DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Specifically, representative Claim 1 recites:
A method, performed at a computing system comprising a processor and a memory, comprising: receiving load data from a load sensor, wherein the load sensor is coupled to a storage area of a shopping cart, wherein the load data comprises load measurements captured by the load sensor, and wherein the load measurements are samples from the load sensor that form a timeseries; detecting, based on the load data, that an item was added to the storage area of the shopping cart; identifying a first set of load measurements captured by the load sensor during a first time period when the item was added; computing a first predicted weight of the item and a confidence score for the first predicted weight by applying a weight prediction model to the first set of load measurements; determining whether the confidence score exceeds a confidence threshold; and responsive to the confidence score of the prediction not exceeding the confidence threshold: identifying a second set of load measurements captured by the load sensor during a second time period when the item was added, wherein the second time period comprises the first time period; and computing a second predicted weight of the item by applying the weight prediction model to the second set of load measurements.
The claim limitations in the abstract idea have been highlighted in bold above; the remaining limitations are “additional elements”.
Under the Step 1 of the eligibility analysis, we determine whether the claims are to a statutory category by considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: Process, machine, manufacture, or composition of matter. The above claim is considered to be in a statutory category (process).
Under the Step 2A, Prong One, we consider whether the claim recites a judicial exception (abstract idea). In the above claim, the highlighted portion constitutes an abstract idea because, under a broadest reasonable interpretation, it recites limitations that fall into/recite an abstract idea exceptions. Specifically, under the 2019 Revised Patent Subject matter Eligibility Guidance, it falls into the grouping of subject matter when recited as such in a claim limitation, that covers mathematical concepts (mathematical relationships, mathematical formulas or equations, mathematical calculations) and mental processes – concepts performed in the human mind including an observation, evaluation, judgement, and/or opinion.
For example, steps of “computing a first predicted weight of the item and a confidence score for the first predicted weight by applying a weight prediction model to the first set of load measurements and computing a second predicted weight of the item by applying the weight prediction model to the second set of load measurements” are treated by the Examiner as belonging to mathematical concept grouping, while the steps of “detecting, based on the load data, that an item was added to the storage area of the shopping cart; identifying a first set of load measurements captured by the load sensor during a first time period when the item was added; determining whether the confidence score exceeds a confidence threshold; identifying a second set of load measurements captured by the load sensor during a second time period when the item was added, wherein the second time period comprises the first time period;” are treated as belonging to mental process grouping.
Similar limitations comprise the abstract ideas of Claims 10 and 19.
Next, under the Step 2A, Prong Two, we consider whether the claim that recites a judicial exception is integrated into a practical application.
In this step, we evaluate whether the claim recites additional elements that integrate the exception into a practical application of that exception.
The above claims comprise the following additional elements:
In Claim 1: a computing system, processor, memory, load sensor
In Claim 10: non-transitory computer readable medium, a computing system, processor, memory, load sensor
In Claim 19: computer system, hardware processor, non-transitory computer readable storage medium, a computing system, processor, memory, load sensor
The additional element of computer system, hardware processor, non-transitory computer readable storage medium, a computing system, processor, memory, load sensor are generally recited and are not qualified as particular machines.
In conclusion, the above additional elements, considered individually and in combination with the other claim elements do not reflect an improvement to other technology or technical field, and, therefore, do not integrate the judicial exception into a practical application. Therefore, the claims are directed to a judicial exception and require further analysis under the Step 2B.
However, the above claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception (Step 2B analysis).
The claims, therefore, are not patent eligible.
With regards to the dependent claims, claims 2-9, 11-18 and 20 provide additional features/steps which are part of an expanded algorithm, so these limitations should be considered part of an expanded abstract idea of the independent claims.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by De Bonet et al. (US11636457B1, 2023-04-25) herein referred to as De Bonet.
Regarding Claim 1, De Bonet teaches a method, performed at a computing system comprising a processor and a memory (Fig. 6A), comprising: receiving load data from a load sensor, wherein the load sensor is coupled to a storage area of a shopping cart (Fig. 5A; Col. 4, lines 17-21: In some instances, the smart cart may determine the action(s) taken with respect to the identified item(s) and may determine the quantities involved based at least in part on weight data generated by one or more weight sensors of the cart), wherein the load data comprises load measurements captured by the load sensor, and wherein the load measurements are samples from the load sensor that form a timeseries (Col. 4, lines 58-64: In order to determine a weight of the basket, the smart cart may utilize an algorithm that estimates weight of the basket by computing mean weights over several windows of varying size from the current instant in time to some instant of time in the past. The final estimated weight at any instant may comprise the average of the means weights computed over the aforementioned windows); detecting, based on the load data, that an item was added to the storage area of the shopping cart (Col. 6, lines 26-32: Envision further that the weight-change data indicates that the basket has lightened by 50 grams. Based on this information (i.e., the weights of the identified items, the current contents of the virtual cart, and the weight-change data), the cart may determine that the user has added one instance of the first item to the basket and removed one instance of the second item); identifying a first set of load measurements captured by the load sensor during a first time period when the item was added (Col. 13, lines 33-42: In either instance, the signal may comprise a set of contiguous weight measurements measured by the weight sensors over time. For example, the signal may indicate that most recent weight measurement (e.g., “W.sub.t”), as well as prior weight measurements (e.g., “W.sub.t-1”, “W.sub.t-2”, “W.sub.t-3”, etc.). In order to determine a weight of the basket, the cart 102 may utilize an algorithm that estimates weight of the basket by computing mean weights over several windows of varying size from the current instant in time to some instant of time in the past); computing a first predicted weight of the item and a confidence score for the first predicted weight by applying a weight prediction model to the first set of load measurements (Fig. 1; Col. 13, lines 11-21: Col. 5, lines 25-37: Thereafter, the algorithm may determine a difference between the largest and smallest mean value and may compare this to a threshold. If the difference is less than a predefined threshold value, the smart cart may store an indication that the weight is stable. If not, the smart cart may store an indication that that weight is not stable. In some instances, the smart cart outputs an indication of one (1) if the weight is determined to be stable and zero (0) if not. Thus, a weight-measurement (or weight-change) component of the smart cart may continually or periodically determine a weight estimation of the basket (using the algorithm discussed above) along with an indication of one or zero indicating whether the weight is stable); determining whether the confidence score exceeds a confidence threshold (Col. 5, lines 25-37: Thereafter, the algorithm may determine a difference between the largest and smallest mean value and may compare this to a threshold. If the difference is less than a predefined threshold value, the smart cart may store an indication that the weight is stable. If not, the smart cart may store an indication that that weight is not stable. In some instances, the smart cart outputs an indication of one (1) if the weight is determined to be stable and zero (0) if not. Thus, a weight-measurement (or weight-change) component of the smart cart may continually or periodically determine a weight estimation of the basket (using the algorithm discussed above) along with an indication of one or zero indicating whether the weight is stable); and responsive to the confidence score of the prediction not exceeding the confidence threshold (Col. 13, lines 33-42); identifying a second set of load measurements captured by the load sensor during a second time period when the item was added, wherein the second time period comprises the first time period (Col. 13, lines 33-42: identifying a second set of load measurements captured by the load sensor during a second time period when the item was added, wherein the second time period comprises the first time period (Col 13, ln 33-42 "In either instance, the signal may comprise a set of contiguous weight measurements measured by the weight sensors over time. For example, the signal may indicate that most recent weight measurement (e.g., "Wt"), as well as prior weight measurements (e.g., "Wt-1", "Wt-2", "Wt-3", etc.). In order to determine a weight of the basket, the cart 102 may utilize an algorithm that estimates weight of the basket by computing mean weights over several windows of varying size from the current instant in time to some instant of time in the past); and computing a second predicted weight of the item by applying the weight prediction model to the second set of load measurements (Fig. 1; Col 13, ln 11-21: At an operation 100(3), however, and sometime after presenting the identification indication(s) 110, the cart 102 may determine an outcome of the event 106. For example, the cart 102 may determine, based on weight data generated by one or more weight sensors of the cart 102, an amount of weight change in the basket of the cart between the time of identifying the item at the operation 100(2) and a prior time, such as a weight of the basket at a previous time that the virtual cart of the user was updated. In order to determine this weight change, the smart cart may utilize one or more algorithms for estimating a current weight of the basket).
Regarding Claim 2, De Bonet teaches the method of claim 1, further comprising: applying an item recognition model to the first predicted weight of the item, wherein the item recognition model is a machine-learning model trained to predict an item identifier based on a weight of the item (Fig. 3B; Col 23, ln 14-22 "As described above, the cart 102 may perform one or more image-recognition techniques to identify the items, including identifying barcodes or other unique visual indicia from the image data. If the cart 102 is unable to identify an item from the image data at 304, then at an operation 306 the cart 102 may analyze weight data generated by one or more weight sensors on the cart 102 to determinate whether a current weight estimation of the basket has stabilized."); and storing the predicted item identifier (Fig. 6B; Col 37, ln 48-56 "The weight-change component 640 may be configured to receive raw weight data 680, in the form or respective signals, from the weight sensors, combine these signals into a single signal representing weight measurements over time, and perform the algorithms described above for determine a current weight estimation of the basket of the cart. The weight-change component 640 may store this weight estimation as weight data 682.").
Regarding Claim 3, De Bonet teaches the method of claim 2, further comprising;
determining a third predicted weight of the item based on a load measurement at a time when the first set of load measurements converges to within a threshold standard deviation from a final load value (Fig. 1; Col 14, ln 2-11 "For example, the algorithm may determine, from the n number of mean values, a largest mean value and a smallest mean value. Thereafter, the algorithm may determine a difference between the largest and smallest mean value and may compare this to a threshold. If the difference is less than a predefined threshold value, the cart 102 may store an indication that the weight is stable. If not, the smart cart may store an indication that that weight is not stable. In some instances, the cart 102 outputs an indication of one (1) if the weight is determined to be stable and zero (0) if not."); and responsive to the confidence score not exceeding the confidence threshold, applying the item recognition model to the third predicted weight of the item (Fig. 1; Col 14, ln 17-28 "If the cart 102 determines that a weight change has occurred that is greater than a threshold value, and if the weight-measurement component outputs an indication that the weight is stable, then the cart 102 may use the weight-change data, potentially along with the image data and/or additional sensor data, to determine a result of any event that occurred in in the basket. For example, in addition to determine the change in weight of the basket (after the current weight estimation stabilizes), the cart 102 may retrieve, from an item catalog, a known weight associated with the identified item(s) 104 and may attempt to determine the outcome of the event 106.").
Regarding Claim 4, De Bonet teaches the method of claim 2, further comprising:
providing, for display at a user interface, an item name corresponding to the predicted item identifier and the first predicted weight of the item (Fig. 1; Col 14, ln 34-42).
Regarding Claim 5, De Bonet teaches the method of claim 2, further comprising:
receiving image data from a camera, wherein the camera is coupled to the storage area of the shopping cart (Fig. SA), and wherein the image data comprises an image frame captured at each of a series of timestamps (Fig. 6A; Col 37, ln 28-31 "The image data 656 may comprise information descriptive of a plurality of picture elements, or pixels, for one or more image frames (e.g., a still picture, multiple picture frames, video frames, etc.)."); wherein applying the item recognition model comprises applying the item recognition model to the image data (Fig. 3A; Col 23, ln 13-18 "At an operation 304, the image data is analyzed to identify one or more items represented in the image data. As described above, the cart 102 may perform one or more image-recognition techniques to identify the items, including identifying barcodes or other unique visual indicia from the image data.").
Regarding Claim 6, De Bonet teaches the method of claim 1, wherein the weight prediction model is a transformer model (Fig. 3B; Col 25, ln 1-5 "As described above and below, the item-identification component may identify a respective barcode of an item to identify the item, may generate feature data from the image data and input the feature data into one or more trained classifiers for identifying the item, and/or the like.").
Regarding Claim 7, De Bonet teaches the method of claim 6, further comprising:
training the weight prediction model based on a set of training examples (Fig. 2; Col 17, ln 8-15 "Furthermore, the cart 102 may identify the item(s) in any number of ways. In one example, the cart 102 analyzes the image data to identify a barcode or other unique visual indicia on the item, while in other instances the cart 102 may generate feature data indicative of visual attributes of the item and may input the feature data into one or more trained models for identifying the item."), each training example comprising a load curve captured by the load sensor during a time period when an item was added and a ground truth weight of the item (Fig. 4A; Col 25, ln 14-20 "The cart may then compare the current weight, determined using the techniques described below with reference to the process 400, to a prior weight, which may have been determined using similar techniques. In addition, the cart may determine whether the current weight meets one or more stability criteria.").
Regarding claim 8, De bonet teaches the method of claim 1, wherein computing the first predicted weight and the second predicted weight comprises: computing the first predicted weight and the second predicted weight at the shopping cart (Fig. 7; Col 41, ln 28-39).
Regarding Claim 9, De Bonet teaches the method of claim 8, wherein the weight prediction model is a statistical model, and wherein applying the weight prediction model to the first set of load measurements comprises: applying a denoising algorithm to the first set of load measurements (Col 19, ln 35-44 "Further, given that noise may exist in the measurement of the weight of the basket, the event-determination component 218 may be configured to compute a score associated with each respective hypothesis using a probabilistic approach, such: Score(counts,delta)=Pr(countsldelta)=Pr(deltalcounts)*Pr(counts)/Pr(delta).");
applying a smoothing algorithm to the first set of load measurements (Col 14, ln 2-11 "After computing these "n" number of mean values, the algorithm may calculate an average of these mean values and may store this average (i.e., the mean of the mean values) as the current weight estimation of the basket. In addition, the cart 102 may utilize an algorithm that compares one or more characteristics of the weight signal to one or more stability criteria to determine whether the weight is stable.");
computing statistical metrics of the first set of load measurements (Col 13, ln 33-44); and determining a confidence score based on the computed statistical metrics, the confidence score indicating whether the first set of load measurements have converged (Col 14, ln 17-33).
Regarding claim 10, De Bonet teaches a non-transitory computer-readable storage medium storing executable instructions that, when executed by a hardware processor (Fig. 6A), cause the hardware processor to perform steps comprising: receiving load data from a load sensor, wherein the load sensor is coupled to a storage area of a shopping cart (Fig. SA; Col 4, ln 17-21 "In some instances, the smart cart may determine the action(s) taken with respect to the identified item(s) and may determine the quantities involved based at least in part on weight data generated by one or more weight sensors of the cart."), wherein the load data comprises load measurements captured by the load sensor, and wherein the load measurements are samples from the load sensor that form a timeseries (Col 4, ln 58-64 "In order to determine a weight of the basket, the smart cart may utilize an algorithm that estimates weight of the basket by computing mean weights over several windows of varying size from the current instant in time to some instant of time in the past. The final estimated weight at any instant may comprise the average of the means weights computed over the aforementioned windows."); detecting, based on the load data, that an item was added to the storage area of the shopping cart (Col 6, ln 26-32 "Envision further that the weight-change data indicates that the basket has lightened by 50 grams. Based on this information (i.e., the weights of the identified items, the current contents of the virtual cart, and the weight-change data), the cart may determine that the user has added one instance of the first item to the basket and removed one instance of the second item."); identifying a first set of load measurements captured by the load sensor during a first time period when the item was added (Col 13, ln 33-42 "In either instance, the signal may comprise a set of contiguous weight measurements measured by the weight sensors over time. For example, the signal may indicate that most recent weight measurement (e.g., "Wt"), as well as prior weight measurements (e.g., "Wt-1", "Wt-2", "Wt-3", etc.). In order to determine a weight of the basket, the cart 102 may utilize an algorithm that estimates weight of the basket by computing mean weights over several windows of varying size from the current instant in time to some instant of time in the past.");
computing a first predicted weight of the item and a confidence score for the first predicted weight by applying a weight prediction model to the first set of load measurements (Col 5, ln 25-37 "Thereafter, the algorithm may determine a difference between the largest and smallest mean value and may compare this to a threshold. If the difference is less than a predefined threshold value, the smart cart may store an indication that the weight is stable. If not, the smart cart may store an indication that that weight is not stable. In some instances, the smart cart outputs an indication of one (1) if the weight is determined to be stable and zero (0) if not. Thus, a weight-measurement (or weight-change) component of the smart cart may continually or periodically determine a weight estimation of the basket (using the algorithm discussed above) along with an indication of one or zero indicating whether the weight is stable."); determining whether the confidence score exceeds a confidence threshold (Col 5, ln 25-37 "Thereafter, the algorithm may determine a difference between the largest and smallest mean value and may compare this to a threshold. If the difference is less than a predefined threshold value, the smart cart may store an indication that the weight is stable. If not, the smart cart may store an indication that that weight is not stable. In some instances, the smart cart outputs an indication of one (1) if the weight is determined to be stable and zero (0) if not. Thus, a weight-measurement (or weight-change) component of the smart cart may continually or periodically determine a weight estimation of the basket (using the algorithm discussed above) along with an indication of one or zero indicating whether the weight is stable."); and responsive to the confidence score of the prediction not exceeding the confidence threshold ((Col 13, ln 33-42): identifying a second set of load measurements captured by the load sensor during a second time period when the item was added, wherein the second time period comprises the first time period (Col 13, ln 33-42 "In either instance, the signal may comprise a set of contiguous weight measurements measured by the weight sensors over time. For example, the signal may indicate that most recent weight measurement (e.g., "Wt"), as well as prior weight measurements (e.g., "Wt-1", "Wt-2", "Wt-3", etc.). In order to determine a weight of the basket, the cart 102 may utilize an algorithm that estimates weight of the basket by computing mean weights over several windows of varying size from the current instant in time to some instant of time in the past."); and computing a second predicted weight of the item by applying the weight prediction model to the second set of load measurements (Fig. l; Col 13, ln 11-21 "At an operation 100(3), however, and sometime after presenting the identification indication(s) 110, the cart 102 may determine an outcome of the event 106. For example, the cart 102 may determine, based on weight data generated by one or more weight sensors of the cart 102, an amount of weight change in the basket of the cart between the time of identifying the item at the operation 100(2) and a prior time, such as a weight of the basket at a previous time that the virtual cart of the user was updated. In order to determine this weight change, the smart cart may utilize one or more algorithms for estimating a current weight of the basket.").
Regarding Claim 11, De Bonet teaches the non-transitory computer-readable storage medium of claim 10, the steps further comprising: applying an item recognition model to the first predicted weight of the item, wherein the item recognition model is a machine-learning model trained to predict an item identifier based on a weight of the item (Fig. 3B; Col 23, ln 14-22 "As described above, the cart 102 may perform one or more image-recognition techniques to identify the items, including identifying barcodes or other unique visual indicia from the image data. If the cart 102 is unable to identify an item from the image data at 304, then at an operation 306 the cart 102 may analyze weight data generated by one or more weight sensors on the cart 102 to determinate whether a current weight estimation of the basket has stabilized."); and storing the predicted item identifier (Fig. 6B; Col 37, ln 48-56 "The weight-change component 640 may be configured to receive raw weight data 680, in the form or respective signals, from the weight sensors, combine these signals into a single signal representing weight measurements over time, and perform the algorithms described above for determine a current weight estimation of the basket of the cart. The weight-change component 640 may store this weight estimation as weight data 682.").
Regarding Claim 12, De Bonet teaches the non-transitory computer-readable storage medium of claim 11, the steps further comprising: determining a third predicted weight of the item based on a load measurement at a time when the first set of load measurements converges to within a threshold standard deviation from a final load value (Fig. 1; Col 14, ln 2-11 "For example, the algorithm may determine, from the n number of mean values, a largest mean value and a smallest mean value. Thereafter, the algorithm may determine a difference between the largest and smallest mean value and may compare this to a threshold. If the difference is less than a predefined threshold value, the cart 102 may store an indication that the weight is stable. If not, the smart cart may store an indication that that weight is not stable. In some instances, the cart 102 outputs an indication of one (1) if the weight is determined to be stable and zero (0) if not."); and responsive to the confidence score not exceeding the confidence threshold, applying the item recognition model to the third predicted weight of the item (Fig. 1; Col 14, ln 17-28 "If the cart 102 determines that a weight change has occurred that is greater than a threshold value, and if the weight-measurement component outputs an indication that the weight is stable, then the cart 102 may use the weight-change data, potentially along with the image data and/or additional sensor data, to determine a result of any event that occurred in in the basket. For example, in addition to determine the change in weight of the basket (after the current weight estimation stabilizes), the cart 102 may retrieve, from an item catalog, a known weight associated with the identified item(s) 104 and may attempt to determine the outcome of the event 106.").
Regarding Claim 13, De Bonet teaches the non-transitory computer-readable storage medium of claim 11, the steps further comprising: providing, for display at a user interface, an item name corresponding to the predicted item identifier and the first predicted weight of the item (Fig. 1; Col 14, ln 34-42).
Regarding Claim 14, De Bonet teaches the non-transitory computer-readable storage medium of claim 11, the steps further comprising: receiving image data from a camera, wherein the camera is coupled to the storage area of the shopping cart (Fig. SA), and wherein the image data comprises an image frame captured at each of a series of timestamps (Fig. 6A; Col 37, ln 28-31 "The image data 656 may comprise information descriptive of a plurality of picture elements, or pixels, for one or more image frames (e.g., a still picture, multiple picture frames, video frames, etc.)."); wherein applying the item recognition model comprises applying the item recognition model to the image data (Fig. 3A; Col 23, ln 13-18 "At an operation 304, the image data is analyzed to identify one or more items represented in the image data. As described above, the cart 102 may perform one or more image-recognition techniques to identify the items, including identifying barcodes or other unique visual indicia from the image data.").
Regarding Claim 15, De Bonet teaches the non-transitory computer-readable storage medium of claim 10, wherein the weight prediction model is a transformer model (Fig. 3B; Col 25, ln 1-5 "As described above and below, the item-identification component may identify a respective barcode of an item to identify the item, may generate feature data from the image data and input the feature data into one or more trained classifiers for identifying the item, and/or the like.").
Regarding Claim 16, De Bonet teaches the non-transitory computer-readable storage medium of claim 15, the steps further comprising: training the weight prediction model based on a set of training examples (Fig. 2; Col 17, ln 8-15 "Furthermore, the cart 102 may identify the item(s) in any number of ways. In one example, the cart 102 analyzes the image data to identify a barcode or other unique visual indicia on the item, while in other instances the cart 102 may generate feature data indicative of visual attributes of the item and may input the feature data into one or more trained models for identifying the item."), each training example comprising a load curve captured by the load sensor during a time periods when an item was added and a ground truth weight of the item (Fig. 4A; Col 25, ln 14-20 "The cart may then compare the current weight, determined using the techniques described below with reference to the process 400, to a prior weight, which may have been determined using similar techniques. In addition, the cart may determine whether the current weight meets one or more stability criteria.").
Regarding claim 17, De Bonet teaches the non-transitory computer-readable storage medium of claim 10, wherein computing the first predicted weight and the second predicted weight comprises:
computing the first predicted weight and the second predicted weight at the shopping cart (Fig. 7; Col 41, ln 28-39).
Regarding Claim 18, De Bonet further teaches the non-transitory computer-readable storage medium of claim 17, wherein the weight prediction model is a statistical model and wherein the step for applying the weight prediction model to the first set of load measurements comprises:
applying a denoising algorithm to the first set of load measurements (Col 19, ln 35-44 "Further, given that noise may exist in the measurement of the weight of the basket, the event-determination component 218 may be configured to compute a score associated with each respective hypothesis using a probabilistic approach, such: Score(counts,delta)=Pr(countsldelta)=Pr(deltalcounts)*Pr(counts)/Pr(delta).");
applying a smoothing algorithm to the first set of load measurements (Col 14, ln 2-11 "After computing these "n" number of mean values, the algorithm may calculate an average of these mean values and may store this average (i.e., the mean of the mean values) as the current weight estimation of the basket. In addition, the cart 102 may utilize an algorithm that compares one or more characteristics of the weight signal to one or more stability criteria to determine whether the weight is stable.");
computing statistical metrics of the first set of load measurements (Col 13, ln 33-44); and
determining a confidence score based on the computed statistical metrics, the confidence score indicating whether the first set of load measurements have converged (Col 14, ln 17-33).
Regarding Claim 19, De Bonet further teaches a computer system comprising:
a hardware processor (Fig. 6A); and a non-transitory computer-readable storage medium storing executable instructions that (Fig. 6A), when executed, cause the hardware processor to perform steps comprising: receiving load data from a load sensor, wherein the load sensor is coupled to a storage area of a shopping cart (Fig. SA; Col 4, ln 17-21 "In some instances, the smart cart may determine the action(s) taken with respect to the identified item(s) and may determine the quantities involved based at least in part on weight data generated by one or more weight sensors of the cart."), wherein the load data comprises load measurements captured by the load sensor, and wherein the load measurements are samples from the load sensor that form a timeseries (Col 4, ln 58-64 "In order to determine a weight of the basket, the smart cart may utilize an algorithm that estimates weight of the basket by computing mean weights over several windows of varying size from the current instant in time to some instant of time in the past. The final estimated weight at any instant may comprise the average of the means weights computed over the aforementioned windows."); detecting, based on the load data, that an item was added to the storage area of the shopping cart (Col 6, ln 26-32 "Envision further that the weight-change data indicates that the basket has lightened by 50 grams. Based on this information (i.e., the weights of the identified items, the current contents of the virtual cart, and the weight-change data), the cart may determine that the user has added one instance of the first item to the basket and removed one instance of the second item."); identifying a first set of load measurements captured by the load sensor during a first time period when the item was added (Col 13, ln 33-42 "In either instance, the signal may comprise a set of contiguous weight measurements measured by the weight sensors over time. For example, the signal may indicate that most recent weight measurement (e.g., "Wt"), as well as prior weight measurements (e.g., "Wt-1", "Wt-2", "Wt-3", etc.). In order to determine a weight of the basket, the cart 102 may utilize an algorithm that estimates weight of the basket by computing mean weights over several windows of varying size from the current instant in time to some instant of time in the past."); computing a first predicted weight of the item and a confidence score for the first predicted weight by applying a weight prediction model to the first set of load measurements (Col 5, ln 25-37 "Thereafter, the algorithm may determine a difference between the largest and smallest mean value and may compare this to a threshold. If the difference is less than a predefined threshold value, the smart cart may store an indication that the weight is stable. If not, the smart cart may store an indication that that weight is not stable. In some instances, the smart cart outputs an indication of one (1) if the weight is determined to be stable and zero (0) if not. Thus, a weight-measurement (or weight-change) component of the smart cart may continually or periodically determine a weight estimation of the basket (using the algorithm discussed above) along with an indication of one or zero indicating whether the weight is stable."); determining whether the confidence score exceeds a confidence threshold (Col 5, ln 25-37 "Thereafter, the algorithm may determine a difference between the largest and smallest mean value and may compare this to a threshold. If the difference is less than a predefined threshold value, the smart cart may store an indication that the weight is stable. If not, the smart cart may store an indication that that weight is not stable. In some instances, the smart cart outputs an indication of one (1) if the weight is determined to be stable and zero (0) if not. Thus, a weight-measurement (or weight-change) component of the smart cart may continually or periodically determine a weight estimation of the basket (using the algorithm discussed above) along with an indication of one or zero indicating whether the weight is stable."); and responsive to the confidence score of the prediction not exceeding the confidence threshold (Col 13, ln 33-42): identifying a second set of load measurements captured by the load sensor during a second time period when the item was added, wherein the second time period comprises the first time period (Col 13, ln 33-42 "In either instance, the signal may comprise a set of contiguous weight measurements measured by the weight sensors over time. For example, the signal may indicate that most recent weight measurement (e.g., "Wt"), as well as prior weight measurements (e.g., "Wt-1", "Wt-2", "Wt-3", etc.). In order to determine a weight of the basket, the cart 102 may utilize an algorithm that estimates weight of the basket by computing mean weights over several windows of varying size from the current instant in time to some instant of time in the past."); and computing a second predicted weight of the item by applying the weight prediction model to the second set of load measurements (Fig. l; Col 13, ln 11-21 "At an operation 100(3), however, and sometime after presenting the identification indication(s) 110, the cart 102 may determine an outcome of the event 106. For example, the cart 102 may determine, based on weight data generated by one or more weight sensors of the cart 102, an amount of weight change in the basket of the cart between the time of identifying the item at the operation 100(2) and a prior time, such as a weight of the basket at a previous time that the virtual cart of the user was updated. In order to determine this weight change, the smart cart may utilize one or more algorithms for estimating a current weight of the basket.").
Regarding Claim 20, De Bonet further teaches the computer system of claim 19, the steps further comprising: applying an item recognition model to the first predicted weight of the item, wherein the item recognition model is a machine-learning model trained to predict an item identifier based on a weight of the item (Fig. 3B; Col 23, ln 14-22 "As described above, the cart 102 may perform one or more image-recognition techniques to identify the items, including identifying barcodes or other unique visual indicia from the image data. If the cart 102 is unable to identify an item from the image data at 304, then at an operation 306 the cart 102 may analyze weight data generated by one or more weight sensors on the cart 102 to determinate whether a current weight estimation of the basket has stabilized."); and storing the predicted item identifier (Fig. 6B; Col 37, ln 48-56 "The weight-change component 640 may be configured to receive raw weight data 680, in the form or respective signals, from the weight sensors, combine these signals into a single signal representing weight measurements over time, and perform the algorithms described above for determine a current weight estimation of the basket of the cart. The weight-change component 640 may store this weight estimation as weight data 682.").
Conclusion
The prior art made record and not relied upon is considered pertinent to applicant’s disclosure.
US 20220198550 A1, 2022-06-23 teaches ystem, methods and programs for automatic verification and validation of users' actions during assembly of products intended for purchase in a shopping cart, more specifically, the disclosure is directed to systems, methods and programs for automatically validating correct identification and markings of items inserted to an artificially intelligent shopping cart by using action-recognition associated with correct scanning/presentation of the item to a product recognition module coupled to the artificially intelligent shopping cart.
CA 3080168 A1, 2020-07-22 teaches system, comprising: at least one load receiver mounted on a shopping cart or basket and configured to receive an item placed into the shopping cart or basket for a weighing operation; a plurality of sensors configured to detect a plurality of parameters relating to the weighing operation of the item including at least one of: a relative angle between a force sensing axis of the at least one load receiver and a direction of gravity, a motion of the shopping cart or basket, and an ambient temperature surrounding the shopping cart or basket and the at least one load receiver; and a processor configured to determine an actual weight of the item based on at least a portion of the plurality of parameters.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL J SINGLETARY whose telephone number is (571)272-4593. The examiner can normally be reached Monday-Friday 8:00am-5:00pm.
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, Catherine Rastovski can be reached at 571-270-0349. 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.
/MICHAEL J SINGLETARY/Examiner, Art Unit 2857
/Catherine T. Rastovski/Supervisory Primary Examiner, Art Unit 2857
Prosecution Insights