messages of a conversation that are more relevant to the user. The system is configured to display content of a first application within an application user interface (UI) and to determine that a message of a second application being monitored includes a trigger feature that comprises a piece of information or an interaction from another user that is worthy of the user's attention. The system can then generate a visual notification for the trigger feature. The visual notification can be displayed in association with a graphical element of the application UI. Upon receiving an indication of a selection of the visual notification, the system can switch from displaying the content of the first application to displaying the message of the second application and trigger feature and/or change visual characteristics associated with the message to bring focus to the message.

This disclosure describes a system that enables a user to efficiently view messages of a conversation that are more relevant to the user. The system is configured to display content of a first application within an application user interface (UI) and to determine that a message of a second application being monitored includes a trigger feature that comprises a piece of information or an interaction from another user that is worthy of the user's attention. The system can then generate a visual notification for the trigger feature. The visual notification can be displayed in association with a graphical element of the application UI. Upon receiving an indication of a selection of the visual notification, the system can switch from displaying the content of the first application to displaying the message of the second application and trigger feature and/or change visual characteristics associated with the message to bring focus to the message.

A method and an apparatus for fusing position information, and a non-transitory computer-readable recording medium are provided. In the method, words of an input sentence are segmented to obtain a first sequence of words in the input sentence, and absolute position information of the words in the first sequence is generated. Then, subwords of the words in the first sequence are segmented to obtain a second sequence including subwords, and position information of the subwords in the second sequence are generated, based on the absolute position information of the words in the first sequence, to which the respective subwords belong. Then, the position information of the subwords in the second sequence are fused into a self-attention model to perform model training or model prediction.