DETAILED ACTION
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
2. This action is in response to amendment filed on 12/22/2025, in which claims 1 – 4, 8, 10, 13, 15, 18, 22 – 23, and 45 was amended, claims+ 16 and 21 was canceled, claim 68 was added, and claims 1 – 6, 8 – 10, 12 – 13, 15, 18 – 19, 22 – 23, 45, and 68 was presented for further examination.
3. Claims 1 – 6, 8 – 10, 12 – 13, 15, 18 – 19, 22 – 23, 45, and 68 are now pending in the application
Continued Examination Under 37 CFR 1.114
4. A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/22/2025 has been entered.
Response to Arguments
5. Applicant’s arguments with respect to claims 1 – 6, 8 – 10, 12 – 16, 18 – 19, 22 – 23, 45, and 68 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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.
6. Claims 1, 4 – 5, 8 – 10, 13, 15, 22, and 68 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al (WO 2020/068421 A1), in view of Oltean et al (US 2010/0274750 A1), in view of Yeleshwarapu et al (US 2011/0087626 A1), and further in view of Bhide et al (US 2019/0155941 A1).
As per claim 1, Wang et al (WO 2020/068421 A1) discloses,
A method for classifying a product into a tariff classification (para.[0003]; “predicting an HSCode of a product with a hybrid machine learning classifier ……..classification involves selecting and applying an expert tree to the additional properties”, where predicting product code for tariff classification is “classifying a product into a tariff classification” as claimed).
the tariff classification being represented by a node in a tree of nodes (para.[0095]; “Tariff codes have a tree-like structure”).
the method comprising: storing the tree of nodes, each node being associated with a text string indicative of a semantic description of that node as a sub-class of a parent of that node (para.[0006]; “obtaining, from a memory, a set of tariff code mappings between chemical component descriptions and tariff codes, where the
tariff codes comprise tariff code prefixes and tariff code suffixes“ and para.[0058]; “Various types of data structures may store the information in such a database, including but not limited to tables, arrays, lists, trees”)
storing multiple classification components, each having a product characterization as input and a classification into one of the nodes as an output (para.[0005]; “a set of tariff code mappings and respective sets of suffix mappings, where the set of tariff code mappings are between chemical component descriptions and tariff codes, where the tariff codes comprise tariff code prefixes and tariff code suffixes, and where each of the tariff code prefixes is associated with a respective set of suffix mappings between properties related to the chemical component descriptions and the tariff code suffixes ……. training a random forest of decision tree classifiers with the feature vectors for the respective descriptions as input and the tariff code prefixes for the respective descriptions as output labels”).
connecting multiple classification components based on the product characterization into a pipeline of independent classification components (para.[0007]; “a plurality of component files, one for each of the tariff code prefixes, that
contain names of chemical components associated with the respective tariff code prefix lire third example embodiment may also involve determining, from the new set of chemical components, a dominant chemical component. The third example embodiment may also involve determining a proportion of the dominant chemical component in comparison to other chemical components in the new set of chemical components”).
each classification component of the pipeline being configured to independently generate digits of the tariff classification additional to a classification output of a classification component upstream in the pipeline (para.[0007]; “selecting, from the plurality of expert trees, a particular expert tree associated with the predicted tariff code prefix. The third example embodiment may also involve obtaining a predicted tariff code suffix by traversing the particular expert tree in accordance with the properties related to the new set of chemical components ……….generating a tariff code for the new set of chemical components by concatenating the predicted tariff code prefix and the predicted tariff code suffix” and para.[159]; “Features necessary for an expert tree to predict HS10-Codes will vary depending on the logic path taken for product classification).
by iteratively performing: selecting one of the multiple classification components based on a current classification of the product, and applying the one of the multiple classification components to the product characterization to update the current classification of the product (para.[0007]; “traversing the particular expert tree in accordance with the properties related to the new set of chemical components” and para.[0145]; “if the HS4-Code is 3901, deciding whether the HS6~eode will be 390110 or 390120 involves checking the specific gravity of the product (see Table 4). If the specific gravity is less than 0.94, the product will have HS6-Code of 390110, else the HS6-Code will be 390120. There are relatively few considerations when predicting higher digits beyond 4 digits of HS-code, and most of the cases/classes can be easily differentiated from one another”).
responsive to meeting a termination condition, outputting the current classification as a final classification of the product (para.[157]; “Suppose that the ethylene content of the product is known to be greater than 95%. As mentioned before, this will result in two possible cases for HS6-Codes: 390110 and 390 120. expert tree system then checks for the specific gravity of the product. If the value of specific gravity is greater than 0.94, the expert tree will predict the HS6-Code to be 390120, else the expert tree wall predict tire HS6-Code to be 390110”).
Wang does not specifically disclose product characterization into a pipeline of independent classification components, the pipeline being specific to the product classification.
However, Oltean et al (US 2010/0274750 A1) in an analogous art discloses,
product characterization into a pipeline of independent classification components (para.[0004]; “data items ( e.g., files) are processed through a data processing pipeline, including a classification pipeline, to facilitate management of the data items based upon their classifications” and para.[0015]; “data classification-enabled solutions, based upon a classification pipeline”).
the pipeline being specific to the product classification (para.[0004]; “classification pipeline obtains metadata ( e.g. business impact, privacy level and so forth) associated with each discovered data item. A set of one or more classifiers classify the data item, if invoked, into classification metadata”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the current invention to incorporate classification pipeline of the system of Oltean into hybrid machine classifiers of the system of Wang to improve classification of data item, thereby reducing data management cost.
Neither Wang nor Oltean specifically disclose the pipeline being a dynamically created selection of components, each component being selected upon an output value of a previous component being available, to thereby create a chain of components.
However, Yeleshwarapu et al (US 2011/0087626 A1) in an analogous art discloses,
and the pipeline being a dynamically created selection of components,
each component being selected upon an output value of a previous component being available, to thereby create a chain of components (para.[0020]; “For each level of the taxonomy, the model provides a confidence level as an output. The confidence level defines the category in which the item is classified on this level of the taxonomy” and para.[0028]; “the system will attempt to select the best possible option (and/or alternate options) at each level of the hierarchy. ……… . (These confidence levels might be informed by earlier users' classification efforts and/or by other factors, as described above)” and para.[0037]; “a hierarchical classification taxonomy, these operations may be repeated as necessary at successive levels of the hierarchy”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate hierarchical product classification process of the system of Yeleshwarapu into classification pipeline of the system of Oltean to improve classification of product that difference between some other categories may not be obvious, thereby preventing corrupt product classification in the system of Wang.
Neither Wang nor Oltean nor Yeleshwarapu specifically disclose the applying further comprises (a) extracting a feature value from the product characterization, the extracting further comprises selecting one of multiple options for the feature value, the multiple options determined for the feature value from the text string indicative of a semantic description of that node, and (b) updating the current classification based on the feature value.
However, Bhide et al (US 2019/0155941 A1) in an analogous art discloses,
the applying further comprises (a) extracting a feature value from the product characterization (para.[0003]; “extracting, for a plurality of features, feature data from the plurality of assets”).
the extracting further comprises selecting one of multiple options for the feature value, the multiple options determined for the feature value from the text string indicative of a semantic description of that node (para.[0003]; “generating a
feature vector based on the extracted feature data, and generating, by a machine learning (ML) algorithm and based on the feature vector” and para.[0016]; “feature vector 109 would include data describing each of the 100 features relative to the assets 1021_N” …….. the feature vectors 109 may be defined based on an analysis of the data in the Assets”).
and (b) updating the current classification based on the feature value (para.[0020]; “Based on the generated feature vector 109, the selected ML algorithm 108 may then generate a ML model 110 specifying one or more new classification rules” and para.[0022]; “updates existing classifications 1031_N based on the rules generated”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate assets level classifications process of the system of Bhide into hierarchical product classification process of the system of Yeleshwarapu and classification pipeline of the system of Oltean to provide less hectic process for classification of assets, thereby improving the policy for classification of assets.
As per claim 4, the rejection of claim 1 is incorporated and further Wang et al (WO 2020/068421 A1) discloses,
wherein selecting one of the multiple classification components is further based on determining a presence of one or more keywords in the product characterization (para.[0101]; “product information data comprises textual information in terms of product name and component names, and numeric information in terms of component proportions (other information such as component CAS number may be used in the later stage of algorithm development)”, where product name is interpreted as “keywords” as claimed).
As per claim 5, the rejection of claim 1 is incorporated and further Wang et al (WO 2020/068421 A1) discloses,
wherein the multiple classification components comprise: classification components that are applicable only if the product is unclassified; and classification components that are applicable only if the product is partly classified (para.[0148]; “a product database typically lacks some information (e.g ,specific gravity, co-monomer ratio, elasticity, etc.) necessary to carry out classification beyond four digits and predict the full HS-Code. Thus, to validate the concept and test the expert tree based system, synthetic information was artificially generated under the assumption that the HS-Codes for products already classified in the product database were correct …. This information can then be used to predict HS-Codes for other products with unknown HS-Codes”).
As per claim 8, the rejection of claim 1 is incorporated and further Wang et al (WO 2020/068421 A1) discloses,
wherein selecting one of the multiple classification components comprises matching keywords defined for the multiple classification components against the product characterization and selecting the component with an optimal match (para.[96]; “new product is then compared with these historical classifications and is assigned a HS-Code based on the best-matched product from the knowledge base. There have been proposals to break down the total product information into a set of keywords and recommend list of HSCodes by implementing a lookup module”).
As per claim 9, the rejection of claim 1 is incorporated and further Wang et al (WO 2020/068421 A1) discloses,
wherein the current classification is represented by a sequence of multiple digits and digits later in the sequence define a classification lower in the tree of nodes (para.[94]; “each product can be assigned to a particular code known as a Harmonized Tariff Schedule Code 18-Code) This code encompasses 8-12 digits depending on the importing-exporting country, with the first 6 digits consistent globally”).
As per claim 10, the rejection of claim 9 is incorporated and further Wang et al (WO 2020/068421 A1) discloses,
wherein the multiple classification components comprise: multiple components for classifying the product into a 2-digits chapter; and multiple components for classifying the product with a 2-digit classification into a 6- digit sub-heading, the termination condition comprises a minimum number of the digit (para.[94]; “a goal is to accurately predict the 10-digit, U.S.-based HS-Codes for chemical-polymers of Chapter 39, which includes the first subheadings 500 of Chapter 39, as shown in Figure 5”).
As per claim 13, the rejection of claim 1 is incorporated and further Wang et al (WO 2020/068421 A1) discloses,
wherein applying the one of the multiple classification components to the product characterization comprises: converting the product characterization into a vector; test each of multiple candidate classifications in relation to the current classification against the vector, and accepting one of the multiple candidate classifications based on the test (Fig.15; “Convert product information 1 I to a vector of numbers” and para.[101]; “feature vector is a representation of a product in which the product information is stored as a vector of numerical values. As mentioned previously, the product information data comprises textual information in terms of product name and component names, and numeric information in terms of component proportions (other information such as component CAS number may be used in the later stage of algorithm development). The task of a feature vector generator is to process this information and map it to a vector in an n-dimensional space”).
As per claim 15, the rejection of claim 1 is incorporated and further Wang et al (WO 2020/068421 A1) discloses,
wherein extracting the feature value comprises evaluating a trained machine learning model, wherein the trained machine learning model has the product characterization as an input, and the feature value as an output (para.[5]; “training a random forest of decision tree classifiers with the feature vectors for the respective descriptions as input and the tariff code prefixes for the respective descriptions as output labels”).
Claim 22 is a system claim corresponding to method claim 1, and rejected under the same reason set forth in connection to the rejection of claim 1 above.
Claim 68 is a non-transitory computer readable medium claim corresponding to method claim 1, and rejected under the same reason set forth in connection to the rejection of claim 1 above.
7. Claims 2, 12, 16, 19, 23, and 45 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al (WO 2020/068421 A1), in view of Oltean (US 2010/0274750 A1), in view of Yeleshwarapu et al (US 2011/0087626 A1), in view of assets level classifications process of the system of Bhide, and further in view of Uy et al (US 2005/0033592 A1).
As per claim 2, the rejection of claim 1 is incorporated, Wang et al (WO 2020/068421 A1), Oltean (US 2010/0274750 A1), and Yeleshwarapu et al (US 2011/0087626 A1), and Bhide et al (US 2019/0155941 A1) does not disclose wherein outputting the current classification comprises generating a user interface, wherein the user interface comprises: an indication of a feature value for each classification component of the pipeline separately, that is determinative of the classification output of that component, and a user interaction element for the user to change the feature value to thereby cause re-creation of the pipeline of classification components downstream from the class.
However, Uy et al (US 2005/0033592 A1) in an analogous art discloses,
wherein outputting the current classification comprises generating a user interface (para.[0016]; “Harmonized Tariff Schedule (HTS) classifications using a software user interface to an electronic database system for storing and classifying HTS codes” and para.[0099]; “the analyst selects the application classification group from a
menu in the TCS”).
wherein the user interface comprises: an indication of a feature value for each classification component of the pipeline separately, that is determinative of the classification output of that component (para.[0016]; “Harmonized Tariff Schedule (HTS) classifications using a software user interface to an electronic database system for storing and classifying HTS codes”, para.[0017]; “classification of Harmonized Tariff Schedule (HTS) codes using a software user interface to an electronic database system, includes assigning HTS codes to products to be imported by a first person using the software user interface”, and para.[0097]; “TCS can include a "main screen" similar to the screen shown in FIG. 3, which may simply include a web page with colorcoded groups of various TCS applications to facilitate identification
and navigation”).
and a user interaction element for the user to change the feature value to thereby cause re-creation of the pipeline of classification components downstream from the class (para.[0017]; classification of Harmonized Tariff Schedule (HTS) codes using a software user interface to an electronic database system, includes assigning HTS codes to products to be imported by a first person using the software user
interface” and para.[0171]; “second personnel may then correct any errors or inconsistencies in the database. Using the two-pass method, an analyst can
perform an overall classification of products at an efficient pace, while another more qualified personnel can review the analyst's work by entering into the TCS system”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the current invention to incorporate multi-pass Harmonized Tariff Schedule classifications of the system of Uy into assets level classifications process of the system of Bhide, hierarchical product classification of the system of Yeleshwarapu, and classification pipeline of the system of Oltean to accurately classify import and export content, thereby maintaining the classification compliance and keeping record maintain by importer and custom broker consistent in the system of Wang.
As per claim 12, the rejection of claim 1 is incorporated, Wang et al (WO 2020/068421 A1), Oltean (US 2010/0274750 A1), and Yeleshwarapu et al (US 2011/0087626 A1), and Bhide et al (US 2019/0155941 A1) does not disclose wherein iteratively performing comprises performing at least three iterations to select at least three classification components for the product.
However, Uy et al (US 2005/0033592 A1) in an analogous art discloses,
wherein iteratively performing comprises performing at least three iterations to select at least three classification components for the product (para.[0095]; “The analyst thereupon navigates to a first subgroup which may include option F. If the analyst selects commodity group B, for example, the analyst's selection may link to sub-group F …… . The analyst in this example has three options in a second sub-group consisting of options G, H, and I……… the analyst may be navigated to a third
subgroup comprising a series of additional questions regarding the part at issue-namely, J, K, L, M, N, 0 and P. Assuming the analyst selects J”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the current invention to incorporate multi-pass Harmonized Tariff Schedule classifications of the system of Uy into assets level classifications process of the system of Bhide, hierarchical product classification of the system of Yeleshwarapu, and classification pipeline of the system of Oltean to accurately classify import and export content, thereby maintaining the classification compliance and keeping record maintain by importer and custom broker consistent in the system of Wang.
As per claim 19, the rejection of claim 1 is incorporated, Wang et al (WO 2020/068421 A1), Oltean (US 2010/0274750 A1), and Bhide et al (US 2019/0155941 A1) does not disclose wherein extracting the feature value comprises selecting one of multiple options for the feature value and the method further comprises determining the multiple options for the feature value from the text string indicative of a semantic description of that node.
However, Uy et al (US 2005/0033592 A1) in an analogous art discloses,
further comprising training the multiple classification components according to a predefined schedule, and refining one or more of the multiple classification components for a further product based on user input related to classifying the product (para.[0018]; “enabling the second person to enter, using the software user interface at the second terminal, one or more changes to the assignments stored by the first person”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the current invention to incorporate multi-pass Harmonized Tariff Schedule classifications of the system of Uy into assets level classifications process of the system of Bhide, hierarchical product classification of the system of Yeleshwarapu, and classification pipeline of the system of Oltean to accurately classify import and export content, thereby maintaining the classification compliance and keeping record maintain by importer and custom broker consistent in the system of Wang.
As per claim 23, the rejection of claim 1 is incorporated, Wang et al (WO 2020/068421 A1), Oltean (US 2010/0274750 A1), Yeleshwarapu et al (US 2011/0087626 A1), and Bhide et al (US 2019/0155941 A1), does not disclose wherein the method further comprises: iteratively classifying, at one of the nodes of the tree, the product into one of multiple child nodes of that node, wherein the classifying comprises: determining a set of features of the product that are discriminative for that node by extracting the features from the text string indicative of a semantic description of that node and determining a feature value for each feature of the product by extracting the feature value from a product characterization, and evaluating a decision model of that node for the determined feature values, the decision model being defined in terms of the extracted feature for that node.
However, Uy et al (US 2005/0033592 A1) in an analogous art discloses,
wherein the method further comprises: iteratively classifying, at one of the nodes of the tree, the product into one of multiple child nodes of that node (para.[0095]; “The analyst thereupon navigates to a first subgroup which may include option F. If the analyst selects commodity group B, for example, the analyst's selection may link to sub-group F …… . The analyst in this example has three options in a second sub-group consisting of options G, H, and I……… the analyst may be navigated to a third
subgroup comprising a series of additional questions regarding the part at issue-namely, J, K, L, M, N, 0 and P. Assuming the analyst selects J”).
wherein the classifying comprises: determining a set of features of the product that are discriminative for that node by extracting the features from the text string indicative of a semantic description of that node (para.[0096]; “analyst may proceed to navigate down the decision tree by successively making more specific classification group selections until the analyst ultimately arrives at the end of a branch namely,
a particular HTS code”).
determining a feature value for each feature of the product by extracting the feature value from a product characterization, and evaluating a decision model of that node for the determined feature values, the decision model being defined in terms of the extracted feature for that node (para.[0065]; “The analyst may begin with the commodity group corresponding to the item at issue, and may be led through the decision tree by answering questions specific to classification of that part (e.g., The part's function? The part's composition?). When the analyst comes to the end of the decision tree, he or she may arrive at a particular HTS code, which may then be
assigned by the TCS to the item at issue”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the current invention to incorporate multi-pass Harmonized Tariff Schedule classifications of the system of Uy into assets level classifications process of the system of Bhide, hierarchical product classification of the system of Yeleshwarapu, and classification pipeline of the system of Oltean to accurately classify import and export content, thereby maintaining the classification compliance and keeping record maintain by importer and custom broker consistent in the system of Wang.
As per claim 45, the rejection of claim 1 is incorporated and further Uy et al (US 2005/0033592 A1) discloses,
As per claim 45, the rejection of claim 1 is incorporated, Wang et al (WO 2020/068421 A1), Oltean (US 2010/0274750 A1), Yeleshwarapu et al (US 2011/0087626 A1), and Bhide et al (US 2019/0155941 A1) does not disclose iteratively classifying, at one of the nodes of the tree, the product into one of multiple child nodes of that node, wherein the classifying comprises: determining whether a current assignment of feature values to features supports a classification from that node, upon determining that the current assignment of feature values to features does not support the classification from that node on a path, selecting one of multiple unresolved features that results in a maximum support for downstream classification, generating a user interface comprising a user input element for a user to enter a value for the selected one of multiple non-valued features; receiving a feature value entered by the user and evaluating a decision model of that node for the received feature value, the decision model being defined in terms of the extracted feature for that node.
However, Uy et al (US 2005/0033592 A1) in an analogous art discloses,
wherein the method further comprises: iteratively classifying, at one of the nodes of the tree, the product into one of multiple child nodes of that node (para.[0095]; “The analyst thereupon navigates to a first subgroup which may include option F. If the analyst selects commodity group B, for example, the analyst's selection may link to sub-group F …… . The analyst in this example has three options in a second sub-group consisting of options G, H, and I……… the analyst may be navigated to a third
subgroup comprising a series of additional questions regarding the part at issue-namely, J, K, L, M, N, 0 and P. Assuming the analyst selects J”).
wherein the classifying comprises: determining whether a current assignment of feature values to features supports a classification from that node (para.[0123]; “an analyst who is initially unsure as to which commodity group is applicable to a given product can now refer to the information in this internal classification system”).
upon determining that the current assignment of feature values to features does not support the classification from that node on a path, selecting one of multiple unresolved features that results in a maximum support for downstream classification (para.[0123]; “analyst identifies the correct internal classification of the part, the analyst can then simply consult the internal classification map for the commodity group classification that corresponds to that internal classification. …….the analyst has an additional vehicle for classifying specific parts. Where the mapping directly links an internal classification to an HTS code, the analyst can simply consult
the internal classification and assign the appropriate HTS code to the product at issue” and para.[0125]; “the mapping may relate to a feature other than function. Further, the mapping may be directly to an HTS code. A map may also link internal classifications to both commodity groups and HTS codes, depending on the selected internal classification”).
generating a user interface comprising a user input element for a user to enter a value for the selected one of multiple non-valued features; receiving a feature value entered by the user and evaluating a decision model of that node for the received feature value, the decision model being defined in terms of the extracted feature for that node (para.[0065]; “The analyst may begin with the commodity group corresponding to the item at issue, and may be led through the decision tree by
answering questions specific to classification of that part (e.g., The part's function? The part's composition?). When the analyst comes to the end of the decision tree, he or she
may arrive at a particular HTS code, which may then be assigned by the TCS to the item at issue”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the current invention to incorporate multi-pass Harmonized Tariff Schedule classifications of the system of Uy into assets level classifications process of the system of Bhide, hierarchical product classification of the system of Yeleshwarapu, and classification pipeline of the system of Oltean to accurately classify import and export content, thereby maintaining the classification compliance and keeping record maintain by importer and custom broker consistent in the system of Wang.
8. Claims 3 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al (WO 2020/068421 A1), in view of Oltean (US 2010/0274750 A1), in view of Yeleshwarapu et al (US 2011/0087626 A1), in view of Bhide et al (US 2019/0155941 A1), in view of Uy et al (US 2005/0033592 A1), and further in view of Black et al (US 11,145,020 B1).
As per claim 3, the rejection of claim 2 is incorporated, Wang et al (WO 2020/068421 A1), Oltean (US 2010/0274750 A1), Yeleshwarapu et al (US 2011/0087626 A1), Bhide et al (US 2019/0155941 A1), and Uy et al (US 2005/0033592 A1) does not disclose wherein the method further comprises re-training the classification component for which the feature value was changed using the changed feature value as a training sample for the re-training.
However, Black et al (US 11,145,020 B1) in an analogous art discloses,
wherein the method further comprises re-training the classification component for which the feature value was changed using the changed feature value as a training sample for the re-training (col.20 lines 28 – 34; “retraining the classification knowledgebase 500 using a prediction feedback system 1300 such that every time a country's regulations change (e.g., new rules or altering duties, and/or the like), the prediction feedback system 1300 may modify the applicable information/
data in the classification knowledgebase 500 to reflect these changes” and col.22 lines 9 – 12; “harmonization process comprises classifying the commodity by assigning the Chapter, Heading and Subheading of the WCO, resulting in a six digit HTC”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the current invention to incorporate the classification scheme of the system of Black into assets level classifications process of the system of Bhide, multi-pass Harmonized Tariff Schedule classification of the system of Uy, and classification pipeline of the system of Oltean to reduce noncompliance and delay associated with incorrect classification of imported goods, thereby facilitating an improvement in managing the clearance of shipments in the system of Wang.
As per claim 18, the rejection of claim 1 is incorporated, Wang et al (WO 2020/068421 A1), Oltean (US 2010/0274750 A1), Bhide et al (US 2019/0155941 A1), and Uy et al (US 2005/0033592 A1) does not disclose wherein the multiple classification components comprise a base-component and a refined-component and the refined-component is associated with multiple options for the feature value that are inherited from the base-component.
However, Black et al (US 11,145,020 B1) in an analogous art discloses,
wherein the multiple classification components comprise a base-component and a refined-component and the refined-component is associated with multiple options for the feature value that are inherited from the base-component (col.20 lines 27 – 34; “configuration may allow for retraining the classification knowledgebase 500 using a prediction feedback system 1300 such that every time a country's regulations change (e.g., new rules or altering duties, and/or the like), the prediction feedback system 1300 may modify the applicable information/data in the classification knowledgebase 500 to reflect these changes”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the current invention to incorporate the classification scheme of the system of Black, assets level classifications process of the system of Bhide, multi-pass Harmonized Tariff Schedule classification of the system of Uy, and classification pipeline of the system of Oltean to reduce noncompliance and delay associated with incorrect classification of imported goods, thereby facilitating an improvement in managing the clearance of shipments in the system of Wang.
9. Claims 6 is rejected under 35 U.S.C. 103 as being unpatentable over Wang et al (WO 2020/068421 A1), in view of Oltean (US 2010/0274750 A1), in view of Yeleshwarapu et al (US 2011/0087626 A1), in view of Bhide et al (US 2019/0155941 A1), and further in view of in view of Black et al (US 11,145,020 B1).
As per claim 6, the rejection of claim 5 is incorporated, Wang et al (WO 2020/068421 A1), Oltean (US 2010/0274750 A1), Yeleshwarapu et al (US 2011/0087626 A1), and Bhide et al (US 2019/0155941 A1), does not disclose wherein each of the classification components that are applicable only if the product is unclassified are configured to classify the product into one of multiple chapters of the tariff classification and the classification components that are applicable only if the product is unclassified comprise trained machine learning models to classify the unclassified product.
However, Black et al (US 11,145,020 B1) in an analogous art discloses,
wherein each of the classification components that are applicable only if the product is unclassified are configured to classify the product into one of multiple chapters of the tariff classification (col.21 lines 35 – 39; “classifying the commodity to the specific tariff code for the import country, also referred to herein as the "commodity
code." The commodity code (also referred to herein as the fully qualified tariff code) may be determined by assigning an eight to ten digit tariff code to the commodity”).
and the classification components that are applicable only if the product is unclassified comprise trained machine learning models to classify the unclassified product (col.18 lines 7 – 8; “the machine learning algorithms may be
trained to predict commodity classifications” and col.29 lines 58 – 59; “retraining the machine learning algorithms utilized by the classification”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the current invention to incorporate the classification scheme of the system of Black into assets level classifications process of the system of Bhide, hierarchical product classification of the system of Yeleshwarapu, and classification pipeline of the system of Oltean to reduce noncompliance and delay associated with incorrect classification of imported goods, thereby facilitating an improvement in managing the clearance of shipments in the system of Wang.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
TITLE: Methods and apparatus for machine learning to produce improved data structures and classification within a database, US 11,720,600 B1 authors: Dixit et al.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AUGUSTINE K. OBISESAN whose telephone number is (571)272-2020. The examiner can normally be reached Monday - Friday 8:30am - 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, Ajay Bhatia can be reached at (571) 272-3906. 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.
/AUGUSTINE K. OBISESAN/
Primary Examiner
Art Unit 2156
2/6/2026