# US 11,030,199 B2 · Systems and methods for contextual retrieval and contextual display of records > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,030,199 B2 - Document ID: US11030199B2 - Status: Granted - Kind: B2 - Application number: 16/205,448 - Filed: 2018-11-30 - Published: 2019-10-31 - Granted: 2021-06-08 - Earliest claimed: 2016-08-09 - Assignees: Ripcord Inc. - Applicants: Ripcord Inc. - Inventors: Michael Moskwinski; Alex Fielding; Kevin Christopher Hall; Kimberly Lembo - Web page: https://patentgrep.com/patent/US11030199B2 ## CPC - G06F 16/24575: {using context} - G06F 16/00: Information retrieval; Database structures therefor; File system structures therefor - G06F 16/243: {Natural language query formulation} - G06F 16/248: Presentation of query results - G06F 16/3329: Natural language query formulation - G06F 16/90335: {Query processing} - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Provided are systems and methods for the contextual retrieval and contextual display of records. A search query and/or search results may be contextually enhanced based on (i) natural language processing (NLP) models, (ii) user behavior, and/or (iii) relationships between various entities involved in a search, such as between users, records, and/or fields of expertise. Contextually enhanced search results may be delivered and displayed to a user on a user interface in a contextually relevant order. ## Claims ### Claim 1 A computer-implemented method for contextual enhancement of search queries, comprising: (a) receiving from a user, via a user interface, a search query; (b) determining, with aid of one or more computer processors, a first natural language processing (NLP) model of a plurality of NLP models corresponding to the search query, wherein the first NLP model corresponds to a first set of one or more keywords; (c) determining, with aid of one or more computer processors, a second NLP model, of the plurality of NLP models, wherein the second NLP model corresponds to a second set of one or more keywords, wherein the first NLP model and the second NLP model have a proximity relationship with a weight value at or above a predetermined threshold; (d) enhancing the search query with keywords of the second set of one or more keywords not originally present in the search query, to generate an enhanced search query; and (e) executing the enhanced search query. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the plurality of NLP models are stored in one or more databases. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein the plurality of NLP models are stored in a graph database. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein the graph database further stores proximity relationships between the plurality of NLP models. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, further comprising determining, with aid of the one or more computer processors, an additional one or more NLP models of the plurality of NLP models, wherein each of the additional one or more NLP models and the first NLP model has a respective proximity relationship with a respective weight value at or above the predetermined threshold, wherein each of the additional one or more NLP models corresponds to a respective set of one or more keywords. ### Claim 6 (depends on 5) The computer-implemented method of claim 5, further comprising enhancing the search query with the respective set of one or more keywords to generate the enhanced search query. ### Claim 7 (depends on 5) The computer-implemented method of claim 5, wherein the first NLP model is determined as corresponding to the search query by tokenizing the search query into one or more tokens to generate a tokenized query, and processing the tokenized query to the first set of one or more keywords. ### Claim 8 (depends on 5) The computer-implemented method of claim 5, wherein the search query is processed to each of the plurality of NLP models to determine the first NLP model as corresponding to the search query. ### Claim 9 A computer system for contextual enhancement of search queries, comprising: one or more processors; a memory, communicatively coupled to the one or more processors, including instructions executable by the one or more processors, individually or collectively, to: (a) receive from a user, via a user interface, a search query; (b) determine, with aid of one or more computer processors, a first natural language processing (NLP) model of a plurality of NLP models corresponding to the search query, wherein the first NLP model corresponds to a first set of one or more keywords; (c) determine, with aid of one or more computer processors, a second NLP model, of the plurality of NLP models, wherein the second NLP model corresponds to a second set of one or more keywords, wherein the first NLP model and the second NLP model have a proximity relationship with a weight value at or above a predetermined threshold; (d) enhance the search query with keywords of the second set of one or more keyword not originally present in the search query, to generate an enhanced search query; and (e) execute the enhanced search query. ### Claim 10 (depends on 9) The computer system of claim 9, further comprising one or more databases, wherein the plurality of NLP models are stored in the one or more databases. ### Claim 11 (depends on 9) The computer system of claim 9, further comprising a graph database, wherein the plurality of NLP models are stored in the graph database. ### Claim 12 (depends on 11) The computer system of claim 11, wherein the graph database further stores proximity relationships between the plurality of NLP models. ### Claim 13 (depends on 9) The computer system of claim 9, wherein the one or more processors are further configured to, individually or collectively, determine an additional one or more NLP models of the plurality of NLP models, wherein each of the additional one or more NLP models and the first NLP model has a respective proximity relationship with a respective weight value at or above the predetermined threshold, wherein each of the additional one or more NLP models corresponds to a respective set of one or more keywords. ### Claim 14 (depends on 13) The computer system of claim 13, wherein the one or more processors are further configured to, individually or collectively, enhance the search query with the respective set of one or more keywords to generate the enhanced search query. ### Claim 15 (depends on 13) The computer system of claim 13, wherein the one or more processors are further configured to, individually or collectively, determine the first NLP model as corresponding to the search query by tokenizing the search query into one or more tokens to generate a tokenized query, and processing the tokenized query to the first set of one or more keywords. ### Claim 16 (depends on 13) The computer system of claim 13, wherein the one or more processors are further configured to, individually or collectively, process the search query to each of the plurality of NLP models to determine the first NLP model as corresponding to the search query.