Knowledge Graph For Conversational Semantic Search
US-2019034780-A1 · Jan 31, 2019 · US
US11797609B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11797609-B2 |
| Application number | US-202016743157-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jan 15, 2020 |
| Priority date | Jan 11, 2018 |
| Publication date | Oct 24, 2023 |
| Grant date | Oct 24, 2023 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method, apparatus and computer program product for presenting a user interface for a conversational system is described. A unified contextual graph for use by the conversational system, the unified contextual graph comprising components based on database queries of the conversational system and a user dialog between a user and the conversational system. For each of a set of user utterances produced in a dialog with the conversational system, a semantic meaning representation is determined. The semantic meaning representations are converted to respective sentential concept graphs. The unified contextual graph is updated based on new sentential concept graphs while the dialog with the conversational system progresses.
Opening claim text (preview).
What is claimed: 1. A method for presenting a user interface for a conversational system comprising: storing a unified contextual graph in a memory of and for use by the conversational system, the unified contextual graph comprising components created by the conversational system from database queries of the conversational system and a user dialog between a user and the conversational system; during a current user dialog between a user and the conversational system, receiving a latest user utterance of a set of user utterances in the current user dialog via the user interface of the conversational system, by the conversational system determining a semantic meaning representation for the latest user utterance; during the current user dialog, converting the semantic meaning representation to a sentential concept graph for the latest user utterance; responsive to receiving the sentential concept graph, updating the unified contextual graph by merging the sentential concept graph with the unified contextual graph; responsive to updating the contextual graph, creating a system response by the conversational system at least in part due to changes in components of the unified contextual graph due to the merge of the sentential concept graph; and as part of the user dialog, presenting the system response together with a representation of at least one changed component of the unified contextual graph which created the system response in the user interface while the current user dialog with the conversational system progresses. 2. The method as recited in claim 1 further comprising: responsive to receiving the sentential concept graph, querying a database of the conversational system, wherein the updating the unified contextual graph is based on semantic matching with domain knowledge stored in the database of the conversational system. 3. The method as recited in claim 1 , wherein the representation of at least one changed component is a graphical element in the user interface and the method further comprising dynamically identifying additional unchanged components of the united contextual graph and presenting the additional unchanged components as graphical elements in the user interface as relevant to the latest user utterance. 4. The method as recited in claim 3 , further comprising identifying concepts and relations that are semantically related to a latest dialog activity in the dialog with the conversational system. 5. The method as recited in claim 3 , further comprising: identifying concepts and relations that are semantically related in the first sentential concept graph to concepts and relations in the unified contextual graph; and in response to identifying the semantically related concepts and relations, constructing a query to a database of the conversational system according to the identified concepts and relations. 6. The method as recited in claim 1 , further comprising; identifying a set of changes to concepts, concept values and concept statuses based on a latest user input; identifying relevant components to the concepts, the concept values and the concept statuses in the unified contextual graph; and identifying changes to relevant components in the unified contextual graph based on results from queries to databases of the conversational system wherein the representation of at least one changed component is a graphical element in the user interface. 7. The method as recited in claim 1 , further comprising: determining that a first component of the unified contextual graph related to a current dialog activity of the latest user utterance is unavailable; responsive to the determination that the first component is unavailable, quantifying a set of factors associated with other respective components of the unified contextual graph, the set of factors including at least one of a concept-level feature, a relation-level feature or a discourse-level feature; ranking the other respective components in the unified contextual graph based on the quantified factors; and presenting a highest ranked component of the other respective components as a graphical element in the user interface. 8. Apparatus, comprising: a processor; computer memory holding computer program instructions executed by the processor for presenting a user interface for a conversational system, the computer program instructions comprising: program code, operative to store a unified contextual graph in a memory of and for use by the conversational system, the unified contextual graph comprising components created by the conversational system from database queries of the conversational system and a user dialog between a user and the conversational system; program code, operative to receive a latest user utterance of a set of user utterances in a current user dialog via the user interface of the conversational system, by the conversational system determining a semantic meaning representation for the latest user utterance; program code, operative to convert the semantic meaning representation to a sentential concept graph for the latest user utterance in the current user dialog; program code responsive to receiving the sentential concept graph, operative to update the unified contextual graph by merging the sentential concept graph with the unified contextual graph in the current user dialog; program code responsive to updating the contextual graph, operative to create a system response by the conversational system at least in part due to changes in components of the unified contextual graph due to the merge of the sentential concept graph in the current user dialog; and program code, operative to present the system response together with a representation of at least one changed component of the unified contextual graph in the user interface while the current user dialog with the conversational system progresses. 9. The apparatus as recited in claim 8 , further comprising: program code, operative to dynamically identify additional unchanged components of the united contextual graph and presenting the additional unchanged components in the user interface as relevant to the latest user utterance. 10. The apparatus as recited in claim 9 , further comprising: program code, operative to identify concepts and relations that are semantically related to a latest dialog activity in the dialog with the conversational system. 11. The apparatus as recited in claim 9 , further comprising: program code, operative to identify concepts and relations that are semantically related in the first sentential concept graph to concepts and relations in the unified contextual graph; and program code, operative to construct a query to a database of the conversational system according to the identified concepts and relations. 12. The apparatus as recited in claim 9 , further comprising: program code, operative to quantify a set of factors associated with respective subgraphs, the set of factors including at least one of a concept-level feature, a relation-level feature or a discourse-level feature; and program code, operative to rank a set of subgraphs in the unified contextual graph based on the quantified factors. 13. The apparatus as recited in claim 9 , further comprising: program code, operative to generate a dialog policy according to a new user intent and a historical utterance in the dialog rather than a latest utterance in the dialog. 14. A computer program product in a non-transitory computer readable medium for use in a data processing system, the computer program product holding computer program instructions executed by the data processing system
Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title
for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range · CPC title
Execution arrangements for user interfaces · CPC title
Help systems · CPC title
Updates performed during online database operations; commit processing · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.