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 .
Response to Amendment
(Submitted on 7/22/2026)
It appears that the applicant has shifted the focus of the invention to medical application (prognostic predictive model).
Regarding 101 Claim Rejection
The examiner had rejected the claim 1, 17 and 18 for the mental step “derive an evaluation
value in the machine learning model for each document data included in the document data
group”. On further analysis of the amended limitation “derive an evaluation value in the machine learning model according to the acquired prediction result corresponding to each document data included in the document data group”, the examiner submits that this is a standard, objective ML evaluation process that typically involves applying defined metrics to prediction results to determine performance. The examiner further submits that if the “evaluation value” is computed internally by a human (e.g., a researcher mentally or on paper) after seeing the model’s prediction, and with no additional technological step is performed, this could be viewed as a mental step. However, if the evaluation is performed by the model itself (e.g., the model outputs a numerical score that is then used in a technological process) or if the evaluation is automated and integrated into a practical application (such as feeding the value into a control system, decision-making algorithm, or other technical process), it may not be considered a mere application of the algorithm. In that case, the step could be part of the “inventive concept” analysis. Spec [0004] and [0005] reciting” valuation value in a machine learning model that uses a document data group including a plurality of document data as input” only suggests that the evaluation value references to a data group without suggesting how it is measured”. The above argument suggests that the examiner can in fact separate the evaluation from the observed prediction result, and on this basis, the examiner concludes that the “deriving evaluation value” is still a mental process as a human can derive the value using a pen and paper by looking at the predicted result of a model perhaps available (e.g., printed as a table).
The examiner submits that the examiner considered claim 3 as it is dependent claim on claim 1 which is” derive the evaluation value for each document data based on the document unit output data as a mental step of data manipulation. However, the examiner submits that the claim 3 adds nothing technically meaningful process to claim 1 that can be non-generic and provides technical improvement to meet the practical application and significantly more.
In CONCLUSION, the examiner hereby RETAINS the 101 rejections on claims 1, 3-9 and 17-19.
Regarding 102 Claim Rejection
- On Page 16, the applicant argues that “Odibat” fails to anticipate the feature of performing at least one of specification of the document …. derived evaluation value” and states that on Page 23-24 with respect to claim 2 that “Odibat” fails to teach the limitation and the applicant states on Page 17 that the same rationale for claim 18.
Examiner’s Response
The examiner submits that the argument is “MOOT” because of the stated limitation is an “amendment”.
- On Page 17, regarding independent claim 10, the applicant argues that the “Londer” fails to teach “calculate, also for another document……. for training” and applies the same rationale for claim 20.
Examiner’s Response
The examiner submits that the argument is “MOOT” because of the stated limitation is an “amendment”.
Regarding 103 Claim Rejection
- On Page 18, the applicant argues on the combination of references fail to teach the claims 2, 7-8], [claims 3-4, 6 and 9], claim 12 and [claims 17 and 19].
Examiner’s Response
The examiner submits with the context of the amendment to the independent claim, the argument is “MOOT”. The examiner has used new reference “ANCONA” to teach the amendments and has used previously used prior art to ensure the consistency of the combination to provide a broad context to the invention claims. Specifically, claim 5 though not “amended” is taught by reference “ANCONA” as the limitation of claim 5 and the examiner considers it as very relevant to the amendments made to claim 1 “individually input each normalized document data into a machine learning model to acquire prediction result corresponding to each document data, wherein the machine Learning model is a prognosis prediction model”.
In CONCLUSION, the examiner hereby REPLACES the 102 rejections on claims 1, 5, 18, 10-11, 13-16 and 20-21 with 103 rejections and rejects claims 1, 3-11 and 13-21 under 103 and MOVE the application to FINAL REJECTION. The applicant has CANCELLED claims 2 and 12.
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, 3-9 and 17-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1:
According to the first part of the analysis, in the instant case, claims 1, 3-9, and 17-19 are directed to an apparatus claim comprising one or more processors and memory. Thus, each of the claims falls within one of the four statutory categories (i.e. process, machine, manufacture, or composition of matter).
Regarding claim 1: (Currently Amended)
Step 2A Prong 1:
“extract a plurality of document data from a document data group” is a mental step of data
manipulation.
“normalize each document data according to a text length of the document data. is a mental
step of data manipulation.
“derive an evaluation value in the machine learning model (except according to the acquired prediction result corresponding to each document data included in the document data group)
” is a mental step of data representation and manipulation.
Additional Elements
Step 2A Prong 2:
“An information processing apparatus comprising: at least one processor, wherein the
processor is configured to: “does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“Individually input each normalized document data into a machine learning model to acquire prediction result corresponding to each document data” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“wherein the machine Learning model is a prognosis prediction model” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)). does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“acquire prediction result output from the machine learning model” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“according to the acquired prediction result corresponding to each document data included in the document data group” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ perform at Least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ specify a display order of the plurality of document data in the document data group;
and initiate a screen displaying the plurality of document data in the specified display order” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Step 2B:
“An information processing apparatus comprising: at least one processor, wherein the
processor is configured to: “does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ Individually input each normalized document data into a machine learning model to acquire prediction result corresponding to each document data” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“wherein the machine Learning model is a prognosis prediction model” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“acquire prediction result output from the machine learning model” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“according to the acquired prediction result corresponding to each document data included in the document data group”
“ perform at Least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ specify a display order of the plurality of document data in the document data group;
and initiate a screen displaying the plurality of document data in the specified display order” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Regarding claim 3: (Original)
Step 2A Prong 1:
“ and derive the evaluation value for each document data based on the document unit output
data” is a mental step of data manipulation.
Additional Elements
Step 2A Prong 2:
“ wherein the processor is configured to: use each document data as input of the machine
learning model to acquire document unit output data which is output for each document data” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Step 2B:
“ wherein the processor is configured to: use each document data as input of the machine
learning model to acquire document unit output data which is output for each document data” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Regarding claim 4: (Original)
Step 2A Prong 1:
“ wherein the evaluation value has a correlation with the document unit output data” is a
mental step of data comparison.
Step 2A Prong 2: no additional elements
Step 2B: no additional elements
Regarding claim 5: (Original)
Step 2A Prong 1:
“ normalize each document data included in the document data group” is a mental step of data
manipulation.
“ and derive the evaluation value for each normalized document data” is a mental step of data
manipulation.
Additional Elements
Step 2A Prong 2:
“ wherein the processor is configured to: “does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Step 2B:
“ wherein the processor is configured to: “does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Regarding claim 6: (Original)
“ extract a plurality of word data from each document data included in the document data
group” is a mental step of data manipulation.
“ the evaluation value in the machine learning model as a word unit evaluation value for each
word data” is a mental step of data manipulation.
“ and derive the evaluation value according to a statistical value of the word unit evaluation
value of the word data included in the document data for each document data” is a math
function using pen and paper.
Additional Elements
Step 2A Prong 2:
“ wherein the processor is configured to: “does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Step 2B:
“ wherein the processor is configured to: “does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Regarding claim 7: (Original)
Step 2A Prong 1:
“ the document data having a greatest first evaluation value, which is derived for each
document data, is used as first document data, and each of the plurality of document data other
than the first document data included in the document data group is used as second document
data” is a mental step of data identification.
Additional Elements
Step 2A Prong 2:
“ and the processor is configured to use each combination data in which the first document data
and the second document data are combined as input of the machine learning model to derive a
second evaluation value from output data which is output for each combination data” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Step 2B:
“ and the processor is configured to use each combination data in which the first document data
and the second document data are combined as input of the machine learning model to derive a
second evaluation value from output data which is output for each combination data” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Regarding claim 8: (Original)
Step 2A Prong 1:
“ give a first display priority to the first document data” is a mental step of data manipulation.
“ and give a second display priority, which is lower than the first display priority, to the second
document data based on the second evaluation value” is a mental step of data manipulation.
Additional Elements
Step 2A Prong 2:
“ wherein the processor is configured to: “does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Step 2B:
“ wherein the processor is configured to: “does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Regarding claim 9: (Original)
Step 2A Prong 1:
“ extract a plurality of word data from each document data included in the document data
Group” is is a mental step of data identification.
“ derive the evaluation value in the machine learning model as a word unit evaluation value for
each word data” is a math function using pen and paper.
“ derive a first statistical value of the word unit evaluation value of the word data included in the
document data for each document data to give a first evaluation value to first evaluation value
document data which is the document data having a greatest first statistical value” is a mental
step of data manipulation.
“ derive, for a plurality of combination data in which the first evaluation value document data,
and each of the plurality of document data other than the first evaluation value document data
included in the document data group are combined, a second statistical value of the word unit
evaluation value of the word data included in the combination data for each combination data
to give a second evaluation value, which is lower than the first evaluation value, to second
evaluation value document data which is the document data having a greatest second statistical
value” is a mental step of data manipulation.
“ and set, in derivation of the second statistical value, the word unit evaluation value of the
word data included in the first evaluation value document data among the word data included
in the document data combined with the first evaluation value document data to be relatively
lower than the word unit evaluation value of the word data which is not included in the first
evaluation value document data” is a mental step of data manipulation.
Additional Elements
Step 2A Prong 2:
“ wherein the processor is configured to: “ does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Step 2B:
“ wherein the processor is configured to: “ does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Regarding claim 17: (Currently Amended)
Step 2A Prong 1:
Regarding claim 1:
Step 2A Prong 1:
“extract a plurality of document data from a document data group” is a mental step of data
manipulation.
“normalize each document data according to a text length of the document data. is a mental
step of data manipulation.
“derive an evaluation value in the machine learning model (except according to the acquired prediction result corresponding to each document data included in the document data group)
” is a mental step of data representation and manipulation
Additional Elements
Step 2A Prong 2:
“An information processing apparatus comprising: at least one processor, wherein the
processor is configured to: “does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“Individually input each normalized document data into a machine learning model to acquire prediction result corresponding to each document data” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“wherein the machine Learning model is a prognosis prediction model” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)). does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“acquire prediction result output from the machine learning model” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“according to the acquired prediction result corresponding to each document data included in the document data group” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ perform at Least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ specify a display order of the plurality of document data in the document data group;
and initiate a screen displaying the plurality of document data in the specified display order” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Step 2B:
“An information processing apparatus comprising: at least one processor, wherein the
processor is configured to: “does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ Individually input each normalized document data into a machine learning model to acquire prediction result corresponding to each document data” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“wherein the machine Learning model is a prognosis prediction model” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“acquire prediction result output from the machine learning model” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“according to the acquired prediction result corresponding to each document data included in the document data group”
“ perform at Least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ specify a display order of the plurality of document data in the document data group;
and initiate a screen displaying the plurality of document data in the specified display order” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Regarding claim 18: (Currently Amended)
Step 2A Prong 1:
“extracting a plurality of document data from a document data group” is a mental step of data
manipulation.
“normalizing each document data according to a text length of the document data” is a mental
step of data manipulation.
“derive an evaluation value in the machine learning model (except according to the acquired prediction result corresponding to each document data included in the document data group)
” is a mental step of data representation and manipulation
Additional Elements
Step 2A Prong 2:
“An information processing method executed by a processor of an information processing
apparatus including at least one processor, the information processing method comprising”
“does not integrate the judicial exception into a practical application. This additional element is
merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ Individually input each normalized document data into a machine learning model to acquire prediction result corresponding to each document data” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“wherein the machine Learning model is a prognosis prediction model” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)). does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“acquire prediction result output from the machine learning model” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“according to the acquired prediction result corresponding to each document data included in the document data group” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ perform at Least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ specify a display order of the plurality of document data in the document data group;
and initiate a screen displaying the plurality of document data in the specified display order” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Step 2B:
“An information processing method executed by a processor of an information processing
apparatus including at least one processor, the information processing method comprising “does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ Individually input each normalized document data into a machine learning model to acquire prediction result corresponding to each document data” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“wherein the machine Learning model is a prognosis prediction model” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“acquire prediction result output from the machine learning model” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“according to the acquired prediction result corresponding to each document data included in the document data group”
“ perform at Least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
“ specify a display order of the plurality of document data in the document data group;
and initiate a screen displaying the plurality of document data in the specified display order” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Regarding claim 19: (Original)
Additional Elements
Step 2A Prong 2:
“ A non-transitory computer-readable medium storing an information processing program that is executable by the processor included in the information processing device to perform the information processing method according to claim 18” does not integrate the judicial exception into a practical application. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
Step 2B:
“ A non-transitory computer-readable medium storing an information processing program that is executable by the processor included in the information processing device to perform the information processing method according to claim 18” does not amount significantly more than the judicial exception in the claim. This additional element is merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(h)).
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.
Claims 1, 5, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over
Andrea ANCONA et al. (hereinafter ANCONA) US 2022/0095977 A1,
in view of Aurélien COQUARD et al. (hereinafter COQUARD)) US 2020/0327172 A1.
Regarding claim 1: (Currently Amended)
ANCONA discloses:
- An information processing apparatus comprising : at Least one processor, wherein the processor is configured to:
[Abstract]:
A monitoring system, and related monitoring and predicting methods of a diuresis for a calculation of a risk of onset of renal failure of a patient, including a device, wherein the device includes a first algorithm for recording, storing, comparing and processing measurements of a urine container and a second algorithm for predicting future measurements of the urine container,
[0230]:
The weight meter of the urine bag, having the functionalities described above
can have
[0230]:
a STM32L476JG processor mounted on the SensorTile module for the control and the management of the data collected by the sensor and their sending via low-power Bluetooth connection to the urine container;
- extract a plurality of document data from a document data group
[0142]:
data collection: continuous measurement of the weight of the hospitalized patient's urine bag,
[0143]:
the definition of the stage of progress of the kidney failure associated with a certain level of risk, and the processing of the patient's diuresis with machine-learning algorithms for the determination and implementation of a predictive model of the onset of acute kidney failure leading to the determination of accurate risk levels of onset of acute kidney failure; [0144]:
sending the data documents and risk levels to a smartphone application owned by the attending physician.
[0148]:
PNG
media_image1.png
526
455
media_image1.png
Greyscale
by means of a first algorithm 15, recording and storing the measurements of the urine container 2 (step 102);
[0150]:
by means of the first algorithm 15, comparing and processing the measurements of the urine container 2 and stored over time to determine a diuretic trend (step 104);
[0151]:
on the basis of the trend determined in the previous step, step 104, by means of a second algorithm 25 comprising an adaptive mathematical model H-25 and a machine-learning mathematical model M-25, predicting the values of future measurements of the urine container 2 and the risk of developing kidney failure (step 105);
[0152]:
transferring the data obtained in the previous step, step 105, to a videoterminal 7 (step 106).
- individually input each normalized document data into a machine learning model to acquire prediction result corresponding to each document data, wherein the machine Learning model is a prognosis prediction model;
[0010];
The diagnosis and timely treatment of AKI can improve the patient's clinical course and prognosis,
[0154]:
the first algorithm 15 comprises a mathematical model for the analysis of the data obtained through the weight meter 3 in order to correlate each weight measurement with the time instant in which it was performed and to calculate a rate of hourly urinary production normalized on the weight of the patient (weight/hour/patient's weight); subsequently, this normalized hourly urinary production rate is compared with the hourly production rate thresholds defined by the KDIGO and RIFLE guidelines for the definition of stages of acute kidney failure AKI;
[0151]:
on the basis of the trend determined in the previous step, step 104, by means of a second algorithm 25 comprising an adaptive mathematical model H-25 and a machine-learning mathematical model M-25, predicting the values of future measurements of the urine container 2 and the risk of developing kidney failure (step 105);
[0010]:
AKI results, therefore, a common, harmful, but potentially treatable condition, in which an acute reduction, even slight, in renal function has a negative effect on the patient's prognosis.
[BRI: A prognostic model is a predictive tool used to estimate the likelihood of a future clinical outcome for an individual, often based on patient-specific data such as demographics, medical history, lab results, and imaging. The “prognostic” label depends on the nature of the prediction, not just the architecture or feature extraction method]
- acquire prediction result output from the machine learning model.
[0106]:
the adaptive mathematical model H-25 comprises linear and non-linear regression models and machine-learning models, preferably artificial neural networks.
[0145]:
Furthermore, with reference to FIG. 2 that illustrates the preferred embodiment of the present invention, a diuresis monitoring method for predicting the risk of kidney failure of a patient constitutes an independent aspect usable independently with respect to the other aspects of the invention,
- derive an evaluation value in the machine learning model according to the acquired prediction result
[0028]:
A system and method capable of monitoring and predicting the diuresis and, more generally, biological fluid, would satisfy the requirements of numerous applications such as, for example, the assessment of the risk of kidney failure and, more generally, the evaluation the state of health of a patient,
[0242]:
The systems herein proposed allow, therefore, to combine the strong innovative value deriving from automation, precision and continuity of the collection of information and their ability to actively interact with the attending physician thanks to a system of data connectivity, to an easy-to-use, cost-efficient technology able to suit the environment of use.
[BRI: Providing an attending physician with timely, accurate, and easy-to-use access to patient data through a secure, cost-efficient, interoperable system can indeed represent a significant evaluation value in healthcare delivery]
- according to the acquired prediction result corresponding to each document data included in the document data group;
[0016]:
Several patent documents report systems that aim to monitor the patient's diuresis for the patient's best management in a hospital environment,
[0144]:
communication of processed data and patient risk levels to the attending physician; such communication, which has the purpose of allowing the doctor to know in real time the diuresis of the patient and the risk levels associated with it
[0144]:
sending the data documents and risk levels to a smartphone application owned by the attending physician.
[0148]:
by means of a first algorithm 15, recording and storing the measurements of the urine container 2 (step 102); [0149] repeating the previous steps, from step 100 to step 102, for a predetermined number of times (step 103); [0150] by means of the first algorithm 15, comparing and processing the measurements of the urine container 2 and stored over time to determine a diuretic trend (step 104);
[BRI: recording and storing the measurements of a urine container is considered document data in both clinical and regulatory contexts]
ANCONA does not explicitly disclose:
- normalize each document data according to a text length of the document data;
- perform at Least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value;
- specify a display order of the plurality of document data in the document data group; and
- initiate a screen displaying the plurality of document data in the specified display order.
However, COQUARD discloses.
- normalize each document data according to a text length of the document data;
[0011]:
In an embodiment, the method comprises parsing a first contract document to identify a plurality of clauses in the first contract document, each clause of the plurality of clauses comprising a sequence of words; generating a plurality of representation vectors based on the first contract document and at least one embedding model, wherein each representation vector of the plurality of representation vectors is generated based on a separate clause of at least a subset of clauses of the plurality of clauses; comparing each representation vector of the plurality of representation vectors with a second plurality of representation vectors stored in a vector database; and generating output data based on the representation vectors and the first contract document,
[0012]:
search contract documents to form one or more groups of contract documents by selecting a first contract document for the or each group and searching for other contract documents having a relevance score within a relevance threshold; determine a most recently revised contract document within the or each group and determining similarity score for each contract document in said group against the most recently revised contract document for the group;
[0109]:
the parameters identified in a processed contract document may be extracted and stored in at least one data structure. In some embodiments, a formatted contract document may be generated based on an unformatted input contract document such that the formatted document includes merge fields corresponding to the plurality of predetermined fields,
[0131]:
In some embodiments, the system may output common clauses from multiple contract documents. This may facilitate the review of multiple contracts by separately identifying clauses that can be reviewed together and/or match to a predetermined format,
[0139]:
Referring to FIG. 9, a contract document processing system according to another embodiment is shown. The system 2000 includes a parsing engine 1002, an authoring module 1004, a contracts database 1012, a search engine 1024, a first similarity score engine 1026A, a second similarity score engine 1026B, a difference engine 1028, a parameter extraction engine 100,
[0140]:
The parsing engine 1002 may be implemented as described with respect to the parsing engine 100 of FIG. 1 and may be arranged to parse contract documents 1000 to identify characters, words, sentences and clauses or any other ordered sequence of characters and which are stored in the contracts database 1012 and may be indexed or identified using a contract identifier for example. The contract documents 1000 may for example be PDF documents that require optical character recognition to identify characters and further processing to identify suitable ordered sequences of characters such as clauses. In another alternative, the contract documents may be text documents such as DOC files which contain text characters but require organization into suitable ordered sequences of characters such as clauses. The parsed contract documents may be stored in any suitable data-structure within the database and may be accessible using SQL queries for example. The contracts database may be any suitable database such as a text database, relational database, object-oriented database for example.
[BRI: embedding a sentence or document using a model that takes a sequence of word embeddings, the resulting sentence/document embedding inherently reflects its length, because the model processes a variable-length sequence of word vectors and aggregates them (e.g., via pooling) into a single vector. A sentence embedding is a fixed-length vector that captures the semantic meaning of an entire sentence]
- perform at least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value;
[0022]:
In an embodiment, the output data comprises the at least one data structure representing the plurality of parameters, the method further comprising: storing the output data as metadata associated with the first contract document; detecting a modification to the first contract document; and in response to detecting the modification, automatically updating the metadata associated with the first contract document based on the modification.
[0018]:
determine a most recently revised contract document within the or each group and determining similarity score for each contract document in said group against the most recently revised contract document for the group; remove contract documents from the or each group having a similarity score within a similarity threshold to form one or more respective filtered groups of contract documents; compare the contract documents of the or each filtered group to determine a template for said filtered group.
[0009]:
In an embodiment differences between the contract documents in a said filtered group and the template for the filtered group may be identified and stored or displayed to a user of the method. The template may comprise one or more clauses with the differences being displayed. Documents which are not grouped with another document may also be identified and displayed.
[0140]:
The parsing engine 1002 may be implemented as described with respect to the parsing engine 100 of FIG. 1 and may be arranged to parse contract documents 1000 to identify characters, words, sentences and clauses or any other ordered sequence of characters and which are stored in the contracts database 1012 and may be indexed or identified using a contract identifier,
[0088]:
As used herein, the term “graphical user interface” or “GUI” refers to a generated display with which a user may interact, either directly or indirectly (e.g., through a keyboard, mouse, touchscreen, and/or the like),
[0148]:
At 1104, the method selects a next ungrouped document. This may be derived from the already received search result and may be based on any suitable metric such as a next database index number. A relevance score between the two selected documents is also determined. This may be implemented by the relevance score engine 1026A, for example by determining a tf-idf value between the two selected documents,
[0152]:
The method may be arranged such that the relevance score is determined with respect to the first selected document and all other documents so that this may result in overlapping rather than exclusive groups of documents. The results of the comparisons may be ordered or sorted in descending order of relevance such that only those documents with a relevance score over the threshold are considered and added to the group so that those having a relevance score above the threshold are readily identified without having to proceed through all steps of the method for all documents. The group size may be limited, for example 5000 documents, so that only the most relevant documents are included.
[BRI: “perform at least one of specification of the document data, which is a display target” refers to a requirement that a system, product, or service must meet one or more specified performance criteria from a defined set of “document data” items, where at least one of those items is designated as a display target. A relevance score is indeed a performance criterion used to determine how relevant a document is to a given query, and it directly influences whether and how a document is displayed in search results. The contract documents in a templated filtered group are identified and stored with metadata, and the display order is determined by the metadata (and any derived evaluation values) rather than the raw document text. This approach enables efficient, automated, and role-specific views of contracts without manually opening each file and the derived evaluation value you mention could be a calculated or prioritized field (e.g., “high priority” if the contract expires in the next 30 days) that influences the display order]
- specify a display order of the plurality of document data in the document data group; and
[0140]:
The parsing engine 1002 may be implemented as described with respect to the parsing engine 100 of FIG. 1 and may be arranged to parse contract documents 1000 to identify characters, words, sentences and clauses or any other ordered sequence of characters and which are stored in the contracts database 1012 and may be indexed or identified using a contract identifier for example
[0088]:
As used herein, the term “graphical user interface” or “GUI” refers to a generated display with which a user may interact
[0137]:
Output component 912 may include a component that provides output information from device 900 (e.g., a display, a speaker, one or more light-emitting diodes (LEDs), etc.).
[BRI: Parse contract document systems can indeed identify and store any ordered sequence of characters from contracts, index them with contract identifiers, and display them in the original document order using the output component]
- initiate a screen displaying the plurality of document data in the specified display order.
[0088]:
As used herein, the term “graphical user interface” or “GUI” refers to a generated display with which a user may interact, either directly or indirectly (e.g., through a keyboard, mouse, touchscreen, and/or the like).
[0091]:
FIG. 1 depicts a system 1000 for processing contract documents according to an embodiment. The system 1000 includes a parsing engine 102, modeling engine 104, comparison engine 106, and parameter extraction engine 108. In some examples, the parsing engine 102, modeling engine 104, comparison engine 106, and parameter extraction engine 108 may all be functions or portions of a single software application. In other embodiments, one or more of the parsing engine 102, modeling engine 104, comparison engine 106, and parameter extraction engine 108 may be distributed and/or separate components, such as separate applications and/or computing devices. A contract document 100 may be input into the parsing engine 102 to be processed. In some examples, a front-end GUI (not shown in FIG. 1) may be used to select a contract document 100 from a local or network location and to input the contract document to the parsing engine 102. In some examples, an API may be used to communicate a contract document 100 to the parsing engine 102 for processing.
[BRI: the GUI’s role in this process is to present the arranged documents in windows, lists, or other visual components, and to provide the interactive elements (menus, buttons, scrollbars) that let the user navigate or modify the display. In a typical modern contract management system, a contract document is first input into a parsing engine for processing, and a front-end GUI can be used to display the parsed results in a specified order for user interaction. A Front-end GUI can then render this data in a controlled “display order” — for example, showing clauses in sequence, tables in their original layout, or key fields in a searchable list]
It would be obvious to one of ordinary skills in the art before the effective filing date of the present application to combine ANCONA and COQUARD.
ANCONA teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
COQUARD teaches normalization and display order.
One of ordinary skills would be motivated to combine ANCONA and COQUARD that provide a shorter distance as a performance metric (COQUARD [0114]).
Regarding claim 5: (Original)
ANCONA discloses:
wherein the processor is configured to:
- normalize each document data included in the document data group;
[0016]:
Several patent documents report systems that aim to monitor the patient's diuresis for the patient's best management in a hospital environment.
[Examiner Note: It appears that there is “typo” as it may be written as patent instead of “patient”]
[0197]:
the first algorithm 150 comprises a mathematical model for the analysis of the data obtained through the weight meter 30 in order to correlate each weight measurement with the time instant in which it was performed and to calculate a rate hourly production of biological fluid normalized on the weight of the patient (weight/hour/patient's weight);
[BRI: normalizing biological fluid data by patient weight (e.g., weight/hour) is a valid and clinically useful practice in patient document systems. By normalization large patient’s fluid can be balanced and help identify abnormal fluid gains or losses more quickly, especially in critically ill patients where fluid overload or underload can rapidly change]
[0202]:
a mathematical model M-250 having as input the output of the adaptive mathematical model H-250, the present value and the past values of the weight measurements of the biological fluid container 20 and the physiological parameters present in the patient's electronic medical record 350, and having as output the risk level—ranging from 1 to 10—of worsening of the patient's health in 24/48 hours after the last weight measurement of the biological fluid container R(t){circumflex over ( )}.
Regarding claim 18: (Currently Amended)
ANCONA discloses:
- An information processing method executed by a processor of an information processing apparatus including at least one processor, the information processing method comprising
[Abstract]:
A monitoring system, and related monitoring and predicting methods of a diuresis for a calculation of a risk of onset of renal failure of a patient, including a device, wherein the device includes a first algorithm for recording, storing, comparing and processing measurements of a urine container and a second algorithm for predicting future measurements of the urine container,
[0230]:
The weight meter of the urine bag, having the functionalities described above
can have
[0230]:
a STM32L476JG processor mounted on the SensorTile module for the control and the management of the data collected by the sensor and their sending via low-power Bluetooth connection to the urine container;
- extracting a plurality of document data from a document data group;
[0142]:
data collection: continuous measurement of the weight of the hospitalized patient's urine bag,
[0143]:
the definition of the stage of progress of the kidney failure associated with a certain level of risk, and the processing of the patient's diuresis with machine-learning algorithms for the determination and implementation of a predictive model of the onset of acute kidney failure leading to the determination of accurate risk levels of onset of acute kidney failure; [0144]:
sending the data documents and risk levels to a smartphone application owned by the attending physician.
[0148]:
PNG
media_image1.png
526
455
media_image1.png
Greyscale
by means of a first algorithm 15, recording and storing the measurements of the urine container 2 (step 102);
[0150]:
by means of the first algorithm 15, comparing and processing the measurements of the urine container 2 and stored over time to determine a diuretic trend (step 104);
[0151]:
on the basis of the trend determined in the previous step, step 104, by means of a second algorithm 25 comprising an adaptive mathematical model H-25 and a machine-learning mathematical model M-25, predicting the values of future measurements of the urine container 2 and the risk of developing kidney failure (step 105);
[0152]:
transferring the data obtained in the previous step, step 105, to a videoterminal 7 (step 106).
- individually input each normalized document data into a machine learning model to acquire prediction result corresponding to each document data, wherein the machine Learning model is a prognosis prediction model;
[0010];
The diagnosis and timely treatment of AKI can improve the patient's clinical course and prognosis,
[0154]:
the first algorithm 15 comprises a mathematical model for the analysis of the data obtained through the weight meter 3 in order to correlate each weight measurement with the time instant in which it was performed and to calculate a rate of hourly urinary production normalized on the weight of the patient (weight/hour/patient's weight); subsequently, this normalized hourly urinary production rate is compared with the hourly production rate thresholds defined by the KDIGO and RIFLE guidelines for the definition of stages of acute kidney failure AKI;
[0151]:
on the basis of the trend determined in the previous step, step 104, by means of a second algorithm 25 comprising an adaptive mathematical model H-25 and a machine-learning mathematical model M-25, predicting the values of future measurements of the urine container 2 and the risk of developing kidney failure (step 105);
[0010]:
AKI results, therefore, a common, harmful, but potentially treatable condition, in which an acute reduction, even slight, in renal function has a negative effect on the patient's prognosis.
[BRI: A prognostic model is a predictive tool used to estimate the likelihood of a future clinical outcome for an individual, often based on patient-specific data such as demographics, medical history, lab results, and imaging. The “prognostic” label depends on the nature of the prediction, not just the architecture or feature extraction method]
- acquire prediction result output from the machine learning model.
[0106]:
the adaptive mathematical model H-25 comprises linear and non-linear regression models and machine-learning models, preferably artificial neural networks.
[0145]:
Furthermore, with reference to FIG. 2 that illustrates the preferred embodiment of the present invention, a diuresis monitoring method for predicting the risk of kidney failure of a patient constitutes an independent aspect usable independently with respect to the other aspects of the invention,
- derive an evaluation value in the machine learning model according to the acquired prediction result
[0028]:
A system and method capable of monitoring and predicting the diuresis and, more generally, biological fluid, would satisfy the requirements of numerous applications such as, for example, the assessment of the risk of kidney failure and, more generally, the evaluation the state of health of a patient,
[0242]:
The systems herein proposed allow, therefore, to combine the strong innovative value deriving from automation, precision and continuity of the collection of information and their ability to actively interact with the attending physician thanks to a system of data connectivity, to an easy-to-use, cost-efficient technology able to suit the environment of use.
[BRI: Providing an attending physician with timely, accurate, and easy-to-use access to patient data through a secure, cost-efficient, interoperable system can indeed represent a significant evaluation value in healthcare delivery]
- according to the acquired prediction result corresponding to each document data included in the document data group;
[0016]:
Several patent documents report systems that aim to monitor the patient's diuresis for the patient's best management in a hospital environment,
[0144]:
communication of processed data and patient risk levels to the attending physician; such communication, which has the purpose of allowing the doctor to know in real time the diuresis of the patient and the risk levels associated with it
[0144]:
sending the data documents and risk levels to a smartphone application owned by the attending physician.
[0148]:
by means of a first algorithm 15, recording and storing the measurements of the urine container 2 (step 102); [0149] repeating the previous steps, from step 100 to step 102, for a predetermined number of times (step 103); [0150] by means of the first algorithm 15, comparing and processing the measurements of the urine container 2 and stored over time to determine a diuretic trend (step 104);
[BRI: recording and storing the measurements of a urine container is considered document data in both clinical and regulatory contexts]
ANCONA does not explicitly disclose:
- normalize each document data according to a text length of the document data;
- perform at Least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value;
- specify a display order of the plurality of document data in the document data group; and
- initiate a screen displaying the plurality of document data in the specified display order.
However, COQUARD discloses.
- normalize each document data according to a text length of the document data;
[0011]:
In an embodiment, the method comprises parsing a first contract document to identify a plurality of clauses in the first contract document, each clause of the plurality of clauses comprising a sequence of words; generating a plurality of representation vectors based on the first contract document and at least one embedding model, wherein each representation vector of the plurality of representation vectors is generated based on a separate clause of at least a subset of clauses of the plurality of clauses; comparing each representation vector of the plurality of representation vectors with a second plurality of representation vectors stored in a vector database; and generating output data based on the representation vectors and the first contract document,
[0012]:
search contract documents to form one or more groups of contract documents by selecting a first contract document for the or each group and searching for other contract documents having a relevance score within a relevance threshold; determine a most recently revised contract document within the or each group and determining similarity score for each contract document in said group against the most recently revised contract document for the group;
[0109]:
the parameters identified in a processed contract document may be extracted and stored in at least one data structure. In some embodiments, a formatted contract document may be generated based on an unformatted input contract document such that the formatted document includes merge fields corresponding to the plurality of predetermined fields,
[0131]:
In some embodiments, the system may output common clauses from multiple contract documents. This may facilitate the review of multiple contracts by separately identifying clauses that can be reviewed together and/or match to a predetermined format,
[0139]:
Referring to FIG. 9, a contract document processing system according to another embodiment is shown. The system 2000 includes a parsing engine 1002, an authoring module 1004, a contracts database 1012, a search engine 1024, a first similarity score engine 1026A, a second similarity score engine 1026B, a difference engine 1028, a parameter extraction engine 100,
[0140]:
The parsing engine 1002 may be implemented as described with respect to the parsing engine 100 of FIG. 1 and may be arranged to parse contract documents 1000 to identify characters, words, sentences and clauses or any other ordered sequence of characters and which are stored in the contracts database 1012 and may be indexed or identified using a contract identifier for example. The contract documents 1000 may for example be PDF documents that require optical character recognition to identify characters and further processing to identify suitable ordered sequences of characters such as clauses. In another alternative, the contract documents may be text documents such as DOC files which contain text characters but require organization into suitable ordered sequences of characters such as clauses. The parsed contract documents may be stored in any suitable data-structure within the database and may be accessible using SQL queries for example. The contracts database may be any suitable database such as a text database, relational database, object-oriented database for example.
[BRI: embedding a sentence or document using a model that takes a sequence of word embeddings, the resulting sentence/document embedding inherently reflects its length, because the model processes a variable-length sequence of word vectors and aggregates them (e.g., via pooling) into a single vector. A sentence embedding is a fixed-length vector that captures the semantic meaning of an entire sentence]
- perform at least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value;
[0022]:
In an embodiment, the output data comprises the at least one data structure representing the plurality of parameters, the method further comprising: storing the output data as metadata associated with the first contract document; detecting a modification to the first contract document; and in response to detecting the modification, automatically updating the metadata associated with the first contract document based on the modification.
[0018]:
determine a most recently revised contract document within the or each group and determining similarity score for each contract document in said group against the most recently revised contract document for the group; remove contract documents from the or each group having a similarity score within a similarity threshold to form one or more respective filtered groups of contract documents; compare the contract documents of the or each filtered group to determine a template for said filtered group.
[0009]:
In an embodiment differences between the contract documents in a said filtered group and the template for the filtered group may be identified and stored or displayed to a user of the method. The template may comprise one or more clauses with the differences being displayed. Documents which are not grouped with another document may also be identified and displayed.
[0140]:
The parsing engine 1002 may be implemented as described with respect to the parsing engine 100 of FIG. 1 and may be arranged to parse contract documents 1000 to identify characters, words, sentences and clauses or any other ordered sequence of characters and which are stored in the contracts database 1012 and may be indexed or identified using a contract identifier,
[0088]:
As used herein, the term “graphical user interface” or “GUI” refers to a generated display with which a user may interact, either directly or indirectly (e.g., through a keyboard, mouse, touchscreen, and/or the like),
[0148]:
At 1104, the method selects a next ungrouped document. This may be derived from the already received search result and may be based on any suitable metric such as a next database index number. A relevance score between the two selected documents is also determined. This may be implemented by the relevance score engine 1026A, for example by determining a tf-idf value between the two selected documents,
[0152]:
The method may be arranged such that the relevance score is determined with respect to the first selected document and all other documents so that this may result in overlapping rather than exclusive groups of documents. The results of the comparisons may be ordered or sorted in descending order of relevance such that only those documents with a relevance score over the threshold are considered and added to the group so that those having a relevance score above the threshold are readily identified without having to proceed through all steps of the method for all documents. The group size may be limited, for example 5000 documents, so that only the most relevant documents are included.
- specify a display order of the plurality of document data in the document data group; and
[0140]:
The parsing engine 1002 may be implemented as described with respect to the parsing engine 100 of FIG. 1 and may be arranged to parse contract documents 1000 to identify characters, words, sentences and clauses or any other ordered sequence of characters and which are stored in the contracts database 1012 and may be indexed or identified using a contract identifier for example
[0088]:
As used herein, the term “graphical user interface” or “GUI” refers to a generated display with which a user may interact
[0137]:
Output component 912 may include a component that provides output information from device 900 (e.g., a display, a speaker, one or more light-emitting diodes (LEDs), etc.).
- initiate a screen displaying the plurality of document data in the specified display order.
[0088]:
As used herein, the term “graphical user interface” or “GUI” refers to a generated display with which a user may interact, either directly or indirectly (e.g., through a keyboard, mouse, touchscreen, and/or the like).
[0091]:
FIG. 1 depicts a system 1000 for processing contract documents according to an embodiment. The system 1000 includes a parsing engine 102, modeling engine 104, comparison engine 106, and parameter extraction engine 108. In some examples, the parsing engine 102, modeling engine 104, comparison engine 106, and parameter extraction engine 108 may all be functions or portions of a single software application. In other embodiments, one or more of the parsing engine 102, modeling engine 104, comparison engine 106, and parameter extraction engine 108 may be distributed and/or separate components, such as separate applications and/or computing devices. A contract document 100 may be input into the parsing engine 102 to be processed. In some examples, a front-end GUI (not shown in FIG. 1) may be used to select a contract document 100 from a local or network location and to input the contract document to the parsing engine 102. In some examples, an API may be used to communicate a contract document 100 to the parsing engine 102 for processing.
[BRI: the GUI’s role in this process is to present the arranged documents in windows, lists, or other visual components, and to provide the interactive elements (menus, buttons, scrollbars) that let the user navigate or modify the display. In a typical modern contract management system, a contract document is first input into a parsing engine for processing, and a front-end GUI can be used to display the parsed results in a specified order for user interaction. A Front-end GUI can then render this data in a controlled “display order” — for example, showing clauses in sequence, tables in their original layout, or key fields in a searchable list]
Claims 3-4, 6-9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over
Andrea ANCONA et al. (hereinafter ANCONA) US 2022/0095977 A1,
in view of Aurélien COQUARD et al. (hereinafter COQUARD)) US 2020/0327172 A1.
further in view of Omar Odibat et al. (hereinafter Odibat) US 2021/0248457 A1,
further in view of Weiguo Li et al. (hereinafter Li) US 2019/0370304 A1,
Regarding claim 3: (Original)
ANCONA does not explicitly disclose:
- wherein the processor is configured to: use each document data as input of the machine learning model to acquire document unit output data which is output for each document data.
However, COQUARD discloses:
- wherein the processor is configured to: use each document data as input of the machine learning model to acquire document unit output data which is output for each document data;
[0012]:
there is provided a system for processing a plurality of contract documents having different formats and clauses. The system comprises at least one processor programmed or configured to: search contract documents to form one or more groups of contract documents by selecting a first contract document for the or each group and searching for other contract documents having a relevance score within a relevance threshold; determine a most recently revised contract document within the or each group and determining similarity score for each contract document in said group against the most recently revised contract document for the group
[0095]:
The modeling engine 104 processes the clauses separately to generate a representation vector for each clause. A representation vector for a clause may be any number of dimensions and may be based on a sequence of word embeddings and/or a sequence of sentence embeddings. In examples, the modeling engine 104 employs an embedding model that is generated from processing textual documents including, but not limited to, a plurality of contract documents, news articles, webpages, and/or any other like text. The model may be a neural network that is trained from such training texts.
- and derive the evaluation value for each document data based on the document unit output data.
[0114]:
In some embodiments, the comparison of representation vectors may be evaluated based on an unsupervised metric that does not require any labels or ground truth data. For example, the metric may be a percentage of character matches based on a semantic differential. The metric may increase each time a closer (i.e., shorter distance) clause is found. Such a metric may be used to evaluate the quality of the embedding model and/or algorithms for parsing contract documents, classifying clauses, and/or the like,
[0024]:
In an embodiment, generating each representation vector comprises determining at least one sentence embedding in a corresponding clause based on the at least one embedding model, wherein each sentence embedding is based on a sequence of word embeddings.
[BRI: a “one sentence embedding” in a clause based on at least one embedding model, where each sentence embedding is derived from a sequence of word embeddings, is a standard NLP pattern. The model takes the word-level vectors, processes them as a sequence, and outputs a single vector that serves as the document unit for that sentence]
It would be obvious to one of ordinary skills in the art before the effective filing date of the present application to combine ANCONA and COQUARD.
ANCONA teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
COQUARD teaches normalization and display order.
One of ordinary skills would be motivated to combine ANCONA and COQUARD that provide a shorter distance as a performance metric (COQUARD [0114]).
Regarding claim 4: (Original)
ANCONA and COQUARD do not explicitly disclose:
- wherein the evaluation value has a correlation with the document unit output data.
However, Odibat discloses:
- wherein the evaluation value has a correlation with the document unit output data.
[0034]:
In an illustrated embodiment, an application for classifying digital assets receives input data that includes attribute data for cloud computing assets in the form of text and non-text data. A non-limiting example of input data includes data extracted from a bill or invoice or other data source for cloud assets computing that includes cost and usage information from one or more providers of cloud computing assets, as well as other data representative of various attribute information that can be mapped to a list of generic attribute columns, such as the following non-limiting example, which is included as an example only for clarity purposes:
PNG
media_image2.png
272
395
media_image2.png
Greyscale
[0023]:
The number of cloud computing assets in many organizations continues to grow, and for some organizations the number of assets is quickly growing to, or has already surpassed, a point where it is impractical for users to manually manage so many assets.
[0024]:
Management of digital assets is further complicated by the fact that organizations within many companies have the authority to independently provision and configure digital assets from multiple different providers. To further complicate things, each provider typically has a different and unique process for tagging and tracking digital assets; some provisioned assets are repurposed and reclassified as organizations shift their strategic focus; and new digital assets arise quickly because many cloud providers include automatic software installation and configuration as a standard part of system deployment.
[0025]:
the illustrative embodiments also recognize that a cognitive asset management system that provides accurate recognition and classification results would be useful for automating many tasks associated with the management of digital assets.
[0062]:
daata processing environment 100 may also take the form of a cloud, and employ a cloud computing model of service delivery for enabling convenient, on-demand network access to a shared pool of configurable computing resources (e.g. networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal management effort or interaction with a provider of the service.
[BRI: Asset management system data is a “document unit data”)
[0035]:
in an embodiment, the feature extraction module includes a deep learning model and a modified TF-IDF model for receiving text input data and standard feature engineering and aggregations for non-text input data. In an embodiment, the output from the feature extraction module includes a plurality of candidate features that are provided to a customizable feature selection module. In an embodiment, the customizable feature selection module ranks the candidate features in order of importance.
[0036]:
In an illustrated embodiment, a modified TF-IDF module creates an input document by merging text fields of assets tagged with a same class label (label-1) to form a single document D(label-1). In some such embodiments, the modified TF-IDF modules calculates scores for all terms in the document.
It would been obvious to one of ordinary skills in the art before the effective filing date of the present application to combine ANCONA, COQUARD and Odibat.
ANCONA teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
COQUARD teaches normalization and display order.
Odibat teaches evaluation value for each word.
One of ordinary skills would have been motivated to combine ANCONA, COQUARD and Odibat that uses a modified TF-IDF model 312 that has improved accuracy over prior TF-IDF models because it has been modified to be more closely associated with a desired context due to a revised input document created by the TF-IDF(Odibat [0081]).
Regarding claim 6: (Original)
ANCONA does not explicitly disclose:
- extract a plurality of word data from each document data included in the document data group;
However, COQUARD discloses:
- extract a plurality of word data from each document data included in the document data group;
[0011]:
the method comprises parsing a first contract document to identify a plurality of clauses in the first contract document, each clause of the plurality of clauses comprising a sequence of words; generating a plurality of representation vectors based on the first contract document and at least one embedding model, wherein each representation vector of the plurality of representation vectors is generated based on a separate clause of at least a subset of clauses of the plurality of clauses
ANCONA and COQUARD do not explosivity disclose:
- the evaluation value in the machine learning model as a word unit evaluation value for each word data;
- and derive the evaluation value according to a statistical value of the word unit evaluation value of the word data included in the document data for each document data.
However, Odibat discloses:
- the evaluation value in the machine learning model as a word unit evaluation value for each word data;
[0026]:
An illustrated embodiment includes a machine learning system that learns from the assets that a company has already tagged and then accurately predicts tagging information for the remaining untagged assets.
[0032]:
The illustrative embodiments further recognize that the use of a TF-IDF model makes it easier to understand how the occurrence of a specific word in a text field contributes to the asset being associated with a class label. However, accuracy is also a key goal, so the illustrative embodiments recognize that a modified TF-IDF is more accurate if it is more closely associated with a desired context by modifying the TF-IDF to re-define an input document to the TF-IDF. The illustrative embodiments also recognize that a modified TF-IDF is more accurate if the IDF component is revised to include term frequency information in place of a binary indication of a number of documents containing the term.
(BRI: TF-IDF represents a “word unit evaluation value”)
- and derive the evaluation value according to a statistical value of the word unit evaluation value of the word data included in the document data for each document data.
[0007]:
the embodiment also includes extracting a set of candidate features from the attribute data using a feature extraction module that evaluates the attribute data using first and second machine learning models, wherein the first machine learning model scores terms in the input document and outputs a first portion of the set of candidate features ranked according to the term scores, and wherein the second machine learning model includes a deep learning model and outputs a second portion of the set of candidate features ranked according to term probabilities
[0036]:
In an illustrated embodiment, a modified TF-IDF module creates an input document by merging text fields of assets tagged with a same class label (label-1) to form a single document D(label-1). In some such embodiments, the modified TF-IDF modules calculates scores for all terms in the document. In some such embodiments, the top N most important terms in the context of a class label are chosen based on the highest scores and are placed in a term list term_list(label-1
It would been obvious to one of ordinary skills in the art before the effective filing date of the present application to combine ANCONA, COQUARD and Odibat.
ANCONA teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
COQUARD teaches normalization and display order.
Odibat teaches evaluation value for each word.
One of ordinary skills would have been motivated to combine ANCONA, COQUARD and Odibat that uses a modified TF-IDF model 312 that has improved accuracy over prior TF-IDF models because it has been modified to be more closely associated with a desired context due to a revised input document created by the TF-IDF(Odibat [0081]).
Regarding claim 7: (Original)
ANCONA and COQUARD do not explicitly disclose:
wherein:
- and the processor is configured to use each combination data in which the first document data and the second document data are combined as input of the machine learning model to derive a second evaluation value from output data which is output for each combination data.
However, Odibat discloses:
wherein:
- and the processor is configured to use each combination data in which the first document data and the second document data are combined as input of the machine learning model to derive a second evaluation value from output data which is output for each combination data.
[0008]:
Another embodiment includes generating an input document that includes a plurality of text fields of attribute data associated with a group of cloud computing assets having a specified label for a specified class. The embodiment also includes extracting a set of candidate features from the attribute data using a feature extraction module that evaluates the attribute data using first and second machine learning models that output respective first and second portions of the set of candidate features having respective candidate feature values
It would been obvious to one of ordinary skills in the art before the effective filing date of the present application to combine ANCONA, COQUARD and Odibat.
ANCONA teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
COQUARD teaches normalization and display order.
Odibat teaches evaluation value for each word.
One of ordinary skills would have been motivated to combine ANCONA, COQUARD and Odibat that uses a modified TF-IDF model 312 that has improved accuracy over prior TF-IDF models because it has been modified to be more closely associated with a desired context due to a revised input document created by the TF-IDF(Odibat [0081]).
ANCONA, COQUAR and Odibat do not explicitly disclose:
- the document data having a greatest first evaluation value, which is derived for each document data, is used as first document data, and each of the plurality of document data other than the first document data included in the document data group is used as second document data,
However, Li discloses:
- the document data having a greatest first evaluation value, which is derived for each document data, is used as first document data, and each of the plurality of document data other than the first document data included in the document data group is used as second document data,
[0013]:
In a feasible embodiment, the obtaining, by the server, a ranking effect evaluation value of the target document ranking list includes evaluating, by the server, a ranking effect of the target document ranking list based on a user behavior, and obtaining the ranking effect evaluation value.
[0014]:
In a feasible embodiment, the obtaining, by the server, a ranking effect evaluation value of the target document ranking list further includes using, by the server as the ranking effect evaluation value, a value provided by the user after the user evaluates a ranking effect of the target document ranking list.
[0012]:
In a feasible embodiment, the ranking, by the server, the M documents based on a ranking model to obtain a target document ranking list includes scoring, by the server, a correlation between each of the M documents and the historical search word based on the ranking model to obtain a scoring result; and ranking, by the server, the M documents in ascending order or descending order of the scoring results to obtain the target document ranking list.
[0053]:
The server ranks the M documents in ascending order or descending order of the scoring results to obtain the document ranking list.
[0055] :
Scoring results obtained by the server by scoring occurrence frequency of the historical search word in all of the M documents based on the ranking model f (q, d, θ) may be represented by a set (d.sub.1′, d.sub.2′ , . . . , d.sub.M′), and the target document ranking list obtained by the server by ranking the M documents in ascending order or descending order of the scoring results may be represented by a set (y.sub.1, y.sub.2, . . . , y.sub.M).
[0056]:
Further, the foregoing process can be represented by σ=(y.sub.1, y.sub.2, . . . , y.sub.M)=sort (d.sub.1, d.sub.2, . . . , d.sub.M). The sort function is a descending-order ranking model or an ascending-order ranking model.
It would have been obvious to one of ordinary skills in the art before the effective filing date of the present application to combine ANCONA, COQUARD, Odibat and Li.
ANCONA teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
COQUARD teaches normalization and display order.
Odibat teaches evaluation value for each word.
Li teaches the largest evaluation value.
One ordinary skill would be motivated to combine ANCONA, COQUARD, Odibat and Li that can improve the user satisfaction of ranking result of the document (Li [0011]).
Regarding claim 8: (Original)
ANCONA, COQUARD and Odibat do not explicitly disclose:
wherein the processor is configured to:
- give a first display priority to the first document data;
- and give a second display priority, which is lower than the first display priority, to the second document data based on the second evaluation value.
However, Li discloses:
wherein the processor is configured to:
- give a first display priority to the first document data;
[0008]:
receiving, by a server, a search word entered by a user; obtaining, by the server, N documents matching the search word, wherein N is a natural number; ranking, by the server, the N documents by using a ranking model to obtain a document ranking list,
[0008]:
one or more historical documents corresponding to the historical search word, and a document ranking list and a ranking effect evaluation value that are corresponding to the historical search word; and displaying, by the server, the document ranking list to the user.
[0012]:
In a feasible embodiment, the ranking, by the server, the M documents based on a ranking model to obtain a target document ranking list includes scoring, by the server, a correlation between each of the M documents and the historical search word based on the ranking model to obtain a scoring result; and ranking, by the server, the M documents in ascending order or descending order of the scoring results to obtain the target document ranking list.
[0008]:
and displaying, by the server, the document ranking list to the user.
- and give a second display priority, which is lower than the first display priority, to the second document data based on the second evaluation value.
[0008]:
receiving, by a server, a search word entered by a user; obtaining, by the server, N documents matching the search word, wherein N is a natural number; ranking, by the server, the N documents by using a ranking model to obtain a document ranking list,
[0012]:
In a feasible embodiment, the ranking, by the server, the M documents based on a ranking model to obtain a target document ranking list includes scoring, by the server, a correlation between each of the M documents and the historical search word based on the ranking model to obtain a scoring result; and ranking, by the server, the M documents in ascending order or descending order of the scoring results to obtain the target document ranking list.
[0008]:
and displaying, by the server, the document ranking list to the user.
- and give a second display priority, which is lower than the first display priority, to the second document data based on the second evaluation value.
[0008]:
receiving, by a server, a search word entered by a user; obtaining, by the server, N documents matching the search word, wherein N is a natural number; ranking, by the server, the N documents by using a ranking model to obtain a document ranking list,
[0012]:
In a feasible embodiment, the ranking, by the server, the M documents based on a ranking model to obtain a target document ranking list includes scoring, by the server, a correlation between each of the M documents and the historical search word based on the ranking model to obtain a scoring result; and ranking, by the server, the M documents in ascending order or descending order of the scoring results to obtain the target document ranking list.
[0008]:
and displaying, by the server, the document ranking list to the user.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine ANCONA, CONQUAD, Odibat and Li.
ANCONA teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
COQUARD teaches normalization and display order.
Odibat teaches evaluation value for each word.
Li teaches the largest evaluation value.
One of ordinary skill would be motivated to combine ANCONA, COQUARD, Odibat and Li that can improve the user satisfaction of ranking result of the document (Li [0011]).
Regarding claim 9: (Original)
ANCONA does not explicitly disclose:
- extract a plurality of word data from each document data included in the document data group;
However, COQUARD discloses:
- extract a plurality of word data from each document data included in the document data group;
[0011]:
the method comprises parsing a first contract document to identify a plurality of clauses in the first contract document, each clause of the plurality of clauses comprising a sequence of words; generating a plurality of representation vectors based on the first contract document and at least one embedding model, wherein each representation vector of the plurality of representation vectors is generated based on a separate clause of at least a subset of clauses of the plurality of clauses
ANCONA and COQUARD do not explosivity disclose:
- the evaluation value in the machine learning model as a word unit evaluation value for each word data;
- and derive the evaluation value according to a statistical value of the word unit evaluation value of the word data included in the document data for each document data.
However, Odibat discloses:
- the evaluation value in the machine learning model as a word unit evaluation value for each word data;
[0026]:
An illustrated embodiment includes a machine learning system that learns from the assets that a company has already tagged and then accurately predicts tagging information for the remaining untagged assets.
[0032]:
The illustrative embodiments further recognize that the use of a TF-IDF model makes it easier to understand how the occurrence of a specific word in a text field contributes to the asset being associated with a class label. However, accuracy is also a key goal, so the illustrative embodiments recognize that a modified TF-IDF is more accurate if it is more closely associated with a desired context by modifying the TF-IDF to re-define an input document to the TF-IDF. The illustrative embodiments also recognize that a modified TF-IDF is more accurate if the IDF component is revised to include term frequency information in place of a binary indication of a number of documents containing the term.
[BRI: TF-IDF represents a “word unit evaluation value”)
- and derive the evaluation value according to a statistical value of the word unit evaluation value of the word data included in the document data for each document data.
[0007]:
the embodiment also includes extracting a set of candidate features from the attribute data using a feature extraction module that evaluates the attribute data using first and second machine learning models, wherein the first machine learning model scores terms in the input document and outputs a first portion of the set of candidate features ranked according to the term scores, and wherein the second machine learning model includes a deep learning model and outputs a second portion of the set of candidate features ranked according to term probabilities
[0036]:
In an illustrated embodiment, a modified TF-IDF module creates an input document by merging text fields of assets tagged with a same class label (label-1) to form a single document D(label-1). In some such embodiments, the modified TF-IDF modules calculates scores for all terms in the document. In some such embodiments, the top N most important terms in the context of a class label are chosen based on the highest scores and are placed in a term list term_list(label-1
It would been obvious to one of ordinary skills in the art before the effective filing date of the present application to combine ANCONA, COQUARD and Odibat.
ANCONA teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
COQUARD teaches normalization and display order.
Odibat teaches evaluation value for each word.
One of ordinary skills would have been motivated to combine ANCONA, COQUARD and Odibat that uses a modified TF-IDF model 312 that has improved accuracy over prior TF-IDF models because it has been modified to be more closely associated with a desired context due to a revised input document created by the TF-IDF(Odibat [0081]).
Regarding claim 19: (Original)
ANCONA and COQUARD do not explicitly disclose:
- A non-transitory computer-readable medium storing an information processing program that is executable by the processor included in the information processing device to perform the information processing method according to claim 18.
However, Odibat discloses:
- A non-transitory computer-readable medium storing an information processing program that is executable by the processor included in the information processing device to perform the information processing method according to claim 18.
[0111];
It would been obvious to one of ordinary skills in the art before the effective filing date of the present application to combine ANCONA, COQUARD and Odibat.
ANCONA teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
COQUARD teaches normalization and display order.
Odibat teaches evaluation value for each word.
One of ordinary skills would have been motivated to combine ANCONA, COQUARD and Odibat that uses a modified TF-IDF model 312 that has improved accuracy over prior TF-IDF models because it has been modified to be more closely associated with a desired context due to a revised input document created by the TF-IDF(Odibat [0081]).
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over
Andrea ANCONA et al. (hereinafter ANCONA) US 2022/0095977 A1,
in view of Aurélien COQUARD et al. (hereinafter COQUARD)) US 2020/0327172 A1,
in view of Alex Londeree et al. (hereinafter Londer) US 2023/0134791 A1.
Regarding claim 17: (Currently Amended)
ANCONA discloses:
- An information processing apparatus comprising: at least one processor, wherein the processor is configured to: for a machine learning model that uses a document data group including a plurality of document data as input and outputs output data,
[0142]:
data collection: continuous measurement of the weight of the hospitalized patient's urine bag,
[0143]:
the definition of the stage of progress of the kidney failure associated with a certain level of risk, and the processing of the patient's diuresis with machine-learning algorithms for the determination and implementation of a predictive model of the onset of acute kidney failure leading to the determination of accurate risk levels of onset of acute kidney failure; [0144]:
sending the data documents and risk levels to a smartphone application owned by the attending physician.
[0148]:
PNG
media_image1.png
526
455
media_image1.png
Greyscale
by means of a first algorithm 15, recording and storing the measurements of the urine container 2 (step 102);
[0150]:
by means of the first algorithm 15, comparing and processing the measurements of the urine container 2 and stored over time to determine a diuretic trend (step 104);
[0151]:
on the basis of the trend determined in the previous step, step 104, by means of a second algorithm 25 comprising an adaptive mathematical model H-25 and a machine-learning mathematical model M-25, predicting the values of future measurements of the urine container 2 and the risk of developing kidney failure (step 105);
[0152]:
transferring the data obtained in the previous step, step 105, to a videoterminal 7 (step 106).
- individually input each normalized document data into a machine learning model to acquire prediction result corresponding to each document data, wherein the machine Learning model is a prognosis prediction model;
[0010];
The diagnosis and timely treatment of AKI can improve the patient's clinical course and prognosis,
[0154]:
the first algorithm 15 comprises a mathematical model for the analysis of the data obtained through the weight meter 3 in order to correlate each weight measurement with the time instant in which it was performed and to calculate a rate of hourly urinary production normalized on the weight of the patient (weight/hour/patient's weight); subsequently, this normalized hourly urinary production rate is compared with the hourly production rate thresholds defined by the KDIGO and RIFLE guidelines for the definition of stages of acute kidney failure AKI;
[0151]:
on the basis of the trend determined in the previous step, step 104, by means of a second algorithm 25 comprising an adaptive mathematical model H-25 and a machine-learning mathematical model M-25, predicting the values of future measurements of the urine container 2 and the risk of developing kidney failure (step 105);
[0010]:
AKI results, therefore, a common, harmful, but potentially treatable condition, in which an acute reduction, even slight, in renal function has a negative effect on the patient's prognosis.
[BRI: A prognostic model is a predictive tool used to estimate the likelihood of a future clinical outcome for an individual, often based on patient-specific data such as demographics, medical history, lab results, and imaging. The “prognostic” label depends on the nature of the prediction, not just the architecture or feature extraction method]
- acquire prediction result output from the machine learning model.
[0106]:
the adaptive mathematical model H-25 comprises linear and non-linear regression models and machine-learning models, preferably artificial neural networks.
[0145]:
Furthermore, with reference to FIG. 2 that illustrates the preferred embodiment of the present invention, a diuresis monitoring method for predicting the risk of kidney failure of a patient constitutes an independent aspect usable independently with respect to the other aspects of the invention,
- derive an evaluation value in the machine learning model according to the acquired prediction result
[0028]:
A system and method capable of monitoring and predicting the diuresis and, more generally, biological fluid, would satisfy the requirements of numerous applications such as, for example, the assessment of the risk of kidney failure and, more generally, the evaluation the state of health of a patient,
[0242]:
The systems herein proposed allow, therefore, to combine the strong innovative value deriving from automation, precision and continuity of the collection of information and their ability to actively interact with the attending physician thanks to a system of data connectivity, to an easy-to-use, cost-efficient technology able to suit the environment of use.
[BRI: Providing an attending physician with timely, accurate, and easy-to-use access to patient data through a secure, cost-efficient, interoperable system can indeed represent a significant evaluation value in healthcare delivery]
- according to the acquired prediction result corresponding to each document data included in the document data group;
[0016]:
Several patent documents report systems that aim to monitor the patient's diuresis for the patient's best management in a hospital environment,
[0144]:
communication of processed data and patient risk levels to the attending physician; such communication, which has the purpose of allowing the doctor to know in real time the diuresis of the patient and the risk levels associated with it
[0144]:
sending the data documents and risk levels to a smartphone application owned by the attending physician.
[0148]:
by means of a first algorithm 15, recording and storing the measurements of the urine container 2 (step 102); [0149] repeating the previous steps, from step 100 to step 102, for a predetermined number of times (step 103); [0150] by means of the first algorithm 15, comparing and processing the measurements of the urine container 2 and stored over time to determine a diuretic trend (step 104);
[BRI: recording and storing the measurements of a urine container is considered document data in both clinical and regulatory contexts]
ANCONA does not explicitly disclose:
- normalize each document data according to a text length of the document data;
- perform at Least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value;
- specify a display order of the plurality of document data in the document data group; and
- initiate a screen displaying the plurality of document data in the specified display order.
However, COQUARD discloses.
- normalize each document data according to a text length of the document data;
[0011]:
In an embodiment, the method comprises parsing a first contract document to identify a plurality of clauses in the first contract document, each clause of the plurality of clauses comprising a sequence of words; generating a plurality of representation vectors based on the first contract document and at least one embedding model, wherein each representation vector of the plurality of representation vectors is generated based on a separate clause of at least a subset of clauses of the plurality of clauses; comparing each representation vector of the plurality of representation vectors with a second plurality of representation vectors stored in a vector database; and generating output data based on the representation vectors and the first contract document,
[0012]:
search contract documents to form one or more groups of contract documents by selecting a first contract document for the or each group and searching for other contract documents having a relevance score within a relevance threshold; determine a most recently revised contract document within the or each group and determining similarity score for each contract document in said group against the most recently revised contract document for the group;
[0109]:
the parameters identified in a processed contract document may be extracted and stored in at least one data structure. In some embodiments, a formatted contract document may be generated based on an unformatted input contract document such that the formatted document includes merge fields corresponding to the plurality of predetermined fields,
[0131]:
In some embodiments, the system may output common clauses from multiple contract documents. This may facilitate the review of multiple contracts by separately identifying clauses that can be reviewed together and/or match to a predetermined format,
[0139]:
Referring to FIG. 9, a contract document processing system according to another embodiment is shown. The system 2000 includes a parsing engine 1002, an authoring module 1004, a contracts database 1012, a search engine 1024, a first similarity score engine 1026A, a second similarity score engine 1026B, a difference engine 1028, a parameter extraction engine 100,
[0140]:
The parsing engine 1002 may be implemented as described with respect to the parsing engine 100 of FIG. 1 and may be arranged to parse contract documents 1000 to identify characters, words, sentences and clauses or any other ordered sequence of characters and which are stored in the contracts database 1012 and may be indexed or identified using a contract identifier for example. The contract documents 1000 may for example be PDF documents that require optical character recognition to identify characters and further processing to identify suitable ordered sequences of characters such as clauses. In another alternative, the contract documents may be text documents such as DOC files which contain text characters but require organization into suitable ordered sequences of characters such as clauses. The parsed contract documents may be stored in any suitable data-structure within the database and may be accessible using SQL queries for example. The contracts database may be any suitable database such as a text database, relational database, object-oriented database for example.
[BRI: embedding a sentence or document using a model that takes a sequence of word embeddings, the resulting sentence/document embedding inherently reflects its length, because the model processes a variable-length sequence of word vectors and aggregates them (e.g., via pooling) into a single vector. A sentence embedding is a fixed-length vector that captures the semantic meaning of an entire sentence]
- perform at least one of specification of the document data, which is a display target, from the document data group and specification of a display order of a document according to the document data based on the derived evaluation value;
[0022]:
In an embodiment, the output data comprises the at least one data structure representing the plurality of parameters, the method further comprising: storing the output data as metadata associated with the first contract document; detecting a modification to the first contract document; and in response to detecting the modification, automatically updating the metadata associated with the first contract document based on the modification.
[0018]:
determine a most recently revised contract document within the or each group and determining similarity score for each contract document in said group against the most recently revised contract document for the group; remove contract documents from the or each group having a similarity score within a similarity threshold to form one or more respective filtered groups of contract documents; compare the contract documents of the or each filtered group to determine a template for said filtered group.
[0009]:
In an embodiment differences between the contract documents in a said filtered group and the template for the filtered group may be identified and stored or displayed to a user of the method. The template may comprise one or more clauses with the differences being displayed. Documents which are not grouped with another document may also be identified and displayed.
[0140]:
The parsing engine 1002 may be implemented as described with respect to the parsing engine 100 of FIG. 1 and may be arranged to parse contract documents 1000 to identify characters, words, sentences and clauses or any other ordered sequence of characters and which are stored in the contracts database 1012 and may be indexed or identified using a contract identifier,
[0088]:
As used herein, the term “graphical user interface” or “GUI” refers to a generated display with which a user may interact, either directly or indirectly (e.g., through a keyboard, mouse, touchscreen, and/or the like),
[0148]:
At 1104, the method selects a next ungrouped document. This may be derived from the already received search result and may be based on any suitable metric such as a next database index number. A relevance score between the two selected documents is also determined. This may be implemented by the relevance score engine 1026A, for example by determining a tf-idf value between the two selected documents,
[0152]:
The method may be arranged such that the relevance score is determined with respect to the first selected document and all other documents so that this may result in overlapping rather than exclusive groups of documents. The results of the comparisons may be ordered or sorted in descending order of relevance such that only those documents with a relevance score over the threshold are considered and added to the group so that those having a relevance score above the threshold are readily identified without having to proceed through all steps of the method for all documents. The group size may be limited, for example 5000 documents, so that only the most relevant documents are included.
[BRI: “perform at least one of specification of the document data, which is a display target” refers to a requirement that a system, product, or service must meet one or more specified performance criteria from a defined set of “document data” items, where at least one of those items is designated as a display target. A relevance score is indeed a performance criterion used to determine how relevant a document is to a given query, and it directly influences whether and how a document is displayed in search results.
The contract documents in a templated filtered group are identified and stored with metadata, and the display order is determined by the metadata (and any derived evaluation values) rather than the raw document text. This approach enables efficient, automated, and role-specific views of contracts without manually opening each file and the derived evaluation value you mention could be a calculated or prioritized field (e.g., “high priority” if the contract expires in the next 30 days) that influences the display order]
- specify a display order of the plurality of document data in the document data group; and
[0140]:
The parsing engine 1002 may be implemented as described with respect to the parsing engine 100 of FIG. 1 and may be arranged to parse contract documents 1000 to identify characters, words, sentences and clauses or any other ordered sequence of characters and which are stored in the contracts database 1012 and may be indexed or identified using a contract identifier for example
[0088]:
As used herein, the term “graphical user interface” or “GUI” refers to a generated display with which a user may interact
[0137]:
Output component 912 may include a component that provides output information from device 900 (e.g., a display, a speaker, one or more light-emitting diodes (LEDs), etc.).
[BRI: Parse contract document systems can indeed identify and store any ordered sequence of characters from contracts, index them with contract identifiers, and display them in the original document order using the output component]
- initiate a screen displaying the plurality of document data in the specified display order.
[0088]:
As used herein, the term “graphical user interface” or “GUI” refers to a generated display with which a user may interact, either directly or indirectly (e.g., through a keyboard, mouse, touchscreen, and/or the like).
[0091]:
FIG. 1 depicts a system 1000 for processing contract documents according to an embodiment. The system 1000 includes a parsing engine 102, modeling engine 104, comparison engine 106, and parameter extraction engine 108. In some examples, the parsing engine 102, modeling engine 104, comparison engine 106, and parameter extraction engine 108 may all be functions or portions of a single software application. In other embodiments, one or more of the parsing engine 102, modeling engine 104, comparison engine 106, and parameter extraction engine 108 may be distributed and/or separate components, such as separate applications and/or computing devices. A contract document 100 may be input into the parsing engine 102 to be processed. In some examples, a front-end GUI (not shown in FIG. 1) may be used to select a contract document 100 from a local or network location and to input the contract document to the parsing engine 102. In some examples, an API may be used to communicate a contract document 100 to the parsing engine 102 for processing.
[BRI: the GUI’s role in this process is to present the arranged documents in windows, lists, or other visual components, and to provide the interactive elements (menus, buttons, scrollbars) that let the user navigate or modify the display. In a typical modern contract management system, a contract document is first input into a parsing engine for processing, and a front-end GUI can be used to display the parsed results in a specified order for user interaction. A Front-end GUI can then render this data in a controlled “display order” — for example, showing clauses in sequence, tables in their original layout, or key fields in a searchable list]
It would be obvious to one of ordinary skills in the art before the effective filing date of the present application to combine ANCONA and COQUARD.
ANCONA teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
COQUARD teaches normalization and display order.
One of ordinary skills would be motivated to combine ANCONA and COQUARD that provide a shorter distance as a performance metric (COQUARD [0114]).
ANCONA, and COQUARD do not explicitly disclose:
- calculate, for a part of the document data for training from the document data group for training, a loss function representing a degree of difference between correct answer data and the output data for each document data for training based on the output data obtained for each document data for training and the correct answer data; and update the machine learning model based on the loss function.
However, Londer discloses:
- calculate, for a part of the document data for training from the document data group for training, a loss function representing a degree of difference between correct answer data and the output data for each document data for training based on the output data obtained for each document data for training and the correct answer data;
[0045]:
the retriever engine 205 may be configured to update the query encoding model and the document encoding model using a match loss function that generates a match loss function result based on the query and the matching sub-documents. A loss function may be described generally as a function that computes the distance between the current output of an operation and the expected output. In accordance with various embodiments of the inventive concept, the reader loss function and/or the match loss function may comprise a regression loss function or a classification loss function.
- and update the machine learning model based on the loss function.
[0034]:
the query encoding model and the document encoding model may be updated using a match loss function result between the query and the matching sub-documents.
[0045]:
reader loss function may be applied to identify the matching sub-document having the lowest reader loss function result. This identified matching sub-document may then be associated with a truth label for the query and the AI reader engine 230 may be updated based on the reader loss function results associated with the matching sub-documents
It would been obvious to one of ordinary skills in the art before the effective filing date of the present application to combine ANCONA, COQUARD and Londer.
ANCOO teaches machine learning based document processing providing an evaluation value for the plurality of the documents.
Londer teaches loss function.
One of ordinary skill would be motivated to combine ANCONA, COQUARD and Londer that can improve the accuracy of the inference or answer generated (Londer [0047]).
Claims 10-11, 13-16, and 20-21 are rejected under 35 103 as being unpatentable over
Alex Londeree et al. (hereinafter Londer) US 2023/0134791 A1,
in view of Craig Schmugar et al. (hereinafter Schmugar) US 2022/0131896 A1.
Regarding claim 10: (Currently Amended)
Londer discloses:
- A learning apparatus of a machine learning model that uses a plurality of document data as input and outputs output data, the learning apparatus comprising:
[0060]:
The data processing apparatus described herein with respect to FIGS. 1 - 8 may be used to facilitate operation of a QA system that provides document level inference according to some embodiments of the inventive concept described herein. These apparatus may be embodied as one or more enterprise, application, personal, pervasive and/or embedded computer systems and/or apparatus that are operable to receive, transmit, process and store data
[0045] :
The retriever engine 205 is further configured to encode both the query and the sub-documents. In some embodiments, the retriever engine 205 may use a vector space model to encode the query and/or the sub-documents
[0044]:
the retriever engine 205 may be configured to divide the document in the knowledge base 210 into a plurality of sub-documents, which may be indexed based on a suitable categorization indicium.
[0045]:
classification involves prediction of an output from a set of finite categorical values.
- at least one processor, wherein the processor is configured to: use, for a plurality of document data for training, each document data for training as input of the machine learning model to acquire output data which is output for each document data for training;
[0044]:
During training, the retriever engine 205 may be configured to discard a current knowledge base or corpus and select a new knowledge base or corpus 215 that may include one or more of the plurality of sub-documents.
[0045]:
During training, the reader engine 230 may be configured to generate an inference about the answer to the query based on each of the matching sub-documents that are concatenated with the query.
- calculate, for a part of the document data for training from the plurality of document data for training, a loss function representing a degree of difference between correct answer data and the output data for each document data for training based on the output data obtained for each document data for training and the correct answer data;
[0045]:
the retriever engine 205 may be configured to update the query encoding model and the document encoding model using a match loss function that generates a match loss function result based on the query and the matching sub-documents. A loss function may be described generally as a function that computes the distance between the current output of an operation and the expected output. In accordance with various embodiments of the inventive concept, the reader loss function and/or the match loss function may comprise a regression loss function or a classification loss function.
[BRI: the distance is the degree of similarity]
- and update the machine learning model based on the loss function.
[0034]:
the query encoding model and the document encoding model may be updated using a match loss function result between the query and the matching sub-documents.
[0045]:
reader loss function may be applied to identify the matching sub-document having the lowest reader loss function result. This identified matching sub-document may then be associated with a truth label for the query and the AI reader engine 230 may be updated based on the reader loss function results associated with the matching sub-documents.
- calculate, also for another document data for training other than the part of document data for training,
[0012]:
In some embodiments of the inventive concept, a method comprises: discarding a current knowledge corpus; selecting a new knowledge corpus; performing operations as follows using an Artificial Intelligence (AI) retriever engine: dividing the new knowledge corpus into a plurality of sub-documents; encoding a query for the plurality of sub-documents using a query encoding model; encoding each of the plurality of sub-documents using a document encoding model; and determining one matching sub-document of the plurality of sub-documents that is a best match for containing an answer to the query based on the encoded query and each of the plurality of encoded sub-documents; performing operations as follows using an AI reader engine: generating an inference about the answer to the query based on a concatenation of the one matching sub-document with the query.
[BRI: the new knowledge training does represent other document training]
Londer does not explicitly disclose:
- the loss function with a weight smaller than a weight of the loss function calculated for the part of document data for training for each data for training;
- and update the machine learning model based also on the loss function of the other document data for training.
However, Schmugar discloses:
- the loss function with a weight smaller than a weight of the part of document data for training for each data for training;
[0028]:
within an industry consortium, it may be expected to share certain enterprise data across the consortium. However, it may be more common to share the enterprise data in a static format such as portable document format (PDF) or a tagged image file (TIF), rather than in a native electronic format such as a Microsoft Office document, or other native binary data.
[0267]:
A common method for refining values includes “gradient descent” and “back-propagation.” An illustrative gradient descent method includes computing a “cost” function, which measures the error in the network.
[0267]:
Each training example will have its own computed cost. Initially, the cost function is very large, because the network doesn't know how to classify objects. As the network is trained and refined, the cost function value is expected to get smaller, as the weights and biases are adjusted toward more useful values.
[BRI: smaller weight means that a loss function has given more importance to certain data points during training, which may require a weighted loss function. This modifies the standard loss by multiplying each term by a class weight or sample weight]
- and update the machine learning model based also on the loss function of the other document data for training.
[0283]:
Individual cost functions can be computed for each training input, and the total cost function for the network can be computed as an average of the individual cost functions.
[0284]:
In block 1420, the network may then compute a negative gradient of this cost function to seek a local minimum value of the cost function, or in other words, the error. For example, the system may use back-propagation to seek a negative gradient numerically. After computing the negative gradient, the network may adjust parameters (weights and biases) by some amount in the “downward” direction of the negative gradient.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Londer and Schmugar.
Londer teaches training of the document data for training from the plurality of document and generating a loss function representing a degree of difference between correct answers.
Schmugar teaches the loss function with a smaller weight (optimized weight)
One of ordinary skills would be motivated to combine Odibat and Schmugar that can adjust the slope of the cost function (Schmugar [0271]).
Regarding claim 11: (Original)
Londer discloses:
- wherein the processor is configured to extract the part of document data for training based on a degree of similarity between the output data and the correct answer data
[0039] :
According to some embodiments of the inventive concept, a QA system may be provided to assist entities, such as providers, payors, researchers, and others to perform queries using patient health care records as a knowledge base or corpus. The QA system may include a health care facility interface server 130, which includes an EMR interface system module 135 to facilitate the transfer of information between the EMR system 120, which the providers use to manage patient charts and records and issue orders
[0039]:
The QA system server 140 along with the QA engine module 145 may be configured to embody an AI driven retriever engine and reader engine for generating inferences in response to one or more queries using a knowledge base or corpus that may be based on the patient records and/or other health care or medical information.
[0045]:
the retriever engine 205 may be configured to update the query encoding model and the document encoding model using a match loss function that generates a match loss function result based on the query and the matching sub-documents. A loss function may be described generally as a function that computes the distance between the current output of an operation and the expected output
(BRI: the QA system is a part of the document data to manages the patient charts to ensure completeness and accuracy of data)
Regarding claim 13: (Original)
Londer discloses:
- wherein the processor is configured to calculate, for the part of document data for training, the loss function by performing weighting based on the output data obtained for each document data for training and the correct answer data.
[0045]:
A vector space model is an algebraic model for representing text documents as vectors of identifiers. Each vector dimension corresponds to a separate term. If a term occurs in the document, its value in the vector is non-zero. There are multiple ways to compute the term values including using a Term Frequency-Inverse Document Frequency (TF-IDF) weighting scheme. TF-IDF is a numerical statistic that is designed to reflect how important a word is to a document in a collection or corpus
Regarding claim 14: (Original)
Londer discloses:
- wherein the processor is configured to set weighting to be larger as a degree of similarity between the output data and the correct answer data is higher.
[0035]:
A query is received and the retriever engine encodes both the query and the sub-documents. The retriever engine determines a sub-document that is a best match for containing the answer to the query using, for example, a match loss function. The query and the matching sub-document are concatenated and communicated to the reader engine, which generates an inference about the answer to the query based on the concatenated matching sub-document and query.
[0045]:
The retriever engine 205 is further configured to encode both the query and the sub-documents.
[0045]:
A loss function may be described generally as a function that computes the distance between the current output of an operation and the expected output
[0045]:
There are multiple ways to compute the term values including using a Term Frequency-Inverse Document Frequency (TF-IDF) weighting scheme. TF-IDF is a numerical statistic that is designed to reflect how important a word is to a document in a collection or corpus
[0045]:
During training, the reader engine 230 may be configured to generate an inference about the answer to the query based on each of the matching sub-documents that are concatenated with the query. A reader loss function may be applied to identify the matching sub-document having the lowest reader loss function result. This identified matching sub-document may then be associated with a truth label for the query and the AI reader engine 230 may be updated based on the reader loss function results associated with the matching sub-documents. Similarly, the retriever engine 205 may be configured to update the query encoding model and the document encoding model using a match loss function that generates a match loss function result based on the query and the matching sub-documents.
[0045]:
A loss function may be described generally as a function that computes the distance between the current output of an operation and the expected output. In accordance with various embodiments of the inventive concept, the reader loss function and/or the match loss function may comprise a regression loss function or a classification loss function. Broadly described, classification involves prediction of an output from a set of finite categorical values. Regression involves prediction of a continuous value from other information.
Regarding claim 15: (Original)
Londer discloses:
wherein the processor is configured to:
- repeatedly update the machine learning model based on the loss function obtained from the part of document data for training;
[0034]:
Some embodiments of the inventive concept differ from conventional QA systems that are trained using a single large knowledge base or corpus dataset to make inferences in that each training iteration and each inference replaces the previous knowledge base or corpus with a unique document.
[0034]:
1) the knowledge base or corpus used in the health care or medical field may be very large making training of the underlying AI system powering the QA system difficult; and 2) the knowledge base or corpus used in the health care or medical field may be populated with patient records,
[0034]:
the QA system according to embodiments of the inventive concept may use a retriever engine-reader engine architecture in which the retriever engine discards a current knowledge base or corpus, selects a new knowledge base or corpus, which is divided into multiple sub-documents. During training mode, both a query and the sub-documents may be encoded and one or more matching sub-documents may be determined based on the encoded query and sub-documents using the retriever engine. The matching sub-documents are each concatenated with the query and communicated to the reader engine, which generates an inference about the answer to the query based on each of these sub-documents that are concatenated with the query. A reader loss function is applied to identify the matching sub-document having the lowest reader loss function result.
[0034]:
the query encoding model and the document encoding model may be updated using a match loss function result between the query and the matching sub-documents.
- and change the number of the part of document data for training to be extracted, according to the number of updates of the machine learning model.
[0044]:
select a new knowledge base or corpus 215 that may include one or more of the plurality of sub-documents
Regarding claim 16: (Original)
Londer discloses:
- wherein: each document data for training is given with a label representing a type of an associated prediction result of the machine learning model
[0045]:
In accordance with various embodiments of the inventive concept, the reader loss function and/or the match loss function may comprise a regression loss function or a classification loss function. Broadly described, classification involves prediction of an output from a set of finite categorical values. Regression involves prediction of a continuous value from other information.
[0045]; The retriever engine 205 is further configured to encode both the query and the sub-documents. In some embodiments, the retriever engine 205 may use a vector space model to encode the query and/or the sub-documents
[0003]:
AI reader engine: generating an inference about the answer to the query based on a concatenation of each of the at least one matching sub-document with the query, each of the at least one matching sub-document having an associated reader loss function result for the inference; identifying one of the at least one matching sub-document having a lowest reader loss function result; and associating the identified one of the at least one matching sub-document with a truth label for the query.
- and the processor is configured to extract the document data for training for each type of the label.
[0027]:
FIGS. 3 - 5 are flowcharts that illustrate training operations and inference operations of the QA system
[0022]:
determining at least one matching sub-document of the plurality of sub-documents that is a match for containing an answer to the query based on the encoded query and each of the plurality of encoded sub-documents
[0022]:
associating the identified one of the at least one matching sub-document with a truth label for the query
Regarding claim 20: (Currently Amended)
Londer discloses:
- A learning method comprising: via a processor, using, for a plurality of document data for training, each document data for training as input of a machine learning model to acquire output data which is output for each document data for training;
[0044]:
During training, the retriever engine 205 may be configured to discard a current knowledge base or corpus and select a new knowledge base or corpus 215 that may include one or more of the plurality of sub-documents.
[0045]:
During training, the reader engine 230 may be configured to generate an inference about the answer to the query based on each of the matching sub-documents that are concatenated with the query.
- calculating, for a part of the document data for training from the plurality of document data for training, a loss function representing a degree of difference between correct answer data and the output data for each document data for training based on the output data obtained for each document data for training and the correct answer data;
[0045]:
the retriever engine 205 may be configured to update the query encoding model and the document encoding model using a match loss function that generates a match loss function result based on the query and the matching sub-documents. A loss function may be described generally as a function that computes the distance between the current output of an operation and the expected output. In accordance with various embodiments of the inventive concept, the reader loss function and/or the match loss function may comprise a regression loss function or a classification loss function.
[0034]:
the query encoding model and the document encoding model may be updated using a match loss function result between the query and the matching sub-documents.
[0045]:
reader loss function may be applied to identify the matching sub-document having the lowest reader loss function result. This identified matching sub-document may then be associated with a truth label for the query and the AI reader engine 230 may be updated based on the reader loss function results associated with the matching sub-documents.
- and update the machine learning model based on the loss function.
[0034]:
the query encoding model and the document encoding model may be updated using a match loss function result between the query and the matching sub-documents.
[0045]:
reader loss function may be applied to identify the matching sub-document having the lowest reader loss function result. This identified matching sub-document may then be associated with a truth label for the query and the AI reader engine 230 may be updated based on the reader loss function results associated with the matching sub-documents
- calculating, also for another document data for training other than the part of document data for training,
[0012]:
In some embodiments of the inventive concept, a method comprises: discarding a current knowledge corpus; selecting a new knowledge corpus; performing operations as follows using an Artificial Intelligence (AI) retriever engine: dividing the new knowledge corpus into a plurality of sub-documents; encoding a query for the plurality of sub-documents using a query encoding model; encoding each of the plurality of sub-documents using a document encoding model; and determining one matching sub-document of the plurality of sub-documents that is a best match for containing an answer to the query based on the encoded query and each of the plurality of encoded sub-documents; performing operations as follows using an AI reader engine: generating an inference about the answer to the query based on a concatenation of the one matching sub-document with the query.
[BRI: the new knowledge training does represent other document training]
Londer does not explicitly disclose:
- the loss function with a weight smaller than a weight of the loss function calculated for the part of document data for training for each data for training;
- and the loss function of the other document data for training
However, Schmugar discloses:
- the loss function with a weight smaller than a weight of the part of document data for training for each data for training;
[0028]:
within an industry consortium, it may be expected to share certain enterprise data across the consortium. However, it may be more common to share the enterprise data in a static format such as portable document format (PDF) or a tagged image file (TIF), rather than in a native electronic format such as a Microsoft Office document, or other native binary data.
[0267]:
A common method for refining values includes “gradient descent” and “back-propagation.” An illustrative gradient descent method includes computing a “cost” function, which measures the error in the network.
[0267]:
Each training example will have its own computed cost. Initially, the cost function is very large, because the network doesn't know how to classify objects. As the network is trained and refined, the cost function value is expected to get smaller, as the weights and biases are adjusted toward more useful values.
- and the loss function of the other document data for training
[0283]:
Individual cost functions can be computed for each training input, and the total cost function for the network can be computed as an average of the individual cost functions.
[0284]:
In block 1420, the network may then compute a negative gradient of this cost function to seek a local minimum value of the cost function, or in other words, the error. For example, the system may use back-propagation to seek a negative gradient numerically. After computing the negative gradient, the network may adjust parameters (weights and biases) by some amount in the “downward” direction of the negative gradient.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Londer and Schmugar.
Londer teaches training of the document data for training from the plurality of document and generating a loss function representing a degree of difference between correct answers.
Schmugar teaches the loss function with a smaller weight (optimized weight)
One of ordinary skills would be motivated to combine Odibat and Schmugar that can adjust the slope of the cost function (Schmugar [0271]).
Regarding claim 21: (Original)
Londer discloses:
- A non-transitory computer-readable medium storing a learning program that is executable by the processor included in an information processing device to perform the learning method according to claim 20.
(see [0022]:
In some embodiments of the inventive concept, a computer program product comprises: a non-transitory computer readable storage medium comprising computer readable program code embodied in the medium that is executable by a processor to perform operations comprising: discarding a current knowledge corpus; selecting a new knowledge corpus; performing operations as follows using an Artificial Intelligence (AI) retriever engine: dividing the new knowledge corpus into a plurality of sub-documents;
[0022]:
performing operations as follows using an AI reader engine:
[0055]:
FIG. 7 illustrates a memory 705 that may be used in embodiments of data processing systems, such as the QA system server 140 of FIG. 1, the retriever engine 205 and reader engine 230 of FIG. 2, and the data processing system 600 of FIG. 6, respectively, to facilitate operation of a QA system that provides document level inference. The memory 705 is representative of the one or more memory devices containing the software and data used for facilitating operations of the QA system server 140 and the QA engine module 145).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the
examiner should be directed to TIRUMALE KRISHNASWAMY RAMESH whose telephone number is (571)272-4605. The examiner can normally be reached by phone.
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, Li B Zhen can be reached on phone (571-272-3768). 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.
/TIRUMALE K RAMESH/Examiner, Art Unit 2121
/Li B. Zhen/Supervisory Patent Examiner, Art Unit 2121
