# US 12,182,137 B2 · Keyword and business tag extraction > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,182,137 B2 - Document ID: US12182137B2 - Status: Granted - Kind: B2 - Application number: 17/648,793 - Filed: 2022-01-24 - Published: 2022-05-12 - Granted: 2024-12-31 - Earliest claimed: 2019-04-14 - Assignees: ZoomInfo Apollo LLC - Applicants: ZoomInfo Apollo LLC - Inventors: Hua Gao; Amit Rai - Web page: https://patentgrep.com/patent/US12182137B2 ## CPC - G06F 16/24578: {using ranking} - G06F 16/2468: {Fuzzy queries} - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 40/295: Named entity recognition - G06F 40/30: Semantic analysis - G06N 5/04: Inference or reasoning models - G06Q 10/06: Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling - G06N 5/048: Fuzzy inferencing - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract An automated predictive analytics system disclosed herein provides a novel technique for industry classification. In one implementation, the analytic system provides a method of matching company names, the method including generating a provider-side company dataset, for each record in a client's company records, identify a list of match candidates from the provider side company dataset that has overlapping company signature fragments, for each client-side company, compute match scores against the list of provider-side match candidates on each signature fragment and form an overall match score, for each client-side company, use the match scores to rank candidates and keep a predetermined number of top predetermined matches, and display the predetermined number of top predetermined matches using a user interface. ## Claims ### Claim 1 A method of matching company names, comprising: receiving a provider side company signature fragment for a provider company, the provider side company signature fragment based on a company name, address, website, or phone number; receiving a client side company dataset having a client side company record related to a client side company; identifying a provider side inexact match candidate based on a comparison of the provider side company signature fragment to the client side company record, the provider side inexact match candidate including an overlap of the provider side company signature fragment with the client side company dataset; and outputting the provider side inexact match candidate. ### Claim 2 (depends on 1) The method of claim 1, further comprising: computing a match score for the provider side inexact match candidate; and outputting the provider side inexact match candidate and the match score. ### Claim 3 (depends on 2) The method of claim 2, further comprising: ranking the provider side company based on the match score, and identifying the ranking of the provider side match candidate as a top match for the client side company. ### Claim 4 (depends on 3) The method of claim 3, further comprising: outputting one or more of the provider side inexact match candidate, the match score, the ranking of the provider side company, and the identification of the ranking as the top match for the client side company. ### Claim 5 (depends on 1) The method of claim 1, wherein the provider side company signature fragment for the provider company is included in a provider side company dataset, and further comprising generating the provider side company dataset by: generating a provider company signature; generating the provider company signature fragment based on the provider company signature; generating a provider company name token based on the provider company signature fragment; generating the provider company signature based on the provider company name token; and generating the provider side company dataset based on the provider company signature. ### Claim 6 (depends on 1) The method of claim 1, further comprising: comparing multiple subsequences of the provider side company signature fragment to respective multiple subsequences of the client side company dataset; and determining the provider side company signature fragment based on the comparison of the multiple subsequences of the provider side company signature fragment to the respective multiple subsequences of the client side company dataset. ### Claim 7 (depends on 6) The method of claim 6, further comprising comparing at least one fuzzy subsequence of the provider side company signature fragment to a respective fuzzy subsequence of the client side company dataset. ### Claim 8 (depends on 6) The method of claim 6, further comprising comparing at least one fuzzy subsequence of the provider side company signature fragment to a respective non-fuzzy subsequence of the client side company dataset. ### Claim 9 (depends on 1) The method of claim 1, further comprising comparing the provider side company signature fragment to the client side company record based on a Levenshtein distance. ### Claim 10 (depends on 1) The method of claim 1, further comprising comparing the provider side company signature fragment to the client side company record based on a cosine similarity. ### Claim 11 (depends on 1) The method of claim 1, further comprising comparing the provider side company signature fragment to the client side company record based on a Euclidean distance. ### Claim 12 (depends on 1) The method of claim 1, further comprising: receiving the client side company dataset having multiple client side company records related to the client side company; identifying multiple provider side inexact match candidates based on a comparison of the provider side company signature fragment to the multiple client side company records; and computing a match score for the provider side match candidate based on each of the multiple provider side inexact match candidates. ### Claim 13 (depends on 12) The method of claim 12, further comprising: weighting each of the multiple provider side inexact match candidates; and computing the match score for the provider side match candidate based on the weighted multiple provider side inexact match candidates. ### Claim 14 (depends on 1) The method of claim 1, further comprising outputting the provider side inexact match candidate to a remote computing device, network, or server. ### Claim 15 (depends on 1) The method of claim 1, further comprising outputting the provider side inexact match candidate to a display of a user interface. ### Claim 16 (depends on 1) The method of claim 1, wherein the comparison of the provider side company signature fragment to the client side company record comprises determining importance and similarity of words in the provider side company signature fragment and the client side company record. ### Claim 17 (depends on 1) The method of claim 1, wherein the comparison of the provider side company signature fragment to the client side company record comprises determining similarity of phonetic representations of words in the provider side company signature fragment and the client side company record.