DETAILED ACTION
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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d).
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.
Claim(s) 19 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Independent claims 1 and 11 recite “classify an utterance intent of a speech utterance”, “extract at least one keyword”, “obtain location information corresponding to the at least one keyword”, and “provide the occupant with a navigation route”. These limitations, as drafted, are a process that, under a broadest reasonable interpretation, covers the abstract idea of “mental processes” because they cover concepts performed in the human mind, including observation, evaluation, judgement, and opinion. See MPEP 2106.04(a)(2). That is, other than reciting “one memory”, “one processor”, and “a first deep learning model”, nothing in the claimed elements preclude the steps from practically being performed by a person listening to a person within a vehicle speak, writing down keywords from the spoken words, and using that information gained to create and give navigation directions.
This judicial exception is not integrated into a practical application because the additional elements “one memory”, “one processor”, and “a first deep learning model” are all recited at a high-level of generality. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Thus, the claims as a whole are directed to an abstract idea (Step 2A, prong two).
Claims 1 and 11 do not include any additional elements that are sufficient to amount to significantly more than the judicial exception because, as discussed above with respect to integration of the abstract idea into a practical applications, the additional elements of “one memory”, “one processor”, and “a first deep learning model” amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (Step 2B).
Dependent claims 2-10 and 11-19 are directed to the utterance itself and the deep learning models. That is, nothing in the claimed elements preclude the steps from practically being performed by a person listening to a person within a vehicle speak, writing down keywords from the spoken words, and using that information gained to create and give navigation directions.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-3, 6-7, 10-13, and 16-17 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Kim (US Patent No. 12,437,755).
Regarding claim 1, Kim discloses a device for providing information based on speech recognition, the device comprising: at least one memory storing computer-executable instructions (Kim col. 5 lines 10-17);
and at least one processor, wherein the at least one processor is configured to execute the computer-executable instructions to (Kim col. 5 lines 10-17): classify an utterance intent of a speech utterance of an occupant of a vehicle (Kim Fig. 11 reference character 1300),
extract at least one keyword corresponding to a slot of the utterance intent from the speech utterance (Kim col. 6 lines 14-22),
obtain location information corresponding to the at least one keyword (Kim col. 12 lines 1-8) by applying a first deep learning model to the at least one keyword when the utterance intent is route setting (Kim col. 6 lines 47-52),
and provide the occupant with a navigation route from a current location of the vehicle occupant to the location information (Kim col. 12 lines 1-8).
Regarding claim 2, Kim discloses all of the limitations of claim 1. Kim further discloses when the utterance intent is any one of a point of interest (POI) guidance (Kim col. 15 lines 43-46), a route description, an accident information guidance, or a congested section check, wherein the at least one processor is configured to ("For example, when the intent is determined to make a call, a signal for making a call may be generated together with a system utterance for guiding the execution of the making a call, and when the intent is determined to be route guidance, a signal for executing route guidance may be generated together with a system utterance to guide the execution of route guidance. Furthermore, when the intent is determined to play music, a signal for executing 'play music' may be generated together with a system utterance guiding the execution of 'play music.'," Kim col. 16 lines 15-24): identify location coordinates based on the at least one keyword (Kim col. 12 lines 1-8),
obtain a POI name (Kim col. 12 lines 1-8) by applying a second deep learning model to the location coordinates (Kim col. 6 lines 47-52),
and provide the POI name (Kim col. 12 lines 1-8).
Regarding claim 3, Kim discloses all of the limitations of claim 2. Kim further discloses wherein the first deep learning model includes (Kim col. 10 lines 42-49): a text encoder trained to encode a training input keyword into a first vector representation (Kim col. 10 lines 50-53 and col. 10 lines 54-58);
and a location decoder trained to output a training output location corresponding to the training input keyword from the first vector representation (Kim col. 11 lines 23-33 and col. 12 lines 1-8, encoders and decoders are inherent components of deep learning models, therefore in order to reach the output of the location/route guidance, the vector representation of the input would need to be decoded to correspond to a location).
Regarding claim 6, Kim discloses all of the limitations of claim 2. Kim further discloses wherein when the utterance intent is the POI guidance (Kim col. 15 lines 43-46), the at least one processor is configured to: obtain first location coordinates around a target location according to the at least one keyword (Kim col. 12 lines 1-8),
obtain first POI names (Kim col. 12 lines 1-8) by applying the second deep learning model to the first location coordinates (Kim col. 6 lines 47-52),
and provide the first POI names (Kim col. 12 lines 1-8).
Regarding claim 7, Kim discloses all of the limitations of claim 2. Kim further discloses wherein when the utterance intent is the route description (Kim col. 15 lines 43-46), the at least one processor is configured to: obtain second location coordinates within the navigation route according to the at least one keyword (Kim col. 12 lines 1-8),
obtain second POI names (Kim col. 12 lines 1-8) by applying the second deep learning model to the second location coordinates (Kim col. 6 lines 47-52),
and provide the second POI names (Kim col. 12 lines 1-8).
Regarding claim 10, Kim discloses all of the limitations of claim 1. Kim further discloses a vehicle comprising the device of claim 1 (Kim col. 7 lines 46-50).
As to claims 11-13, method claims 11-13 and system claims 1-3 are related as system and method of using same, with each claimed element’s function corresponding to the respective system step. Accordingly, claims 11-13 are similarly rejected under the same rationale as applied above with respect to the system claims.
As to claims 16-17, method claims 6-7 and system claims 16-17 are related as system and method of using same, with each claimed element’s function corresponding to the respective system step. Accordingly, claims 16-17 are similarly rejected under the same rationale as applied above with respect to the system claims.
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) 4-5 and 14-15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kim, in view of Mohammadi et al. ("NLP-enabled trajectory map-matching in urban road networks using transformer sequence-to-sequence model", 04/18/2024), hereinafter referred to as Mohammadi.
Regarding claim 4, Kim discloses all of the limitations of claim 3. However, Kim fails to disclose wherein the second deep learning model includes: a location encoder trained to encode a training input location into a second vector representation; and a text decoder trained to output a training output keyword corresponding to the training input location from the second vector representation.
Mohammadi discloses an NLP-enabled map-matching using transformers.
Mohammadi teaches wherein the second deep learning model includes: a location encoder trained to encode a training input location into a second vector representation ("Let g = (g1,g2,...,gn) be the transformed version of T = {(x1,y1),(x2,y2),...,(xn,yn)}, representing the variable length input sequence, here in this study, a sequence of grid cells, each of which encompasses each GPS point," Mohammadi pg. 4 C. Objective Function);
and a text decoder trained to output a training output keyword corresponding to the training input location from the second vector representation ("...and r = (r1,r2,...,rm) be the variable-length output sequence, i.e., sequence of road segments, m is the length of the output sequence," Mohammadi pg. 4 C. Objective Function).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim’s method for processing the intents of dialogue by including Mohammadi’s usage of a location encoder and text decoder. This would enable better and more accurate handling of the input, i.e. the location being spoken, as encoder-decoder architectures allow for mapping of variable length inputs to flexible outputs. This usage would enable for better contextual understanding of what the user is attempting to convey.
Regarding claim 5, Kim, in view of Mohammadi, discloses all of the limitations of claim 4. However, Kim fails to disclose wherein the text encoder and the location encoder have trained to reduce a difference between the first vector representation and the second vector representation when the training input keyword corresponds to the training input location.
Mohammadi teaches wherein the text encoder and the location encoder have trained to reduce a difference between the first vector representation and the second vector representation when the training input keyword corresponds to the training input location ("The objective can be optimized using backpropagation of cross-entropy loss through time, which computes the gradients of the objective with respect to the model parameters and updates the parameters using gradient descent. Once the model is trained, it can be used to generate segment-based trajectories for new input sequences," Mohammadi pg. 4 C. Objective Function).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim’s method for processing the intents of dialogue by including Mohammadi’s usage a loss function. A loss function is a critical piece in any machine learning or deep learning application. Loss functions work to optimize the algorithm and to minimize error, thereby improving accuracy.
As to claims 14-15, method claims 4-5 and system claims 14-15 are related as system and method of using same, with each claimed element’s function corresponding to the respective system step. Accordingly, claims 14-15 are similarly rejected under the same rationale as applied above with respect to the system claims.
Claim(s) 8-9 and 18-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kim, in view of Hashizume et al. (US Patent No. 7,333,889).
Regarding claim 8, Kim discloses all of the limitations of claim 2. Kim further discloses according to the at least one keyword based on accident information (Kim col. 6 lines 14-22), obtain a third POI name (Kim col. 12 lines 1-8) by applying the second deep learning model to the third location coordinates (Kim col. 6 lines 47-52).
However, Kim does not disclose wherein when the utterance intent is the accident information guidance, the at least one processor is configured to: identify third location coordinates for an accident point within a spatial range. Hashizume discloses a car navigation system that displays traffic information.
Hashizume teaches wherein when the utterance intent is the accident information guidance, the at least one processor is configured to: identify third location coordinates for an accident point within a spatial range ("For example, the traffic-related information includes the place where the traffic congestion occurs, the traffic congested area length, the traffic congestion information composed of a traffic congestion level and a travel time (time needed for the travel) for each of links constituting the traffic congested area, and the traffic regulation information such as traffic closure due to accident or construction work and closure of entrances and exits for highways and the like," Hashizume col. 5 lines 66-67 and col. 6 lines 1-6).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim’s method for processing the intents of dialogue by including Hashizume’s identification of a location where an accident has occurred. Including any information into a navigation system that could potentially delay a user’s travels would be beneficial to the user. This would allow them to take a different route, bypassing the traffic, accident, or congestion and to arrive to their destination at their desired time.
Regarding claim 9, Kim discloses all of the limitations of claim 2. Kim further discloses according to the at least one keyword based on traffic information (Kim col. 6 lines 14-22), obtain a fourth POI name (Kim col. 12 lines 1-8) by applying the second deep learning model to the fourth location coordinates (Kim col. 6 lines 47-52).
However, Kim does not disclose wherein when the utterance intent is the congested section check, the at least one processor is configured to: identify fourth location coordinates for a congested section within a spatial range.
Hashizume teaches wherein when the utterance intent is the congested section check, the at least one processor is configured to: identify fourth location coordinates for a congested section within a spatial range ("For example, the traffic-related information includes the place where the traffic congestion occurs, the traffic congested area length, the traffic congestion information composed of a traffic congestion level and a travel time (time needed for the travel) for each of links constituting the traffic congested area, and the traffic regulation information such as traffic closure due to accident or construction work and closure of entrances and exits for highways and the like," Hashizume col. 5 lines 66-67 and col. 6 lines 1-6).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim’s method for processing the intents of dialogue by including Hashizume’s identification of a location where an accident has occurred. Including any information into a navigation system that could potentially delay a user’s travels would be beneficial to the user. This would allow them to take a different route, bypassing the traffic, accident, or congestion and to arrive to their destination at their desired time.
As to claims 18-19, method claims 8-9 and system claims 18-19 are related as system and method of using same, with each claimed element’s function corresponding to the respective system step. Accordingly, claims 18-19 are similarly rejected under the same rationale as applied above with respect to the system claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US Patent Application Publication No. 2019/0204907
US Patent Application Publication No. 2021/0125611
US Patent No. 10,418,032
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ADAM MICHAEL WEAVER whose telephone number is (571)272-7062. The examiner can normally be reached Monday-Friday, 8AM-5PM EST.
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.
/ADAM MICHAEL WEAVER/Examiner, Art Unit 2658
/RICHEMOND DORVIL/Supervisory Patent Examiner, Art Unit 2658