DETAILED ACTION
The following NON-FINAL Office Action is in response to application 18/792560 filed on 08/02/2024.
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 . 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 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.
Status of Claims
Claims 1-16 are currently pending and have been rejected as follows.
Claim Objections
Claims 11-12 and 14-16 are objected to because of the following informalities:
Claim 11 recites the limitation “wherein the ML models control decides when and how each asset tracker obtains a future tracking point along its route”. Examiner recommends Applicant amend the claim to recite either “wherein the ML models control when” or “wherein the ML models decides when”. Dependent Claim 12 inherits the objection as it does not cure the deficiencies of Claim 11.
Claim 14 recites the limitation “wherein the ML-based adaptive tracking server uses a suite of ML-based adaptive tracking model to adjust a tracking rate or upload time of the next set of adaptive tracking units on-the-fly when a before entering a no signal spot”. Examiner recommends Applicant amend the claim by removing “when a”. Dependent Claims 15-16 inherit the objection as they do not cure the deficiencies of Claim 14.
Claim 15 recites the limitation “wherein the ML-based adaptive tracking server uses a suite of ML-based adaptive tracking models to adjust its tracking rate or upload time on-the-fly to prevent an unnecessary transmission attempt the next set of adaptive tracking units”. Examiner recommends Applicant amend the limitation to recite “attempt of the next set of adaptive tracking units”. Dependent Claim 16 inherits the objection as it does not cure the deficiencies of Claim 15.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 13-16 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 13 recites the limitation of “using the plurality of adaptive tracking units to collect all tracking information; uploading all the tracking information to the ML‐based adaptive tracking server; with the adaptive tracking server, using all the information uploaded from all adaptive tracking units to train an ML‐based adaptive tracking model”.
The term “all” renders the claim indefinite as it is unclear what “all tracking information” includes and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Examiner interprets and recommends Applicant amend the claim limitations to recite “using the plurality of adaptive tracking units to collect tracking information; uploading the tracking information to the ML‐based adaptive tracking server; with the adaptive tracking server, using all the information uploaded from all adaptive tracking units to train an ML‐based adaptive tracking model”. Dependent Claims 14-16 inherit the rejection as they do not cure the deficiencies of claim 13.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-2, 4, and 13-16 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1
Claims 1-2, 4, and 13-16 are directed to a method (i.e., a process). Thus, all the claims fall within one of the four statutory categories of invention.
Regarding Claims 1-2 and 4
Step 2A Prong 1
Independent Claim 1 recites the limitations of:
…tracks one or more IoT assets;
… change and update a … tracking rate utilized by the asset tracker; and
…based on learned behavior of similar trackers that followed a same route or a similar route to the route followed by the plurality of asset trackers.
Organizing Human Activity
The limitations of Claim 1 stated above are processes that under broadest reasonable interpretation covers “certain methods of organizing human activity” (managing personal behavior or relationships or interactions between people or commercial/legal interactions). Specifically, commercial interactions or business relations directed to asset tracking in light of paragraph 114 of Applicant’s specification “In some examples, the mobile units 210 can be implemented in vehicle tracking such as monitoring routes of the vehicle, fuel consumption of the vehicle, driver behavior, and even facilitate theft prevention and recovery. The mobile units 210 can be implemented in a cargo and supply chain management situation such as monitoring shipments to reduce theft, misplacement, and ensure that the cargo reaches their destination on time. The mobile units 210 can be implemented in tracking personal assets and valuables such as keeping location data 30 of personal valuables like boats, motorcycles, and expensive equipment. The mobile units 210 can be implemented in rental and leasing scenarios such as maintaining the safe and correct usage of equipment, vehicles, and other assets. The mobile units 210 can be implemented in field service management such as monitoring the location of on-field employees and equipment and improving efficiency and coordination.”
Accordingly, the limitations above recite a judicial exception (an abstract idea that falls within the organizing human activity grouping) and the analysis must therefore proceed to Step 2A Prong 2.
Step 2A Prong 2
The judicial exception is not integrated into a practical application. In particular, Claim 1 recites the additional elements of “providing a plurality of asset trackers following a route” and “configuring each asset tracker to autonomously change and update the tracking technology” which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use. Limiting application of the abstract idea to asset tracking and monitoring by asset trackers is simply an attempt to limit the use of the abstract idea to a particular technological environment. See MPEP2106.05(h).
Further “training and validating a plurality of autonomous asset machine-learned (ML) models” may also amount to generally linking the use of the judicial exception to a particular technological environment or field of use specifically limiting the abstract idea to a machine learning environment.
Accordingly, the additional elements do not integrate the abstract idea into a practical application, whether individually or viewed in an ordered combination, because field of use does not impose meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
Step 2B
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “providing”, “configuring”, and “training” amount to generally linking the use of the judicial exception to a particular technological environment or field of use. Limiting application of the abstract idea to asset tracking/configuring/monitoring by the asset trackers and to a machine learning environment is simply an attempt to limit the use of the abstract idea to a particular technological environment.
None of the steps of Claim 1 when evaluated individually or as an ordered combination amount to significantly more than the abstract idea. The additional elements are merely used to perform the limitations directed to organizing human activity, thus, the analysis does not change when considered as an ordered combination. Even when considered in combination, the additional elements of Claim 1 amount to no more generally linking to a field of use which cannot provide an inventive concept. Thus, the additional elements do not meaningfully limit the claim. Accordingly, claim 1 is ineligible.
Dependent Claim 2 recites an additional element of one or more mobile units which are recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component. See MPEP2106.05(f). Further tracking the one or more mobile units is further narrowing the abstract idea identified above.
Dependent Claim 4 specifies that each asset tracker uses a plurality of tracking technologies and tracking rate or upload time which is further narrowing the abstract idea identified above.
Nothing in dependent claims 2 and 4 adds additional elements that are sufficient to amount to significantly more than the judicial exception. Accordingly, claims 1-2 and 4 are ineligible.
Examiner recommends Applicant further define what the tracking technologies are and how the ML models control the tracking technologies in order to overcome the eligibility rejection. For example, paragraph 116 of Applicant’s specification details a tracking technology of adjusting a communication standard and/or Claim 6 further specifies tracking ping rates are controlled.
Regarding Claims 13-16
Step 2A Prong 1
Independent Claim 13 recites the limitations of:
…records a location, a location availability, a sensor data and transmits the location, the location availability, the sensor data information
… collect all tracking information;
uploading all the tracking information …;
… using all the information uploaded…; and
… deciding when and how a next set of adaptive tracking units obtain tracking points along a tracked route that is the same as or similar to the first route.
Organizing Human Activity
The limitations of Claim 13 stated above are processes that under broadest reasonable interpretation covers “certain methods of organizing human activity” (managing personal behavior or relationships or interactions between people or commercial/legal interactions). Specifically, commercial interactions or business relations directed to asset tracking in light of paragraph 114 of Applicant’s specification “In some examples, the mobile units 210 can be implemented in vehicle tracking such as monitoring routes of the vehicle, fuel consumption of the vehicle, driver behavior, and even facilitate theft prevention and recovery. The mobile units 210 can be implemented in a cargo and supply chain management situation such as monitoring shipments to reduce theft, misplacement, and ensure that the cargo reaches their destination on time. The mobile units 210 can be implemented in tracking personal assets and valuables such as keeping location data 30 of personal valuables like boats, motorcycles, and expensive equipment. The mobile units 210 can be implemented in rental and leasing scenarios such as maintaining the safe and correct usage of equipment, vehicles, and other assets. The mobile units 210 can be implemented in field service management such as monitoring the location of on-field employees and equipment and improving efficiency and coordination.”
Accordingly, the limitations above recite a judicial exception (an abstract idea that falls within the organizing human activity grouping) and the analysis must therefore proceed to Step 2A Prong 2.
Step 2A Prong 2
The judicial exception is not integrated into a practical application. In particular, Claim 13 recites the additional elements of a remote storage and analysis service comprising a machine learning (ML)-based adaptive tracking server and a ML-based adaptive tracking model. Each additional element is recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component. See MPEP2106.05(f).
Claim 13 also recites “providing a plurality of adaptive tracking units along a first route” which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use. Limiting application of the abstract idea to asset tracking and monitoring by adaptive tracking units is simply an attempt to limit the use of the abstract idea to a particular technological environment. See MPEP2106.05(h).
Further “train an ML-based adaptive tracking model” may also amount to generally linking the use of the judicial exception to a particular technological environment or field of use. Limiting application of the abstract idea of “deciding” to execution by the trained ML-based adaptive tracking model is simply an attempt to limit the use of the abstract idea to a particular technological environment.
Accordingly, the additional elements do not integrate the abstract idea into a practical application, whether individually or viewed in an ordered combination, because mere instructions to apply the exception using a generic computer component and field of use does not impose meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
Step 2B
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of a remote storage and analysis service comprising a machine learning (ML)-based adaptive tracking server and a ML-based adaptive tracking model to perform the limitations noted above amount to no more than mere instructions to apply the exception using a generic computer component.
Again, “providing” and “train” amount to generally linking the use of the judicial exception to a particular technological environment or field of use. Limiting application of the abstract idea to asset tracking/monitoring by the adaptive tracking units and execution by the trained ML-based adaptive tracking model is simply an attempt to limit the use of the abstract idea to a particular technological environment.
None of the steps of Claim 13 when evaluated individually or as an ordered combination amount to significantly more than the abstract idea. The additional elements are merely used to perform the limitations directed to organizing human activity, thus, the analysis does not change when considered as an ordered combination. Even when considered in combination, the additional elements of Claim 13 amount to no more than mere instructions to implement the abstract idea on a computer and field of use which cannot provide an inventive concept. Thus, the additional elements do not meaningfully limit the claim. Accordingly, claim 13 is ineligible.
Dependent Claim 14 and Claim 15 add an additional element of a suite of ML-based adaptive tracking models which are recited at a high-level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component. See MPEP2106.05(f).
Further the models merely adjust a tracking rate/upload time which is further narrowing the abstract idea identified above.
Dependent Claim 16 adds an additional element of a machine learning algorithm trained which is limiting application of the abstract idea of “predict route issues for the next set of adaptive tracking units” to execution by the trained ML algorithm. Thus, the limitation is generally linking the use of the abstract idea to a particular technological environment.
Nothing in dependent claims 14-16 adds additional elements that are sufficient to amount to significantly more than the judicial exception. Accordingly, claims 13-16 are ineligible.
Examiner notes that “a suite of ML-based adaptive tracking models” of Claims 14-15 is not related to the trained “ML-based adaptive tracking model” of Claim 13.
Examiner recommends Applicant amend the claims to link the trained “ML-based adaptive tracking model” of Claim 13 to the concept of Claims 14-15. As an example for Applicant’s consideration: “wherein based on the ML-based adaptive tracking model, the ML- based adaptive tracking server determines when the next set of adaptive tracking units will enter a no signal spot, and before the next set of adaptive tracking units enters the determined no signal spot, the ML- based adaptive tracking server adjusts a tracking rate or upload time of next set of adaptive tracking units on-the-fly”.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-16 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Chen et al. (US2025/0119834).
As per independent Claim 1,
Chen teaches a method for machine-learning (ML) based adaptive Internet of Things (IoT) asset tracking comprising: (para. 27 IoT devices in vehicles that travel over a geographic area and are configured to wake up at predefined intervals to perform a position fix and collect sensor data and transmit it to the fleet management system (FMS) backend which uses the data to manage the IoT devices)
providing a plurality of asset trackers following a route, wherein each asset tracker tracks one or more IoT assets (para. 56 and para. 82 IoT device; figure 6 and para. 99-100 plurality of IoT devices may be or may include the user equipment (UE) and they may be located on vehicles or shipping containers; figure 7 and para. 108-109 IoT devices used to track and manage assets being transported and they report position fix and sensor data along a route; figure 9 and para. 119-122 where in para. 120-121 data is collected)
configuring each asset tracker to autonomously change and update a tracking technology and tracking rate utilized by the asset tracker (figure 8 and para. 110-118 specifically para. 116 “determine a course of action to take that conserves battery life of the first IoT device 604 while meeting reporting criteria” where the IoT device determines a time to wake up, whether to determine position fix and collect sensor data, and whether to transmit the data; para. 117 where the IoT device determines when to sleep and when to wake up and para. 118 when to enter a standby mode)
training and validating a plurality of autonomous asset machine-learned (ML) models based on learned behavior of similar trackers that followed a same route or a similar route to the route followed by the plurality of asset trackers (para. 128 where the ML model facilitates an IoT device to make better decisions pertaining to waking up to perform position fixes and/or report sensor data, enables an IoT device to wake up at an opportunistic time to determine position information and send it to the FMS backend, etc.; see also para. 112-118 where in para. 112 “based on prior knowledge from IoT devices that experienced conditions similar to those of the first IoT device 604, the server ML/AI model 822 may predict a likelihood (i.e., a probability) of a success of an event” where the conditions are based on the fleet characteristics in para. 111 indications of paths travelled by the fleet of IoT devices and para. 86 “in one aspect, an improved fleet management system is described herein in which UEs wake up to perform position fixes and in which the UEs transmit in high probability situations (as opposed to low probability situations). This can be predicted by artificial intelligence (AI)/machine learning (ML) based on knowledge from previous devices that experienced similar conditions”; figure 9 and para. 122-127 “training” - where the ML models are trained and “validating” in para. 127 the weights of the machine learning model may be adjusted to reduce error and move the output closer to the target and para. 45-46 ML model training and updates – tuning and corrective actions (“validating”))
As per dependent Claim 2,
Chen teaches the method of claim 1.
Chen further teaches:
wherein each asset tracker tracks one or more mobile units (figure 6 and para. 99-100 plurality of IoT devices may include the user equipment (UE) and they may be located on vehicles or shipping containers; para. 56 and para. 82 IoT device; figure 7 and para. 108-109 IoT devices used to track and manage assets being transported and they report position fix and sensor data along a route; see also para. 27)
As per dependent Claim 3,
Chen teaches the method of claim 2.
Chen further teaches:
wherein the ML models control a behavior of the one or more mobile units to conserve a battery power of the one or more mobile units (para. 28 IoT device may have a limited battery life so waking up and unsuccessfully transmitting position fix and sensor data may rapidly drain the battery; para. 29 “a UE may conserve battery power by opportunistically waking up at a time when performance of the position fix and/or transmission of the sensor data is likely to be successful, as opposed to blindly waking up at a predetermined wake-up time instance where the UE has no knowledge of whether performance of the position fix and/or transmission of the sensor data will be successful”; Para. 86 Using this information passed from a backend to the device, the device may run a local ML/AI engine to determine a suitable course of action to take to conserve battery based on reporting criteria of the device and current conditions; see also figure 8 and para. 110-118 specifically para. 116 “determine a course of action to take that conserves battery life of the first IoT device 604 while meeting reporting criteria” where the IoT device determines a time to wake up, whether to determine position fix and collect sensor data, and whether to transmit the data)
As per dependent Claim 4,
Chen teaches the method of claim 1.
Chen further teaches:
wherein each asset tracker utilize a plurality of tracking technologies and tracking rate or upload time (para. 110-118 where in para. 116 where the IoT device determines a time to wake up, whether to determine position fix and collect sensor data, (“tracking technologies”) and whether to transmit the data (“tracking rate or upload time”); para. 117 the IoT device decides when to sleep and wake up (“tracking technologies”); see also para. 111 fleet characteristics such as indications of paths, retries of transmissions, signal power, device battery which are used in para. 112 to compute the likelihood of success of performing the position fix and transmitting sensor data and para. 55 to perform the position fix through use of signal measurements, a position estimate, and velocity computation)
As per dependent Claim 5,
Chen teaches the method of claim 4.
Chen further teaches:
wherein the ML models control a plurality of tracking technologies of each asset tracker to conserve a battery power of each asset tracker (para. 28 IoT device may have a limited battery life so waking up and unsuccessfully transmitting position fix and sensor data may rapidly drain the battery; para. 29 “a UE may conserve battery power by opportunistically waking up at a time when performance of the position fix and/or transmission of the sensor data is likely to be successful, as opposed to blindly waking up at a predetermined wake-up time instance where the UE has no knowledge of whether performance of the position fix and/or transmission of the sensor data will be successful”; para. 86 Using this information passed from a backend to the device, the device may run a local ML/AI engine to determine a suitable course of action to take to conserve battery based on reporting criteria of the device and current conditions; see also para. 112-118 specifically para. 117 the IoT device decides when to sleep and wake up as low power sleep mode consumes less battery power; see also para. 28 and 128)
As per dependent Claim 6,
Chen teaches the method of claim 5.
Chen further teaches:
wherein the ML models control a plurality of tracking ping rates of each asset tracker to conserve the battery power of each asset tracker (para. 96-99 where in para. 96 frequencies of position fixes based on tradeoff between a frequency of an update and power; para. 28 IoT device may have a limited battery life so waking up and unsuccessfully transmitting position fix and sensor data may rapidly drain the battery; para. 29 “a UE may conserve battery power by opportunistically waking up at a time when performance of the position fix and/or transmission of the sensor data is likely to be successful, as opposed to blindly waking up at a predetermined wake-up time instance where the UE has no knowledge of whether performance of the position fix and/or transmission of the sensor data will be successful”; para. 86 Using this information passed from a backend to the device, the device may run a local ML/AI engine to determine a suitable course of action to take to conserve battery based on reporting criteria of the device and current conditions; see also para. 112-118 specifically para. 116 where the IoT device wakes up and performs position fix and collects sensor data without transmitting both to the FMS backend due to predicted interference; see also para. 28 and 128)
As per dependent Claim 7,
Chen teaches the method of claim 6.
Chen further teaches:
wherein the plurality of tracking technologies comprises a location of each mobile unit (para. 116 where the IoT device determines a course of action to take such as waking up at time T(j) and reporting a position fix and/or transmit sensor data; para. 55 compute the position of the UE; para. 89 position fix of the IoT device; para. 111 indications of path travelled by the fleet of IoT devices provided as a time series data of longitude and latitude coordinates; see also figure 4 and para. 76-81)
As per dependent Claim 8,
Chen teaches the method of claim 7.
Chen further teaches:
wherein the plurality of tracking technologies comprises a location source of each mobile unit (para. 116 where the IoT device determines a course of action to take such as waking up at time T(j) and reporting a position fix and/or transmit sensor data; para. 55 positioning the UE involves signal measurements based on various signals and systems such as NR signals, NR enhanced cell ID, DL time difference of arrival, etc. which are techniques that rely on identifying a source of the signal in order to determine the location of the UE; see also para. 119-122 where in 120, wireless connectivity on routes include spatial and temporal variations where spatial variations include distance of an IoT device to a signal source and structures near the IoT device and signal source and temporal variations include situations like heavy network traffic; para. 63 the UE can determine the physical cell identifier and use it to determine the demodulation RS; see also figure 4 and para. 76-81)
As per dependent Claim 9,
Chen teaches the method of claim 8.
Chen further teaches:
wherein the plurality of tracking technologies comprises a location fix time of each mobile unit (para. 116 where the IoT device determines a course of action to take such as waking up at time T(j) and reporting a position fix and/or transmit sensor data; figure 4 and para. 76-81 where the UE position is based on reference signal measurements that account for time difference – the UE transmits UL-SRS at a Time (SRS_TX) and receives a positioning reference signal at a Time (PRS_RX) and the UE may determine the round trip time (RTT) which is used to estimate the location of the UE (“location fix time”); para. 55 positioning the UE involves signal measurements based on various signals and systems such as NR signals, NR enhanced cell ID, DL time difference of arrival, UL-TDOA etc. which are techniques that rely on identifying a source of the signal and identifying the time differences of signal arrival in order to determine the location of the UE; see also para. 111 “the indications of the paths 812 may be time series data of longitude and latitude coordinates”)
As per dependent Claim 10,
Chen teaches the method of claim 9.
Chen further teaches:
wherein the plurality of tracking technologies comprises a radio type used by each mobile unit (para. 116 where the IoT device determines a course of action to take such as waking up at time T(j) and reporting a position fix and/or transmit sensor data; para. 48-49 UEs communicate through a variety of communication systems such as Bluetooth, WIFI, LTE, NR; para. 55 to compute the position of the UE through use of signal measurements, a position estimate, and velocity computation where the signal measured may be based on a satellite positioning system, LTE signals, wireless local area network signals, Bluetooth signals, etc.; para. 86, 97-98, 109 considerations of connectivity and coverage conditions of UE’s; para. 120 wireless connectivity on routes by measuring connectivity signals; see also figure 4 and para. 76-81)
As per dependent Claim 11,
Chen teaches the method of claim 10.
Chen further teaches:
wherein the ML models control decides when and how each asset tracker obtains a future tracking point along its route (para. 128 where the ML model facilitates an IoT device to make better decisions pertaining to waking up to perform position fixes and/or report sensor data, enables an IoT device to wake up at an opportunistic time to determine position information and send it to the FMS backend, etc.; “when and how” - para. 112-118 where after analysis by the ML models, in para. 116 the IoT device determines a time to wake up, whether to determine position fix and collect sensor data, and whether to transmit the data; see also para. 86)
As per dependent Claim 12,
Chen teaches the method of claim 11.
Chen further teaches:
wherein the ML models reduce a power demand of each tracker by not requiring an update during a portion of the route where there is a weaker network connectivity (para. 86 “Some approaches for asset tracking and monitoring may not consider connectivity/coverage conditions of UEs. If a device wakes up at its periodic interval and performs a GPS fix and wireless connectivity (e.g., cellular, WLAN, satellite, etc.) is poor, the device may not be able to send data to the server”; Para. 97-99 IoT devices may encounter “dead zone” of coverage; see also para. 112-118 specifically para. 116 where the IoT device wakes up and transmits sensor data without performing a position fix due to poor coverage for location determination and where the IoT device wakes up and performs position fix and collects sensor data without transmitting both to the FMS backend due to predicted interference; see also para. 28-29 “a UE may conserve battery power by opportunistically waking up at a time when performance of the position fix and/or transmission of the sensor data is likely to be successful, as opposed to blindly waking up at a predetermined wake-up time instance where the UE has no knowledge of whether performance of the position fix and/or transmission of the sensor data will be successful”; see also para. 128)
As per independent Claim 13,
Chen teaches a method for implementing adaptive tracking for asset tracking of a set of mobile units comprising: (para. 27 IoT devices in vehicles that travel over a geographic area and are configured to wake up at predefined intervals to perform a position fix and collect sensor data and transmit it to the fleet management system (FMS) backend which uses the data to manage the IoT devices)
providing a plurality of adaptive tracking units along a first route, wherein each adaptive tracking unit records a location, a location availability, a sensor data and transmits the location, the location availability, the sensor data information to a remote storage and analysis service comprising a Machine Learning (ML)‐based adaptive tracking server (para. 56 and para. 82 IoT device; figure 6 and para. 99-100 plurality of IoT devices may be or may include the user equipment (UE) and they may be located on vehicles or shipping containers; “location” - para. 101 IoT device includes a position fix unit that determines a position of the IoT device; “sensor data” - para. 102 IoT device includes sensors which collect sensor data; para. 106 IoT device includes a signal predictor that determines opportunistic times to wake up to perform the position fix and report the position fix and sensor data to the FMS backend; para. 110 FMS backend collects fleet characteristics of the fleet of IoT devices; “location availability” - para. 111 the fleet characteristics include indications of signal power of the fleet of IoT devices; see also for location availability para. 86, 97-98, 109 considerations of connectivity and coverage conditions of UE’s; para. 120 wireless connectivity on routes by measuring connectivity signals; see also figure 4 and para. 76-81)
using the plurality of adaptive tracking units to collect all tracking information (figure 7 and para. 108-109 IoT devices used to track and manage assets being transported and they report position fix and sensor data along a route; figure 9 and para. 119-122 where in para. 120-121 data is collected from the IoT devices)
uploading all the tracking information to the ML‐based adaptive tracking server (figure 6 and para. 105 the FMS backend may be a server; para. 103-105 where the position fix and sensor data are transmitted to the FMS backend; para. 110 FMS backend collects fleet characteristics of the fleet of IoT devices; figure 9 and para. 119-122 where in para. 122 the FMS backend may accumulate historical data to train the ML engine)
with the adaptive tracking server, using all the information uploaded from all adaptive tracking units to train an ML‐based adaptive tracking model (para. 105 FMS backend may process and analyze position fix, sensor data, and other data to identify anomalies pertaining to the IoT devices and may also update a location and health status of the IoT devices; figure 8 and para. 110-112 where in para. 111 the fleet characteristics include indications of signal power of the fleet of IoT devices and in para. 112 the server ML engine of the FMS backend computes a first likelihood of success of the IoT device successfully transmitting position fix and sensor data; figure 9 and para. 122-127 where the ML model is trained)
with the ML‐based adaptive tracking model, deciding when and how a next set of adaptive tracking units obtain tracking points along a tracked route that is the same as or similar to the first route (para. 128 where the ML model facilitates an IoT device to make better decisions pertaining to waking up to perform position fixes and/or report sensor data, enables an IoT device to wake up at an opportunistic time to determine position information and send it to the FMS backend, etc.; see also para. 112-118 where in para. 112 “based on prior knowledge from IoT devices that experienced conditions similar to those of the first IoT device 604, the server ML/AI model 822 may predict a likelihood (i.e., a probability) of a success of an event” where the conditions are based on the fleet characteristics in para. 111 indications of paths travelled by the fleet of IoT devices and para. 86 “in one aspect, an improved fleet management system is described herein in which UEs wake up to perform position fixes and in which the UEs transmit in high probability situations (as opposed to low probability situations). This can be predicted by artificial intelligence (AI)/machine learning (ML) based on knowledge from previous devices that experienced similar conditions.”)
As per dependent Claim 14,
Chen teaches the computerized method of claim 13.
Chen further teaches:
wherein the ML-based adaptive tracking server uses a suite of ML-based adaptive tracking model to adjust a tracking rate or upload time of the next set of adaptive tracking units on-the-fly when a before entering a no signal spot (Para. 128 “Third, as ML/AI engines may run on both an FMS backend and on an IoT device, the backend may leverage the historical data and the IoT device may utilize an output of the backend ML/AI engine and data pertaining to a current situation of the IoT device in order to determine a next action to take” where the actions would be when to wake up to perform position fixes and/or report data to the FMS backend; para. 86 “Some approaches for asset tracking and monitoring may not consider connectivity/coverage conditions of UEs. If a device wakes up at its periodic interval and performs a GPS fix and wireless connectivity (e.g., cellular, WLAN, satellite, etc.) is poor, the device may not be able to send data to the server”; Para. 97-99 IoT devices may encounter “dead zone” of coverage; see also para. 112-118 specifically para. 111 fleet characteristics such as indications of paths travelled, retries of transmission, and signal power of the fleet of IoT devices, para. 112 fleet characteristics used as “prior knowledge from IoT devices that experienced conditions similar to those of the first IoT device”, para. 115 “based on prior knowledge from IoT devices that experienced conditions similar to those of the first IoT device 604 and based on current conditions of the first IoT device 604”, para. 116 where the IoT device wakes up and transmits sensor data without performing a position fix due to poor coverage for location determination)
As per dependent Claim 15,
Chen teaches the computerized method of claim 14.
Chen further teaches:
wherein the ML-based adaptive tracking server uses a suite of ML-based adaptive tracking models to adjust its tracking rate or upload time on-the-fly to prevent an unnecessary transmission attempt the next set of adaptive tracking units (para. 28 IoT device may have a limited battery life so waking up and unsuccessfully transmitting position fix and sensor data may rapidly drain the battery; para. 29 “a UE may conserve battery power by opportunistically waking up at a time when performance of the position fix and/or transmission of the sensor data is likely to be successful, as opposed to blindly waking up at a predetermined wake-up time instance where the UE has no knowledge of whether performance of the position fix and/or transmission of the sensor data will be successful”; para. 86 Using this information passed from a backend to the device, the device may run a local ML/AI engine to determine a suitable course of action to take to conserve battery based on reporting criteria of the device and current conditions; Para. 128 “Third, as ML/AI engines may run on both an FMS backend and on an IoT device, the backend may leverage the historical data and the IoT device may utilize an output of the backend ML/AI engine and data pertaining to a current situation of the IoT device in order to determine a next action to take” where the actions would be when to wake up to perform position fixes and/or report data to the FMS backend; see also para. 112-118 specifically para. 111 fleet characteristics such as indications of paths travelled, retries of transmission, and signal power of the fleet of IoT devices, para. 112 fleet characteristics used as “prior knowledge from IoT devices that experienced conditions similar to those of the first IoT device”, para. 115 “based on prior knowledge from IoT devices that experienced conditions similar to those of the first IoT device 604 and based on current conditions of the first IoT device 604”, para. 116 where the IoT device wakes up and performs position fix and collects sensor data without transmitting both to the FMS backend due to predicted interference; see also para. 28)
As per dependent Claim 16,
Chen teaches the computerized method of claim 15.
Chen further teaches:
wherein a machine learning algorithm is trained to predict route issues for the next set of adaptive tracking units (para. 98 challenges in tracking and managing the fleet of IoT devices “route issues” such as lack of knowledge about whether location determination is possible and whether connectivity is available to send location and health data, dead zones of coverage, etc.; para. 86 “UEs wake up to perform position fixes and in which the UEs transmit in high probability situations (as opposed to low probability situations). This can be predicted by artificial intelligence (AI)/machine learning (ML) based on knowledge from previous devices that experienced similar conditions”; para. 106, 112-118 signal predictor used to determine opportunistic times to wake up to perform position fix and report position fix; see also 119-122)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Jantzi et al. (US2024/0292185)
Silverman et al. (US2022/0239531)
Ramalho de Oliveira et al. (US2021/0211852)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Lisa Ma whose telephone number is (571)272-2495. The examiner can normally be reached Monday to Thursday 7 AM - 5 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://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shannon Campbell can be reached at (571)272-5587. 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.
/L.M./Examiner, Art Unit 3628
/RUPANGINI SINGH/Primary Examiner, Art Unit 3628