CTFR 18/237,932 CTFR 82506 Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Response to Arguments 07-38-01 AIA Applicant’s arguments, see page 12 , filed 3/26/2026 , with respect to 35 U.S.C. 101 have been fully considered and are persuasive. The rejection of claims 1-20 has been withdrawn. 07-37 AIA Applicant's arguments filed 3/26/2026 have been fully considered but they are not persuasive. Regarding applicants arguments “Without conceding to the merits of the rejection, claim 1 has been amended to recite inter alia "generating, based on the first comparative analysis information, a first plurality of metric scores for the first OCR application" and "generating, based on the second comparative analysis information, a second plurality of metric scores for the second OCR application." Reddy and Kumar, alone or in combination, fail to teach at least these features. No portion of Reddy teaches generating a plurality of metric scores for an OCR application. The Office Action alleges that Reddy's paragraph [0039] teaches "that a number of identical characters is computed for each OCR engine" based on Reddy's description that "the word of the output text is compared to a corresponding word of the known text sample to determine whether the two words are identical (424). If the two words are identical, then a score is incremented by the number of characters within the word of the output text." Office Action, p. 22 (quoting Reddy, 1[0039]). But assuming arguendo that Reddy's "score[] incremented by the number of characters within the word of the output text" is a metric score, Reddy does not perform "generating, based on the first comparative analysis information, a first plurality of metric scores for the first OCR application" and "generating, based on the second comparative analysis information, a second plurality of metric scores for the second OCR application" as claimed (emphasis added). Rather, Reddy merely increments a single score for each OCR engine. Reddy, 1[0039] The examiner notes that these new elements are disclosed by the combination of Reddy US 20120134589 A1 in view of Anthony US 11657222 B1 and Kumar US 20240185151 A1. The addition of the Anthony reference renders these arguments moot in view of the new grounds of rejection. Applicant further argues: Additionally, Reddy does not teach "cause, based on the stored correlation, at least one of: execution, by the computing platform, of the preferred OCR application to perform the first operation, or execution, by a user device different from the computing platform, of the preferred OCR application to perform the first operation" as now recited in claim 1. The Office Action alleges that Reddy teaches these features as previously recited in claim 6 because Reddy allegedly describes "that during an OCR operation the output of the preferred OCR engine with the highest confidence score may be used when performing OCR of the at [sic] particular text type." Office Action, pp. 25-26 (citing Reddy, 1[0019]). But Reddy describes that "[i]t may be decided to select the text 108 that was output by the OCR engine 104C having the highest confidence value for the text type of the text represented with the image 102." Reddy, 1[[0019]. Reddy thus does not "cause, based on the stored correlation, at least one of: execution, by the computing platform, of the preferred OCR application to perform the first operation, or execution, by a user device different from the computing platform, of the preferred OCR application to perform the first operation," Reddy merely selects an output of an OCR engine for use-the execution of the OCR engine has already occurred, and was not "based on the stored correlation" as claimed. The examiner disagrees with the above argument. Determining which results of OCR engine to select could be considered part of “execution” of the preferred OCR application. The claim does not prohibit the execution of other OCR applications. The word execution is broad and could encompass the entirety of the OCR process performed to determine the final output including the selection of the preferred output . Claim Rejections - 35 USC § 103 07-20-aia AIA 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. 07-21-aia AIA Claim (s) 1, 3-5, 7-8, 10-12, 14-15 17-18 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Reddy US 20120134589 A1 in view of Anthony US 11657222 B1 and Kumar US 20240185151 A1 . Re claim 1 Reddy discloses A computing platform comprising: at least one processor (see paragraph 44 processor); and memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to (see paragraph 44 non transitory computer readable medium storing the program see paragraph 42 note that the medium may be a memory): generate a script for evaluating performance of an optical character recognition (OCR) application (see paragraph 44 and figure 3 note the systems for evaluating the OCR application is implemented with a computer program i.e. a script), wherein the script is configured to output metric scores based on comparing original resources to modified resources (see paragraph 35 note that a OCR output is compared to original known text); retrieve an original resource from a resource repository (see paragraph 31 note that a known text sample is retrieved see paragraph 43 and figure 5 note that known text samples are stored on the computer readable medium); generate a first modified resource by executing a first OCR application on the original resource (see paragraph 34 note that an image of a known text sample is input into the OCR for a plurality of OCR engines); generate a second modified resource by executing a second OCR application on the original resource see paragraph 34 note that an image of a known text sample is input into the OCR for a plurality of OCR engines), wherein the second OCR application is different from the first OCR application (see paragraph 34 note that an image of a known text sample is input into the OCR for a plurality of OCR engines see also for example figure 1 note that different OCR engines produce different results); execute the script for the first OCR application and the second OCR application, wherein executing the script for first OCR application and the second OCR application includes: (see paragraph 44 and figure 3 note the systems for evaluating the OCR application is implemented with a computer program i.e. a script) generating first comparative analysis information for the first OCR application by comparing the original resource to the first modified resource (see paragraph 34 note that for each OCR application the OCR result is compared to the original known text); generating second comparative analysis information for the second OCR application by comparing the original resource to the second modified resource (see paragraph 34 note that for each OCR application the OCR result is compared to the original known text); generating, based on the first comparative analysis information, one or more metric scores for the first OCR application (see paragraph 39 note that a number of identical characters is computed for each OCR engine “the word of the output text is compared to a corresponding word of the known text sample to determine whether the two words are identical (424). If the two words are identical, then a score is incremented by the number of characters within the word of the output text”) generating, based on the second comparative analysis information, one or more metric scores for the second OCR application (see paragraph 39 note that a number of identical characters is computed for each OCR engine “the word of the output text is compared to a corresponding word of the known text sample to determine whether the two words are identical (424). If the two words are identical, then a score is incremented by the number of characters within the word of the output text”); generating, based on the one or more metric scores for the first OCR application, a first weighted score (see paragraph 39 “The score ultimately is divided by the total number of characters within the words of the output text to yield the confidence value of the OCR engine for the text type of the known text sample (428). As before, the method 420 is repeated for each OCR engine, to determine the confidence value of each OCR engine for the text type of the known text sample” note that the number is divided by the number of words in the sample to create the confidence value for each OCR engine, alternatively the method of paragraph 38 could be used); and generating, based on the one or more metric scores for the second OCR application, a second weighted score; (see paragraph 39 “The score ultimately is divided by the total number of characters within the words of the output text to yield the confidence value of the OCR engine for the text type of the known text sample (428). As before, the method 420 is repeated for each OCR engine, to determine the confidence value of each OCR engine for the text type of the known text sample” note that the number is divided by the number of words in the sample to create the confidence value for each OCR engine alternatively the method of paragraph 38 could be used); identify, based on comparing the first weighted score and the second weighted score, a preferred OCR application for use in a first operation (see paragraph 19 “It may be decided to select the text 108 that was output by the OCR engine 104C having the highest confidence value for the text type of the text represented within the image 102. As such, in the example of FIG. 1, the text 108A is selected, as indicated by the star 110 in FIG. 1, as at least provisionally correct for the text within the image 102” note that the system may use the OCR result from the highest confidence for a particular text type); and store a correlation between the first operation and the preferred OCR application at the resource repository (see paragraphs 35 and 19 note that confidence values representing the confidence between each OCR engine and a particular text type are maintained and used by the system these confidence values represent a correlation between OCR of the text type and the confidence of the region they must be stored at least temporarily to be used by the system (i.e. the repository)) cause, based on the stored correlation, at least one of: execution, by the computing platform, of the preferred OCR application to perform the first operation, or execution, by a user device different from the computing platform, of the preferred OCR application to perform the first operation. (See paragraph 19 “Therefore, which of the text 108 at least provisionally correctly corresponds to the text represented within the image 102 is selected based on the confidence values 106 of the OCR engines 104 for the text type of this text. As depicted in FIG. 1, the OCR engine 104A has a confidence value of 0.9 for this type of text, whereas the OCR engine 104B has a confidence value of 0.7, and the OCR engine 104C has a confidence value of 0.5. It may be decided to select the text 108 that was output by the OCR engine 104C having the highest confidence value for the text type of the text represented within the image 102. As such, in the example of FIG. 1, the text 108A is selected, as indicated by the star 110 in FIG. 1, as at least provisionally correct for the text within the image 102.” Note that during an OCR operation the output of the preferred OCR engine with the highest confidence may be used when performing OCR of the particular text type. This corresponds to the execution of the preferred OCR operation.) Reddy does not expressly disclose Wherein metric scores comprise plurality of metric scores and generating weighted scores by applying different multipliers to each metric score of the plurality of metric scores. Anthony discloses Wherein metric scores comprise plurality of metric scores (see column 8 lines 48-67 “One or more accuracy metrics may be generated for each extracted string based on a comparison of the extracted string with its respective ground truth value. For example, such an accuracy metric may be a Boolean indication of whether or not the extracted string matches the ground truth value. Such a Boolean indication may indicate whether the match is exact, or whether the match is a fuzzy match or an approximate string match. For example, a fuzzy or approximate string match may indicate that strings have at least a threshold degree of similarity, such as an edit distance below a threshold. In some other implementations, the accuracy metric may indicate a magnitude of extraction error. For example, the magnitude of extraction error may be indicated by an edit distance between the extracted string and the ground truth value, indicating a minimum number of operations required to transform the extracted string into the ground truth value. Such an edit distance may be normalized to the length of either the extracted string or the ground truth value. When the strings are numeric, the magnitude of error may be indicated by an absolute or fractional numeric difference between the extracted string and the ground truth value.” The examiner notes that accuracy may be based on multiple accuracy values). and generating weighted scores by applying different multipliers to each metric score of the plurality of metric scores (see column 9 lines 20-30 “For a given extracted string the average of the accuracy metrics of the most similar extracted strings may be an unweighted average or a weighted average. The weighted average may assign larger weights to the accuracy metrics of other extracted strings having larger extraction errors, such as larger edit distances between these strings and their respective ground truth values.”). The examiner notes that the teachings of Anthony could be to generate the first and second weighted scores as disclosed in Reddy. The motivation to combine is “significantly improved estimate of the accuracy of an associated extracted text string” (see column 5 lines1-5). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy and Anthony to reach the aforementioned advantage. Reddy further does not expressly disclose a communication interface communicatively coupled to the at least one processor; Kumar discloses communication interface communicatively coupled to the at least one processor (see paragraph 22 note the computer system use a communication interface). The motivation to combine is to allow the system to send and receive data (See paragraph 22). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar to reach the aforementioned advantage. Re claim 3 Reddy further discloses performing operations using a script (see paragraph 44 and figure 3 note the systems for evaluating the OCR application is implemented with a computer program i.e. a script). Reddy does not expressly disclose generate, and based on the one or more metric scores for the first OCR application, one or more visual representations for the first OCR application; and output, for the first OCR application, at least one visual representation of the one or more visual representations in a first format. Kumar discloses generate, and based on the one or more metric scores for the first OCR application, one or more visual representations for the first OCR application (see paragraph 6 “wherein analyzing the electronic documents comprises applying a character recognition algorithm to the first document, and assigning a confidence factor to each of the values; and providing a report of the data instances in a graphical user interface (GUI)” note that a report is presented about the confidence of values recognized by the OCR algorithm ); and output, for the first OCR application, at least one visual representation of the one or more visual representations in a first format (see paragraph 6 and 30 note that a report may be generated and output to a graphical user interface of a display ). The motivation to combine is “the output summary may be configured to convey the results of the analysis processes” (see paragraph 47). One of ordinary skill in the art could have easily used the teachings of Kumar to display a report about the results of the analysis processes of Reddy. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar to reach the aforementioned advantage. Re claim 4 Kumar further discloses output, in a second format different from the first format and based on receiving user input, the at least one visual representation (see paragraph 30 “In some embodiments, the report engine 131 may generate a document (e.g., text file, excel file, PDF, etc.)” note that the report may be in various format). Re claim 5 Reddy discloses wherein the first weighted score and the second weighted score correspond to a file type of the original resource. (see paragraph 10 “Specifically, each of a number of different OCR engines has a confidence value for each of a number of different text types“ note that the text type of the file corresponds to the file type ) Re claim 7 Reddy discloses receive a request to perform the first operation; execute, based on the stored correlation, the preferred OCR application to perform the first operation (see paragraph 19 “ Therefore, which of the text 108 at least provisionally correctly corresponds to the text represented within the image 102 is selected based on the confidence values 106 of the OCR engines 104 for the text type of this text. As depicted in FIG. 1, the OCR engine 104A has a confidence value of 0.9 for this type of text, whereas the OCR engine 104B has a confidence value of 0.7, and the OCR engine 104C has a confidence value of 0.5. It may be decided to select the text 108 that was output by the OCR engine 104C having the highest confidence value for the text type of the text represented within the image 102. As such, in the example of FIG. 1, the text 108A is selected, as indicated by the star 110 in FIG. 1, as at least provisionally correct for the text within the image 102.” Note that during an OCR operation the output of the preferred OCR engine with the highest confidence may be used when performing OCR of the at particular text type.) receive a request to perform a second operation different from the first operation; and execute a third OCR application different from the preferred OCR application to perform the second operation. (see paragraph 29 and 30 “ The method 200 can be performed on a word-by-word basis for multiple words within the unknown text of an image. The text type of each such word may further be different. For example, different words within the text may have different fonts, different font sizes, some words may be underlined whereas other words may not be underlined, some words may be italicized whereas other words may not be italicized, and so on. Each OCR engine has a confidence value for each different text type.” Note that the second operation could correspond to a different word in the document of a different text type with a different confidence value. See also paragraph 9 note that it is contemplated that different OCR engines will be most accurate for different text types, see figure 1 note that at least 3 OCR engines may be used). Re claim 8 Reddy discloses A method comprising: at a computing device comprising at least one processor (see paragraph 44 processor), and memory; (see paragraph 44 non transitory computer readable medium storing the program see paragraph 42 note that the medium may be a memory): generating a script for evaluating performance of an optical character recognition (OCR) application (see paragraph 44 and figure 3 note the systems for evaluating the OCR application is implemented with a computer program i.e. a script), wherein the script is configured to output metric scores based on comparing original resources to modified resources (see paragraph 35 note that a OCR output is compared to original known text ); retrieving an original resource from a resource repository (see paragraph 31 note that a known text sample is retrieved see paragraph 43 and figure 5 note that known text samples are stored on the computer readable medium); generating a first modified resource by executing a first OCR application on the original resource (see paragraph 34 note that an image of a known text sample is input into the OCR for a plurality of OCR engines ); generating a second modified resource by executing a second OCR application on the original resource see paragraph 34 note that an image of a known text sample is input into the OCR for a plurality of OCR engines), wherein the second OCR application is different from the first OCR application (see paragraph 34 note that an image of a known text sample is input into the OCR for a plurality of OCR engines see also for example figure 1 note that different OCR engines produce different results); executing the script for the first OCR application and the second OCR application, wherein executing the script for first OCR application and the second OCR application includes: (see paragraph 44 and figure 3 note the systems for evaluating the OCR application is implemented with a computer program i.e. a script) generating first comparative analysis information for the first OCR application by comparing the original resource to the first modified resource (see paragraph 34 note that for each OCR application the OCR result is compared to the original known text); generating second comparative analysis information for the second OCR application by comparing the original resource to the second modified resource(see paragraph 34 note that for each OCR application the OCR result is compared to the original known text); generating, based on the first comparative analysis information, one or more metric scores for the first OCR application (see paragraph 39 note that a number of identical characters is computed for each OCR engine “the word of the output text is compared to a corresponding word of the known text sample to determine whether the two words are identical (424). If the two words are identical, then a score is incremented by the number of characters within the word of the output text”) generating, based on the second comparative analysis information, one or more metric scores for the second OCR application (see paragraph 39 note that a number of identical characters is computed for each OCR engine “the word of the output text is compared to a corresponding word of the known text sample to determine whether the two words are identical (424). If the two words are identical, then a score is incremented by the number of characters within the word of the output text”); generating, based on the one or more metric scores for the first OCR application, a first weighted score (see paragraph 39 “The score ultimately is divided by the total number of characters within the words of the output text to yield the confidence value of the OCR engine for the text type of the known text sample (428). As before, the method 420 is repeated for each OCR engine, to determine the confidence value of each OCR engine for the text type of the known text sample” note that the number is divided by the number of words in the sample to create the confidence value for each OCR engine, alternatively the method of paragraph 38 could be used); and generating, based on the one or more metric scores for the second OCR application, a second weighted score; (see paragraph 39 “The score ultimately is divided by the total number of characters within the words of the output text to yield the confidence value of the OCR engine for the text type of the known text sample (428). As before, the method 420 is repeated for each OCR engine, to determine the confidence value of each OCR engine for the text type of the known text sample” note that the number is divided by the number of words in the sample to create the confidence value for each OCR alternatively the method of paragraph 38 could be used ); identifying, based on comparing the first weighted score and the second weighted score, a preferred OCR application for use in a first operation ( see paragraph 19 “It may be decided to select the text 108 that was output by the OCR engine 104C having the highest confidence value for the text type of the text represented within the image 102. As such, in the example of FIG. 1, the text 108A is selected, as indicated by the star 110 in FIG. 1, as at least provisionally correct for the text within the image 102” note that the system may use the OCR result from the highest confidence for a particular text type); and storing a correlation between the first operation and the preferred OCR application at the resource repository (see paragraphs 35 and 19 note that confidence values representing the confidence between each OCR engine and a particular text type are maintained and used by the system these confidence values represent a correlation between OCR of the text type and the confidence of the region they must be stored at least temporarily to be used by the system (i.e the repository)) cause, based on the stored correlation, at least one of: execution, by the computing platform, of the preferred OCR application to perform the first operation, or execution, by a user device different from the computing platform, of the preferred OCR application to perform the first operation. (See paragraph 19 “Therefore, which of the text 108 at least provisionally correctly corresponds to the text represented within the image 102 is selected based on the confidence values 106 of the OCR engines 104 for the text type of this text. As depicted in FIG. 1, the OCR engine 104A has a confidence value of 0.9 for this type of text, whereas the OCR engine 104B has a confidence value of 0.7, and the OCR engine 104C has a confidence value of 0.5. It may be decided to select the text 108 that was output by the OCR engine 104C having the highest confidence value for the text type of the text represented within the image 102. As such, in the example of FIG. 1, the text 108A is selected, as indicated by the star 110 in FIG. 1, as at least provisionally correct for the text within the image 102.” Note that during an OCR operation the output of the preferred OCR engine with the highest confidence may be used when performing OCR of the particular text type. This corresponds to the execution of the preferred OCR operation.) Reddy does not expressly disclose Wherein metric scores comprise plurality of metric scores and generating weighted scores by applying different multipliers to each metric score of the plurality of metric scores. Anthony discloses Wherein metric scores comprise plurality of metric scores (see column 8 lines 48-67 “One or more accuracy metrics may be generated for each extracted string based on a comparison of the extracted string with its respective ground truth value. For example, such an accuracy metric may be a Boolean indication of whether or not the extracted string matches the ground truth value. Such a Boolean indication may indicate whether the match is exact, or whether the match is a fuzzy match or an approximate string match. For example, a fuzzy or approximate string match may indicate that strings have at least a threshold degree of similarity, such as an edit distance below a threshold. In some other implementations, the accuracy metric may indicate a magnitude of extraction error. For example, the magnitude of extraction error may be indicated by an edit distance between the extracted string and the ground truth value, indicating a minimum number of operations required to transform the extracted string into the ground truth value. Such an edit distance may be normalized to the length of either the extracted string or the ground truth value. When the strings are numeric, the magnitude of error may be indicated by an absolute or fractional numeric difference between the extracted string and the ground truth value.” The examiner notes that accuracy may be based on multiple accuracy values). and generating weighted scores by applying different multipliers to each metric score of the plurality of metric scores (see column 9 lines 20-30 “For a given extracted string the average of the accuracy metrics of the most similar extracted strings may be an unweighted average or a weighted average. The weighted average may assign larger weights to the accuracy metrics of other extracted strings having larger extraction errors, such as larger edit distances between these strings and their respective ground truth values.”). The examiner notes that the teachings of Anthony could be to generate the first and second weighted scores as disclosed in Reddy. The motivation to combine is “significantly improved estimate of the accuracy of an associated extracted text string” (see column 5 lines1-5). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy and Anthony to reach the aforementioned advantage. Reddy further does not expressly disclose a communication interface communicatively coupled to the at least one processor; Kumar discloses communication interface communicatively coupled to the at least one processor (see paragraph 22 note the computer system use a communication interface). The motivation to combine is to allow the system to send and receive data (See paragraph 22). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar to reach the aforementioned advantage. Re claim 10 Reddy does not expressly disclose at the computing device: generating, using the script and based on the one or more metric scores for the first OCR application, one or more visual representations for the first OCR application; and outputting, for the first OCR application, at least one visual representation of the one or more visual representations in a first format. Kumar discloses generating, using the script and based on the one or more metric scores for the first OCR application, one or more visual representations for the first OCR application (see paragraph 6 “wherein analyzing the electronic documents comprises applying a character recognition algorithm to the first document, and assigning a confidence factor to each of the values; and providing a report of the data instances in a graphical user interface (GUI)” note that a report is presented about the confidence of values recognized by the OCR algorithm ); and outputting, for the first OCR application, at least one visual representation of the one or more visual representations in a first format (see paragraph 6 and 30 note that a report may be generated and output to a graphical user interface of a display ). The motivation to combine is “the output summary may be configured to convey the results of the analysis processes” (see paragraph 47). One of ordinary skill in the art could have easily used the teachings of Kumar to display a report about the results of the analysis processes of Reddy. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar to reach the aforementioned advantage. Re claim 11 Kumar further discloses wherein the outputting the at least one visual representation comprises outputting, in a second format different from the first format and based on receiving user input, the at least one visual representation (see paragraph 30 “In some embodiments, the report engine 131 may generate a document (e.g., text file, excel file, PDF, etc.)” note that the report may be in various format). Re claim 12 Reddy discloses wherein the first weighted score and the second weighted score correspond to a file type of the original resource. (see paragraph 10 “Specifically, each of a number of different OCR engines has a confidence value for each of a number of different text types“ note that the text type of the file corresponds to the file type ) Re claim 14 Reddy discloses receiving a request to perform the first operation; executing, based on the stored correlation, the preferred OCR application to perform the first operation (see paragraph 19 “Therefore, which of the text 108 at least provisionally correctly corresponds to the text represented within the image 102 is selected based on the confidence values 106 of the OCR engines 104 for the text type of this text. As depicted in FIG. 1, the OCR engine 104A has a confidence value of 0.9 for this type of text, whereas the OCR engine 104B has a confidence value of 0.7, and the OCR engine 104C has a confidence value of 0.5. It may be decided to select the text 108 that was output by the OCR engine 104C having the highest confidence value for the text type of the text represented within the image 102. As such, in the example of FIG. 1, the text 108A is selected, as indicated by the star 110 in FIG. 1, as at least provisionally correct for the text within the image 102.” Note that during an OCR operation the output of the preferred OCR engine with the highest confidence may be used when performing OCR of the at particular text type.) receiving a request to perform a second operation different from the first operation; and executing a third OCR application different from the preferred OCR application to perform the second operation. (See paragraph 29 and 30 “The method 200 can be performed on a word-by-word basis for multiple words within the unknown text of an image. The text type of each such word may further be different. For example, different words within the text may have different fonts, different font sizes, some words may be underlined whereas other words may not be underlined, some words may be italicized whereas other words may not be italicized, and so on. Each OCR engine has a confidence value for each different text type.” Note that the second operation could correspond to a different word in the document of a different text type with a different confidence value. See also paragraph 9 note that it is contemplated that different OCR engines will be most accurate for different text types see figure 1 note that at least 3 OCR engines may be used). Re claim 15 Reddy discloses One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, and memory, cause the computing platform to (see paragraph 44 processor); (see paragraph 44 non transitory computer readable medium storing the program see paragraph 42 note that the medium may be a memory): generate a script for evaluating performance of an optical character recognition (OCR) application (see paragraph 44 and figure 3 note the systems for evaluating the OCR application is implemented with a computer program i.e. a script), wherein the script is configured to output metric scores based on comparing original resources to modified resources (see paragraph 35 note that a OCR output is compared to original known text); retrieve an original resource from a resource repository (see paragraph 31 note that a known text sample is retrieved see paragraph 43 and figure 5 note that known text samples are stored on the computer readable medium); generate a first modified resource by executing a first OCR application on the original resource (see paragraph 34 note that an image of a known text sample is input into the OCR for a plurality of OCR engines); generate a second modified resource by executing a second OCR application on the original resource see paragraph 34 note that an image of a known text sample is input into the OCR for a plurality of OCR engines), wherein the second OCR application is different from the first OCR application (see paragraph 34 note that an image of a known text sample is input into the OCR for a plurality of OCR engines see also for example figure 1 note that different OCR engines produce different results); execute the script for the first OCR application and the second OCR application, wherein executing the script for first OCR application and the second OCR application includes: (see paragraph 44 and figure 3 note the systems for evaluating the OCR application is implemented with a computer program i.e. a script) generating first comparative analysis information for the first OCR application by comparing the original resource to the first modified resource (see paragraph 34 note that for each OCR application the OCR result is compared to the original known text); generating second comparative analysis information for the second OCR application by comparing the original resource to the second modified resource (see paragraph 34 note that for each OCR application the OCR result is compared to the original known text); generating, based on the first comparative analysis information, one or more metric scores for the first OCR application (see paragraph 39 note that a number of identical characters is computed for each OCR engine “the word of the output text is compared to a corresponding word of the known text sample to determine whether the two words are identical (424). If the two words are identical, then a score is incremented by the number of characters within the word of the output text”) generating, based on the second comparative analysis information, one or more metric scores for the second OCR application (see paragraph 39 note that a number of identical characters is computed for each OCR engine “the word of the output text is compared to a corresponding word of the known text sample to determine whether the two words are identical (424). If the two words are identical, then a score is incremented by the number of characters within the word of the output text”); generating, based on the one or more metric scores for the first OCR application, a first weighted score (see paragraph 39 “The score ultimately is divided by the total number of characters within the words of the output text to yield the confidence value of the OCR engine for the text type of the known text sample (428). As before, the method 420 is repeated for each OCR engine, to determine the confidence value of each OCR engine for the text type of the known text sample” note that the number is divided by the number of words in the sample to create the confidence value for each OCR engine, alternatively the method of paragraph 38 could be used); and generating, based on the one or more metric scores for the second OCR application, a second weighted score; (see paragraph 39 “The score ultimately is divided by the total number of characters within the words of the output text to yield the confidence value of the OCR engine for the text type of the known text sample (428). As before, the method 420 is repeated for each OCR engine, to determine the confidence value of each OCR engine for the text type of the known text sample” note that the number is divided by the number of words in the sample to create the confidence value for each OCR engine alternatively the method of paragraph 38 could be used); identify, based on comparing the first weighted score and the second weighted score, a preferred OCR application for use in a first operation (see paragraph 19 “It may be decided to select the text 108 that was output by the OCR engine 104C having the highest confidence value for the text type of the text represented within the image 102. As such, in the example of FIG. 1, the text 108A is selected, as indicated by the star 110 in FIG. 1, as at least provisionally correct for the text within the image 102” note that the system may use the OCR result from the highest confidence for a particular text type); and store a correlation between the first operation and the preferred OCR application at the resource repository (see paragraphs 35 and 19 note that confidence values representing the confidence between each OCR engine and a particular text type are maintained and used by the system these confidence values represent a correlation between OCR of the text type and the confidence of the region they must be stored at least temporarily to be used by the system (i.e. the repository)). cause, based on the stored correlation, at least one of: execution, by the computing platform, of the preferred OCR application to perform the first operation, or execution, by a user device different from the computing platform, of the preferred OCR application to perform the first operation. (See paragraph 19 “Therefore, which of the text 108 at least provisionally correctly corresponds to the text represented within the image 102 is selected based on the confidence values 106 of the OCR engines 104 for the text type of this text. As depicted in FIG. 1, the OCR engine 104A has a confidence value of 0.9 for this type of text, whereas the OCR engine 104B has a confidence value of 0.7, and the OCR engine 104C has a confidence value of 0.5. It may be decided to select the text 108 that was output by the OCR engine 104C having the highest confidence value for the text type of the text represented within the image 102. As such, in the example of FIG. 1, the text 108A is selected, as indicated by the star 110 in FIG. 1, as at least provisionally correct for the text within the image 102.” Note that during an OCR operation the output of the preferred OCR engine with the highest confidence may be used when performing OCR of the particular text type. This corresponds to the execution of the preferred OCR operation.) Reddy does not expressly disclose Wherein metric scores comprise plurality of metric scores and generating weighted scores by applying different multipliers to each metric score of the plurality of metric scores. Anthony discloses Wherein metric scores comprise plurality of metric scores (see column 8 lines 48-67 “One or more accuracy metrics may be generated for each extracted string based on a comparison of the extracted string with its respective ground truth value. For example, such an accuracy metric may be a Boolean indication of whether or not the extracted string matches the ground truth value. Such a Boolean indication may indicate whether the match is exact, or whether the match is a fuzzy match or an approximate string match. For example, a fuzzy or approximate string match may indicate that strings have at least a threshold degree of similarity, such as an edit distance below a threshold. In some other implementations, the accuracy metric may indicate a magnitude of extraction error. For example, the magnitude of extraction error may be indicated by an edit distance between the extracted string and the ground truth value, indicating a minimum number of operations required to transform the extracted string into the ground truth value. Such an edit distance may be normalized to the length of either the extracted string or the ground truth value. When the strings are numeric, the magnitude of error may be indicated by an absolute or fractional numeric difference between the extracted string and the ground truth value.” The examiner notes that accuracy may be based on multiple accuracy values). and generating weighted scores by applying different multipliers to each metric score of the plurality of metric scores (see column 9 lines 20-30 “For a given extracted string the average of the accuracy metrics of the most similar extracted strings may be an unweighted average or a weighted average. The weighted average may assign larger weights to the accuracy metrics of other extracted strings having larger extraction errors, such as larger edit distances between these strings and their respective ground truth values.”). The examiner notes that the teachings of Anthony could be to generate the first and second weighted scores as disclosed in Reddy. The motivation to combine is “significantly improved estimate of the accuracy of an associated extracted text string” (see column 5 lines1-5). therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy and Anthony to reach the aforementioned advantage. Reddy further does not expressly disclose a communication interface communicatively coupled to the at least one processor; Kumar discloses communication interface communicatively coupled to the at least one processor (see paragraph 22 note the computer system use a communication interface). The motivation to combine is to allow the system to send and receive data (See paragraph 22). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar to reach the aforementioned advantage. Re claim 17 Reddy does not expressly disclose generate, using the script and based on the one or more metric scores for the first OCR application, one or more visual representations for the first OCR application; and output, for the first OCR application, at least one visual representation of the one or more visual representations in a first format. Kumar discloses generate, using the script and based on the one or more metric scores for the first OCR application, one or more visual representations for the first OCR application (see paragraph 6 “wherein analyzing the electronic documents comprises applying a character recognition algorithm to the first document, and assigning a confidence factor to each of the values; and providing a report of the data instances in a graphical user interface (GUI)” note that a report is presented about the confidence of values recognized by the OCR algorithm ); and output, for the first OCR application, at least one visual representation of the one or more visual representations in a first format (see paragraph 6 and 30 note that a report may be generated and output to a graphical user interface of a display ). The motivation to combine is “the output summary may be configured to convey the results of the analysis processes” (see paragraph 47). One of ordinary skill in the art could have easily used the teachings of Kumar to display a report about the results of the analysis processes of Reddy. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar to reach the aforementioned advantage. Re claim 18 Reddy discloses wherein the first weighted score and the second weighted score correspond to a file type of the original resource. (see paragraph 10 “Specifically, each of a number of different OCR engines has a confidence value for each of a number of different text types“ note that the text type of the file corresponds to the file type ) Re claim 20 Reddy discloses receive a request to perform the first operation; execute, based on the stored correlation, the preferred OCR application to perform the first operation (see paragraph 19 “Therefore, which of the text 108 at least provisionally correctly corresponds to the text represented within the image 102 is selected based on the confidence values 106 of the OCR engines 104 for the text type of this text. As depicted in FIG. 1, the OCR engine 104A has a confidence value of 0.9 for this type of text, whereas the OCR engine 104B has a confidence value of 0.7, and the OCR engine 104C has a confidence value of 0.5. It may be decided to select the text 108 that was output by the OCR engine 104C having the highest confidence value for the text type of the text represented within the image 102. As such, in the example of FIG. 1, the text 108A is selected, as indicated by the star 110 in FIG. 1, as at least provisionally correct for the text within the image 102.” Note that during an OCR operation the output of the preferred OCR engine with the highest confidence may be used when performing OCR of the at particular text type.) receive a request to perform a second operation different from the first operation; and execute a third OCR application different from the preferred OCR application to perform the second operation. (see paragraph 29 and 30 “The method 200 can be performed on a word-by-word basis for multiple words within the unknown text of an image. The text type of each such word may further be different. For example, different words within the text may have different fonts, different font sizes, some words may be underlined whereas other words may not be underlined, some words may be italicized whereas other words may not be italicized, and so on. Each OCR engine has a confidence value for each different text type.” Note that the second operation could correspond to a different word in the document of a different text type with a different confidence value. See also paragraph 9 note that it is contemplated that different OCR engines will be most accurate for different text types, see figure 1 note that at least 3 OCR engines may be used) . 07-21-aia AIA Claim (s) 2, 9 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Reddy US 20120134589 A1 in view of Anthony US 11657222 B1 and Kumar US 20240185151 A1 in further view of Hubel US 20150350562 A1 . Re claim 2 Reddy discloses generating a weighted score for a third OCR application (see paragraph 39 “The score ultimately is divided by the total number of characters within the words of the output text to yield the confidence value of the OCR engine for the text type of the known text sample (428). As before, the method 420 is repeated for each OCR engine, to determine the confidence value of each OCR engine for the text type of the known text sample” note that the number is divided by the number of words in the sample to create the confidence value for each OCR engine imply multiple OCR engines there may be at least 3 OCR engines see figure 1. Reddy does not expressly disclose enhance, based score for a OCR application and using at least one image-enhancement application, at least one modified resource corresponding to the OCR application. Hubel discloses enhance, based score for a OCR application and using at least one image-enhancement application, at least one modified resource corresponding to the OCR application (see paragraph 35 “However confidence information is obtained, the process at 503 may use the information to determine if further image combinations may be desirable in order to enhance the prominence and decipherability of the characters or symbols present” note that image enhancement may be performed if a confidence is low to improve). The motivation to combine is repeat the OCR if the confidence is too low (see paragraph 35). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar with Hubel to reach the aforementioned advantage. Re claim 9 Reddy discloses generating a weighted score for a third OCR application (see paragraph 39 “The score ultimately is divided by the total number of characters within the words of the output text to yield the confidence value of the OCR engine for the text type of the known text sample (428). As before, the method 420 is repeated for each OCR engine, to determine the confidence value of each OCR engine for the text type of the known text sample” note that the number is divided by the number of words in the sample to create the confidence value for each OCR engine imply multiple OCR engines there may be at least 3 OCR engines see figure 1. Reddy does not expressly disclose enhancing, based score for a OCR application and using at least one image-enhancement application, at least one modified resource corresponding to the OCR application. Hubel discloses enhancing, based score for a OCR application and using at least one image-enhancement application, at least one modified resource corresponding to the OCR application (see paragraph 35 “However confidence information is obtained, the process at 503 may use the information to determine if further image combinations may be desirable in order to enhance the prominence and decipherability of the characters or symbols present” note that image enhancement may be performed if a confidence is low to improve). The motivation to combine is repeat the OCR if the confidence is too low (see paragraph 35). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar with Hubel to reach the aforementioned advantage. Re claim 16 Reddy discloses generating a weighted score for a third OCR application (see paragraph 39 “The score ultimately is divided by the total number of characters within the words of the output text to yield the confidence value of the OCR engine for the text type of the known text sample (428). As before, the method 420 is repeated for each OCR engine, to determine the confidence value of each OCR engine for the text type of the known text sample” note that the number is divided by the number of words in the sample to create the confidence value for each OCR engine imply multiple OCR engines there may be at least 3 OCR engines see figure 1. Reddy does not expressly disclose enhance, based score for a OCR application and using at least one image-enhancement application, at least one modified resource corresponding to the OCR application. Hubel discloses enhance, based score for a OCR application and using at least one image-enhancement application, at least one modified resource corresponding to the OCR application (see paragraph 35 “However confidence information is obtained, the process at 503 may use the information to determine if further image combinations may be desirable in order to enhance the prominence and decipherability of the characters or symbols present” note that image enhancement may be performed if a confidence is low to improve). The motivation to combine is repeat the OCR if the confidence is too low (see paragraph 35). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar with Hubel to reach the aforementioned advantage . 07-21-aia AIA Claim (s) 21-23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Reddy US 20120134589 A1 in view of Anthony US 11657222 B1 and Kumar US 20240185151 A1 in further view of Romain Karpinski, Devashish Lohani, Abdel Belaid. Metrics for Complete Evaluation of OCR Performance. IPCV’18- The 22nd Int’l Conf on Image Processing, Computer Vision, & Pattern Recognition, Jul 2018, Las Vegas, United States . Re claim 21 Anthony discloses wherein the first plurality of metric scores comprises at least a fuzzy matching ratio. (See column 8 lines 50-67 “Such a Boolean indication may indicate whether the match is exact, or whether the match is a fuzzy match or an approximate string match. For example, a fuzzy or approximate string match may indicate that strings have at least a threshold degree of similarity, such as an edit distance below a threshold” note that the edit distance may be normalized by length). Anthony Reddy and Kumar does not expressly disclose wherein the first plurality of metric scores comprises at least two of the following: a case sensitive character error rate; a case insensitive character error rate; a fuzzy matching ratio; a Levenshtein ratio; and a capture rate corresponding to a character error rate. Karpinski discloses a Levenshtein ratio; and a capture rate corresponding to a character error rate (see section 3.1.1 note that Levenshtien distance is used to calculate a ratio, see equation 3a). One of ordinary skill in the art could have easily used Levenshtien ratio as one of the metrics in the combination of Reddy Anthony and Kumar and the results, the metric is used as one of the metrics, would have been predictable. In both situation the combined elements perform the same function separately as they do in the combination which is to evaluate the error of an OCR application. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar with Karpinski to reach the aforementioned advantage. Re claim 22 Anthony discloses wherein the first plurality of metric scores comprises at least a fuzzy matching ratio. (See column 8 lines 50-67 “Such a Boolean indication may indicate whether the match is exact, or whether the match is a fuzzy match or an approximate string match. For example, a fuzzy or approximate string match may indicate that strings have at least a threshold degree of similarity, such as an edit distance below a threshold” note that the edit distance may be normalized by length). Anthony Reddy and Kumar does not expressly disclose wherein the first plurality of metric scores comprises at least two of the following: a case sensitive character error rate; a case insensitive character error rate; a fuzzy matching ratio; a Levenshtein ratio; and a capture rate corresponding to a character error rate. Karpinski discloses a Levenshtein ratio; and a capture rate corresponding to a character error rate (see section 3.1.1 note that Levenshtien distance is used to calculate a ratio, see equation 3a). One of ordinary skill in the art could have easily used Levenshtien ratio as one of the metrics in the combination of Reddy Anthony and Kumar and the results, the metric is used as one of the metrics, would have been predictable. In both situation the combined elements perform the same function separately as they do in the combination which is to evaluate the error of an OCR application. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar with Karpinski to reach the aforementioned advantage. Re claim 23 Anthony discloses wherein the first plurality of metric scores comprises at least a fuzzy matching ratio. (See column 8 lines 50-67 “Such a Boolean indication may indicate whether the match is exact, or whether the match is a fuzzy match or an approximate string match. For example, a fuzzy or approximate string match may indicate that strings have at least a threshold degree of similarity, such as an edit distance below a threshold” note that the edit distance may be normalized by length). Anthony Reddy and Kumar does not expressly disclose wherein the first plurality of metric scores comprises at least two of the following: a case sensitive character error rate; a case insensitive character error rate; a fuzzy matching ratio; a Levenshtein ratio; and a capture rate corresponding to a character error rate. Karpinski discloses a Levenshtein ratio; and a capture rate corresponding to a character error rate (see section 3.1.1 note that Levenshtien distance is used to calculate a ratio, see equation 3a). One of ordinary skill in the art could have easily used Levenshtien ratio as one of the metrics in the combination of Reddy Anthony and Kumar and the results, the metric is used as one of the metrics, would have been predictable. In both situation the combined elements perform the same function separately as they do in the combination which is to evaluate the error of an OCR application. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Reddy Anthony and Kumar with Karpinski to reach the aforementioned advantage. Conclusion 07-40 AIA Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL . See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to SEAN T MOTSINGER whose telephone number is (571)270-1237. The examiner can normally be reached 9AM-5PM. 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, Chineyere Wills-Burns can be reached at (571) 272-9752. 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. /SEAN T MOTSINGER/Primary Examiner, Art Unit 2673 Application/Control Number: 18/237,932 Page 2 Art Unit: 2673 Application/Control Number: 18/237,932 Page 3 Art Unit: 2673 Application/Control Number: 18/237,932 Page 4 Art Unit: 2673 Application/Control Number: 18/237,932 Page 5 Art Unit: 2673 Application/Control Number: 18/237,932 Page 6 Art Unit: 2673 Application/Control Number: 18/237,932 Page 7 Art Unit: 2673 Application/Control Number: 18/237,932 Page 8 Art Unit: 2673 Application/Control Number: 18/237,932 Page 9 Art Unit: 2673 Application/Control Number: 18/237,932 Page 10 Art Unit: 2673 Application/Control Number: 18/237,932 Page 11 Art Unit: 2673 Application/Control Number: 18/237,932 Page 12 Art Unit: 2673 Application/Control Number: 18/237,932 Page 13 Art Unit: 2673 Application/Control Number: 18/237,932 Page 14 Art Unit: 2673 Application/Control Number: 18/237,932 Page 15 Art Unit: 2673 Application/Control Number: 18/237,932 Page 16 Art Unit: 2673 Application/Control Number: 18/237,932 Page 17 Art Unit: 2673 Application/Control Number: 18/237,932 Page 18 Art Unit: 2673 Application/Control Number: 18/237,932 Page 19 Art Unit: 2673 Application/Control Number: 18/237,932 Page 20 Art Unit: 2673 Application/Control Number: 18/237,932 Page 21 Art Unit: 2673 Application/Control Number: 18/237,932 Page 22 Art Unit: 2673
Prosecution Insights