# US 10,771,427 B2 · Systems and methods for determining character entry dynamics for text segmentation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,771,427 B2 - Document ID: US10771427B2 - Status: Granted - Kind: B2 - Application number: 15/046,814 - Filed: 2016-02-18 - Published: 2017-08-24 - Granted: 2020-09-08 - Earliest claimed: 2016-02-18 - Assignees: VerSign, Inc. - Applicants: Verisign, Inc. - Inventors: Andrew West - Web page: https://patentgrep.com/patent/US10771427B2 ## CPC - H04L 61/4511: using domain name system [DNS] - G06F 40/242: Dictionaries - G06F 40/247: Thesauruses; Synonyms - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G10L 15/05: Word boundary detection - H04L 61/302: {Administrative registration, e.g. for domain names at internet corporation for assigned names and numbers [ICANN]} - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract A method can include receiving a string of characters. The method can include determining one or more possible word boundaries for words in the string of characters based at least partially on a segmentation process. The method can also include determining, for each character in the string of characters, an amount of time between entry of each character on an input device. The method can include determining, based at least partially on the amount of time and the one or more possible word boundaries, one or more actual word boundaries for the words in the string of characters. The method can also include outputting one or more determined words in the string of characters based at least partially on the one or more actual word boundaries. ## Claims ### Claim 1 A method, implemented by a computer, for determining user-specific word boundaries in a domain name, the method comprising: receiving a string of non-space delimited alphanumeric characters entered by a user, the string of non-space delimited alphanumeric characters comprising a plurality of words, and representing a potential domain name to be registered; obtaining a time value associated with a time at which each non-space delimited alphanumeric character is entered by the user; determining one or more possible word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters based at least partially on a segmentation process; determining, by the computer and for each character in the string of non-space delimited alphanumeric characters, an amount of time taken between each time value associated with the time at which each non-space delimited alphanumeric character is entered by the user, wherein the amount of time is filtered; determining, by the computer and based on each amount of time between each time value and the one or more possible word boundaries, one or more actual time-specified word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters; segmenting, by the computer, the string of non-space delimited alphanumeric characters into a time-specified set of words based on the one or more actual time-specified word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters; determining, by the computer, one or more alternate words for a word from the time-specified set of words, wherein the one or more alternate words have a similar meaning to the word; creating, by the computer, one or more domain names using the one or more alternate words and the time-specified set of words; and displaying, to the user, a registration availability of the one or more domain names. ### Claim 2 (depends on 1) The method of claim 1, wherein determining one or more actual time-specified word boundaries comprises: determining a pair of characters that has a first amount of time between entry of the pair of characters that exceeds a second amount of time; comparing the pair of characters to the one or more possible word boundaries; and determining, based on the comparison, that the pair of characters is an actual time-specified word boundary if any of the one or more possible word boundaries match the pair of characters. ### Claim 3 (depends on 2) The method of claim 2, wherein the second amount of time is an amount of time between entry of other pairs of characters. ### Claim 4 (depends on 1) The method of claim 1, the method further comprising: receiving a selection of at least one of the one or more domain names; and registering the at least one of the one or more domain names. ### Claim 5 (depends on 1) The method of claim 1, wherein the segmentation process comprises one or more of a dictionary segmentation, a character co-occurrence segmentation, a linguistic segmentation, or a word fitness segmentation. ### Claim 6 (depends on 1) The method of claim 1, wherein the amount of time is filtered by excluding a delay between at least two of the non-space delimited alphanumeric characters that is above a predetermined threshold. ### Claim 7 A method, implemented by a computer, for determining user-specific word boundaries in a search string, the method comprising: receiving a string of non-space delimited alphanumeric characters entered by a user, the string of non-space delimited alphanumeric characters comprising a plurality of words, and representing a search request; obtaining a time value associated with a time at which each non-space delimited alphanumeric character is entered by the user; determining one or more possible word boundaries between the plurality words in the string of non-space delimited alphanumeric characters based at least partially on a segmentation process; determining, by the computer and for each character in the string of non-space delimited alphanumeric characters, an amount of time taken between each time value associated with the time at which each non-space delimited alphanumeric character is entered by the user, wherein the amount of time is filtered; determining, by the computer and based on each amount of time between each time value and the one or more possible word boundaries, one or more actual time-specified word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters; segmenting, by the computer, the string of non-space delimited alphanumeric characters into a time-specified set of words based on the one or more actual time-specified word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters; outputting, to a search engine, the time-specified set of words; and receiving results of a search for the time-specified set of words from the search engine. ### Claim 8 (depends on 7) The method of claim 7, wherein determining one or more actual time-specified word boundaries comprises: determining a pair of characters that has a first amount of time between entry of the pair of characters that exceeds a second amount of time; comparing the pair of characters to the one or more possible word boundaries; and determining, based on the comparison, that the pair of characters is an actual time-specified word boundary if any of the one or more possible word boundaries matches the pair of characters. ### Claim 9 (depends on 8) The method of claim 8, wherein the second amount of time is an amount of time between entry of other pairs of characters. ### Claim 10 (depends on 7) The method of claim 7, wherein the segmentation process comprises one or more of a dictionary segmentation, a character co-occurrence segmentation, a linguistic segmentation, or a word fitness segmentation. ### Claim 11 A method, implemented by a computer, for autocorrecting a string of non-space delimited alphanumeric characters based on character entry timing by a user, the method comprising: receiving the string of non-space delimited alphanumeric characters entered by the user, the string of non-space delimited alphanumeric characters comprising a plurality of words, and representing entry of the string of non-space delimited alphanumeric characters on an input device; obtaining a time value associated with a time at which each non-space delimited alphanumeric character is entered by the user; determining one or more possible word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters based at least partially on a segmentation process; determining, by the computer and for each character in the string of non-space delimited alphanumeric characters, an amount of time taken between each time value associated with the time at which each non-space delimited alphanumeric character is entered by the user, wherein the amount of time is filtered; determining, by the computer and based on each amount of time between each time value and the one or more possible word boundaries, one or more actual time-specified word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters; segmenting, by the computer, the string of non-space delimited alphanumeric characters into a time-specified set of words based on the one or more actual time-specified word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters; and outputting, to the input device, the time-specified set of words, whereby the input device automatically completes or automatically corrects a display of the string of non-space delimited alphanumeric characters entered by the user based on the time-specified set of words. ### Claim 12 (depends on 11) The method of claim 11, wherein determining one or more actual time-specified word boundaries comprises: determining a pair of characters that has a first amount of time between entry of the pair of characters that exceeds a second amount of time; comparing the pair of characters to the one or more possible word boundaries; and determining, based on the comparison, that the pair of characters is an actual time-specified word boundary if any of the one or more possible word boundaries matches the pair of characters. ### Claim 13 (depends on 12) The method of claim 12, wherein the second amount of time is an amount of time between entry of other pairs of characters. ### Claim 14 (depends on 11) The method of claim 11, wherein the segmentation process comprises one or more of a dictionary segmentation, a character co-occurrence segmentation, a linguistic segmentation, or a word fitness segmentation. ### Claim 15 A non-transitory computer-readable medium comprising instructions which, when executed by at least one processor, cause the at least one processor to perform a method comprising: receiving a string of non-space delimited alphanumeric characters entered by a user, the string of non-space delimited alphanumeric characters comprising a plurality of words, and representing a potential domain name to be registered; obtaining a time value associated with a time at which each non-space delimited alphanumeric character is entered by the user; determining one or more possible word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters based at least partially on a segmentation process; determining, by the processor and for each character in the string of non-space delimited alphanumeric characters, an amount of time taken between each time value associated with the time at which each non-space delimited alphanumeric character is entered by the user, wherein the amount of time is filtered; determining, by the processor and based on each amount of time between each time value and the one or more possible word boundaries, one or more actual time-specified word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters; segmenting, by the processor, the string of non-space delimited alphanumeric characters into a time-specified set of words based on the one or more actual time-specified word boundaries between the plurality of words in the string of non-space delimited alphanumeric characters; determining, by the processor, one or more alternate words for a word from the time-specified set of words, wherein the one or more alternate words have a similar meaning to the word; creating, by the processor, one or more domain names using the one or more alternate words and the time-specified set of words; and displaying, to the user, a registration availability of the one or more domain names. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein determining one or more actual time-specified word boundaries comprises: determining a pair of characters that has a first amount of time between entry of the pair of characters that exceeds a second amount; comparing the pair of characters to the one or more possible word boundaries; and determining, based on the comparison, that the pair of characters is an actual time-specified word boundary if any of the one or more possible word boundaries match the pair of characters. ### Claim 17 (depends on 16) The non-transitory computer-readable medium of claim 16, wherein the second amount of time is an amount of time between entry of other pairs of characters. ### Claim 18 (depends on 15) The non-transitory computer-readable medium of claim 15, the method further comprising: receiving a selection of at least one of the one or more domain names; and registering the at least one of the one or more domain names. ### Claim 19 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the segmentation process comprises one or more of a dictionary segmentation, a character co-occurrence segmentation, a linguistic segmentation, or a word fitness segmentation.