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 .
DETAILED ACTION
Status of Claims
This First Office action is in reply to the application and preliminary amendments filed on 16 January 2025.
Original Claim 10 has been cancelled. Original Claim 9 has been amended. New Claims 11-13 have been added.
Claims 1-9, 11-13 are currently pending and have been examined. The Information Disclosure Statement filed 16 January 2025 has been considered by the Examiner. A signed copy is enclosed with this Office Action.
Inventorship
This application currently names joint inventors. In considering patentability of the claims under 35 U.S.C. 103(a), the Examiner presumes that the subject matter of the various claims was commonly owned at the time any inventions covered therein were made absent any evidence to the contrary. Applicants are advised of the obligation under 37 CFR 1.56 to point out the inventor and invention dates of each claim that was not commonly owned at the time a later invention was made in order for the Examiner to consider the applicability of 35 U.S.C. 103(c) and potential 35 U.S.C. 102(e), (f) or (g) prior art under 35 U.S.C. 103(a).
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55. Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy filed on 03 August 2021.
Specification
The instant Specification is objected to. Applicant is reminded of the proper content of an abstract of the disclosure.
A patent abstract is a concise statement of the technical disclosure of the patent and should include that which is new in the art to which the invention pertains. The abstract should not refer to purported merits or speculative applications of the invention and should not compare the invention with the prior art.
If the patent is of a basic nature, the entire technical disclosure may be new in the art, and the abstract should be directed to the entire disclosure. If the patent is in the nature of an improvement in an old apparatus, process, product, or composition, the abstract should include the technical disclosure of the improvement. The abstract should also mention by way of example any preferred modifications or alternatives.
Where applicable, the abstract should include the following: (1) if a machine or apparatus, its organization and operation; (2) if an article, its method of making; (3) if a chemical compound, its identity and use; (4) if a mixture, its ingredients; (5) if a process, the steps.
Extensive mechanical and design details of an apparatus should not be included in the abstract. The abstract should be in narrative form and generally limited to a single paragraph within the range of 50 to 150 words in length.
See MPEP § 608.01(b) for guidelines for the preparation of patent abstracts.
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.
Broadly recited Claims 1-9, 11-13 are rejected under 35 U.S.C. §101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, natural phenomenon, or an abstract idea) because the claimed invention is directed to a judicial exception (i.e., a law of nature, natural phenomenon, or an abstract idea) without significantly more. The claims as a whole recite certain grouping of an abstract idea and are analyzed in the following step process:
Step 1: Method Claims 1-9, 11-13 are not entirely focused to a statutory category of invention. Although new dependent Claims support independent Claims 1 and 8 as for a processor, the memory having at least one program stored thereon is considered software per se, and software is not considered statutory unless further supported by a non-transitory computer storage medium. Likewise for dependent Claims 12 and 13 that recite a readable medium having a computer program stored thereon, the readable medium is should be recited as non-transitory computer readable storage medium. Paragraphs 89-93 in the instant un-published specification indicates the storage medium can be non-transitory (nonvolatile) or transitory (volatile) and transitory or volatile media is not statutory. The above cited claims should be amended appropriately. Despite this failure to pass Step 1, the Examiner proceeds to the next steps of the analysis.
Step 2A: Prong One: Claims 1-9, 11-13 recite limitations that set forth the abstract ideas, namely, the claims as a whole recite the claimed invention as directed to an abstract idea without significantly more. The claims describe methods of passenger flow prediction models. The claims recite steps for:
“acquiring passenger flows of a station in an urban rail transit line from a 1st statistical moment to an Nth statistical moment;
inputting the passenger flows from the 1st statistical moment to the Nth statistical moment into a trained passenger flow prediction model, to obtain a predicted passenger flow of the station in the urban rail transit line at an (N+1)th statistical moment;
wherein the passenger flow prediction model performs the processing of: generating a passenger flow matrix according to the passenger flows from the 1st statistical moment to the Nth statistical moment, wherein a first dimension of the passenger flow matrix is a time dimension, and a second dimension and a third dimension of the passenger flow matrix are spatial dimensions, and positions of the passenger flows of the station in the spatial dimensions represent a connection relationship of stations, where N is an integer greater than or equal to 2;
performing a first convolution operation and a first full connection operation on the passenger flow matrix in the spatial dimensions to obtain spatial feature information;
performing a second convolution operation and a second full connection operation on the passenger flow matrix in the time dimension to obtain temporal feature information;
and performing a third full connection operation and normalization on the spatial feature information and the temporal feature information, to obtain predicted data of the spatial dimensions corresponding to the (N+1)th statistical moment, and outputting, according to the predicted data of the spatial dimensions corresponding to the (N+1)th statistical moment, the predicted passenger flow of the station in the urban rail transit line at the (N+1)th statistical moment”
As detailed in the MPEP 2106 and commensurate to the two-part subject matter eligibility framework decision in the Federal court decision in Alice Corp. Pty. Ltd. V. CLS Bank International et al., (Alice), 2019 revised patent subject matter eligibility guidance (2019 PEG) and the October 2019 Update: Subject Matter Eligibility (“October 2019 Update), and the new “July 2024 Guidance Update on Patent Subject Matter Eligibility Examples, including on Artificial Intelligence”, the 2019 PEG explains that the abstract idea exception includes the following groupings of subject matter. The 35 U.S.C. 101 Step 2A, Prong One analysis focuses on whether a claim recites a judicial exception by evaluating if it falls into one of three specific groupings: mathematical concepts, mental processes, or certain methods of organizing human activity. The claims recite mathematical calculations (convolutions, matrices, statistical moments) applied to human scheduling and transit data and based on the provided steps above, the analysis for Step 2A Prong One is as follows:
Mathematical concepts – mathematical relationships, mathematical formulas or equations, mathematical calculations. Statistical Moments: Processing data from a "1st statistical moment to an Nth statistical moment". Matrix Manipulation: Transforming data into a three-dimensional "passenger flow matrix" (time, space, space). Convolution Operations: Performing "a first convolution operation" and "a second convolution operation." These are fundamental mathematical operations used to filter and transform digital arrays. Full Connection Operations: Performing linear algebraic weight multiplications and bias additions ("full connection operations"). Normalization: Applying a mathematical function to scale data ranges.
Certain methods of organizing human activity –managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions). Passenger Flows: It tracks, calculates, and predicts "passenger flows of a station in an urban rail transit line". Transportation Management: Managing and predicting the movement of people within a commercial or public transit system is a fundamental method of organizing human activity (managing transport logistics).
Mental processes – concepts performed in the human mind (including an observation, evaluation, judgment, opinion).
See MPEP § 2106.04(a) III C. Hence, the claims are ineligible under Step 2A Prong one. Furthermore, the dependent claims are merely directed to the particulars of the abstract idea and likewise do not add significantly more to the above-identified judicial exception.
Prong Two: Claims 1-9, 11-13: With regard to this step of the analysis (as explained in MPEP § 2106.04(d)), the judicial exception is not integrated into a practical application. Claims 1-9, 11-13 only recite an additional element directed to a “processor; memory; computer program; readable medium; device” (e.g., see Applicants’ un-published Specification ¶’s 89-93). Therefore, the claims only contain a computer component that is cited at a high level of generality and are merely invoked as a tool to perform the abstract idea. Simply implementing an abstract idea on a computer is not a practical application of the abstract idea. Furthermore, the dependent claims are merely directed to the particulars of the abstract idea and likewise do not add significantly more to the above-identified judicial exception. The limitations of the claims do not transform the abstract idea that they recite into patent-eligible subject matter because the claims simply instruct the practitioner to implement the abstract idea using a generally-recited computer components and furthermore do not amount to an improvement to a computer or any other technology, and thus are ineligible. See MPEP § 2106.05(f) (h).
Step 2B: As explained in MPEP § 2106.05, Claims 1-9, 11-13 do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements when considered both individually and as an ordered combination do not amount to significantly more than the abstract idea nor recites additional elements that integrate the judicial exception into a practical application. The additional element of “processor; memory; computer program; readable medium; device”, etc. are generically-recited computer-related element. that amount to a mere instruction to “apply it” (the abstract idea) on the computer-related element (see MPEP § 2106.05 (f) – Mere Instructions to Apply an Exception). This additional element in the claims is recited at a high level of generality and are merely limiting the field of use of the judicial exception (see MPEP §2106.05 (h) – Field of Use and Technological Environment). There is no indication that any further combination of elements improves the function of a computer or improves any other technology. Furthermore, the dependent claims are merely directed to the particulars of the abstract idea and likewise do not add significantly more to the above-identified judicial exception. The limitations of the claims do not transform the abstract idea that they recite into patent-eligible subject matter because the claims simply instruct the practitioner to implement the abstract idea using a generally-recited computer component, and furthermore do not amount to an improvement to a computer or any other technology, and thus are ineligible.
The Examiner interprets that the steps of the claimed invention both individually and as an ordered combination result in Mere Instructions to Apply a Judicial Exception (see MPEP §2106.05 (f)). These claims recite only the idea of a solution or outcome with no restriction on how the result is accomplished and no description of the mechanism used for accomplishing the result. Here, the claims utilize a processor (e.g., see Applicants’ un-published Specification ¶’s 89-93) regarding using existing computer processors and does not provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016)). Software implementations are accomplished with standard programming techniques with logic to perform connection steps, processing steps, comparison steps and decisions steps. These claims are directed to being a commonplace business method being applied on a general-purpose computer processor (see Alice Corp. Pty, Ltd. V. CLS Bank Int’l, 134 S. Ct. 2347, 1357, 110 USPQ2d 1976, 1983 (2014)); Versata Dev. Group, Inc., v. SAP Am., Inc., 793 D.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015)). Based on all these, Examiner finds that when viewed either individually or in combination, this additional claim element does not provide meaningful limitation(s) that raise to the high standards of eligibility to transform the abstract idea(s) into a patent eligible application of the abstract idea(s) such that the claim(s) amounts to significantly more than the abstract idea(s) itself. Accordingly, Claims 1-9, 11-13 are rejected under 35 U.S.C. §101 because the claimed invention is directed to a judicial exception (i.e. abstract idea exception) without significantly more.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Broadly recited Claims 1-9, 11-13 are rejected under 35 U.S.C. 103 as being unpatentable over Mintz (US 2019/0012909) in view of Hu et al. (Hu) (US 2023/0062565) and in further view of Huang et al. (Huang) (US 2020/0042799).
With regard to Claims 1-8, 11-13, Mintz teaches a passenger flow prediction method/model training method/electronic device/readable medium having a computer program stored thereon which, when executed by a processor, comprising: at least one processor; and a memory having at least one program stored thereon which, when executed by the at least one processor, causes the at least one processor to (a processor of the computing apparatus to execute the computing logic to perform computing functions and/or operations. In one example, logic may be embedded in various types of memory and/or firmware, e.g., silicon blocks of various chips and/or processors. Logic may be included in, and/or implemented as part of, various circuitry, e.g. radio circuitry, receiver circuitry, control circuitry, transmitter circuitry, transceiver circuitry, processor circuitry, and/or the like. In one example, logic may be embedded in volatile memory and/or non-volatile memory, including random access memory, read only memory, programmable memory, magnetic memory, flash memory, persistent memory; an apparatus, a device and/or a system including means for triggering, causing, controlling, and/or performing one or more, e.g., some or all, of the operations of the method. In one example, an apparatus, a device and/or a system may include one or more components, modules and/or units, for example, including circuitry and/or logic, configured to trigger, cause, control, and/or perform one or more, e.g., some or all, of the operations) (see at least paragraphs 26-30):
acquiring passenger (vehicles and passengers; classes of vehicles (e.g., passenger cars, trucks, etc.) flows (Dynamic Traffic Assignment (DTA); simulated traffic flow predictions based on realistic models; statistical, physical, behavioral models; flows on a road network; Dynamic current traffic flows; traffic predictions; DTA flow) from a 1st statistical moment to an Nth statistical moment (model predictive control; statistical prediction; A demand Model which divides the network into zones among which trip pairs are assigned, and expanded for real time traffic predictions by a demand prediction model for zone to zone demand of trips. A demand prediction model, which expands the demand model is aimed at enabling real time demand predictions according to past demand data, possibly with the support of historical data which may apply statistical prediction models associated possibly with pattern recognition methods for differential statistical demand prediction. Advanced demand model may include demand control models such as road toll and early/late trip departure recommendations in association with a demand prediction model; A supply Model, which models the network traffic flow development, and which includes sub-models which are, but not limited to, road network characteristics at a level of links and intersections, routes and route choice model for the non controlled paths according to classes of vehicles, plans of traffic control means such as traffic lights and variable signals, and, with high resolution DTA, also intra link related traffic model such as lane changes and behavior related car following having a as potential to be expanded to intra and inter link control models; Weighted Least Squares Estimation approach) (see at least paragraphs 51-56, 96, 108-113, 122, 288-90, 543, 609, 616);
inputting the passenger flows (FIG. 1h differs from FIG. 1g by enabling to feed traffic predictions from a path control system to a traffic light control optimization system 215 through 214 enabling to improve traffic lights control in forward time intervals covered by the predicted flows. This further enables to get feedback from 215 through 216 for adapted traffic light plans according to the traffic predictions from 217 and improve accordingly the path control) from the 1st statistical moment to the statistical moment into a trained passenger flow prediction model, to obtain a predicted passenger flow at an statistical moment (model predictive control; statistical prediction; A demand Model which divides the network into zones among which trip pairs are assigned, and expanded for real time traffic predictions by a demand prediction model for zone to zone demand of trips. A demand prediction model, which expands the demand model is aimed at enabling real time demand predictions according to past demand data, possibly with the support of historical data which may apply statistical prediction models associated possibly with pattern recognition methods for differential statistical demand prediction. Advanced demand model may include demand control models such as road toll and early/late trip departure recommendations in association with a demand prediction model; A supply Model, which models the network traffic flow development, and which includes sub-models which are, but not limited to, road network characteristics at a level of links and intersections, routes and route choice model for the non controlled paths according to classes of vehicles, plans of traffic control means such as traffic lights and variable signals, and, with high resolution DTA, also intra link related traffic model such as lane changes and behavior related car following having a as potential to be expanded to intra and inter link control models; Weighted Least Squares Estimation approach) (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543, 616);
generating a passenger flow matrix according to the passenger flows from the 1st statistical moment to the Nth statistical moment (a state time interval, which for example may be long enough to enable sufficient reduction in coefficient variation of a state vector, and which might be too long to avoid time varying non linearity of the DTA supply model, can't be represented by a single observation matrix with a functionality similar to the functionality of an observation matrix used by for example a Kalman Filter (and even by a single observation matrix of derivatives as used for example by EKF). In order to overcome this issue, according to some embodiments, multi time related inverse or pseudo inverse observation matrixes are used as a chain to represent piecewise backward linear relation between the state vector and corrected output from a measurement model according to field measurements. In this respect, the state estimation time interval is divided into multiple intra time intervals which each of them may be short enough to enable piecewise linearization by construction of a chain of observation matrixes for intra time intervals and which each observation matrix is converted into an inverse or pseudo inverse observation matrix for back propagating corrected output from a measurement to a state vector update. Each inverse or pseudo inverse observation matrix which refers to an intra time interval, and which is not the latest intra time interval in the state estimation time interval, is used to back propagate simulated measurements corrected according to field measurements, to prior intra time interval. Such back propagation is performed within the time related inverse or pseudo inverse observation matrixes used as a chain to represent piecewise backward relation which converts gradually corrected output from a measurement model according to field measurements to a state vector update. With such an approach the units of the measurements should be the same as the units of the state vector), wherein a first dimension of the passenger flow matrix is a time dimension, and a second dimension and a third dimension of the passenger flow matrix are spatial dimensions, and positions of the passenger flows of the station in the spatial dimensions represent a connection relationship of stations (A more accurate but more complex approach may use inverse DTA supply model, instead of inverse or pseudo inverse observation matrixes, which makes piecewise approach to be redundant. According to some embodiments, the piecewise state estimation of a demand state vector is expanded to overlapped piecewise state estimation of the demand state vector, where a piecewise state estimation of the demand state vector is performed by overlapped state estimation time intervals, whereby subsequent state estimation time intervals overlap in their intra time intervals except of two intervals which are, for example, the last intra time interval of the latest piecewise estimation time interval and the first intra time interval of the prior estimation time interval. With such an approach more frequent estimations can be obtained while enabling state estimation time interval with lower coefficient variations in the demand state vector) (see at least paragraphs 609-617);
performing a first convolution operation and a first full connection operation on the passenger flow (passenger; DTA flow) matrix (matrix; matrixes) in the spatial (time; temporal) dimensions to obtain spatial feature information (subject to identified location of a front end of a queue, the length of the queue, and preferably arrival and departure rates from a queue which develops on a network, temporal capacity correction is made to a respective location on the network, by rerunning the DTA supply model according to the estimated time in which the DTA flow has deviated from the field flow according to field measurements. With such a case, updates that were made to the demand state estimation under traffic irregularity, which wasn't identified at the time of the update, should preferably be re-updated by a post state estimation process according to temporal changes made to capacities of network links, and preferably according to respective changes to parameters of the route choice model to short term reaction of drivers to traffic loads on the network) (see at least paragraphs 43, 609-617);
performing a second convolution operation and a second full connection operation on the passenger flow matrix in the time dimension (multi time related inverse or pseudo inverse observation matrixes are used as a chain to represent piecewise backward linear relation between the state vector and corrected output from a measurement model according to field measurements. In this respect, the state estimation time interval is divided into multiple intra time intervals which each of them may be short enough to enable piecewise linearization by construction of a chain of observation matrixes for intra time intervals and which each observation matrix is converted into an inverse or pseudo inverse observation matrix for back propagating corrected output from a measurement to a state vector update. Each inverse or pseudo inverse observation matrix which refers to an intra time interval, and which is not the latest intra time interval in the state estimation time interval, is used to back propagate simulated measurements corrected according to field measurements, to prior intra time interval) to obtain temporal feature information (subject to identified location of a front end of a queue, the length of the queue, and preferably arrival and departure rates from a queue which develops on a network, temporal capacity correction is made to a respective location on the network, by rerunning the DTA supply model according to the estimated time in which the DTA flow has deviated from the field flow according to field measurements. With such a case, updates that were made to the demand state estimation under traffic irregularity, which wasn't identified at the time of the update, should preferably be re-updated by a post state estimation process according to temporal changes made to capacities of network links, and preferably according to respective changes to parameters of the route choice model to short term reaction of drivers to traffic loads on the network) (see at least paragraphs 43, 609-617);
performing a third full connection operation and normalization on the spatial feature information and the temporal feature information, to obtain predicted data of the spatial dimensions corresponding to the statistical moment (multi time related inverse or pseudo inverse observation matrixes are used as a chain to represent piecewise backward linear relation between the state vector and corrected output from a measurement model according to field measurements. In this respect, the state estimation time interval is divided into multiple intra time intervals which each of them may be short enough to enable piecewise linearization by construction of a chain of observation matrixes for intra time intervals and which each observation matrix is converted into an inverse or pseudo inverse observation matrix for back propagating corrected output from a measurement to a state vector update. Each inverse or pseudo inverse observation matrix which refers to an intra time interval, and which is not the latest intra time interval in the state estimation time interval, is used to back propagate simulated measurements corrected according to field measurements, to prior intra time interval) to obtain temporal feature information (subject to identified location of a front end of a queue, the length of the queue, and preferably arrival and departure rates from a queue which develops on a network, temporal capacity correction is made to a respective location on the network, by rerunning the DTA supply model according to the estimated time in which the DTA flow has deviated from the field flow according to field measurements. With such a case, updates that were made to the demand state estimation under traffic irregularity, which wasn't identified at the time of the update, should preferably be re-updated by a post state estimation process according to temporal changes made to capacities of network links, and preferably according to respective changes to parameters of the route choice model to short term reaction of drivers to traffic loads on the network), and outputting, according to the predicted data of the spatial dimensions corresponding to the statistical moment, the predicted passenger flow at the statistical moment (piecewise linear relation constructed for non linear relation between the state vector and corrected output from a measurement model according to field measurements. With such an approach, a state time interval, which for example may be long enough to enable sufficient reduction in coefficient variation of a state vector, and which might be too long to avoid time varying non linearity of the DTA supply model, can't be represented by a single observation matrix with a functionality similar to the functionality of an observation matrix used by for example a Kalman Filter (and even by a single observation matrix of derivatives as used for example by EKF). In order to overcome this issue, according to some embodiments, multi time related inverse or pseudo inverse observation matrixes are used as a chain to represent piecewise backward linear relation between the state vector and corrected output from a measurement model according to field measurements. In this respect, the state estimation time interval is divided into multiple intra time intervals which each of them may be short enough to enable piecewise linearization by construction of a chain of observation matrixes for intra time intervals and which each observation matrix is converted into an inverse or pseudo inverse observation matrix for back propagating corrected output from a measurement to a state vector update. Each inverse or pseudo inverse observation matrix which refers to an intra time interval, and which is not the latest intra time interval in the state estimation time interval, is used to back propagate simulated measurements corrected according to field measurements, to prior intra time interval. Such back propagation is performed within the time related inverse or pseudo inverse observation matrixes used as a chain to represent piecewise backward relation which converts gradually corrected output from a measurement model according to field measurements to a state vector update. With such an approach the units of the measurements should be the same as the units of the state vector) (see at least paragraphs 43, 609-617);
Mintz does not specifically teach of a station in an/the urban rail transit line. Hu teaches of a station in an/the urban rail transit line (acquiring passenger flow data of a rail transit station according to the original data; building a passenger flow prediction model of the rail transit station according to the passenger flow data of the rail transit station; acquiring a passenger flow volume of the rail transit station in a preset period according to the passenger flow prediction model; and performing coordinated dispatching on vehicles and passengers of the rail transit station according to the passenger flow volume of the preset period; a rail transit vehicle operation map may be received from a rail transit signal system, so as to obtain arrival and departure time information of the vehicles waiting for arrival at the rail transit station, thus acquiring the number of the vehicles waiting for arrival at the rail transit station in the preset period. Therefore, the number of the vehicles waiting for arrival and the real-time vehicle-mounted passenger flow data of the vehicles waiting for arrival are combined for analysis to obtain the transport capacity of the vehicles waiting for arrival in the preset period) in analogous art of passenger flow prediction for the purposes of: “the real-time vehicle-mounted passenger flow data of the vehicles waiting for arrival are combined for analysis to obtain the transport capacity of the vehicles waiting for arrival in the preset period” (see at least paragraphs 70-82; Abstract).
It would have been obvious to one of ordinary skill in the art at the time of the invention to include the intelligent dispatching method and system for rail transit as taught by HU in the system of Mintz, since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Mintz in view of Hu does not teach where N is an integer greater than or equal to 2/(N+1)th/ where j is an integer between 1 and N/ normalization on. Huang teaches where N is an integer greater than or equal to 2/(N+1)th/where j is an integer between 1 and N (Point-to-point flow data refer to information of traffic (e.g., the number of vehicles) flowing from one point to another within a certain period of time. The point-to-point flow data is an important instrument for traffic pattern understanding, traffic flow management, and transportation infrastructure decision making. For example, the number of vehicles passing between a point pair can be used to estimate a number of people travelling between the points; the number of vehicles passing between a point pair can be used to estimate a number of people travelling between the points. In this disclosure, point-to-point traffic may comprise origin-destination (O-D or OD) traffic, that is, traffic passing through an origin point at an earlier time and through a destination point at a later time; OD flow estimation; a network composed of N=11 bayonets is applied to the disclosed algorithm. OD-flows are bidirectional for each pair of nodes, therefore N (N−1)=182 different ODs are considered here. Index of OD-flow is given by the standard permutation, i.e., (i−1).Math.(N−1)+(j−1)−1(i<j), where i=Index of O, j=Index of D, and I(⋅) is the indicator function. The dataset includes OD counts from bayonet data and trajectory data for one month. The first three quarters of the data forms the training set and the remaining forms the testing data. In one example, a time window of 24 hours may be used, in another word, w=24×60/ΔT=48 intervals are used to make a prediction. The lookout l=1, that is, the past 48 intervals data is used to predict the next 1 interval (e.g., 30 min) OD-flows. For this reason, the input data was reshaped to a 3-mode tensor, with each slice being a 48×182 matrix. The whole neural network may be trained by minimizing the mean squared error between the prediction and the actual OD-flow count from bayonets data. The training uses batch size of 128 and trains 125 epochs, and 10% of training data is used for training validation)/normalization on (The final output 110-dimension vector is the prediction for the 110 ODs for the next time interval. The fully connected layers use scaled exponential linear unit as their activation function. Batch normalization layers are added to each layer except for the final output layer) in analogous art of traffic flow management for the purposes of: “The disclosed models can make prediction of OD flows of an urban network solely based on trajectory data. The proposed semi-supervised learning model is able to offer predictions for OD flows with limited spatial coverage of ground truth data” (see at least paragraphs 33-35, 56-76)
It would have been obvious to one of ordinary skill in the art at the time of the invention to include the system and method for point-to-point traffic prediction as taught by Huang in the system of HU and in view of the system of Mintz, since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
With regard to Claim 2, Mintz teaches: generating a two-dimensional first matrix corresponding to a jth statistical moment according to the passenger flow at the jth statistical moment (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543); and splicing two-dimensional first matrixes corresponding to all the statistical moments into the passenger flow matrix in the time dimension (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543).
With regard to Claim 3, Mintz teaches:
performing the first convolution operation X times and a first activation function operation times on the passenger flow matrix in the spatial dimensions to obtain first convolution operation results (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543);
converting each first convolution operation result into a one-dimensional first vector (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543);
splicing X first vectors into a one-dimensional second vector; and performing the first full connection operation and the first activation function operation on the second vector to obtain the spatial feature information (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543).
With regard to Claim 4, Mintz teaches:
performing the first convolution operation for the first time and the first activation function operation for the first time on the passenger flow matrix in the spatial dimensions to obtain a first convolution operation result for the first time (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543);
performing the first convolution operation and the first activation function operation and first convolution operation result for the ith time to obtain a first convolution operation result (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543).
With regard to Claim 5, Mintz teaches:
converting the passenger flow matrix into a two-dimensional second matrix under the condition of ensuring that the time dimension is unchanged (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543);
performing the second convolution operation X times and a first activation function operation X times on the second matrix to obtain X second convolution operation results (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543);
converting each second convolution operation result into a one- dimensional third vector (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543);
splicing X third vectors into a one-dimensional fourth vector; and performing the second full connection operation and the first activation function operation on the fourth vector to obtain the temporal feature information (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543).
With regard to Claim 6, Mintz teaches:
performing the second convolution operation for the first time and the first activation function operation for the first time on the second matrix to obtain a second convolution operation result for the first time (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543);
performing the second convolution operation and the first activation function operation on a second convolution operation result for the ith time to obtain a second convolution operation result (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543).
With regard to Claim 7, Mintz teaches:
splicing the spatial feature information and the temporal feature information into a one-dimensional fifth vector, and performing the third full connection operation and a first activation function operation on the fifth vector to obtain spatial-temporal feature information (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543) ;
performing the spatial-temporal feature information to obtain predicted data of the spatial dimensions corresponding to statistical moment (see at least paragraphs 51-56, 96, 108-113, 122, 226, 288-90, 543).
Conclusion
The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure:
Song et al. (US 2024/0351615)
Vasseur et al. (US 2015/0195149)
Mintz (WO 2021/048826 A1)
Li, Haiying, et al. "Short-term passenger flow prediction under passenger flow control using a dynamic radial basis function network." Applied Soft Computing 83 (2019): 105620.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to THOMAS L MANSFIELD whose telephone number is (571)270-1904. The examiner can normally be reached M-Thurs, alt. Fri. (9-6).
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, Patricia Munson can be reached at (571) 270-5396. 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.
THOMAS L. MANSFIELD
Examiner
Art Unit 3623
/THOMAS L MANSFIELD/Primary Examiner, Art Unit 3624
Prosecution Insights