Methods and servers for triggering query answers

{
  "publication_number": "US2026105092A1",
  "country": "US",
  "kind": "A1",
  "title": "Methods and servers for triggering query answers",
  "abstract": "A method of triggering a query answer, executable by a server communicatively coupled with a user device, the method comprising: acquiring a user query in natural language; ranking documents based on respective document-query relevance scores, the document-query relevance scores being indicative of document relevance to the query; determining, for top N documents from the ranking, respective document-answer relevance scores using a first machine learning model, the respective document-answer relevance scores being indicative of how likely content from the documents satisfies the query; re-ranking the top N documents based on document-answer relevance scores; generating, using a second machine learning model, a query answer in natural language based on content snippets from top M documents from the re-ranking; and triggering display of the query answer on the user device.",
  "claims": [
    "1. A method of triggering a query answer, the method executable by a server communicatively coupled with a user device, the method comprising: acquiring a user query in a natural language; ranking a plurality of documents into a ranked list of documents based on respective document-query relevance scores, a given document-query relevance score being indicative of how relevant a given document from the plurality of documents is to the user query; determining, for a top N documents in the ranked list of documents using a first machine learning model, respective document-answer relevance scores, a given document-answer relevance score being indicative of how likely content from a given document amongst the top N documents is to satisfy the user query as an answer; ranking the top N documents into an other ranked list based on the respective document-answer relevance scores; generating, using a second machine learning model based on content snippets from a top M documents in the other ranked list, a query answer in the natural language; and triggering display of the query answer on the user device. 2. The method of claim 1, wherein the method further comprises determining, using a search engine, a plurality of documents relevant to the user query. 3. The method of claim 2, wherein the determining the plurality of documents relevant to the user query using the search engine further includes accessing a database in real-time. 4. The method of claim 1, wherein the method further comprises generating a rephrased query using the user query, using the rephrased query instead of the user query for ranking the plurality of documents. 5. The method of claim 1, wherein the method further comprises acquiring a query context associated with the user query, the query context comprising one or more dialogue strings in the natural language. 6. The method of claim 1, wherein the generating the query answer is further based on the query context. 7. The method of claim 1, wherein N is an integer. 8. The method of claim 1, wherein M is an integer. 9. The method of claim 1, wherein content from the given document amongst the top N documents is a text content. 10. The method of claim 1, wherein content snippets from the top M documents in the other ranked list are text content snippets. 11. A method of training a first machine learning model, the method comprising: training a third machine learning model based on a training set including: a training query, a training document, a first training answer and a second training answer, the first training answer and the second training answer having been generated based on content in the training document, the third machine learning model being trained in a pairwise manner to generate a logit value indicative of which one amongst the first training answer and the second training answer is a better training answer to the training query; generating, by the trained third machine learning model, an other logit value in a pointwise manner based on an other training query, an other training document, and an other answer having been generated based on content in the other training document; training the first machine learning model using an other training set including: the other training query, the other training document, and the other logit value, the first machine learning model being trained to predict the other logit value using the other training query and the other training document and indicative of how likely content from the other training document is to satisfy the training query if an answer is to be generated based on the content; using the first machine learning model for generating an in-use logit value based on an in-use query and an in-use document; if the in-use logit value is indicative of that in-use content of the in-use document is to satisfy the in-use query if an in-use answer is generated based on the in-use content, generating the in-use answer to the in-use query using the in-use content from the in-use document; and triggering display of the in-use answer on a user device. 12. The method of claim 11, wherein the generation of the first training answer and the second training answer further includes sampling of a baseline answer. 13. The method of claim 11, wherein training the first machine learning model using the other training set further includes iteratively adjusting at least one parameter of the first machine learning model to predict the other logit value. 14. The method of claim 11, wherein training the first machine learning model further includes using at least one reinforcement learning model. 15. A server for triggering a query answer, the server communicatively coupled with a user device, the server being configured to: acquire a user query in a natural language; rank a plurality of documents into a ranked list of documents based on respective document-query relevance scores, a given document-query relevance score being indicative of how relevant a given document from the plurality of documents is to the user query; determine, for a top N documents in the ranked list of documents using a first machine learning model, respective document-answer relevance scores, a given document-answer relevance score being indicative of how likely content from a given document amongst the top N documents is to satisfy the user query as an answer; rank the top N documents into an other ranked list based on the respective document-answer relevance scores; generate, using a second machine learning model based on content snippets from a top M documents in the other ranked list, a query answer in the natural language; and trigger display of the query answer on the user device. 16. The server of claim 15, wherein the server is further configured to determine, using a search engine, a plurality of documents relevant to the user query. 17. The server of claim 16, wherein the determining the plurality of documents relevant to the user query using the search engine further includes accessing a database in real-time. 18. The server of claim 15, wherein the server is further configured to generate a rephrased query using the user query, using the rephrased query instead of the user query for ranking the plurality of documents. 19. The server of claim 15, wherein the server is further configured to acquire a query context associated with the user query, the query context comprising one or more dialogue strings in the natural language. 20. The server of claim 15, wherein the generating the query answer is further based on the query context."
  ],
  "cpc": [
    "G06F 16/3344",
    "G06F 16/3338",
    "G06F 16/335",
    "G06F 16/35",
    "G06N 20/00"
  ],
  "filing_date": "2025-10-15",
  "publication_date": "2026-04-16",
  "priority_date": "2024-10-15",
  "application_number": "US-202519359622-A"
}