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 .
Specification
The lengthy specification has not been checked to the extent necessary to
determine the presence of all possible minor errors. Applicant's cooperation is
requested in correcting any errors of which applicant may become aware in the
specification.
Examiner Notes
Examiner cites particular columns, paragraphs, figures and line numbers in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant fully consider the references in their entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner. The entire reference is considered to provide disclosure relating to the claimed invention. The claims & only the claims form the metes & bounds of the invention. Office personnel are to give the claims their broadest reasonable interpretation in light of the supporting disclosure. Unclaimed limitations appearing in the specification are not read into the claim. Prior art was referenced using terminology familiar to one of ordinary skill in the art. Such an approach is broad in concept and can be either explicit or implicit in meaning. Examiner's Notes are provided with the cited references to assist the applicant to better understand how the examiner interprets the applied prior art. Such comments are entirely consistent with the intent & spirit of compact prosecution.
Claim Objections
Claims 1, 6-7, 9 and 19-20 are objected to because of the following informalities:
Claims 1, 6-7, 9 and 19-20 recite “output at least the at least one expected device attribute.” Examiner propose to amend the limitation as “output the at least one expected device attribute”
Claim 6 recites “the apparatus is caused to: cause population of a user interface comprising an interface element associated with each device attribute of the at least one expected device attribute.
Claim 7 recites “the apparatus is caused to: identify image data corresponding to the at least one expected device attribute; and cause rendering of a user interface comprising at least the image data.”
Claim 9 recites “the apparatus is caused to: cause rendering of a user interface comprising a textual description of the at least one expected device attribute.”
Examiner propose to remove “cause”.
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.
Claim 4 is 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 4 recites “SKU” in the limitation without definition. Therefore, claim 4 is indefinite.
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 non-statutory subject matter. These claims are directed to an abstract idea without significantly more.
As to claim 1,
Step 1: Claim 1 is directed to a method. Therefore, the claim is eligible under Step 1 for being directed to processes.
Step 2A Prong One
Claim 1 recites
receive at least one device identifier associated with a device; (input data)
apply the at least one device identifier to an expected device attribute model that determines at least one expected device attribute associated with the device; (mental process)
and output at least the at least one expected device attribute. (output data)
The claimed concept is a method of determining device attribute associate with the device by evaluating input data is directed to “Mental Process” grouping. Therefore, claim 1 is an abstract idea.
Step 2A Prong Two
The receiving data step is recited at a high level of generality (i.e., as a general means of receiving input for use in the evaluation step) and amounts to mere data collecting, which is a form of insignificant extra-solution activity.
The outputting step of a model is recited at a high level of generality (i.e. as a general means of outputting data) and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
The claim recites additional elements such as “the apparatus comprising at least one processor and at least one non-transitory memory including computer-coded instructions thereon”. Each of the additional limitations is no more than mere instructions to apply the exception using a generic computer component. Simply implementing the abstract idea on a generic computer is not a practical application of the abstract idea. See applicant’s specification [0077] Fig. 2 for generic computer description.
The judicial exception is not integrated into a practical application.
Step 2B:
The same analysis of Step 2A Prong Two applies here in 2B. The present claim does not recite any limitation that would integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B. See MPEP 2106.05(d).
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Thus, claim 1 is not patent eligible. Same conclusion for dependent claims of claim 1. See below.
2. The apparatus of claim 1, wherein the at least one expected device attribute comprises a device manufacturer, a device model, a device operating system, a device color, a device capacity, a device country of origin, or a combination of the device manufacturer, the device model, the device operating system, the device color, the device capacity, and the device country of origin. (data description)
3. The apparatus of claim 1, wherein the at least one device identifier comprises device data that is unavailable via physically accessing an exterior of the device. (data description)
4. The apparatus of claim 1, wherein the at least one device identifier comprises a device serial number, a device international manufacturer equipment identifier, a device SKU, a device part number, or a combination of the device serial number, the device international manufacturer equipment identifier, the device SKU, and the device part number. (data description)
5. The apparatus of claim 1, wherein to apply the at least one device identifier to the expected device attribute model the apparatus is caused to at least: determine the at least one expected device attribute comprising an expected physical condition of the device. (mental process)
6. The apparatus of claim 1, wherein to output the at least at least one expected device attribute the apparatus is caused to: cause population of a user interface comprising an interface element associated with each device attribute of the at least one expected device attribute. (output data)
7. The apparatus of claim 1, wherein to output at least the at least one expected device attribute the apparatus is caused to: identify image data corresponding to the at least one expected device attribute; (mental process)
and cause rendering of a user interface comprising at least the image data. (output data)
8. The apparatus of claim 7, further comprising modifying the image data to include damage indication data associated with the device, (mental process)
and wherein the image data comprises a representation of damage corresponding to the data indication data. (data description)
9. The apparatus of claim 1, wherein to output the at least at least one expected device attribute the apparatus is caused to: cause rendering of a user interface comprising a textual description of the at least one expected device attribute. (data description)
10. The apparatus of claim 1, wherein the expected device attribute model is trained to determine a confidence value associated with each of the at least one expected device attribute. (mental process)
11. The apparatus of claim 1, wherein the expected device attribute model is trained to generate a confidence value associated with each of a plurality of candidate device attributes, and wherein the apparatus determines the at least one expected device attribute based at least in part on each confidence value satisfying a confidence threshold. (mental process)
12. The apparatus of claim 1, wherein the at least one expected device attribute comprises a plurality of candidate device attributes corresponding to a particular device attribute type. (data description)
13. The apparatus of claim 1, the apparatus further caused to: receive feedback attribute data associated with at least a particular expected device attribute of the at least one expected device attribute, (input)
wherein the feedback attribute data indicates whether the particular expected device attribute accurately represented an actual device attribute of the device; (data description)
and update training of the expected device attribute model based at least in part on the feedback attribute data. (mental process)
14. The apparatus of claim 1, the apparatus further caused to: receive an image representation of the device; (input)
process the image representation of the device utilizing at least one computer vision model that determines at least one actual device attribute associated with the device; (mere instructions to apply an exception)
generate comparison data representing results of a comparison of the actual device attribute with the at least one expected device attribute; (mental process)
and output the comparison data. (output)
15. The apparatus of claim 1, wherein to receive the at least one device identifier associated with the device the apparatus is caused to: receive an image representation of the device; (input)
and process the image representation of the device utilizing at least one computer vision model that extracts at least a first device identifier from the image representation. (mere instructions to apply an exception)
16. The apparatus of claim 1, wherein to receive the at least one device identifier associated with the device the apparatus is caused to: retrieve the at least one identifier via a software request executed on the device. (generic computer function)
17. The apparatus of claim 1, wherein the expected device attribute model comprises at least one specially-trained machine learning model. (data description)
18. The apparatus of claim 1, the apparatus further caused to: initiate a computer-implemented process based at least in part on the at least one expected device attribute. (generic computer function)
Same conclusion for independent claims 19-20. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Thus, claims 1-20 are not patent eligible.
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.
Claim(s) 1-7, 9-20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Balakrishnan yet al (US 20220058227 A1), hereinafter Balakrishnan.
1. An apparatus for modeling expected device attributes, Balakrishnan discloses the apparatus comprising at least one processor and at least one non-transitory memory including computer-coded instructions thereon, the computer coded instructions, with the at least one processor, cause the apparatus to:
[0044] Fig. 1
Balakrishnan discloses receive at least one device identifier associated with a device;
Balakrishnan [0109] “As shown in the example method A210 of FIG. 11B, the Predictor retrieves a product data attribute(s) based on a formatting convention of the input data (Act A212). For example, various formatting conventions for product identifications are pre-defined and well known, such as Universal Product Codes (UPC), European Article Numbers (EAN) and Amazon Standard Identification Number (ASIN). By identifying a portion of the input data that is structured according to a formatting convention, the Predictor may determine which data sources to search for more product data attributes or may perform a search based on the portion of the input data that is structured according to a formatting convention. The Predictor augments the input data with the retrieved product data attributes for a product data record that corresponds with a product described by the input data (Act A214).”
Balakrishnan discloses apply the at least one device identifier to an expected device attribute model that determines at least one expected device attribute associated with the device; and
Balakrishnan [0111] “The Predictor feeds the product data record into one or more machine learning (ML) models to identify at least one predictive attribute that corresponds with identifying accurate product information (Act A216-2). For example, the Predictor may feed the augmented product data record into a machine learning model trained for named entity recognition (“NER”) to isolate important attributes. That is, if the product data record has the name of the product, the NER model may isolate (or select) a machine learning variable that maps to product names as a variable that is highly likely to facilitate one or more ML models in predicting accurate product information. …”
Balakrishnan discloses output at least the at least one expected device attribute.
Balakrishnan [0113] “The Predictor feeds the predictor data into the one or more ML models to estimate additional data for one or more null fields in the product data record (Act A220). For example, the Predictor feeds a merged record into one or more ML models to estimate data about the product that should be in the product data record given all the various types of data in the merged record. For example, if the merged record has formatted data based on the product's brand and weight, the one or more ML models may estimate additional product specifications (e.g., height, dimensions). A classification model may estimate categorial parameters of the product, such as country of origin, if the product data record lacks such information. A logistic regression model may also estimate continuous parameters, such as weight, if the product data record lacks such information. The Predictor updates the product data record with the predicted additional data to generate an enriched product data record (Act A222).”
2. The apparatus of claim 1, Balakrishnan discloses wherein the at least one expected device attribute comprises a device manufacturer, a device model, a device operating system, a device color, a device capacity, a device country of origin, or a combination of the device manufacturer, the device model, the device operating system, the device color, the device capacity, and the device country of origin.
Balakrishnan [0113] “The Predictor feeds the predictor data into the one or more ML models to estimate additional data for one or more null fields in the product data record (Act A220). For example, the Predictor feeds a merged record into one or more ML models to estimate data about the product that should be in the product data record given all the various types of data in the merged record. For example, if the merged record has formatted data based on the product's brand and weight, the one or more ML models may estimate additional product specifications (e.g., height, dimensions). A classification model may estimate categorial parameters of the product, such as country of origin, if the product data record lacks such information. A logistic regression model may also estimate continuous parameters, such as weight, if the product data record lacks such information. The Predictor updates the product data record with the predicted additional data to generate an enriched product data record (Act A222).”
3. The apparatus of claim 1, Balakrishnan discloses wherein the at least one device identifier comprises device data that is unavailable via physically accessing an exterior of the device.
Balakrishnan [0118-0119] “An example method A216-1-1 for ranking historical product data records is shown in FIG. 11D, generating at least one product identifier based on the augmented product data record (Act A216-1-1-1). A variety of techniques may be employed by one or more embodiments to isolate product identifiers from the augment product record. An embodiment may store a table of common identifier paradigms and their associated patterns and then compare pieces of text from the augmented product data record against each pattern…. An example method A218-1 for merging a product data record, ranked historical product data records and a predictive attribute(s) is shown in FIG. 11E. The Predictor generates a merged record according to a meaningful and usable format for various ML models to estimate additional product data. The Predictor creates the merged record by combining the augmented product data record, the ranked historical product data records and the predictive attribute (Act A218-1-1). The Predictor formats the merged record to correspond with one or more defined ML input parameters (Act A218-1-2). An example of an ML input parameter may be a respective source metadata for the data in one or more fields (field data) of the merged record. The source metadata indicates the source of a corresponding data value (e.g., input data, historical data, online data, database data, etc.).
4. The apparatus of claim 1, Balakrishnan discloses wherein the at least one device identifier comprises a device serial number, a device international manufacturer equipment identifier, a device SKU, a device part number, or a combination of the device serial number, the device international manufacturer equipment identifier, the device SKU, and the device part number.
Balakrishnan [0115] An example method A212-1 for retrieving product data attribute(s) based on a formatting convention of input data in shown in FIG. 11C. The Predictor determines whether the format of an identifier portion of the input data corresponds to a global, vendor-specific or location-specification identification convention (Act A212-1-1). For example, the Predictor determines whether the input data, or part of the input data, is formatted according to a known product identification system that is commonly known. A global convention may be Universal Product Codes (UPCs), European Article Numbers (EANs), International Standard Book Number or Global Trade Item Numbers (GTINs). A vendor-specific convention may be Manufacturer Part Numbers (MPN), Stock-Keeping Units (SKUs) or Amazon Standard Identification Number (ASIN). A location-specific convention may be a Uniform Resource Locator (URL).
5. The apparatus of claim 1, Balakrishnan discloses wherein to apply the at least one device identifier to the expected device attribute model the apparatus is caused to at least: determine the at least one expected device attribute comprising an expected physical condition of the device.
Balakrishnan [0113] “The Predictor feeds the predictor data into the one or more ML models to estimate additional data for one or more null fields in the product data record (Act A220). For example, the Predictor feeds a merged record into one or more ML models to estimate data about the product that should be in the product data record given all the various types of data in the merged record. For example, if the merged record has formatted data based on the product's brand and weight, the one or more ML models may estimate additional product specifications (e.g., height, dimensions). A classification model may estimate categorial parameters of the product, such as country of origin, if the product data record lacks such information. A logistic regression model may also estimate continuous parameters, such as weight, if the product data record lacks such information. The Predictor updates the product data record with the predicted additional data to generate an enriched product data record (Act A222).”
6. The apparatus of claim 1, Balakrishnan discloses wherein to output the at least at least one expected device attribute the apparatus is caused to: cause population of a user interface comprising an interface element associated with each device attribute of the at least one expected device attribute.
Balakrishnan [0098] “As shown in FIG. 10A, an example system A100 of the Predictor may include an augmentation/enrichment engine module A102, and estimation engine module A104, a classification engine module A106, a product data record module A108 and a user interface (U.I.) module A110. The system A100 may communicate with a user device A140 to display output, via a user interface A144 generated by an application engine A142. A machine learning network A130 and one or more databases A120, A122, A124 may further be components of the system A100 as well.” See Fig. 10D.
7. The apparatus of claim 1, Balakrishnan discloses wherein to output at least the at least one expected device attribute the apparatus is caused to: identify image data corresponding to the at least one expected device attribute; and cause rendering of a user interface comprising at least the image data.
Balakrishnan [0073] “FIGS. 6F-G illustrate an exemplary method 650 for extracting product attributes using computer vision, and which may comprise a continuation of method 600 for extracting product attributes. As described above, in step 604, a screenshot is captured of the website. In step 653, all the HTML elements of the web page are retrieved from the screenshot. The HTML elements may include the visual representation of the HTML elements, such as an image of the HTML elements extracted from the screenshot. Moreover, the HTML elements, may include their visual properties, such as color and height, and coordinates on the web page. In step 654, HTML elements with similar characteristics may be combined. For example, HTML elements with adjacent or overlapping coordinates may be combined. In step 655, a bounding box is computed around each of the HTML elements. The bounding boxes may comprise coordinates, such as a left and right X value and top and bottom Y value. The bounding boxes may be derived based on the HTML code of the HTML elements. In step 656, an image may be captured of the contents of each bounding box and these images may be input to a computer vision model. In step 657, the computer vision may predict a label for each image to identify each as a product attribute or not. If the image corresponds to a product attribute, the computer vision model may predict which product attribute it corresponds to. In step 658, if multiple images correspond to the same product attribute, then these conflicts may be resolved. For example, the computer vision model may output associated confidence values, and the label with the highest confidence value may be applied.” See Fig. 7E-7F.
9. The apparatus of claim 1, Balakrishnan discloses wherein to output the at least at least one expected device attribute the apparatus is caused to: cause rendering of a user interface comprising a textual description of the at least one expected device attribute.
Balakrishnan [0065] “FIG. 6B illustrates HTML elements selected from a web page 610. The HTML elements may include a product title 611, product rating 612, price 613, product description 614, size 615, quantity 616, shopping cart button 617, and about button 618. The HTML elements may be identified automatically by analyzing text patterns, though the identity of what the HTML elements correspond to may not be known until after method 600 is performed. For each element, CSS properties may be identified based on the web page 610 source code. CSS properties may include font-size, font-weight, position, relative size, and so on. Other properties may also be computed, such as the number of words, number of sentences, and so on. Some features may be computed relative to other elements on the page, such as distance from other elements.”
10. The apparatus of claim 1, Balakrishnan discloses wherein the expected device attribute model is trained to determine a confidence value associated with each of the at least one expected device attribute.
Balakrishnan [0073] “… In step 657, the computer vision may predict a label for each image to identify each as a product attribute or not. If the image corresponds to a product attribute, the computer vision model may predict which product attribute it corresponds to. In step 658, if multiple images correspond to the same product attribute, then these conflicts may be resolved. For example, the computer vision model may output associated confidence values, and the label with the highest confidence value may be applied.”
11. The apparatus of claim 1, Balakrishnan discloses wherein the expected device attribute model is trained to generate a confidence value associated with each of a plurality of candidate device attributes,
Balakrishnan [0073] “… In step 657, the computer vision may predict a label for each image to identify each as a product attribute or not. If the image corresponds to a product attribute, the computer vision model may predict which product attribute it corresponds to. In step 658, if multiple images correspond to the same product attribute, then these conflicts may be resolved. For example, the computer vision model may output associated confidence values, and the label with the highest confidence value may be applied.”
and wherein the apparatus determines the at least one expected device attribute based at least in part on each confidence value satisfying a confidence threshold.
Balakrishnan [0105] “… In one embodiment, the output of the modules A102, A104, A106 may be merged and resolved by the product data record module A108 in order to eliminate data redundancies by selecting output data for the product data record A108-1 with a highest confidence score.” Examiner considers “the highest” as the “threshold”.
12. The apparatus of claim 1, Balakrishnan discloses wherein the at least one expected device attribute comprises a plurality of candidate device attributes corresponding to a particular device attribute type.
Balakrishnan [0084] “FIG. 8B illustrates a process by which raw attribute values 804 from product page variations 309 may be standardized. A master list of attribute values 811 may be stored and accessed. The master list of attribute values 811 may comprise all the valid attribute values. For fields with numerical ranges, like weights, the master of list of attribute values 811 might not enumerate all the possible values but instead identify the standardized units for the value so that product page variations listing other units may be standardized. In some embodiments, the master list of attribute values 811 may comprise a mapping from non-standardized attributes (e.g., grey) to the standard attribute values (e.g., gray). The raw attribute values 804 may undergo a normalization process 805 where the master list of attribute values 811 is accessed to identify the corresponding standardized attributed values. The resulting attribute values 806 may be output.”
13. The apparatus of claim 1, Balakrishnan discloses the apparatus further caused to: receive feedback attribute data associated with at least a particular expected device attribute of the at least one expected device attribute,
Balakrishnan [0087] “In one embodiment, product database 315 comprises a full-document store or free-text database. The product database 315 may store the full text identifying the products, attributes, and available attribute values. For example, a database entry for a product may include information about all the attributes and all the potential values of those attributes. This enables a user to quickly review all the possible variations of a product. The product database 315 may include one or more indices allowing for quick search and retrieval.”
Balakrishnan discloses wherein the feedback attribute data indicates whether the particular expected device attribute accurately represented an actual device attribute of the device;
Balakrishnan [0117] “The Predictor may determine that the input data does not conform to any type of formatting convention. In such a case, the Predictor identifies relevant product data based on uncategorized user-generated text if there is not determine format (Act A212-1-3). For example, when the input data is user-generated text input, it usually contains some information to directly describe the product being shipped. Depending on the availability and specificity of the text input provided, the user-generated text input may be sufficient to completely describe the product and thereby can be used to populate the product data record. In another example, if the user-generated text input may include the words “. . . mobile phone . . . ” and part of a product barcode. The Predictor can use “mobile phone” and the incomplete barcode to find information online or data values from historical shipment records of mobile phones.”
Balakrishnan discloses update training of the expected device attribute model based at least in part on the feedback attribute data.
Balakrishnan [0126] “The enricher module A102-4 may determine that the product input data A300 is uncategorized, user-generate text, and thereby was not handled by the other modules A102-1, A102-2, A102-3. For example, the product input data A300 may be partial, unstructured or an incomplete text description of the product. The enricher module A102-4 may send the product input data's A300 text as-is to the machine learning network A130 to train one or more machine learning models or to receive machine learning output that estimates and predicts product information.”
14. The apparatus of claim 1, the apparatus further caused to: Balakrishnan discloses receive an image representation of the device; process the image representation of the device utilizing at least one computer vision model that determines at least one actual device attribute associated with the device;
Balakrishnan [0073] “FIGS. 6F-G illustrate an exemplary method 650 for extracting product attributes using computer vision, and which may comprise a continuation of method 600 for extracting product attributes. As described above, in step 604, a screenshot is captured of the website. In step 653, all the HTML elements of the web page are retrieved from the screenshot. The HTML elements may include the visual representation of the HTML elements, such as an image of the HTML elements extracted from the screenshot. Moreover, the HTML elements, may include their visual properties, such as color and height, and coordinates on the web page. In step 654, HTML elements with similar characteristics may be combined. For example, HTML elements with adjacent or overlapping coordinates may be combined. In step 655, a bounding box is computed around each of the HTML elements. The bounding boxes may comprise coordinates, such as a left and right X value and top and bottom Y value. The bounding boxes may be derived based on the HTML code of the HTML elements. In step 656, an image may be captured of the contents of each bounding box and these images may be input to a computer vision model. In step 657, the computer vision may predict a label for each image to identify each as a product attribute or not. If the image corresponds to a product attribute, the computer vision model may predict which product attribute it corresponds to. In step 658, if multiple images correspond to the same product attribute, then these conflicts may be resolved. For example, the computer vision model may output associated confidence values, and the label with the highest confidence value may be applied.”
Balakrishnan discloses generate comparison data representing results of a comparison of the actual device attribute with the at least one expected device attribute; and output the comparison data.
Balakrishnan [0130] “The merger module A104-3 receives the product data record A108-1, the ranked historical product data records and the predictive attribute(s). A comparison of data fields across the ranked historical product data records and the product data record A108-1 is performed to based on a merger of the historical product records with the actual input product data record. For data fields common between the product data record A108-1 and each respective historical product data records, the merger module A104-3 prioritizes use of the data fields from the input product data record. For data fields present only in the historical product data records, the merger module A104-3 compares the values available across the various historical product data records and picks a value available from the highest ranked historical product data record. Picking the available value from the highest ranked historical product data record ensures that one value is prioritized when conflicting data field values might be amongst different historical product data records. The merger module A104-3 generates a merged record based on the product data record A108-1, the ranked historical product data records and the predictive attribute(s), such that the merged record is formatted according to machine learning parameters so that the merged record can be used as input to one or more ML models. Such formatting may include adding metadata about each field in the product data record A108-1, such as data indicating the data source of the value in the corresponding field. The formatting may include a confidence score for data in one or more fields.”
15. The apparatus of claim 1, Balakrishnan discloses wherein to receive the at least one device identifier associated with the device the apparatus is caused to: receive an image representation of the device; and process the image representation of the device utilizing at least one computer vision model that extracts at least a first device identifier from the image representation.
Balakrishnan [0073] “FIGS. 6F-G illustrate an exemplary method 650 for extracting product attributes using computer vision, and which may comprise a continuation of method 600 for extracting product attributes. As described above, in step 604, a screenshot is captured of the website. In step 653, all the HTML elements of the web page are retrieved from the screenshot. The HTML elements may include the visual representation of the HTML elements, such as an image of the HTML elements extracted from the screenshot. Moreover, the HTML elements, may include their visual properties, such as color and height, and coordinates on the web page. In step 654, HTML elements with similar characteristics may be combined. For example, HTML elements with adjacent or overlapping coordinates may be combined. In step 655, a bounding box is computed around each of the HTML elements. The bounding boxes may comprise coordinates, such as a left and right X value and top and bottom Y value. The bounding boxes may be derived based on the HTML code of the HTML elements. In step 656, an image may be captured of the contents of each bounding box and these images may be input to a computer vision model. In step 657, the computer vision may predict a label for each image to identify each as a product attribute or not. If the image corresponds to a product attribute, the computer vision model may predict which product attribute it corresponds to. In step 658, if multiple images correspond to the same product attribute, then these conflicts may be resolved. For example, the computer vision model may output associated confidence values, and the label with the highest confidence value may be applied.”
16. The apparatus of claim 1, Balakrishnan discloses wherein to receive the at least one device identifier associated with the device the apparatus is caused to: retrieve the at least one identifier via a software request executed on the device.
Balakrishnan [0124] “If the source is not accessible, the vendor module A102-2 may query one or more web search engines based on the source and the identifier. If matching information is returned in search result and is directly available product data, then the vendor module A102-2 sends the product data to the product data record A108-1. If no product data is available by way of the search results, the vendor module A102-2 sends the source and the identifier to the retriever module A102-3. If no matching information is returned by the search, the vendor module A102-2 may discard the identifier and the identified source.”
17. The apparatus of claim 1, Balakrishnan discloses wherein the expected device attribute model comprises at least one specially-trained machine learning model.
Balakrishnan [0069] “In some embodiments, a single machine learning model may be used to classify each of the HTML elements to product attributes. In other embodiments, separate machine learning models may be used for individual product attributes. For example, one machine learning model may be used for detecting the size attribute and another may be used for detecting the color attribute.”
18. The apparatus of claim 1, Balakrishnan discloses the apparatus further caused to: initiate a computer-implemented process based at least in part on the at least one expected device attribute.
Balakrishnan [0068] “In step 622, HTML elements may be selected from the web page, including their various properties and coordinates. In step 623, the machine learning model may be applied to the HTML elements to predict whether they correspond to a product attribute, and which product attribute they correspond to, if so.”
Regarding Claim 19-20, the same ground of rejection is made as discussed above for substantially similar rationale of claim 1.
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.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Balakrishnan yet al (US 20220058227 A1), hereinafter Balakrishnan. In view of Bogolea et al (US 2023/0421705 A1), hereinafter Bogolea.
8. The apparatus of claim 7, Balakrishnan does not appear to explicitly disclose further comprising modifying the image data to include damage indication data associated with the device, and wherein the image data comprises a representation of damage corresponding to the data indication data.
However, Bogolea discloses further comprising modifying the image data to include damage indication data associated with the device, [0071] “For example, for a list of 20 product types assigned to a particular shelving segment associated with a particular shelving segment address, the computer system can aggregate 20 product models—from the database of millions of product models—for subsequent comparison to an image of the particular shelving segment in Blocks S150 and S152, wherein each product model represents a primary face of a product packaging for one product type in the list of product types assigned to the particular shelving segment. In this example, the computer system can also aggregate additional product models of product types in this list of product types, such as representing alternate or seasonal product packaging, other sides of product packagings, or damaged product packagings of these product types, as described above.”
and wherein the image data comprises a representation of damage corresponding to the data indication data [0091] “In particular, in the foregoing implementations, the computer system can identify a discrete object represented in a first subregion of the image as a product unit of a first product type in Block S150 in response to relatively strong correlation between features extracted from the first subregion of the image and features represented in a first product model representing the first product type. The computer system can then tag the first subregion of the image with a SKU or other identifier of a product unit depicted by the first product model. Furthermore, if the first product model is tagged with additional data, such as packaging side, packaging orientation, product description, supplier, supply period, graphics release date, packaging damage, etc. of the first product type, the computer system can also copy these data (e.g., in the form of tags or image metadata) to the first subregion of the image depicting the object thus identified as a product unit of the first product type.”
Balakrishnan and Bogolea are analogous art because they are from the “same field of endeavor” product data analysis.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Balakrishnan and Bogolea before him or her, to modify the model of Balakrishnan to include the imaging feature of Bogolea because this com,bination improve the performance of the model.
The suggestion/motivation for doing so would have been Bogolea [0186] “The computer system can align these 2D overlays over panoramic images of corresponding shelving structures and then serve these composite images to an associate (or a manager, corporate representative) through a manager portal, thereby enabling the associate to view both real visual data of the store and quantitative and qualitative stock data extracted from these visual data, as shown in FIG. 4.”
Therefore, it would have been obvious to combine Balakrishnan and Bogolea to obtain the invention as specified in the instant claim(s).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHUEN-MEEI GAN whose telephone number is (469)295-9127. The examiner can normally be reached Monday-Friday 9:00 am to 4:00 pm EST.
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, Rehana Perveen can be reached at 571-272-3676. 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.
/CHUEN-MEEI GAN/Primary Examiner, Art Unit 2189
Prosecution Insights