DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/22/2025 has been entered.
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 .
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 1-5, 7-13, and 15-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea (data analysis and manipulation) without significantly more.
Independent claims 1, 10, and 17 recites, “receiving call data of a call in an interaction recording system of a call center recorder, wherein the interaction recording system is located behind a firewall of an internal network sub-environment”, “storing the call data in an electronic database, wherein the call data includes interaction metadata”, “generating a speech-to-text transcript by analyzing call audio in the call data, wherein the speech-to-text transcript corresponds to words spoken by one or more callers during the call”, and “generating an anonymized transcript corresponding to the speech-to-text transcript by identifying, removing, replacing, or obscuring one or more alpha- numeric personally identifiable information according to a selected mode of anonymization, redaction, or de-identification and using a trained machine learning model, classifying the one or more alpha-numeric personally identifiable information into a type of personally identifiable information, and selecting a mode of anonymization, redaction, or de-identification based on the type of personally identifiable information, wherein the selected mode of anonymization, redaction, or de-identification includes at least one of (1) replacing the alpha-numeric personally identifiable information with a predetermined character,(2) replacing the alpha-numeric personally identifiable information with a random word, (3) replacing the alpha-numeric personally identifiable information with a similar word, or (4) replacing the alpha-numeric personally identifiable information with a descriptor”.
First, the limitation of receiving call data, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting a “processor”, “memory”, and a “non-transitory computer readable medium”, nothing in the claim precludes the step from practically being performed in the mind. For example, “receiving” in the context of this claim encompasses receiving recorded audio, which a human can do by in the mind. Next, the limitation of storing call data, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but of the elements listed above, “storing” in the context of this claim encompasses holding data, which a human can do in the mind or with a pen and paper. Next, the limitation of transcribing text, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but of the elements listed above, “generating” in the context of this claim encompassing converting speech into text which a human can do with a pen and paper. Lastly, the limitation of generating anonymized transcripts, as drafted, is a process, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but of the elements listed above, “generating” in the context of this claim encompasses editing written text, which a human can do with a pen and paper.
The judicial exception is not integrated into a practical application. In particular, the claim only recites the additional elements, using a “processor”, “memory”, and a “non-transitory computer readable medium” to perform the claimed limitations. These elements in these steps are recited at a high-level of generality such that is amounts no more than mere instructions to apply the exception using generic computer component. The recited environment and machine learning model do not clearly integrate the idea into a practical application without more detail on the technological improvement. Accordingly, the additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements of using a “processor”, “memory”, and a “non-transitory computer readable medium” to perform the data anonymization limitations amounts to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. The claim is not patent eligible.
Dependent claims 2-5, 7-9, 11-13, 15-16, and 18-19 are also rejected for the same reasons provided in independent claim 1, 10, and 17 above. The dependent claims, including the further recited limitation, does not integrate the abstract idea into a practical application and the additional elements, taken individually and in combination do not contribute to an inventive concept. In other words, the dependent claims are directed to an abstract idea without significantly more.
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 1-16 and 18-20 of U.S. Patent No. US 11250876 B1. Although the claims at issue are not identical, they are not patentably distinct from each other because the claims of the issued patent are narrower in scope than that of the instant application. Please see the table below for the claim mapping.
Instant Application No: 17/563,191
Issued Patent No: US 11250876 B1
A computer implemented method for anonymizing data, comprising: receiving call data of a call in an interaction recording system of a call center recorder, wherein the interaction recording system is located behind a firewall of an internal network sub- environment; and within the internal network sub-environment: (i) storing the call data in an electronic database, wherein the call data includes interaction metadata, (ii) generating a speech-to-text transcript by analyzing call audio in the call data, wherein the speech-to-text transcript corresponds to words spoken by one or more callers during the call, and (iii) generating an anonymized transcript corresponding to the speech-to-text transcript by identifying, removing, replacing, or obscuring one or more alpha-numeric personally identifiable information.
(Currently Amended) A computer implemented method for confidential sentiment analysis, comprising: receiving call data of a call in an interaction recording system of a call center recorder, wherein the interaction recording system is located behind a firewall of an internal network sub-environment, within the internal network sub-environment: _I) storing the call data in an electronic database, wherein the call data includes interaction metadata, (j} generating a speech-to-text transcript by analyzing call audio in the call data, wherein the speech-to-text transcript corresponds to words spoken by one or more callers during the call, (iii) generating an anonymized transcript corresponding to the speech-to-text transcript by identifying, removing, replacing, or obscuring one or more alpha- numeric personally identifiable information (iv) generating a sentiment score by analyzing the anonymized transcript using a sentiment analysis service.
The method of claim 1, wherein the interaction recording system is located behind the firewall of the internal network sub-environment, the method further comprising: collecting a consent of the caller to store the call data.
2. (Currently Amended) The method of claim 1, wherein the interaction recording system is located behind the firewall of the internal network sub-environment includes collecting [[the]] a consent of the caller to store the call data.
The method of claim 1, wherein storing the call data includes storing caller identification information.
3. (Currently Amended) The method of claim 1, wherein storing the call data in the electronic database, wherein storinq the call data includes interaction metadata includes storing caller identification information.
The method of claim 1, wherein generating the anonymized transcript by identifying, removing, replacing, or obscuring one or more alpha-numeric personally identifiable information is based on matching regular expression patterns against the speech-to-text transcript.
4. (Currently Amended) The method of claim 1, wherein generating the anonymized transcript by identifying, removing, replacing, or obscuring one or more alpha- numeric personally identifiable information word- is based on matching regular expression patterns against the speech-to-text transcript.
The method of claim 1, wherein generating the anonymized transcript by identifying, removing, replacing, or obscuring one or more alpha-numeric personally identifiable information is based on matching keywords in the speech-to-text transcript to one or more corpora of words.
5. (Currently Amended) The method of claim 1, wherein generating the anonymized transcript by identifying, removing, replacing, or obscuring one or more alpha- numeric personally identifiable information words is based on matching keywords in the speech-to-text transcript to one or more corpora of words.
The method of claim 1, wherein generating the anonymized transcript by identifying, removing, replacing, or obscuring one or more alpha-numeric personally identifiable information is based on analyzing the speech-to-text transcript using a trained machine learning model.
6. (Currently Amended) The method of claim 1, wherein generating the anonymized transcript by identifying, removing, replacing, or obscuring one or more alpha- numeric personally identifiable information words is based on analyzing the speech-to-text transcript using a trained machine learning model.
The method of claim 1, further comprising: generating a sentiment score by analyzing the anonymized transcript using a sentiment analysis service.
7. (Original) The method of claim 1, wherein generating the sentiment score by analyzing the anonymized transcript using the sentiment analysis service…
The method of claim 7, wherein generating the sentiment score by analyzing the anonymized transcript using the sentiment analysis service includes generating a time series wherein each time step corresponds to a time in the anonymized transcript, and each time step is associated with a sentiment score, wherein the sentiment score indicates the sentiment at the respective time step.
7. (Original) The method of claim 1, wherein generating the sentiment score by analyzing the anonymized transcript using the sentiment analysis service includes generating a time series wherein each time step corresponds to a time in the anonymized transcript, and each time step is associated with a sentiment score, wherein the sentiment score indicates the sentiment at the respective time step.
The method of claim 7, wherein generating the sentiment score by analyzing the anonymized transcript using the sentiment analysis service includes generating an intra-call sentiment score.
8. (Original) The method of claim 1, wherein generating the sentiment score by analyzing the anonymized transcript using the sentiment analysis service includes generating an intra-call sentiment score.
A computing system for anonymizing data, comprising one or more processors, and a memory including computer executable instructions that, when executed by the one or more processors, cause the computing system to: receive call data of a call in an interaction recording system of a call center recorder, wherein the interaction recording system is located behind a firewall of an internal network sub-environment; and within the internal network sub-environment: (i) store the call data in an electronic database, wherein the call data includes interaction metadata, (ii) generate a speech-to-text transcript by analyzing call audio in the call data, wherein the speech-to-text transcript corresponds to words spoken by one or more callers during the call, and (iii) generate an anonymized transcript corresponding to the speech-to- text transcript by identifying, removing, replacing, or obscuring one or more alpha-numeric personally identifiable information.
9.(Currently Amended) A confidential sentiment analysis computing system, comprising one or more processors, and a memory including computer executable instructions that, when executed by the one or more processors, cause the computing system to: receive call data of a call in an interaction recording system of a call center recorder, wherein the interaction recording system is located behind a firewall of an internal network sub-environment, within the internal network sub-environment: .I} store the call data in an electronic database, wherein the call data includes interaction metadata, (j} generate a speech-to-text transcript by analyzing call audio in the call data, wherein the speech-to-text transcript corresponds to words spoken by one or more callers during the call, (iii) generate an anonymized transcript corresponding to the speech-to-text transcript by identifying, removing, replacing, or obscuring one or more alpha- numeric personally identifiable information words, and (iv) generate a sentiment score by analyzing the anonymized transcript using a sentiment analysis service.
11. The computing system of claim 10, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: collect a consent of the caller to store the call data.
10. (Currently Amended) The computing system of claim 9, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: collect [[the]] a consent of the caller to store the call data.
12. The computing system of claim 10, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: generate the anonymized transcript by matching regular expression patterns against the speech-to-text transcript.
11. (Original) The computing system of claim 9, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: generate the anonymized transcript by matching regular expression patterns against the speech-to-text transcript.
13. The computing system of claim 10, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: generate the anonymized transcript by matching keywords in the speech-to-text transcript to one or more corpora of words.
12. (Original) The computing system of claim 9, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: generate the anonymized transcript by matching keywords in the speech-to-text transcript to one or more corpora of words.
14. The computing system of claim 10, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: generate the anonymized transcript by analyzing the speech-to-text transcript using a trained machine learning model.
13. (Original) The computing system of claim 9, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: generate the anonymized transcript by analyzing the speech-to-text transcript using a trained machine learning model.
15. The computing system of claim 10, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: generate a time series wherein each time step corresponds to a time in the anonymized transcript, and each time step is associated with a sentiment score, wherein the sentiment score indicates a sentiment at the respective time step.
14. (Original) The computing system of claim 9, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: generate a time series wherein each time step corresponds to a time in the anonymized transcript, and each time step is associated with a sentiment score, wherein the sentiment score indicates the sentiment at the respective time step.
16. The computing system of claim 10, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: generating an intra-call sentiment score.
15. (Original) The computing system of claim 9, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to: generating an intra-call sentiment score.
17. A non-transitory computer readable medium containing program instructions for anonymizing data that when executed, cause a computer system to: receive call data of a call in an interaction recording system of a call center recorder, wherein the interaction recording system is located behind a firewall of an internal network sub- environment; and within the internal network sub-environment: (i) store the call data in an electronic database, wherein the call data includes interaction metadata, (ii) generate a speech-to-text transcript by analyzing call audio in the call data, wherein the speech-to-text transcript corresponds to words spoken by one or more callers during the call, and (iii) generate an anonymized transcript corresponding to the speech-to-text transcript by identifying, removing, replacing, or obscuring one or more alpha-numeric personally identifiable information.
16. (Currently Amended) A non-transitory computer readable medium containing program instructions that when executed, cause a computer system to: receive call data of a call in an interaction recording system of a call center recorder, wherein the interaction recording system is located behind a firewall of an internal network sub-environment, within the internal network sub-environment: _I) store the call data in an electronic database, wherein the call data includes interaction metadata, _(i generate a speech-to-text transcript by analyzing call audio in the call data, wherein the speech-to-text transcript corresponds to words spoken by one or more callers during the call, (iii) generate an anonymized transcript corresponding to the speech-to-text transcript by identifying, removing, replacing, or obscuring one or more alpha- numeric personally identifiable information words, and (iv) generate a sentiment score by analyzing the anonymized transcript using a sentiment analysis service.
18. The non-transitory computer readable medium of claim 17, including further program instructions that when executed, cause a computer system to: generate the anonymized transcript by matching regular expression patterns against the speech-to-text transcript.
18. (Original) The non-transitory computer readable medium of claim 16, including further program instructions that when executed, cause a computer system to: generate the anonymized transcript by matching regular expression patterns against the speech-to-text transcript.
19. The non-transitory computer readable medium of claim 17, including further program instructions that when executed, cause a computer system to: generate the anonymized transcript by matching keywords in the speech-to-text transcript to one or more corpora of words.
19. (Original) The non-transitory computer readable medium of claim 16, including further program instructions that when executed, cause a computer system to: generate the anonymized transcript by matching keywords in the speech-to-text transcript to one or more corpora of words.
20. The non-transitory computer readable medium of claim 17, including further program instructions that when executed, cause a computer system to: generate the anonymized transcript by analyzing the speech-to-text transcript using a trained machine learning model.
20. (Original) The non-transitory computer readable medium of claim 16, including further program instructions that when executed, cause a computer system to: generate the anonymized transcript by analyzing the speech-to-text transcript using a trained machine learning model.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claims 1, 3-5, 10, 12-13, and 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over Dwyer et al. US 20150195406 A1 (hereinafter Dwyer), in view of Bodapati et al. US 11531846 B1 (hereinafter Bodapati).
Regarding claims 1, 10, 17, Dwyer teaches a computer implemented method for anonymizing data, a computing system for anonymizing data, a non-transitory computer readable medium containing program instructions for anonymizing data that when executed, cause a computer system to:
one or more processors, and a memory including computer executable instructions that, when executed by the one or more processors cause the computing system to ([203] “The processes may be realized in one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors or other programmable device, along with internal and/or external memory”, The hardware components for the system to anonymizing data includes microcontrollers, processors and memory, [204] “The computer executable code may be created using a structured programming language such as C, an object oriented programming language such as C++, or any other high-level or low-level programming language”, programming languages provide the executable instructions for the hardware components):
receiving call data of a call in an interaction recording system of a call center recorder ([0023], “a machine for automating support for a call center agent may be clearly programmed to carry out the steps of: receiving a copy of vocal communications from a plurality of heterogeneous sources in near real-time or real-time”, real-time vocal communications are received by a call center; [0029], “automatically generating new categories for a customer communications analysis system may include analyzing sets of archived call recordings”, the call center records the incoming calls);
wherein the interaction recording system is located behind a firewall of an internal network sub- environment; and within the internal network sub-environment: ([0193] “The methods and systems described herein may be deployed in part or in whole through a machine that executes computer software on a server, client, firewall, gateway, hub, router, or other such computer and/or networking hardware. The software program may be associated with a server that may include a file server, print server, domain server, internet server, intranet server and other variants such as secondary server, host server, distributed server and the like”, the firewall mentioned is interpreted as “behind a firewall” of the network environment. The firewall prevents access through security of intranet form external sources; [0159] “The system may provide for workflow facilities, such as including an observer view for monitoring and addressing the most critical events in real-time, an agent view for monitoring recent call performance, a call flow view for receiving real-time intra-call feedback, and the like”, internal monitoring of agents by a supervisor);
(i) storing the call data in an electronic database, wherein the call data includes interaction metadata, ([0030] “program for a sortable database of acoustically analyzed communications stored thereon, wherein the program instructs a microprocessor to perform the following steps including receiving incoming vocal communications, analyzing the acoustics of the incoming vocal communications, assigning one or more metadata values to the incoming vocal communications”, call data is stored in a database with an assigned metadata value for the incoming data);
(ii) generating a speech-to-text transcript by analyzing call audio in the call data, wherein the speech-to-text transcript corresponds to words spoken by one or more callers during the call, ([0082] “Audio conversations are ingested by the system along with call metadata and speech-to-text transcription is performed to generate a transcript that is analyzed using a set of linguistic and acoustic rules to look for certain key words, phrases, topics, and acoustic characteristics”, a transcript is generated based off the works spoken in the call);
(iii) generating an anonymized transcript corresponding to the speech-to-text transcript by identifying, removing, replacing, or obscuring one or more alpha-numeric personally identifiable information according to a selected mode of anonymization, redaction, or de-identification, wherein the selected mode of anonymization, redaction, or de-identification includes at least one of (1) replacing the alpha-numeric personally identifiable information with a predetermined character, (2) replacing the alpha-numeric personally identifiable information with a random word, (3) replacing the alpha- numeric personally identifiable information with a similar word, or (4) replacing the alpha-numeric personally identifiable information with a descriptor ([0164] “The location of sensitive data in the recognized communications is identified and "tagged" using an exhaustive list of language "patterns" (credit card strings, expiration dates, ccv codes, social security numbers, and a multitude of other PII data). The start and stop locations/times are annotated and passed on for redaction”, personally identifiable information from the speech to text transcripts are removed; FIG. 19, 1912, [0165] “rules of analysis 1912 may comprise key words and phrases, the presence of numbers or series of numbers, and the like. In embodiments, the rules of analysis 1912 may comprise rules such as: automatically redact all numbers where two or more numbers are found in sequence; automatically redact numbers identified as being separated by less than a specified number of words”, examiner interprets the various rules to be the different modes of redaction and the keywords / phrases to indicate the classification; [0171] “Information such as credit card number, security code, expiration date, PIN number, date of birth, driver's license data, social security number, account data, and the like may be redacted to facilitate compliance. In embodiments, keywords may be located in the transcript of an audio call and numbers redacted based on a set of rules of analysis 1912”; [0172-0173] shows examples of redaction based off keywords (classification); [0164] “The tagged words may be removed entirely or substituted for other placeholder words that can be recognized”, examiner interprets placeholder words as a descriptor, similar word, or random word and the tagged words to be pii; [0172] “The final transcript after redaction reads "what is the card number you will be using today oh let me find my card it is in my wallet take your time my purse is always such a mess let me see here oh here it is the number is redacted redacted heaven uh redacted redacted thank you now what is the expiration date . . . .””, here the examiner interprets “redacted” as the random word).
Dwyer does not teach using a trained machine learning model, by: classifying the one or more alpha-numeric personally identifiable information into a type of personally identifiable information, and selecting a mode of anonymization, redaction, or de-identification based on the type of personally identifiable information,
However, Bodapati teaches using a trained machine learning model (FIG. 7, 120),
by: classifying the one or more alpha-numeric personally identifiable information into a type of personally identifiable information ([Column 4, line 24-30] “the model endpoint may include a plurality of models, where each model corresponds to a different type of sensitive data that is to be redacted. For example, a first model at the model endpoint may be trained to identify names, a second model may be trained to identify addresses, a third model may be trained to identify account numbers, etc”; [Column 7, line 7 – Column 7, line 11] ““My name is Tom. My age is 23. My sister's name is Sara. Her age is 12”. And after redaction, the redacted transcript may include: “My name is <NAME>1111. My age is <AGE>1112. My sister's name is <NAME>1113. Her age is <AGE>1114”), and
selecting a mode of anonymization, redaction, or de-identification based on the type of personally identifiable information ([Column 5, line 30-34] “the user may select which sensitive data types are to be redacted from among the currently supported sensitive data types, including the newly added sensitive data type and the pre-existing sensitive data types.”),
Dwyer and Bodapati are considered to be analogous to the claimed invention because both are in the same field of speech analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the conversation analytics system of Dwyer with technique of classifying personally identifiable information into a type taught by Bodapati in order to improve techniques of extending sensitive data tagging without reannotating training data (see Bodapati [Abstract]).
Regarding claim 3, Dwyer in view of Bodapati teaches all of the limitations of claim 1, upon which claim 3 depends.
Additionally, Dwyer teaches storing the call data includes storing caller identification information ([0096] “A single searchable database may be used to store all of the received customer input such as: vocal stream as received; text translation of the received vocal stream; text as received; categorization; scoring; system metadata such as source of customer input, customer identification, agent ID, and the like; and the like”, the customer identification from the call is stored in a searchable database).
Regarding claim 4, Dwyer in view of Bodapati teaches all of the limitations of claim 1, upon which claim 4 depends.
Additionally, Dwyer teaches generating the anonymized transcript by identifying, removing, replacing, or obscuring one or more alpha-numeric personally identifiable information is based on matching regular expression patterns against the speech-to-text transcript ([0162] “In some cases it may be more desirable to simply remove or delete any personally identifiable information from stored data. Businesses are not allowed to store PCI sensitive information such as account numbers or security codes. The redaction capability, by using conversational and acoustic analysis, can heuristically identify millions of possible combinations of potentially sensitive data and tag them. Additionally, instead of having a few dozen patterns, there are several hundred, each of them created and tested against a very large set of real data. Finally, when a “potential” area is identified, other patterns are deployed to ensure accuracy and overlap”, personally identifiable information (PII) is removed from the transcript based on patterns found in the text).
Regarding claim 5, Dwyer in view of Bodapati teaches all of the limitations of claim 1, upon which claim 5 depends.
Additionally, Dwyer teaches generating the anonymized transcript by identifying, removing, replacing, or obscuring one or more alpha-numeric personally identifiable information is based on matching keywords in the speech-to-text transcript to one or more corpora of words ([0163] “PCI Targeted Redaction redacts numbers associated with specific types of PCI data. Redaction is performed based on locating keywords in the transcripts, and redacting numbers near those keywords”, sensitive information is removed from the transcript based on keywords).
Regarding claim 12, Dwyer in view of Bodapati teaches all of the limitations of claim 10, upon which claim 12 depends.
Additionally, Dwyer teaches the memory containing further instructions that, when executed by the one or more processors, cause the computing system to ([203-204], the system consist of programmable instruction for hardware components to execute):
generate the anonymized transcript by matching regular expression patterns against the speech-to-text transcript ([0162] “In some cases it may be more desirable to simply remove or delete any personally identifiable information from stored data. Businesses are not allowed to store PCI sensitive information such as account numbers or security codes. The redaction capability, by using conversational and acoustic analysis, can heuristically identify millions of possible combinations of potentially sensitive data and tag them. Additionally, instead of having a few dozen patterns, there are several hundred, each of them created and tested against a very large set of real data. Finally, when a “potential” area is identified, other patterns are deployed to ensure accuracy and overlap”, personally identifiable information (PII) is removed from the transcript based on patterns found in the text).
Regarding claim 13, Dwyer in view of Bodapati teaches all of the limitations of claim 10, upon which claim 13 depends.
Additionally, Dwyer teaches the computing system of claim 10, the memory containing further instructions that, when executed by the one or more processors, cause the computing system to ([203-204], the system consists of programmable instruction for hardware components to execute):
generate the anonymized transcript by matching keywords in the speech-to-text transcript to one or more corpora of words ([0163] “PCI Targeted Redaction redacts numbers associated with specific types of PCI data. Redaction is performed based on locating keywords in the transcripts, and redacting numbers near those keywords”, sensitive information is removed from the transcript based on keywords).
Regarding claim 18, Dwyer in view of Bodapati teaches all of the limitations of claim 17, upon which claim 18 depends.
Additionally, Dwyer teaches generate the anonymized transcript by matching regular expression patterns against the speech-to-text transcript ([0162] “In some cases it may be more desirable to simply remove or delete any personally identifiable information from stored data. Businesses are not allowed to store PCI sensitive information such as account numbers or security codes. The redaction capability, by using conversational and acoustic analysis, can heuristically identify millions of possible combinations of potentially sensitive data and tag them. Additionally, instead of having a few dozen patterns, there are several hundred, each of them created and tested against a very large set of real data. Finally, when a “potential” area is identified, other patterns are deployed to ensure accuracy and overlap”, personally identifiable information (PII) is removed from the transcript based on patterns found in the text).
Regarding claim 19, Dwyer in view of Bodapati teaches all of the limitations of claim 17, upon which claim 19 depends.
Additionally, Dwyer teaches generate the anonymized transcript by matching keywords in the speech-to-text transcript to one or more corpora of words ([0163] “PCI Targeted Redaction redacts numbers associated with specific types of PCI data. Redaction is performed based on locating keywords in the transcripts, and redacting numbers near those keywords”, sensitive information is removed from the transcript based on keywords).
Claims 7-9 and 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over Dwyer in view of Bodapati, as shown above in claim 1, in further view of Sivasubramanian et al. US 20210157834 A1 (hereinafter Sivasubramanian)
Regarding claim 7, Dwyer in view of Bodapati teaches all of the limitations of claim 1, upon which claim 7 depends.
Dwyer in view of Bodapati fails to teach generating a sentiment score by analyzing the anonymized transcript using a sentiment analysis service
However, Sivasubramanian teaches generating a sentiment score by analyzing the anonymized transcript using a sentiment analysis service (Fig. 2, elements 208 (STT), 206 (contact analysis service) and NLP service 210, [0034] contact analytics service powered by AI/machine learning, [0039] contact analytics service transcribing calls and using machine learning on transcript, [0054] contact analytics service 206 performing PII redaction, Output of 206 (redacted transcript) passed on to NLP service 210, where 210 performs sentiment analysis according to para [0074] and sentiment scores from sentiment analysis according to [0075]).
Dwyer in view of Bodapati in view of Sivasubramanian are considered to be analogous to the claimed invention because all are in the same field of speech analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the conversation analytics system of Dwyer in view of Bodapati with technique of scoring anonymized transcripts taught by Sivasubramanian in order to improve support searching and diagnostic capabilities in a customer contact service (see Sivasubramanian [0032]).
Regarding claim 8, Dwyer in view of Bodapati in view of Sivasubramanian teaches all of the limitations of claim 7, upon which claim 8 depends.
Additionally, Sivasubramanian teaches generating the sentiment score by analyzing the anonymized transcript using the sentiment analysis service includes generating a time series wherein each time step corresponds to a time in the anonymized transcript, and each time step is associated with a sentiment score, wherein the sentiment score indicates a sentiment at the respective time step (Fig. 2, elements 208 (STT), 206 (contact analysis service) and NLP service 210, [0034] contact analytics service powered by AI/machine learning, [0039] contact analytics service transcribing calls and using machine learning on transcript, [0054] contact analytics service 206 performing PII redaction, Output of 206 (redacted transcript) passed on to NLP service 210, where 210 performs sentiment analysis according to para [0074] and sentiment scores from sentiment analysis according to [0075], [0048], [0156], and FIG. 15 shows real time sentiment scoring).
Regarding claim 9, Dwyer in view of Bodapati in view of Sivasubramanian teaches all of the limitations of claim 7, upon which claim 9 depends.
Additionally, Sivasubramanian teaches generating the sentiment score by analyzing the anonymized transcript using the sentiment analysis service includes generating an intra-call sentiment score. (Fig. 2, elements 208 (STT), 206 (contact analysis service) and NLP service 210, [0034] contact analytics service powered by AI/machine learning, [0039] contact analytics service transcribing calls and using machine learning on transcript, [0054] contact analytics service 206 performing PII redaction, Output of 206 (redacted transcript) passed on to NLP service 210, where 210 performs sentiment analysis according to para [0074] and sentiment scores from sentiment analysis according to [0075], [0048], [0156], and FIG. 15 shows real time sentiment scoring used to analyze a call and chat data in real time).
Regarding claim 15, Dwyer in view of Bodapati teaches all of the limitations of claim 10, upon which claim 15 depends.
Dwyer in view of Bodapati fails to teach generating a time series wherein each time step corresponds to a time in the anonymized transcript, and each time step is associated with a sentiment score, wherein the sentiment score indicates the sentiment at the respective time step.
However, Sivasubramanian teaches generating a time series wherein each time step corresponds to a time in the anonymized transcript, and each time step is associated with a sentiment score, wherein the sentiment score indicates the sentiment at the respective time step (Fig. 2, elements 208 (STT), 206 (contact analysis service) and NLP service 210, [0034] contact analytics service powered by AI/machine learning, [0039] contact analytics service transcribing calls and using machine learning on transcript, [0054] contact analytics service 206 performing PII redaction, Output of 206 (redacted transcript) passed on to NLP service 210, where 210 performs sentiment analysis according to para [0074] and sentiment scores from sentiment analysis according to [0075], [0048], [0156], and FIG. 15 shows real time sentiment scoring).
Dwyer in view of Bodapati in view of Sivasubramanian are considered to be analogous to the claimed invention because all are in the same field of speech analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the conversation analytics system of Dwyer in view of Bodapati with technique of generating time series taught by Sivasubramanian in order to improve support searching and diagnostic capabilities in a customer contact service (see Sivasubramanian [0032]).
Regarding claim 16, Dwyer in view of Bodapati teaches all of the limitations of claim 10, upon which claim 16 depends.
Dwyer in view of Bodapati fails to teach generating an intra-call sentiment score
However, Sivasubramanian teaches generating an intra-call sentiment score. (Fig. 2, elements 208 (STT), 206 (contact analysis service) and NLP service 210, [0034] contact analytics service powered by AI/machine learning, [0039] contact analytics service transcribing calls and using machine learning on transcript, [0054] contact analytics service 206 performing PII redaction, Output of 206 (redacted transcript) passed on to NLP service 210, where 210 performs sentiment analysis according to para [0074] and sentiment scores from sentiment analysis according to [0075], [0048], [0156], and FIG. 15 shows real time sentiment scoring used to analyze a call and chat data in real time).
Dwyer in view of Bodapati in view of Sivasubramanian are considered to be analogous to the claimed invention because all are in the same field of speech analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the conversation analytics system of Dwyer in view of Bodapati with technique of generating an intra-call sentiment score taught by Sivasubramanian in order to improve support searching and diagnostic capabilities in a customer contact service (see Sivasubramanian [0032]).
Claims 2 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Dwyer in view of Bodapati as shown in claim 1, in further view of Shriberg et al. US 20190385711 A1 (hereinafter Shriberg).
Regarding claim 2, Dwyer in view of Bodapati teaches all of the limitations of claim 1, upon which claim 2 depends.
Additionally, Dwyer teaches wherein the interaction recording system is located behind the firewall of the internal network sub-environment ([0197] “The methods and systems described herein may be deployed in part or in whole through network infrastructures. The network infrastructure may include elements such as computing devices, servers, routers, hubs, firewalls, clients, personal computers, communication devices, routing devices and other active and passive devices, modules and/or components as known in the art”, the interaction recording system is interpreted to be located behind the firewall mentioned of the network environment).
Dwyer in view of Bodapati fails to teach collecting a consent of a caller to store the call data.
However, Shriberg teaches collecting a consent of a caller to store the call data ([0502] “The system may be able to use standard clinical encounters to train voice biomarker models. The system may collect recordings of clinical encounters for physical complaints. The complaints may be regarding injuries, sicknesses, or chronic conditions. The system may record, with patient permission, conversation patients have with health care providers during appointments”, the system may only record conversations of patient encounter with the permission of the customer)
Dwyer in view of Bodapati in view of Shriberg are considered to be analogous to the claimed invention because all are in the same field of speech analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the conversation analytics system of Dwyer in view of Bodapati with the system that obtains the consent to record conversations taught by Shriberg in order to improve assessing the mental state of patients (see Shriberg [0005]).
Regarding claim 11, Dwyer in view of Bodapati teaches all of the limitations of claim 10, upon which claim 11 depends.
Additionally, Dwyer teaches the memory containing further instructions that, when executed by the one or more processors, cause the computing system to ([203-204], the system consist of programmable instruction for hardware components to execute).
However, Dwyer in view of Bodapati fails to teach collect a consent of a caller to store the call data.
However, Shriberg teaches collect a consent of a caller to store the call data ([0502] “The system may be able to use standard clinical encounters to train voice biomarker models. The system may collect recordings of clinical encounters for physical complaints. The complaints may be regarding injuries, sicknesses, or chronic conditions. The system may record, with patient permission, conversation patients have with health care providers during appointments”, The system may only record conversations of patient encounter with the permission of the customer)
Dwyer in view of Bodapati in view of Shriberg are considered to be analogous to the claimed invention because all are in the same field of speech analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the conversation analytics system of Dwyer in view of Bodapati with the system that obtains the consent to record conversations taught by Shriberg in order to improve assessing the mental state of patients (see Shriberg [0005]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Middleman (US 9141659 B1) teaches methods and systems for scrubbing confidential insurance account information are provided. According to embodiments, a scrubbing server can receive a request to scrub confidential insurance data that includes the contents of an insurance account information database and an indication of the category of confidential data stored in the database. The scrubbing server can scrub the valid data contained in the received database, replacing confidential information with "scrambled" data that is not confidential. The scrubbing server can transmit the contents of the scrubbed database back to the requesting party.
Gervais et al. (US 20100042583 A1) teaches original data is retrieved from an original data source. The original data may be automatically searched for potential personal information, such as a person's name, address, or Social Security number. An obfuscation method may be selected from a plurality of potential obfuscation methods. The potential personal information in the original data may then be automatically replaced with fictional data in accordance with the selected obfuscation method.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZEESHAN SHAIKH whose telephone number is (703)756-1730. The examiner can normally be reached Monday-Friday 7:30AM-5:00PM.
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, Richemond Dorvil can be reached at (571) 272-7602. 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.
/ZEESHAN MAHMOOD SHAIKH/Examiner, Art Unit 2658
/RICHEMOND DORVIL/Supervisory Patent Examiner, Art Unit 2658