Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 2, 4 13 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Borras et al. (US 11,989,955 B2) (hereinafter referred to as Borras) in view of Tsesmetzis et al. (WO 2017063052 A1) (hereinafter referred to as Tsesmetzis).
Regarding claim 1, Borras teaches a system (Borras, Fig 8, tolling system 800) comprising:
at least one hardware processor; and
at least one non-transitory processor-readable medium storing instructions to be executed by the at least one hardware processor (Borras, Fig 8, geofence definition server 824 and tolling billing server 828; Tolling system 800 includes tolling agency data center with geofence definition server 824 and tolling billing server 828. Col. 11, lines 4-9: Servers inherently include processors and non-transitory storage media executing stored instructions to perform the disclosed tolling methods.) to:
access toll records of a plurality of toll gates (Borras, see Claim 1: “a tolling location…one tolling location of a plurality of tolling locations.” FIG. 4: multiple lanes 402a-402e, Col 9, lines 7-10: {This figure shows multiple lanes 402a-402e, as is common in many tolling locations (i.e. tolling plazas)}), the toll records include sensor data from Radio Frequency Identifier (RFID) sensors (Borras, RFID sensors: Col. 1, lines 38-40: “A toll transponder uses radio communication to communicate with a toll reader when passing through a tolling location. Typically the toll reader is mounted on a gantry over a particular lane of traffic.”; Fig (FIG. 2A, step 206): “the toll reader attempts to read a toll transponder in the vehicle as it passes under the gantry.” Col 6, lines 44-55) and image sensors installed at the plurality of toll gates, wherein the sensor data comprises data associated with RFID tags from the RFID sensors and image data from the image sensors (Borras, Fig 2A, step 204; Image sensors: Col. 1, lines 54-61: “a high speed camera captures an image of the rear of the vehicle, which includes the license tag.”; Col. 7, lines 32-44: “the camera produces one or more images of the rear of the vehicle as it passes the midpoint.”; Fig 8, toll point 808, Col. 11, lines 2-4);
determine from the toll records of a first toll gate of the plurality of toll gates, that a vehicle passed through the first toll gate without paying toll (Borras, (FIG. 2A, step 206), Col. 7, lines 48 – col 8, line 19: “if in step 206 no toll transponder responded, then the method proceeds to step 218...” (equivalent to passing without paying));
process the image data from the image sensors installed at one or more of the first toll gate and at least a subset of the plurality of toll gates via automatic image recognition techniques (Borras, Col. 1, lines 54-61: “the captured image is processed using character recognition to automatically obtain the vehicle license tag number from the image.”, Col. 7, lines 61-65 (FIG. 2A, step 224): “a conventional OCR process is applied to the image(s)/video captured at the gantry camera to obtain a license tag number.”);
identify the vehicle via the processing of the image data (Borras, Col. 1, lines 54-65: “If that process is successful, then the toll can be charged to the owner of the vehicle. For example, the license tag number can be cross referenced with those vehicles registered with the toll system to find a match.”; Col. 7, line 65 -Col 8, line 4 (FIG. 2A, step 226): “the acquired license tag number is compared to a list of authorized accounts and if a suitable match is found then the associated customer is charged.”);
automatically execute a correlation process that correlates the toll records pertaining to the vehicle to mobile communication network data of base stations proximate to one or more of the first toll gate and at least the subset of the plurality of toll gates; determine, based on the correlation, identification information of a mobile device corresponding to a user of the vehicle; and transmit a notification to the mobile device regarding payment of the toll based at least on the identification information (Borras, Fig 8, Col 10, line 62 – Col 11, line 32: Further, the toll point 808 reports lane and crossing times to the billing server 828, and the mobile device 816 also reports lane and crossing time information to the billing server 828 so that the billing server 828 can match lane and crossing time information reported by the mobile device 816 and toll point 808 and bill the appropriate entities. Any lane a crossing time records reported by the toll point 808 that can't be matched are returned or flagged for manual review of the images.).
While Borras teaches accessing toll records of a plurality of toll gates, it does not explicitly teach accessing the toll records of a plurality of toll gates along a roadway.
Reference Tsesmetzis teaches a system that detects a toll for a vehicle that includes accessing the toll records of a plurality of toll gates (Tsemetzis, paragraphs [0002], [0044], [0060], [0080], Toll zones may have a single toll gate or multiple toll gates, for example, an entry toll gate to indicate the vehicle has entered the toll zone and an exit toll gate, which indicates the vehicle has exited the toll zone.” Toll information database contains geographical locations of plurality of toll zones.) along a roadway (Tsemetzis, paragraphs [0095-0098], Typically a toll zone represents a road, motorway, tunnel or bridge.” Multiple toll zones along roads/motorways are contemplated. Example: Sydney Harbour Bridge, Sydney Harbour Tunnel, M2, M5 South West, Eastern Distributor, Lane Cove Tunnel — all along roadway networks.)
These arts are analogous since they are both related to imaging devices that track toll operations. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to modify the toll system of Borras to include a plurality of toll gates along a roadway as taught by Tsesmetzis.
Borras contemplates “a plurality of tolling locations” as seen in claim 1 and FIG. 4: multiple lanes 402a-402e but primarily illustrates a single tolling plaza.
Tsesmetzis teaches that toll zones represent “a road, motorway, tunnel or bridge” as seen in paragraph [0002] and may have “a single toll gate or multiple toll gates, for example, an entry toll gate to indicate the vehicle has entered the toll zone and an exit toll gate, which indicates the vehicle has exited the toll zone” as seen in paragraph [0044]. Tsesmetzis further teaches that tolling across multiple zones along a roadway requires centralized data coordination, as “other toll zones may affect a determination whether a toll is payable” as seen in paragraph [0096].
One of ordinary skill would have been motivated to combine these references because both Borras and Tsesmetzis independently disclose centralized servers that aggregate toll transaction data and deploying Borras’s toll gate infrastructure (RFID readers and cameras) at multiple locations along a roadway as seen in Tsesmetzis. This confirmation is standard practice and yields nothing more than the predictable result of a multi-gate toll system with centralized record access. See KSR Int’l Co. v. Teleflex Inc., 550 U.S. 398, 416 (2007); MPEP § 2143(I)©.
Regarding claim 2, the combination of Borras and Tsesmetzis teaches the system of claim 1, and also teaches wherein the instructions to identify the vehicle from the image data further cause the at least one hardware processor (Borras, Col 7, lines 37 - to Col 8, line 3, Col 11, lines 23-32, Tolling billing server 828 processes toll transactions including image-based identification via OCR. “a conventional OCR process is applied to the image(s)/video captured at the gantry camera to obtain a license tag number.) to: classify the toll records into three categories (Borras, Fig 2A (steps 206-234, Col, 7, line 32 – Col 8, line 19, The sequential decision process in Fig 2A routes toll transactions through distinct processing paths based on identification outcome. The processing flow creates three functionally distinct outcome groups.) and (Tsesmetzis, paragraphs [0003-0004], Tsesmetzis teaches that toll systems differentiate between vehicles with tolling devices (registered), vehicles without tolling devices but identifiable by license plate recognition, and unidentifiable vehicles. “Electronic tolling systems require the use of a specific tolling device such as an E-Tag or E-Toll… modern toll gates also typically have licence plate recognition for vehicles that do not possess a specific tolling device. When a vehicle passes through a toll gate and a specific tolling device is not detected, a photograph is taken.) including a first category of toll records of registered vehicles with RFID tags that are successfully scanned (Borras, Fig 2A (steps 206–210, Step 206: “the toll reader attempts to read a toll transponder in the vehicle as it passes under the gantry.” If transponder responds → Step 210: “the toll customer is charged the toll fee.” The transponder is linked to a registered toll account.) or toll records of registered vehicles with license plates successfully identified from the image sensors (Borras, Step 224-226: OCR process obtains license tag number, which is “compared to a list of authorized accounts and if a suitable match is found then the associated customer is charged.” This represents a registered vehicle identified by license plate rather than transponder.) a second category of toll records of unregistered vehicles with license plates successfully identified from the image sensors of the first toll gate (Borras, Fig 2A, steps 230-232: When OCR successfully reads the plate but it does NOT match the whitelist of authorized accounts: “the tolling system automatically obtains owner information from the motor vehicle registry and issues an invoice letter.” and FIG. 1, steps 120-124: “the matter can be submitted to the DMV for identification of the vehicle’s owner, then… issuance of an invoice and violation letter can be sent by the tolling agency to the registered owner of the vehicle.” This is precisely an “unregistered” vehicle (no toll account) with a successfully identified license plate.) and a third category with toll records of unidentified vehicles including vehicles with unidentified license plates from the image data (Borras, Step 228-234 (FIG. 2A): When OCR fails or characters cannot be recognized: “it is determined if there are missing characters, or characters that could not be identified by the OCR process… then in step 234 a manual review process is conducted.” FIG. 1, step 114: “In instances in step 112 where the confidence of the OCR process is below the required threshold, or one or more characters could not be recognized, in step 114 a manual review is necessary to identify the characters.” Also Claim 6: “responsive to detecting the approach of the vehicle, attempting to automatically recognize a license plate number of the vehicle; and wherein performing the reconciliation process is performed in response to failing to automatically recognize the license plate number of the vehicle.”).
Regarding claim 4, the combination of Borras and Tsesmetzis teaches the system of claim 1, and also wherein the instructions to identify the vehicle from the image data further cause the at least one hardware processor to: identify a license plate of the vehicle from the image data (Borras, Col. 7, lines 61-65, If no match is found in step 222, then, following the “B” continuator the method proceeds to step 224 where a conventional OCR process is applied to the image(s)/video captured at the gantry camera to obtain a license tag number.); and determine that a license plate number of the vehicle is unidentifiable from the image data (Borras, Col. 7, line 61 – Col 8, line 19: “missing characters, or characters that could not be identified”).
Claims 13 and 18 are rejected for the same reasons as claim 1.
Claims 3 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Borras et al. (US 11,989,955 B2) (hereinafter referred to as Borras) in view of Tsesmetzis et al. (WO 2017063052 A1) (hereinafter referred to as Tsesmetzis) and further in view of Kim et al. (KR 101688535 B1) (hereinafter referred to as Kim).
Regarding claim 3, the combination of Borras and Tsesmetzis teaches the system of claim 2, but does not explicitly teach wherein the instructions to identify the vehicle from the image data further cause the at least one hardware processor to: identify the vehicle from the image data captured by the image sensors of the first toll gate and at least the subset of the plurality of toll gates that include a preceding toll gate and a succeeding toll gate of the first toll gate.
Reference Kim teaches a system for managing a tollgate that teaches wherein the instructions to identify the vehicle from the image data further cause the at least one hardware processor (Kim, paragraph [0027], Control unit 700 analyzes images to obtain vehicle information including “vehicle identifier” (vehicle number). “The control unit 700 analyzes the entry image transmitted from the entry detection unit 100 to obtain the lane of the entry vehicle entering the entry zone, the vehicle type, the speed, and the vehicle identifier.”) to: identify the vehicle from the image data captured by the image sensors of the first toll gate (Kim, paragraph [0034] Gate sensing unit 300 acquires “gate image” at the fare adjustment section (toll gate proper). Control unit 700 analyzes gate images to identify vehicles and determine waiting vehicles at each gate. The system identifies vehicles at the toll gate itself.) and at least the subset of the plurality of toll gates that include a preceding toll gate (Kim, paragraphs [0024-0027]: Entrance sensing unit 100 is disposed in an entry section that precedes the toll gate. “The entrance detection unit 100 is disposed in an entry section of a tollgate in which the number of lanes is extended, and detects a vehicle entering the entry section.” CCTVs capture “entry image” of vehicles before they reach the toll gate. Control unit 700 analyzes entry images to obtain “the lane of the entry vehicle entering the entry zone, the vehicle type, the speed, and the vehicle identifier.”) and a succeeding toll gate of the first toll gate (Kim, paragraphs [0036-0037]:Entry (advance) detection unit 500 is disposed in an exit/advance section that succeeds the toll gate. “The advance detection unit 500 is disposed in the advance section of the tollgate in which the number of lanes is reduced, and detects the merged vehicle in accordance with the decrease of the lane.” CCTVs capture “entry image” (advance/exit image) of vehicles after they pass through the toll gate. Control unit 700 analyzes these images to track vehicles in the exit section.).
These arts are analogous since they are all related to imaging devices that track toll operations. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to modify the toll system of Borras in view of Tsesmetzis to further incorporate image-based vehicle identification at multiple sequential detection points including a preceding and succeeding toll gate, as taught by Kim.
Kim discloses a toll gate control system that deploys CCTV cameras at three sequential stations along a toll gate section: an entrance sensing unit 100 in an entry section preceding the toll gate, a gate sensing unit 300 at the toll gate, and an advance detection unit 500 in an exit section succeeding the toll gate (FIG. 2; Claim 1). A centralized control unit 700 receives and analyzes images from all three stations to obtain vehicle identifiers and track vehicles through the entire toll section.
One of ordinary skill would have been motivated to combine these teachings because:
(1) Borras already teaches that OCR-based license plate identification sometimes fails (Borras, Col. 7, line 61 – Col 8, line 19: “missing characters, or characters that could not be identified”), creating a need for alternative or supplemental identification mechanisms. Capturing images at multiple points along the vehicle’s path increases the likelihood of successful identification, as conditions (lighting, angle, obstruction) vary at each point.
(2) Kim demonstrates that deploying cameras at sequential positions along a toll section (preceding, at-gate, and succeeding) and centralizing the image analysis at a single control unit is a known and effective architecture for toll gate vehicle management.
(3) Tsesmetzis teaches that toll systems operate with entry and exit toll gates along roadways (paragraph [0044]), confirming that multiple toll gates in sequence is standard practice. Combining Borras’s OCR identification with Kim’s multi-station imaging yields the predictable result of improved vehicle identification rates by providing multiple imaging opportunities for the same vehicle.
(4) The combination applies Kim’s known technique (multi-point CCTV imaging with centralized analysis) to improve Borras’s similar system (single-point imaging with OCR) in the same way (providing redundant imaging for vehicles that may be unidentifiable from a single capture), yielding predictable results. See KSR Int’l Co. v. Teleflex Inc., 550 U.S. 398, 416 (2007); MPEP § 2143(I)©.
Claim 14 is rejected for the same reason as claim 3.
Claims 5-12, 15-17 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Borras et al. (US 11,989,955 B2) (hereinafter referred to as Borras) in view of Tsesmetzis et al. (WO 2017063052 A1) (hereinafter referred to as Tsesmetzis) and further in view of ZHAO et al. (CN 112819979 A) (hereinafter referred to as ZHAO).
Regarding claim 5, the combination of Borras and Tsesmetzis teaches the system of claim 1, but does not explicitly teach wherein the instructions to execute the correlation process automatically correlating the toll records pertaining to the vehicle to the mobile communication network data further cause the at least one hardware processor to: execute an event-based matching technique that comprises temporal alignment, sequence similarity and event context matching of events emitted by the sensors of the first toll gate and at least the subset of the plurality of toll gates and events fired by the base stations proximate to the first toll gate and at least the subset of the plurality of toll gates; calculate a similarity score via the execution of the event-based matching technique; and identify a subset of the events fired by the base stations for the mobile device corresponding to the vehicle based on the similarity score.
Reference ZHAO teaches an ETC charging system and method for tolls that teaches wherein the instructions to execute the correlation process automatically correlating the toll records pertaining to the vehicle to the mobile communication network data (ZHAO, see Claim 1, Claim 4 and Claim 8 and Fig 1, steps 103-106: Processor automatically correlates toll records (vehicle identification at toll station) with mobile communication network data (connection information from base stations/operator platform.) further cause the at least one hardware processor (ZHAO, ETC charging device 300) to:
execute an event-based matching technique (ZHAO, see Claim1 and Fig 1, steps 103-106 and Claim 7 (matching logic): ZHAO matches discrete toll passage events against discrete base station connection events.) that comprises temporal alignment (ZHAO, see Claim 4, Claim 6 and Fig 2, step 202 (step 202; “[T-t, T+t]” time window): ZHAO teaches temporal alignment: toll passage time T aligned with base station connection time window [T-t, T+t]), sequence similarity (ZHAO, see Claim 6 and Fig 2, steps 201-203 (“multiple samples,” “big data process,” “for each toll station”): ZHAO evaluates consistency across multiple sequential toll stations (implicitly comparing toll passage sequence with base station connection sequence)) and event context matching (ZHAO, see Claim 6, Claim 7 and Fig 1, step 106: ZHAO performs event context matching: the spatial context of the toll event (toll station identity/location) is matched against the spatial context of the base station event (which base station the device is connected to), using the pre-established site association table as the matching framework.) of events emitted by the sensors of the first toll gate and at least the subset of the plurality of toll gates (ZHAO, see Claim 3, Claim 6 and Fig 1, step 103 and Fig 2, step 202: ZHAO teaches that sensors at each toll station (OBU reader, camera) emit events when vehicles pass through.) and events fired by the base stations proximate to the first toll gate and at least the subset of the plurality of toll gates (ZHAO, see Claim 4, Claim 6 and Fig 1, step 105 (signal coverage range and see the association table): ZHAO teaches base stations proximate to toll gates fire/send connection information (events showing which devices connected when), accessed from operator platform or directly from the base station.);
calculate a similarity score via the execution of the event-based matching technique (ZHAO, see Claim 6 and Fig 2, steps 202-203 (“confidence level,” “highest confidence,” “big data process”): ZHAO teaches calculating a numerical “confidence level” (score) through the event-based matching process; the base station with the “highest confidence” is selected. (This is a calculated similarity/correlation score.));
and identify a subset of the events fired by the base stations for the mobile device corresponding to the vehicle based on the similarity score (ZHAO, see Claim 6 (confidence scoring); Claim 7 (device identification using association); see (Table 1 example — selecting mobile phone number 13088888888’s events as the match): ZHAO teaches using the confidence-based association (similarity score) to identify which mobile device’s base station connection events correspond to the vehicle at the toll station.).
These arts are analogous since they are all related to imaging devices that track toll operations. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to modify the toll system of Borras in view of Tsesmetzis to further incorporate the event-based matching technique comprising temporal alignment, sequence similarity, event context matching, similarity score calculation, and base station event subset identification for a mobile device, as taught and taught by ZHAO.
One of ordinary skill in the art would have been motivated to combine these teachings because:
(1) Borras already teaches a tolling system that seeks to identify vehicles and reconcile toll transactions, including scenarios where primary identification methods (transponder reading, OCR) fail (Borras, (Borras, Col. 7, line 61 – Col 8, line 19: “missing characters, or characters that could not be identified”), creating a need for alternative or supplemental identification mechanisms. Capturing images at multiple points along the vehicle’s path increases the likelihood of successful identification, as conditions (lighting, angle, obstruction).
(2) Tsesmetzis already teaches addresses toll determination using mobile device proximity to toll zones and communication through base stations see paragraphs [0041], [0044] and [0087].
(3) ZHAO teaches identifying which specific mobile device corresponds to a vehicle at a toll station by correlating toll records with base station connection data from the cellular network operator see the Abstract and Claims 1, 4, 6, 7.
A person of ordinary skill would have been motivated to look to solutions within this same field to enhance the reliability and accuracy of vehicle-to-device correlation. See MPEP § 2141.01(a) (analogous art includes references from the same field of endeavor).
Regarding claim 6, the combination of Borras, Tsesmetzis and ZHAO teaches the system of claim 5, and also wherein the instructions to execute the temporal alignment further cause the at least one hardware processor to: calculate temporal overlap (ZHAO, Description ([T-t, T+t] window); Claim 4 (“connection time”); Claim 6 (“corresponding to the current time”); Description (step 202): ZHAO teaches calculating temporal overlap between toll events and base station events. It explicitly calculates whether base station event timestamps overlap with toll gate event timestamps within a defined temporal window [T-t, T+t])) of the events associated with the vehicle from the first toll gate, at least the subset of the plurality of toll gates (ZHAO, see Claim 3, Claim 6 and Fig 1, step 103 and Fig 2, step 202: ZHAO teaches that events associated with each vehicle is collected at each toll station (multiple stations).) and the base stations based on a sequence of event timestamps (ZHAO, see Claim 4 (“connection time”); Claim 6 (“for each toll station,” “corresponding to the current time”); Description ([T-t, T+t]; “multiple samples”; “a period of time”): ZHAO teaches temporal overlap calculated based on a sequence of event timestamps: toll passage times (T₁, T₂, T₃…) at each sequential station paired with base station connection times, checked for overlap within defined windows.)
Regarding claim 7, the combination of Borras, Tsesmetzis and ZHAO teaches the system of claim 6, and also wherein the instructions to obtain the sequence similarity further cause the at least one hardware processor to: align and compare sequence of the events associated with the vehicle from the first toll gate, at least the subset of plurality of toll gates and the base stations (ZHAO, see Claim 4 and Claim 6: ZHAO teaches aligning the events by: At each toll station, the toll passage event (time T) is temporally aligned with the base station connection event (connection time within [T-t, T+t]). The events from both sources are aligned based on their temporal correspondence at each geographic point and comparing the sequences by: The system compares the toll passage sequence (which toll stations the vehicle passes through, in order) against the base station connection sequence (which base stations the device connects to, in order). At each point in the sequence, the system checks whether the base station connected to the device matches the base station associated with the toll station. The comparison is performed across multiple sequential toll stations, thereby effectively aligning and comparing two event sequences.).
Regarding claim 8, the combination of Borras, Tsesmetzis and ZHAO teaches the system of claim 7, and also wherein the instructions to align and compare the sequence of events associated with the vehicle further cause the at least one hardware processor to: implement dynamic time wrapping (DTW), wherein the sequence of events are ordered and compared as time series data (ZHAO, see the description of ([T-t, T+t]); Claim 4; Claim 6, ZHAO teaches events are ordered chronologically and compared with temporal tolerance. The [T-t, T+t] window permits temporal flexibility — “when the vehicle sample passes through the toll station A at T time… the mobile phone number will be connected to the base station near the toll station A at [T-t, T+t] time period.” A base station event need not occur at exactly time T but within a tolerance window — functionally equivalent to DTW’s temporal warping of two ordered time series.); compare the ordered time series data via a longest common subsequence (LCS) process (ZHAO, see the description (“multiple samples,” “big data process”); Claim 6; Fig 2, steps 202-203, ZHAO teaches the confidence-building process identifies consistent matching patterns across ordered observations: “through a period of time of multiple samples, the big data process, can obtain the confidence level of each base station corresponding to the toll station.” The system finds which sequential toll-station-to-base-station pairings consistently recur across multiple ordered observations — functionally equivalent to finding the longest common subsequence of matching events between two ordered sequences.); and match event contexts via extracting and comparing temporal metadata from the first toll gate, at least the subset of the plurality of toll gates and the base stations (ZHAO, see the description (“at T time”); Claim 4 (“connection time”); Claim 6 (“corresponding to the current time,” “for each toll station”), ZHAO teaches temporal metadata extracted from toll gates: “at T time” (time of vehicle passage); “corresponding to the current time” (Claim 6; step 202). Temporal metadata extracted from base stations: “the connection information comprises the connection time and the second station information of the communication base station connected with the mobile phone number” (Claim 4). Comparison: toll gate temporal metadata (time T) compared against base station temporal metadata (connection time) within [T-t, T+t]. Performed “for each toll station” across multiple gates.).
Regarding claim 9, the combination of Borras, Tsesmetzis and ZHAO teaches the system of claim 5, and also wherein the instructions to execute the correlation process of automatically correlating the toll records pertaining to the vehicle to the mobile communication network data further cause the at least one hardware processor to: pre-process event data of events fired by the sensors of the first toll gate and at least the subset of the plurality of toll gates (ZHAO, see Claim 2 and Fig 1, step 101, ZHAO teaches setup/pre-processing phase collects and organizes toll station data before operational matching: “collecting the first station information of the toll station” (step 101). “The first station information is the name of the toll station.”) and events from the mobile network data fired by the base stations proximate to the first toll gate and at least the subset of the plurality of toll gates (ZHAO, see Claim 2 and Fig 1, step 102, ZHAO teaches base station data pre-processed: “collecting the second station information of the communication base station capable of covering each toll station in the first station information” (step 102). Base stations proximate to toll gates: “the toll station A through the vehicle is located in the signal coverage range of the first communication base station.”), wherein pre-processing the event data includes normalizing locations (ZHAO, see Claim 2 and Fig 1, step 102, ZHAO teaches the system normalizes disparate location representations into a unified framework by creating the “toll station and communication base station site associated table” — mapping toll station locations (“first station information”) and base station locations (“second station information”) into a single common association framework.) and mapping corresponding events fired at same location by the sensors and the base stations (ZHAO, see Claim 6 and Fig 2, step 203, ZHAO teaches the site association table explicitly maps which sensor events correspond to which base station events at the same geographic location: “for each toll station, the communication base station with the highest confidence in different types of communication base station as the communication base station associated with the toll station.” The association table maps toll station events ↔ base station events at the same coverage area: “the toll station A through the vehicle is located in the signal coverage range of the first communication base station.”).
Regarding claim 10, the combination of Borras, Tsesmetzis and ZHAO teaches the system of claim 9, and wherein the instructions to pre-process the event data further cause the at least one hardware processor to: filter invalid and outlier data (ZHAO, see Claim 6 and Fig 2, step 203 and Claim 7, ZHAO teaches confidence-based filtering removes outliers: “for each toll station, the communication base station with the highest confidence” — low-confidence associations (outliers/anomalies) are excluded. The “big data process” over “multiple samples” statistically filters noise. Abnormal state detection: “when the vehicle passing state is abnormal” — invalid events identified and separated from normal processing.); and impute missing data from available dataset of the events (ZHAO, see Claim 6, ZHAO teaches the pre-established “toll station and communication base station site associated table” (Claim 2) provides expected base station associations when real-time data is incomplete — the system knows which base station should correspond to each toll station from historical observations, imputing the expected connection. Additionally, “different types of communication base station” (Claim 6) provides alternative operator data sources when one source has gaps.).
Regarding claim 11, the combination of Borras, Tsesmetzis and ZHAO teaches the system of claim 5, and wherein the instructions to execute the correlation process further cause the at least one hardware processor to: extract spatial features of the events emitted by the sensors of the first toll gate and the subset of toll gates (ZHAO, see Claim 2; Claim 6 and Fig 2, step 202, ZHAO teaches spatial feature from toll gate events: “recording the first station information of the toll station” — the toll station identity/name is the spatial feature. “The first station information is the name of the toll station.”) extract temporal features of the events emitted by the sensors of the first toll gate and the subset of toll gates (ZHAO, see Claim 6, ZHAO teaches temporal feature from toll gate events: “at T time” (time of vehicle passage); “corresponding to the current time” (Claim 6; step 202).) and events fired by the base stations proximate to the first toll gate and at least the subset of the plurality of toll gates (ZHAO, see Claim 2, Claim 4 and Claim 6, ZHAO teaches spatial feature from base station events: “the second station information of the communication base station connected with the mobile phone number” — base station identity/site is the spatial feature. The “toll station and communication base station site associated table” encodes geographic relationships. Temporal feature from base station events: “the connection information comprises the connection time” — the connection time is the temporal feature extracted from base station events. From proximate base stations at multiple toll gates: “the toll station A through the vehicle is located in the signal coverage range of the first communication base station.” Performed “for each toll station.”).
Regarding claim 12, the combination of Borras, Tsesmetzis and ZHAO teaches the system of claim 11, and wherein the instructions to calculate the similarity score further cause the at least one hardware processor to: calculate the similarity score using a composite scoring mechanism (ZHAO, see Claim 6, and Fig 2, steps 202-203, ZHAO teaches the confidence level is a composite score computed from multiple factors evaluated together: “adding 1 to the confidence level of the second station information of the communication base station relative to the first station information of the toll station” — incremented only when all factors simultaneously align. Final selection by composite score: “the communication base station with the highest confidence.”) that weighs spatial (ZHAO, see Claim 7, ZHAO teaches spatial similarity weighed: confidence increments only when the base station matches the toll station’s geographic association — “the second station information of the communication base station connected with the mobile phone number is the second station information of the communication base station associated with the toll station through which the vehicle passes.” If spatial correspondence fails, confidence does not increment.), temporal (ZHAO, see the description of ([T-t, T+t]), ZHAO teaches temporal similarity weighed: confidence increments only when temporal overlap is confirmed within [T-t, T+t] — “when the vehicle sample passes through the toll station A at T time… the mobile phone number will be connected to the base station near the toll station A at [T-t, T+t] time period.” If temporal overlap fails, confidence does not increment.) and event similarity (ZHAO, see Claim 7, and Table 1 example, ZHAO teaches event similarity weighed: confidence increments only when the full event chain matches — correct vehicle → correct phone number → correct base station connection verified (Claim 7). The system validates the vehicle-to-device-to-base-station correspondence. If event matching fails, confidence does not increment.).
Regarding claim 15, the combination of Borras and Tsesmetzis teaches the method of claim 13 but does not explicitly teach wherein determining the identification information of the mobile device further comprises: tracking, by the processor, handover information of the mobile device based on the correlation.
Reference ZHAO teaches an ETC charging method for tolls that teaches wherein determining the identification information of the mobile device (ZHAO, see the Abstract, and under the Detailed Ways Section, the description of Fig 1, paragraphs 3-6 and paragraphs 23-38: The ETC system determines which mobile phone number (mobile device) corresponds to the vehicle passing through the toll station. When multiple phone numbers are associated with one vehicle, the system identifies which specific phone is present at the toll station by checking base station connection data.) further comprises: tracking, by the processor (ZHAO, Fig 3, second collecting unit 304 and data processing unit 304, under the Detailed Ways Section, the description of Fig 3, paragraphs 46-50: The processor (data processing unit 304) actively tracks mobile device connection information.), handover information of the mobile device based on the correlation (ZHAO, see under the Detailed Ways Section, the description of Fig 1, paragraphs 3-8 and paragraphs 23-38: The system collects “connection information of the mobile phone number and the communication base station,” which includes “the connection time and the second station information of the communication base station connected with the mobile phone number.” This connection information reveals which base station the device is currently connected to reflecting the result of handovers as the device moves between cells. The system tracks these connections from the operator’s network: “collecting the connection information of the mobile phone number and the communication base station from the mobile communication platform of the operator.” The base station tracking is performed and interpreted based on the pre-established toll station which is equivalent to the base station correlation table.).
These arts are analogous since they are all related to imaging devices that track toll operations. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to modify the toll system of Borras in view of Tsesmetzis to further incorporate tracking of mobile device handover/connection information based on a toll-station-to-base-station correlation, as taught by ZHAO.
ZHAO teaches an ETC toll charging system that collects “connection information of the mobile phone number and the communication base station from the mobile communication platform of the operator” see ZHAO, Claim 4, including connection time and base station identity, and interprets this data “based on the toll station and the communication base station site associated table” see ZHAO, Claim 1 to identify which mobile device is present at the toll station.
One of ordinary skill in the art would have been motivated to combine these teachings because:
(1) Borras already teaches a tolling system that seeks to identify vehicles and reconcile toll transactions, including scenarios where primary identification methods (transponder reading, OCR) fail (Borras, (Borras, Col. 7, line 61 – Col 8, line 19: “missing characters, or characters that could not be identified”), creating a need for alternative or supplemental identification mechanisms. Capturing images at multiple points along the vehicle’s path increases the likelihood of successful identification, as conditions (lighting, angle, obstruction).
ZHAO provides an additional identification and verification mechanism — tracking which mobile device is physically present at the toll station via base station connection data that would supplement Borras’s identification capabilities and provide a fallback identification method.
(2) Tsesmetzis already teaches that mobile devices communicate through base stations proximate to toll zones see Tsesmetzis, paragraph [0041]: “The base station 112 facilitates the communication between the mobile device 104 and the network 110”) and that mobile device location can be inferred from base station proximity see Tsesmetzis, paragraph [0083]: “cell triangulation from nearby base stations 112”).
ZHAO extends this concept by teaching that base station connection data — obtained from the operator’s network can be used not merely for communication, but as an active identification and correlation mechanism.
(3) ZHAO explicitly addresses the problem of identifying the correct mobile device/user when multiple devices are associated with a vehicle: “when the vehicle identification information of the traffic ETC lane is associated with a plurality of mobile phone number, it can automatically and accurately identify the user in the vehicle by collecting respectively connection information of each number and the communication base station” see ZHAO Abstract. This solves a practical problem relevant to any toll system correlating vehicles with mobile devices determining which specific device among many is actually present in the vehicle.
(4) ZHAO teaches that tracking base station connections provides an anti-fraud security mechanism: “intelligent theft-proof, effectively preventing the stolen vehicle, stolen ETC card and so on; when the vehicle and ETC card are separated, the vehicle user ETC account is damaged; greatly enhancing the safety and user account” see ZHAO Abstract. One of ordinary skill would have been motivated to incorporate this security mechanism into the Borras/Tsesmetzis system to verify that the mobile device associated with a toll account is physically present at the toll gate, preventing fraudulent toll evasion.
(5) The combination applies ZHAO’s known technique (tracking mobile device base station connections obtained from the cellular operator and correlating them with toll station passages via a pre-established association table) to improve the Borras and Tsesmetzis combination (a toll system that already correlates toll records with mobile device data) in the same way (adding network-side mobile device tracking for improved identification and verification), yielding the predictable result of a toll system that can identify and verify the mobile device present in a vehicle by tracking its handover/connection information through the cellular network. See KSR Int’l Co. v. Teleflex Inc., 550 U.S. 398, 416 (2007); MPEP § 2143(I)©.
Regarding claim 16, the combination of Borras, Tsesmetzis and ZHAO teaches the method of claim 13, and also wherein determining the identification information of the mobile device further comprises: extracting, by the processor, location data of the base stations (ZHAO, see under the Detailed Ways Section, the description of Figs 1 and 2, paragraphs 3-12: The system collects “the second station information of the communication base station capable of covering each toll station in the first station information” see Claim 2. The system builds a “toll station and communication base station site associated table” see Claim 2 and Fig1, step 102. The word “site” explicitly denotes location/geographic information. The association table maps which base stations geographically cover which toll stations. This requires and encodes base station location data.), and timestamp information indicating mobile devices that are connected to corresponding ones of the base stations (ZHAO, see claim 4 and claim 11 and Fig 1, step 105 and Table 1 Example: ZHAO explicitly teaches extracting timestamp information (connection time) indicating which mobile devices (mobile phone numbers) are connected to which base stations (second station information)) at time of passage of the vehicle through the first toll gate (ZHAO, see claim 1 and claim 6, Fig 1, steps 103-105 and Fig 2, step 202 and description of the time window [T-t, T+t]): The time window is defined as [T-t, T+t] around the passage time T: “when the vehicle sample passes through the toll station A at T time… the mobile phone number will be connected to the base station near the toll station A at [T-t, T+t] time period”.)(Connection information explicitly collected “corresponding to the current time” when “the vehicle passes through the ETC lane of the toll station” and at least the subset of the plurality of toll gates.) and at least the subset of the plurality of toll gates (ZHAO, see claim 6 and Fig 1, step 102 and Fig 2, step 202-203 (for each toll station))(Process explicitly performed at each of multiple toll stations).
Regarding claim 17, the combination of Borras, Tsesmetzis and ZHAO teaches the method of claim 13, and teaches wherein identification information of the mobile device further comprises one or more of International Mobile Equipment Identity (IMEI), International Mobile Subscriber Identity (IMSI), and Mobile Station International Subscriber Directory Number (MSISDN) (ZHAO, see claim 1, “determining the mobile phone number corresponding to the vehicle according to the identification information of the vehicle”{MSISDN used as device identifier} ZHAO explicitly and extensively teaches MSISDN (mobile phone number) as the identification information of the mobile device. The entire system is built around using the “mobile phone number” to identify the mobile device. MSISDN is the mobile phone number — they are technically identical.).
Regarding claim 19, the combination of Borras, Tsesmetzis and ZHAO teaches the non-transitory processor-readable storage medium of claim 18, and teaches wherein a particular data record of the toll records comprises in addition to the sensor data (Tsesmetzis, paragraphs [0003] and [0044]: Toll gates generate records: “an entry toll gate to indicate the vehicle has entered the toll zone and an exit toll gate, which indicates the vehicle has exited the toll zone” see paragraph [0044]. Background: “modern toll gates also typically have licence plate recognition” see paragraph [0003] — sensor data in toll records.), location data corresponding to a location of a toll gate generating the data record (Tsesmetzis, paragraphs [0062], [0087], [0095-0098], [0136]: Toll zone location data is associated with toll records.) and time data corresponding to a time of capture of the data record by one or more of the sensors of the toll gate (ZHAO, see claim 6 and Fig 2, step 202: Toll data records include time of capture: “when the vehicle passes through the ETC lane of the toll station” the time of passage is recorded. “collecting the second station information of the communication base station connected with the mobile phone number corresponding to the current time and the vehicle identification information” (Claim 6; step 202). The “current time” when the vehicle passes and sensors capture data is recorded. Also: “when the vehicle sample passes through the toll station A at T time” (Description) — explicit timestamp of sensor capture event.) and wherein the mobile communication network data comprises mobile device information generated by one or more of the base stations (ZHAO, see claim 4 and claim 11 and Fig 1, step 105: Explicitly teaches mobile device information generated by/accessible from base stations. “collecting the connection information of the mobile phone number and the communication base station from the mobile communication platform of the operator” (Claim 4). Alternatively: “when owning authorization, directly communicating with the communication base station; determining the connection information of the mobile phone number and the communication base station through the information sent by the communication base station” (Claim 4). This explicitly states that the base station generates/sends information about which mobile devices are connected.), the mobile device information comprising timestamp data (ZHAO, see claim 4, claim 6, claim 11 and Fig 1, step 105: Explicitly teaches timestamp data in the mobile device information: “the connection information comprises the connection time and the second station information of the communication base station connected with the mobile phone number” (Claim 4). The “connection time” is timestamp data — indicating WHEN the mobile device was connected to the base station. Additionally: “collecting the second station information of the communication base station connected with the mobile phone number corresponding to the current time” (Claim 6) — temporal data associated with the connection record. Example: “[T-t, T+t] time period” (Description) — explicit time window tracked.), mobile device identification data (ZHAO, see claim 4, Fig 1, step 105 and Table 1 example: mobile phone numbers “13088888888”, “13077777777”): “Mobile phone number” (MSISDN) = mobile device identification data in the base station connection records.), and location data of the base stations (ZHAO, see claim 1, claim 4, claim 6 and Fig 4, step 102: Explicitly teaches location data of the base stations as part of the connection records/association table: “the second station information of the communication base station” (Claim 2, 4, 6) — this identifies the base station, which has a known geographic location. “toll station and communication base station site associated table” (Claim 2) — the word “site” denotes geographic location. “the toll station A through the vehicle is located in the signal coverage range of the first communication base station” (Description) — geographic coverage area known. The association table maps base station identity/location to toll station identity/location. Furthermore: “second station information is the name of the communication base station” (Claim 2) — the name/identifier of the base station which corresponds to a specific physical location. The system knows WHERE each base station is (relative to toll stations) and this location data is stored in the site association table and used in the determination process.).
Regarding claim 20, the combination of Borras, Tsesmetzis and ZHAO teaches the non-transitory processor-readable storage medium of claim 18, and teaches wherein the notification comprises transaction information associated with the vehicle (Tsesmetzis, paragraphs [0057-0058], [0063]: Notifications explicitly contain transaction information associated with the vehicle: “Notifications relating to a toll may include… a notification that a toll is payable, and may include a payable amount” see paragraph [0057]. “the notification may include one or more of: toll zone information, such as an indication of the toll zone 107 for which the toll is payable; a monetary amount of the toll; and an indication of the time of travel through the toll zone 107” see paragraph [0058]. The notification is associated with the specific vehicle: “a notification may be sent to a mobile device 104 associated with a user 106 that a toll is due” see paragraph [0063] the user’s device is associated with their vehicle.), a link configured to facilitate payment of the toll for the vehicle (Tsesmetzis, paragraphs [0046], [0056-0057], [0063-0064]: Tsesmetzis teaches notifications that facilitate payment: “Notifications relating to a toll may include… a notification that a toll is payable, and may include a payable amount” see paragraph [0057]. The system processes payments through the mobile device: “the server 120 may process payment of the toll using the mobile device 104” see paragraph [0056]. Critically: “a notification may be sent to a mobile device 104 associated with a user 106 that a toll is due, and a payment for the toll may be processed through a linked payment method” see paragraph [0063]. The notification triggers/facilitates payment processing. Furthermore: “the notification may provide an option to select an account to use to pay the toll” see paragraph [0064]. “The notification may include a payment confirmation” see paragraph [0065]. Tsesmetzis also teaches: “the mobile device 104 may include an application… configured to… facilitate payment of tolls” see paragraph [0046]. The application on the device processes toll payments and can be activated/linked through notifications. The notification provides a mechanism to initiate/facilitate payment — either through the linked payment method or by presenting the user with an option to select an account and pay.).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SUPERVISORY PATENT EXAMINER TWYLER HASKINS whose telephone number is (571)272-7406. The SUPERVISORY PATENT EXAMINER TWYLER HASKINS can normally be reached Mon- Thursday: 7:30 am-4:30 pm.
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:/Awwww.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, GROUP DIRECTOR GREGORY TOATLEY can be reached at (571) 272-4650. 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:/Awww.uspto.gov/patents/apply/patent-center for more information about Patent Center and https:/Awww.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.
/TWYLER L HASKINS/ Supervisory Patent Examiner, Art Unit 2639
Prosecution Insights