DETAILED ACTION
This action is responsive to communications filed on June 28, 2024. This action is made Non-Final.
Claims 1-20 are pending in the case.
Claims 1, 11, and 16 are independent claims.
Claims 1-20 are rejected.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims of of U.S. Patent No. 12,045,561. Although the claims at issue are not identical, they are not patentably distinct from each other as indicated below.
18/759,373 claims
18070,202 claims
1. A method for disambiguating data, the method comprising:
receiving a set of pre-determined domain-relevant keywords and key phrases;
receiving one or more word frequency lists;
splitting compound words of the set of pre-determined domain-relevant keywords and
key phrases into multiple components to generate a set of seed words;
generating a set of sound-alike words for each seed word in the set of seed words based on the generated set of seed words and the one or more word frequency lists, each of the sound-alike words in the set of sound-alike words including words derived from consecutive seed words;
ranking the set of sound-alike words to provide an indication of their respective relevance to the set of pre-determined domain-relevant keywords and key phrases.
1. A method for disambiguating data, the method comprising:
receiving a set of pre-determined domain-relevant keywords and key phrases;
receiving one or more word frequency lists;
splitting compound words of the set of pre-determined domain-relevant keywords and key phrases into multiple components to generate a set of seed words;
generating a set of sound-alike words for each seed word in the set of seed words based on the generated set of seed words and the one or more word frequency lists, wherein the set of sound-alike words includes single words derived from two consecutive seed words, wherein the set of sound-alike words are generated using a spelling correction algorithm employing a string-edit distance to address potential spelling errors made by a speech recognition system, and wherein the edit distance used by the spelling correction algorithm is based on a syntactic class of a respective input phrase;
and ranking the set of sound-alike words to provide an indication of their respective relevance to the set of pre-determined domain-relevant keywords and key phrases.
2. The method of claim 1, wherein the compound words are split using a Hunspell
morphological analyzer.
2. The method of claim 1, wherein the compound words are split using a Hunspell morphological analyzer.
3. The method of claim 1, wherein the compound words are split using a double
metaphone phonetic algorithm.
10. wherein the compound words are split using a double metaphone phonetic algorithm.
4. The method of claim 1, wherein the set of sound-alike words are generated using a spelling correction algorithm to address potential spelling errors made by a speech recognition system.
1. wherein the set of sound-alike words are generated using a spelling correction algorithm employing a string-edit distance to address potential spelling errors made by a speech recognition system
5. The method of claim 1, wherein the set of sound-alike words are generated using a word formation module to address potential grammatical errors made by a speech recognition system.
5. The method of claim 1, wherein the set of sound-alike words are generated using a word formation module to address potential grammatical errors made by a speech recognition system.
6. The method of claim 1, wherein the set of sound-alike words are generated using a lookalike
sound-alike algorithm to generate single words from consecutive words.
6. The method of claim 1, wherein the set of sound-alike words are generated using a look-alike sound-alike algorithm to generate single words from consecutive words.
7. The method of claim 1, further comprising analyzing a transcript of a conversation using
the ranked set of sound-alike words to identify risks.
7. The method of claim 1, further comprising analyzing a transcript of a conversation using the ranked set of sound-alike words to identify risks.
8. The method of claim 7, wherein the ranking further comprises calculating a score that
quantifies a relevance of a respective sound-alike word.
23. … wherein the ranking further comprises calculating a score that quantifies a relevance of a respective sound-alike word.
9. The method of claim 8, wherein the respective sound-alike word is considered to be a
match with a term in the transcript when the score reaches a threshold value.
24. … wherein the respective sound-alike word is considered to be a match with a term in the transcript when the score reaches a threshold value.
10. The method of claim 7, wherein the ranking takes into account the grammatical
correctness of a respective sound-alike word.
25. … wherein the respective sound-alike word is considered to be a match with a term in the transcript when the score reaches a threshold value.
11. corresponds to claim 1.
12. corresponds to claim 4.
13. corresponds to claim 5.
14. corresponds to claim 6.
15. corresponds to claim 7.
16. corresponds to claim 1.
17. corresponds to claim 3.
18. corresponds to claim 4.
19. corresponds to claim 5.
20. corresponds to claim 6.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Step 1: Independent claims 1, 11, and 16 are directed towards a method, system, and non-transitory medium, respectively. Therefore, these claims, as well as their dependent claims, are directed towards one of the four statutory categories (process, machine (i.e. apparatus), manufacture, or composition of matter.
With respect to claim 1:
2A Prong 1:
Claim 1 recites the following judicial exceptions:
splitting compound words of the set of pre-determined domain-relevant keywords and key phrases into multiple components to generate a set of seed words (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may analyze and process compound words into components and determine seed words).
generating a set of sound-alike words for each seed word in the set of seed words based on the generated set of seed words and the one or more word frequency lists, each of the sound-alike words in the set of sound-alike words derived from consecutive seed words (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may determine sound-alike words from consecutive words).
ranking the set of sound-alike words to provide an indication of their respective relevance to the set of pre-determined domain-relevant keywords and key phrases (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may determine sound-alike words from consecutive words and rank the words relative to other words and/or phrases).
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
a method for disambiguating data, the method comprising: receiving a set of pre-determined domain-relevant keywords and key phrases; receiving one or more word frequency lists (mere instructions to apply the exception or implement the exception on a computer (e.g. computer may used to retrieve domain related words and phrases and word frequency information; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations).
With respect to claim 2:
2A Prong 1:
Claim 2 recites the following judicial exceptions:
wherein the compound words are split (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may analyze and process compound words into components and determine seed words).
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
using a Hunspell morphological analyzer (mere instructions to apply the exception or implement the exception on a computer (e.g. computer may use an algorithm to parse and process words; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations).
With respect to claim 3:
2A Prong 1:
Claim 3 recites the following judicial exceptions:
wherein the compound words are split (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may analyze and process compound words into components and determine seed words).
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
using a double metaphone phonetic algorithm (mere instructions to apply the exception or implement the exception on a computer (e.g. computer may use an algorithm to parse and process words; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations).
With respect to claim 4:
2A Prong 1:
Claim 4 recites the following judicial exceptions:
wherein the set of sound-alike words are generated (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may determine sound-alike words from consecutive words).
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
using a spelling correction algorithm to address potential spelling errors made by a speech recognition system (mere instructions to apply the exception or implement the exception on a computer (e.g. computer may use an algorithm to parse and process words; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations).
With respect to claim 5:
2A Prong 1:
Claim 5 recites the following judicial exceptions:
wherein the set of sound-alike words are generated (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may determine sound-alike words from consecutive words).
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
using a word formation module to address potential grammatical errors made by a speech recognition system (mere instructions to apply the exception or implement the exception on a computer (e.g. computer may use an algorithm to parse and process words; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations).
With respect to claim 6:
2A Prong 1:
Claim 6 recites the following judicial exceptions:
wherein the set of sound-alike words are generated (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may determine sound-alike words from consecutive words).
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
using a look-alike sound-alike algorithm to generate single words from consecutive words (mere instructions to apply the exception or implement the exception on a computer (e.g. computer may use an algorithm to parse and process words; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations).
With respect to claim 7:
2A Prong 1:
Claim 7 recites the following judicial exceptions:
analyzing a transcript of a conversation using the ranked set of sound-alike words to identify risks (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may analyze documents and identify risks by comparing or relating to sound-alike words.).
With respect to claim 8:
2A Prong 1:
Claim 8 recites the following judicial exceptions:
wherein the ranking further comprising calculating a score that quantifies a relevance of a respective sound-alike word (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may analyze documents and identify risks by comparing or relating to sound-alike words. Further, a person may determine the significance of sound-alike word and assign a value thereto).
With respect to claim 9:
2A Prong 1:
Claim 9 recites the following judicial exceptions:
wherein the respective sound-alike word is considered to be a match with a term in the transcript when the score reaches a threshold value (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may analyze documents and identify risks by comparing or relating to sound-alike words. Further, a person may determine the significance of sound-alike word and assign a value thereto).
With respect to claim 10:
2A Prong 1:
Claim 10 recites the following judicial exceptions:
wherein the respective sound-alike word is considered to be a match with a term in the transcript when the score reaches a threshold value (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may analyze documents and identify risks by comparing or relating to sound-alike words. Further, a person may determine the significance of sound-alike word and assign a value thereto while accounting for grammar).
Claim 11:
Claim 11 substantially corresponds to claim 1 and is rejected under the same rationale.
Claim 12:
Claim 12 substantially corresponds to claim 4 and is rejected under the same rationale.
Claim 13:
Claim 13 substantially corresponds to claim 5 and is rejected under the same rationale.
Claim 14:
Claim 14 substantially corresponds to claim 6 and is rejected under the same rationale.
Claim 15:
Claim 15 substantially corresponds to claim 7 and is rejected under the same rationale.
Claim 16:
Claim 16 substantially corresponds to claim 1 and is rejected under the same rationale.
Claim 17:
Claim 17 substantially corresponds to claim 3 and is rejected under the same rationale.
Claim 18:
Claim 18 substantially corresponds to claim 4 and is rejected under the same rationale.
Claim 19:
Claim 19 substantially corresponds to claim 5 and is rejected under the same rationale.
Claim 20:
Claim 20 substantially corresponds to claim 6 and is rejected under the same rationale.
2B continued: After considering all claim elements individually and as an ordered combination, it is determined that the claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 3, 4, 11, 12, and 16-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karagiannis et al., US Patent Application Publication no. US 2021/0141860 (“Karagiannis”), in view of Bikel et al., US Patent No. US 9,324,323 (“Bikel”), and further in view of Tran et al., US Patent Application Publication no. US 2022/0036883 (“Tran”).
Claim 1:
Karagiannis teaches or suggests a method for disambiguating data, the method comprising:
receiving a set of predetermined … keywords and key phrases (see para. 0029 - phonetic similarity model can use a phonetic algorithm for indexing words by their pronunciation or how they should sound when spoken.);
splitting compound words of the set of predetermined keywords and key phrases into multiple components to generate a set of seed words (see para. 0029 - phonetic similarity model can be a metaphone or double metaphone algorithm; Using one of these algorithms, the spellchecking service can take an incorrectly spelled word (i.e., an OOV word identified at operation 106) and create one or more codes (e.g., one code for a metaphone algorithm, two codes for a double metaphone algorithm);
generating a set of sound-alike words for the seed words in the set of seed words based on the generated set of seed words (see para. 0029 - directory for words with the same or similar metaphone. Words that have the same or similar metaphone can become possible alternative spellings.);
ranking the set of sound-alike words to provide an indication of their respective relevance to the set of pre-determined keywords and key phrases (see para. 0029 – identify the probability of each word in the pool with the highest probabilities being those with the same or most similar metaphones.).
Though Karagiannis teaches that the nature of the model may depend on the language(s) used (para. 0029), Karagiannis does not explicitly disclose that the keywords and key phrases are domain-relevant; receiving one or more word frequency lists; based on the one or more word frequency lists … derived from consecutive seed words.
Bikel teaches or suggests at the keywords and key phrases are domain-relevant; receiving one or more word frequency lists; based on the one or more word frequency lists (see col. 9, lines 60-61 - statistical representation of how often words co-occur in particular general or topic-specific contexts; col. 10, lines 7-12 - language model 314 can be customized based on a specific topic. language model may segment training data into two or three word parts. For any two words in the model, the model includes a probabilistic distribution as to the identity of the third word. For example, the language model presented with the words "Texas weather" can determine that the third word is likely "Austin" and not "Boston."; col. 15, lines 1-9 - unknown word may be one of several similar sounding words that are associated with different topics. the words in that topic language model ( e.g., "Boston") will have their scores adjusted relatively higher than other, similar sounding words that occur in relatively lower-weighted topics.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Karagiannis, to include the keywords and key phrases are domain-relevant; receiving one or more word frequency lists; based on the one or more word frequency lists for the purpose of efficiently determining word relevance based on occurrence, topic, and sound, improving recognition candidate generation, as taught by Bikel (col. 10 and 15).
Tran further teaches or suggests wherein the set of sound-alike words includes single words derived from two consecutive seed words (see para. 0035 - MLLPU 120 may be configured to provide a context-sensitive understanding of textual inputs; para. 0036 - MLLPU 120 may be configured to provide a context-sensitive understanding of textual inputs to disambiguate phrases that sound similar and may be misinterpreted by the NLPU 115. For example, the command "insert table" sounds very much like the word "insertable" which may be included in textual input spoken by the user. machine learning models used by the MLLPU 120 may be trained to identify ambiguous words or phrases in included in the text output by the NLPU 115 and may make a determination whether the user intended to issue the command "insert table" or merely to include the word "insertable" in the textual content provided to the application 105. user may use the word "insertable" in a sentence with certain words, such as "insertable into" which may indicate that user intended to use the word "insertable" rather than issue the command "insert table." Machine learning model(s) may take into account the type of application being used by the user when disambiguating between multiple possible utterances. For example, the model may determine that the command "insert table" was more probable where the user is working in a spreadsheet application and is less likely if the user is working in a messaging application.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Karagiannis, to include wherein the set of sound-alike words includes single words derived from two consecutive seed words for the purpose of efficiently disambiguating words and phrases based on sounding similar and using a pre-trained model, improving determining intended words and phrases, as taught by Tran (0036).
Claim(s) 11 and 16:
Claim(s) 11 and 16 correspond to Claim 1, and thus, Karagiannis, Bikel, and Tran teach or suggest the limitations of claim(s) 11 and 16 as well.
Claim 3:
Karagiannis further teaches or suggests wherein the compound words are split using a double metaphone phonetic algorithm (see para. 0029 - phonetic similarity model can be a metaphone or double metaphone algorithm; Using one of these algorithms, the spellchecking service can take an incorrectly spelled word (i.e., an OOV word identified at operation 106) and create one or more codes (e.g., one code for a metaphone algorithm, two codes for a double metaphone algorithm).
Claim(s) 17:
Claim(s) 17 correspond to Claim 3, and thus, Karagiannis, Bikel, and Tran teach or suggest the limitations of claim(s) 17 as well.
Claim 4:
Karagiannis further teaches or suggests wherein the set of sound-alike words are generated using a spelling correction algorithm to address potential spelling errors made by a speech recognition system (see para. 0029 - spellchecking service utilizes the error model. The error model can be a distribution which models the probability that a given error has occurred in an utterance such as the user input received at operation 104. In operation 114, the error model can contain a plurality of error models including phonetic similarity models, probabilistic edit distance models, and neural embeddings models. A phonetic similarity model can use a phonetic algorithm for indexing words by their pronunciation or how they should sound when spoken. directory for words with the same or similar metaphone. Words that have the same or similar metaphone can become possible alternative spellings.).
Claim(s) 12 and 18:
Claim(s) 12 and 18 correspond to Claim 4, and thus, Karagiannis, Bikel, and Tran teach or suggest the limitations of claim(s) 12 and 18 as well.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karagiannis, in view of Bikel, in view of Tran, and further in view Pirinen et al., "Creating and weighting hunspell dictionariesas finite-state automata." Investigationes Linguisticae 21 (2010): 1-16.
Claim 2:
Karagiannis does not explicitly disclose wherein the compound words are split using a Hunspell morphological analyzer.
Pirinen teaches or suggests wherein the compound words are split using a Hunspell morphological analyzer (see Fig. 1, 2; section 3.1 - root forms of words with information about morphological affix classes to combine with the roots list of strings containing the root forms of the words in the morphology.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Karagiannis, to include wherein the compound words are split using a Hunspell morphological analyzer for the purpose of efficiently parsing words into useful parts, improving word analysis correction processes, as taught by Pirinen (3.1).
Claim(s) 5, 13, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karagiannis, in view of Bikel, in view of Tran, and further in view of Huang et al., US Patent Application Publication no. US 2020/0135186 (“Huang”).
Claim 5:
As indicated above, Karagiannis teaches wherein the set of sound-alike words are generated using a word formation module.
Karagiannis does not does not explicitly disclose to address potential grammatical errors made by a speech recognition system.
Huang teaches or suggests to address potential grammatical errors made by a speech recognition system (see para. 0019 - sequence candidates comprising various combinations of words or phrases may be obtained; para. 0020 - apply a language model to the one or more sequence candidates. distinguish between words and phrases that sound similar and make sure W complies with grammar. For example, the phrases "recognize speech" and "wreck a nice beach" may be pronounced similarly but carry very different meanings. For another example, "get me a peach" and "give impeach" may be pronounced similarly but the latter is not grammatically sound.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Karagiannis, to include to address potential grammatical errors made by a speech recognition system for the purpose of efficiently using a language model to check word sequences, improving phrase grammar compliance, as taught by Huang (0020).
Claim(s) 13 and 19:
Claim(s) 13 and 19 correspond to Claim 5, and thus, Karagiannis, Bikel, Tran, and Huang teach or suggest the limitations of claim(s) 13 and 19 as well.
Claim(s) 6, 14, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karagiannis, in view of Bikel, Tran, and further in view of Lambert, Bruce L., et al. "Similarity as a risk factor in drug-name confusion errors: the look-alike (orthographic) and sound-alike (phonetic) model." Medical care (1999): 1214-1225 (“Lambert”).
Claim 6:
As indicated above, Karagiannis teaches or suggests wherein the set of sound-alike words are generated … to generate single words from consecutive words.
Karagiannis does not explicitly disclose using a look-alike sound-alike algorithm.
Lambert teaches or suggests using a look-alike sound-alike algorithm (see Abstract, p. 3 - test of drug name confusion potential can be formed using objective measures of orthographic similarity, orthographic distance, and phonetic distance; Introduction, p. 6 - methods for computing orthographic (i.e., spelling) similarity between words.20-22 I addition, phonetic (i.e., sound-based) methods continue to be developed as tools for searching databases of proper names.19, 23, 24 If these methods could be validated and systematically combined; Measures, p. 8 - generated using a look-alike sound-alike algorithm; Findings, p. 16 - demonstrated that automated measures of orthographic and phonetic similarity can be used to distinguish between known error pairs and controls drawn from the same population of names.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Karagiannis, to include using a look-alike sound-alike algorithm for the purpose of efficiently determining words and phrases that appear similar and/or sound similar, reducing identification confusion, as taught by Lambert (Introduction).
Claim(s) 14 and 20:
Claim(s) 14 and 20 correspond to Claim 6, and thus, Karagiannis, Bikel, Tran, and Lambert teach or suggest the limitations of claim(s) 14 and 20 as well.
Claim(s) 7 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karagiannis, in view of Bikel, Tran, and further in view of Jacobson et al., US Patent Application Publication no. US 2022/0051127 (“Jacobson”).
Claim 7:
As indicated above, Karagiannis teaches or suggests using the ranked set of sound-alike words.
Karagiannis does not explicitly disclose analyzing a transcript of a conversation using … sound-alike words to identify risks.
Jacobson teaches or suggests analyzing a transcript of a conversation using … sound-alike words to identify risks (see para. 0037 - textual analysis of the potentially unacceptable electronic communication. threat determination computing platform 110 may perform the textual analysis based on a language model. Generally, a language model may be a probability distribution over a collection of words. In some instances, the language model may depend on a set of words that appeared previously (e.g., unigram models, n-gram models, bidirectional models, and so forth). In some embodiments, a language model may differentiate between two collections of words that may sound similar but have different meanings.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Karagiannis, to include analyzing a transcript of a conversation using … sound-alike words to identify risks for the purpose of efficiently performing textual analysis in an electronic communication using probability distributions and sound similarities, improving threat identification, as taught by Jacobson (0037).
Claim(s) 15:
Claim(s) 15 correspond to Claim 7, and thus, Karagiannis, Bikel, Tran, and Jacobson teach or suggest the limitations of claim(s) 15 as well.
Claim(s) 8 and 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karagiannis, in view of Bikel, Tran, in view of Jacobson, and further in view of Elangovan et al., US Patent Application Publication no. US 2020/0349943 (“Elangovan”).
Claim 8:
Karagiannis does not explicitly disclose wherein the ranking further comprises calculating a score that quantifies a relevance of a respective sound-alike word.
Elangovan further teaches or suggests wherein the ranking further comprises calculating a score that quantifies a relevance of a respective sound-alike word (see para. 0013 - resolve the contact, a value associated with the contact name slot, which in the illustrative embodiment may correspond to the text "bob," may be used to query a contact list associated with the individual; para. 0014 - contact entry in the contact list may be compared with the text value, and a confidence score may be generated indicating a likelihood that the text value and the contact entry are equal. If the confidence score is greater than a confidence score threshold, then this may indicate that the entry likely includes the text value. For example, contact entries such as "Bob," "Bobby," and "Bob, Jr." may each result in a confidence score that exceeds the confidence score threshold when compared against the text value "bob.” phonetically similar entries may also be returned. For example, when performing automatic speech recognition, a double metaphone process may be employed to identify other words that substantially sound like the text value. As an illustrative example, the word "bob" may sound similar to the word "rob." In this scenario, the contact list may also be queried for the word "rob," and any contact entries having a confidence score exceeding the confidence score threshold may also be returned.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Karagiannis, to include wherein the ranking further comprises calculating a score that quantifies a relevance of a respective sound-alike word for the purpose of efficiently identifying potential matches based on words that substantially sound like an query text, improving query resolution, as taught by Elangovan (0013 and 0014).
Claim 9:
As indicated above, Jacobson teaches or suggests term in the transcript.
Elangovan further teaches or suggests wherein the respective sound-alike word is considered to be a match with a term in the transcript when the score reaches a threshold value (see para. 0013 - resolve the contact, a value associated with the contact name slot, which in the illustrative embodiment may correspond to the text "bob," may be used to query a contact list associated with the individual; para. 0014 - contact entry in the contact list may be compared with the text value, and a confidence score may be generated indicating a likelihood that the text value and the contact entry are equal. If the confidence score is greater than a confidence score threshold, then this may indicate that the entry likely includes the text value. For example, contact entries such as "Bob," "Bobby," and "Bob, Jr." may each result in a confidence score that exceeds the confidence score threshold when compared against the text value "bob.” phonetically similar entries may also be returned. For example, when performing automatic speech recognition, a double metaphone process may be employed to identify other words that substantially sound like the text value. As an illustrative example, the word "bob" may sound similar to the word "rob." In this scenario, the contact list may also be queried for the word "rob," and any contact entries having a confidence score exceeding the confidence score threshold may also be returned.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Karagiannis, to include wherein the respective sound-alike word is considered to be a match with a term in the transcript when the score reaches a threshold value for the purpose of efficiently identifying potential matches based on words that substantially sound like an query text, improving query resolution, as taught by Elangovan (0013 and 0014).
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Karagiannis, in view of Bikel, Tran, in view of Jacobson, and further in view of Gupta et al., US Patent Application Publication no. US 2007/0179777 (“Gupta”).
Claim 10:
As indicated above, Karagiannis teaches or suggests the ranking.
Gupta further teaches or suggests takes into account the grammatical correctness of a respective sound-alike word (see para. 0031 - grammar generator 112 categorizes 308 the sentence structures and constructs grammar, e.g., Finite State Grammar Transducer (FSGT) models, using these structures para. 074 - statistical n-gram model picks candidate phrases and FSGT discards the nonsensical and non grammatical phrases leading to a correct match; para. 0075 - method for speech recognition. model is used 406 in the second pass to generate and rank possible matching word phrases. ranked extracted word phrases are sent 408 through the tagging POS portion of the FSGT.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Karagiannis, to include takes into account the grammatical correctness of a respective sound-alike word for the purpose of efficiently recognizing speech by discarding nonsensical and non grammatical phrases, improving speech recognition and intent determination, as taught by Gupta (0075).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Andrew T McIntosh whose telephone number is (571)270-7790. The examiner can normally be reached M-Th 8:00am-5:30pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Tamara Kyle can be reached at 571-272-4241. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ANDREW T MCINTOSH/Primary Examiner, Art Unit 2144
Prosecution Insights