DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 01/12/2026 has been entered.
Response to Arguments
Applicant's arguments filed on 01/12/2026 with respect to claims 1 - 20 have been considered but are not persuasive.
Please refer to the following office action, which clearly sets forth the reasons for non-persuasiveness.
Applicant argues that Trovato fails to teach upon determining the identification of the object, generating a set of steps of a workflow to compound a medication associated with the object based on the identification of the object.
Examiner notes that Trovato teaches upon determining the identification of the object, generating a set of steps of a workflow to compound a medication associated with the object based on the identification of the object in at least paragraphs 0048 – 0053. First bar code on vial is identified (i.e. object identified) then multiple steps are carried out (i.e. generating a set of steps of stages of structured process designed to produce a specific output, note each step has its own specific process i.e. steps related to object identified) according to identified bar code.
Claim Rejections - 35 USC § 103
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:
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claims 1 – 20 are rejected under 35 U.S.C. 103 as being unpatentable over Trovato (US PgPub No. 2019/0151545) in view of LIN (US PgPub No. 2023/0032433).
Regarding claim 1, Trovato teaches a pharmaceutical compounding device (figures 2 – 9, 12 – 14, 18, and 20 item 201 also figure 1 item 101), comprising: a processor (figure 1 item 2002); a visible light camera (figure 20 item 403); an infrared camera (figure 20 item 404); a transparent tray comprising a scale plate (figures 3 and 6 item 301 also paragraphs 0042, 0046, 0087; weight sensor with tray as shown in figure 2 item 209 also paragraphs 0042, 0055, 0065, and 0081); an electronic display (figure 1 item 107); and a memory storing instructions that, when executed by the processor (figure 1 items 105 and 106 also figure 20 items 2002 and 2003), perform operations comprising: capturing an image of an object placed on the scale plate using the visible light camera (paragraph 0067 also paragraphs 0043, 0054, 0070, 0080 - 0086; photographs taken); accessing a plurality of models stored in a memory of the pharmaceutical compounding device (paragraphs 0043 – 0048, 0061, and 0086; bar code to identify stored in memory; correct medication was identified by the barcode scan); determining an identification of the object based at least in part on the image of the object using image analysis techniques using a model using at least a first one of the plurality of models (paragraphs 0043 – 0048, 0061, and 0086; bar code to identify; correct medication was identified by the barcode scan); upon determining the identification of the object, generating a set of steps of a workflow to compound a medication associated with the object based on the identification of the object (at least paragraphs 0048 – 0053, First bar code on vial is identified (i.e. object identified) then multiple steps are carried out (i.e. generating a set of steps of stages of structured process designed to produce a specific output, note each step has its own specific process i.e. steps related to object identified) according to identified bar code; paragraph 0048; compounding assistance device 201 requires that the user present vial 204 to bar code scanner 402, so that the identifying bar code on vial 204 can be read, and the system can verify that the correct vial with the correct concentration has been provided. If not, then an error message is generated and the compounding task is stopped. The scanning process is illustrated in FIG. 5, along with an example prompt shown on screen 208. Compounding assistance device 201 may automatically recognize that the barcode has been detected, and may move to the next step. Alternatively, an acknowledgment from the user may be required, in this and other steps); and generating a notification on the electronic display based on the workflow (paragraph; 0007, 0048, 0156; controller is programmed to guide a user of the compounding assistance device through a pharmaceutical compounding task using one or more prompts shown on the display; also figures 5 – 9, 12 - 13).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 2, as mentioned above in the discussion of claim 1, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches comprising at least one of: a printer configured to print labels (figure 13 item 1303 printing item 1301), a visible light source configured to illuminate the object on the scale plate (figure 4 item 405), a barcode scanner (figure 4 item 402), adjustable leveling knobs configured to level the pharmaceutical compounding device, a network interface (figure 2 item 207), or an infrared area light source positioned below the transparent tray and configured to illuminate the object through the transparent tray (paragraph 0042 and figure 3 item 302; infrared light panel).
Regarding claim 3, as mentioned above in the discussion of claim 1, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches wherein the operations further comprise preprocessing the image of the object prior to determining an identification of the object (figures 10 – 11, 15, and/or 17; object image cropped and captured).
Regarding claim 4, as mentioned above in the discussion of claim 3, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches wherein the preprocessing the image comprises cropping the image (figures 10 – 11, 15, and/or 17; object image cropped and captured).
Regarding claim 5, as mentioned above in the discussion of claim 1, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches wherein the operations further comprise: comparing the identification of the object to a plurality of consumable products expected for the workflow (paragraph 0052, compare weights also figure 8; paragraph 0057, compare weights also figure 12; also paragraphs 0074 - 0075); and when there is a mismatch between the identification of the object and the expected consumable products, generate an alert to display on the electronic display (paragraph 0052, compare weights also figure 8 and displaying instructions; paragraph 0057, compare weights also figure 12 and displaying instructions; also paragraphs 0074 - 0075).
Regarding claim 6, as mentioned above in the discussion of claim 1, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches wherein the operations further comprise: generating a count for a consumable product based on the identification and on the image with a second one of the plurality of models (paragraph 0052, compare weights also figure 8; paragraph 0057, compare weights also figure 12; also paragraphs 0074 - 0075); and storing the count in a memory of the pharmaceutical compounding device (paragraph 0052, compare weights also figure 8 and storing; paragraph 0057, compare weights also figure 12 and storing; also paragraphs 0074 - 0075).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 7, as mentioned above in the discussion of claim 1, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches wherein the operations further comprise: determining that the object is an intravenous fluid bag (paragraphs 0057 – 0058); determining based at least in part on the image of the object using at least a third one of the plurality of models whether the object is within a field of view of the image (paragraph 0156; guide a user of the compounding assistance device through a pharmaceutical compounding task using one or more prompts shown on the display; also paragraph 0075, previous photograph may be compared with the current photograph in a number of orientations and positions; paragraph 0044, a robotic mechanism may hold an item to be photographed in the field of view of a camera in any orientation); when the captured image of the object is determined as being at least partially outside the field of view, generate an alert to reposition the intravenous fluid bag on the scale plate and capture a second image of the object (paragraph 0156; guide a user of the compounding assistance device through a pharmaceutical compounding task using one or more prompts shown on the display); and when the captured image of the object is determined as being inside of the field of view, store the image and continue the workflow (figures 12 – 13).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 8, as mentioned above in the discussion of claim 1, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches determining that the object is a syringe (paragraph 0056; detect syringe); capturing a second image with of the object placed on the scale plate with an infrared camera (paragraph 0055); detecting a presence of an air bubble inside a fluid within the syringe based at least in part on the second image and using a fourth one of the plurality models (paragraphs 0056 and 0061; bubbles); and generating an alert that is displayed on the pharmaceutical compounding device when the presence of the air bubble is detected (paragraph 0061; user sees the bubbles photograph).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 9, as mentioned above in the discussion of claim 1, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches wherein the operations further comprise: determining that the object is a syringe (paragraph 0056; detect syringe); capturing a second image with of the object placed on the scale plate with an infrared camera (paragraph 0055); determining a volume of a fluid inside the syringe based at least in part on the second image and using a fourth one of the plurality of models (figure 8); and storing the determined volume of the fluid in a memory of the pharmaceutical compounding device (figure 8 and paragraph 0052).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 10, as mentioned above in the discussion of claim 9, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches wherein the operations further comprise generating a notification for a user if the volume of the fluid is greater or less than a threshold amount of an expected volume of the fluid based on the workflow (figure 8 and paragraph 0052).
Regarding claim 11, as mentioned above in the discussion of claim 1, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches a weight scale underneath the scale plate (figures 3 and 6 item 301 also paragraphs 0042, 0046, 0087; weight sensor with tray as shown in figure 2 item 209 also paragraphs 0042, 0055, 0065, and 0081; Note: applicant does not specifically define what is meant by high precision as it is a subjective term).
Regarding claim 12, as mentioned above in the discussion of claim 11, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches where a measurement of the weight scale is fed into the model (figure 8 and 12; also figures 3 and 6 item 301 also paragraphs 0042, 0046, 0087; weight sensor with tray as shown in figure 2 item 209 also paragraphs 0042, 0055, 0065, and 0081; Note: applicant does not specifically define what is meant by high precision as it is a subjective term).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 13, Trovato teaches method performed by a pharmaceutical compounding device (figures 2 – 9, 12 – 14, 18, and 20 item 201 also figure 1 item 101) for verifying a compounding operation, the method comprising: capturing an image of an object placed on a scale plate using a visible light camera (paragraph 0067 also paragraphs 0043, 0054, 0070, 0080 - 0086; photographs taken); accessing a plurality of models stored in a memory of the pharmaceutical compounding device (paragraphs 0043 – 0048, 0061, and 0086; bar code to identify stored in memory; correct medication was identified by the barcode scan); determining an identification of the object based at least in part on the image of the object using techniques using at least a first one of the plurality of models (paragraphs 0043 – 0048, 0061, and 0086; bar code to identify; correct medication was identified by the barcode scan); upon determining the identification of the object, generating a set of steps of a workflow to compound a medication associated with the object based on the identification of the object (at least paragraphs 0048 – 0053, First bar code on vial is identified (i.e. object identified) then multiple steps are carried out (i.e. generating a set of steps of stages of structured process designed to produce a specific output, note each step has its own specific process i.e. steps related to object identified) according to identified bar code; paragraph 0048; compounding assistance device 201 requires that the user present vial 204 to bar code scanner 402, so that the identifying bar code on vial 204 can be read, and the system can verify that the correct vial with the correct concentration has been provided. If not, then an error message is generated and the compounding task is stopped. The scanning process is illustrated in FIG. 5, along with an example prompt shown on screen 208. Compounding assistance device 201 may automatically recognize that the barcode has been detected, and may move to the next step. Alternatively, an acknowledgment from the user may be required, in this and other steps); and generating a notification on an electronic display based on the workflow (paragraph; 0007, 0048, 0156; controller is programmed to guide a user of the compounding assistance device through a pharmaceutical compounding task using one or more prompts shown on the display; also figures 5 – 9, 12 - 13).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 14, as mentioned above in the discussion of claim 13, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches wherein the operations further comprise: comparing the identification of the object to a plurality of consumable products expected for the workflow (paragraph 0052, compare weights also figure 8; paragraph 0057, compare weights also figure 12; also paragraphs 0074 - 0075); and when there is a mismatch between the identification of the object and the expected consumable products, generate an alert to display on the electronic display (paragraph 0052, compare weights also figure 8 and displaying instructions; paragraph 0057, compare weights also figure 12 and displaying instructions; also paragraphs 0074 - 0075).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 15, as mentioned above in the discussion of claim 13, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches generating a count for a consumable product based on the identification and on the image with a second one of the plurality of models (paragraph 0052, compare weights also figure 8; paragraph 0057, compare weights also figure 12; also paragraphs 0074 - 0075); storing the count in a memory of the pharmaceutical compounding device (paragraph 0052, compare weights also figure 8 and storing; paragraph 0057, compare weights also figure 12 and storing; also paragraphs 0074 - 0075).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 16, as mentioned above in the discussion of claim 13, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches determining that the object is an intravenous fluid bag (paragraphs 0057 – 0058); determining based at least in part on the image of the object using at least a third one of the plurality of models whether the object is within a field of view of the image (paragraph 0156; guide a user of the compounding assistance device through a pharmaceutical compounding task using one or more prompts shown on the display; also paragraph 0075, previous photograph may be compared with the current photograph in a number of orientations and positions; paragraph 0044, a robotic mechanism may hold an item to be photographed in the field of view of a camera in any orientation); when the captured image of the object is determined as being at least partially outside the field of view, generate an alert to reposition the intravenous fluid bag on the scale plate and capture a second image of the object (paragraph 0156; guide a user of the compounding assistance device through a pharmaceutical compounding task using one or more prompts shown on the display); when the captured image of the object is determined as being inside of the field of view, store the image and continue the workflow (figures 12 – 13).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 17, as mentioned above in the discussion of claim 13, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches determining that the object is a syringe (paragraph 0056; detect syringe); capturing a second image with of the object placed on the scale plate with an infrared camera (paragraph 0055); detecting a presence of an air bubble inside a fluid within the syringe based at least in part on the second image and using a fourth one of the plurality models (paragraphs 0056 and 0061; bubbles); and generating an alert that is displayed on the pharmaceutical compounding device when the presence of the air bubble is detected (paragraph 0061; user sees the bubbles photograph).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 18, as mentioned above in the discussion of claim 13, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches wherein the operations further comprise: determining that the object is a syringe (paragraph 0056; detect syringe); capturing a second image with of the object placed on the scale plate with an infrared camera (paragraph 0055); determining a volume of a fluid inside the syringe based at least in part on the second image and using a fourth one of the plurality of models (figure 8); and storing the determined volume of the fluid in a memory of the pharmaceutical compounding device (figure 8 and paragraph 0052).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Regarding claim 19, as mentioned above in the discussion of claim 18, Trovato in view of in view of LIN teach all of the limitations of the parent claim. Additionally, Trovato teaches wherein the operations further comprise generating a notification for a user if the volume of the fluid is greater or less than a threshold amount of an expected volume of the fluid based on the workflow (figure 8 and paragraph 0052).
Regarding claim 20, Trovato teaches non-transitory computer readable medium storing instructions that when executed by a processor (paragraphs 0033, 0085, 0123, and 0139) of a pharmaceutical compounding device (figures 2 – 9, 12 – 14, 18, and 20 item 201 also figure 1 item 101) performs operations comprising: capturing an image of an object placed on a scale plate using a visible light camera (paragraph 0067 also paragraphs 0043, 0054, 0070, 0080 - 0086; photographs taken); accessing a plurality of models stored in a memory of the pharmaceutical compounding device (paragraphs 0043 – 0048, 0061, and 0086; bar code to identify stored in memory; correct medication was identified by the barcode scan); determining an identification of the object based at least in part on the image of the object using techniques using at least a first one of the plurality of models (paragraphs 0043 – 0048, 0061, and 0086; bar code to identify; correct medication was identified by the barcode scan); upon determining the identification of the object, generating a set of steps of a workflow to compound a medication associated with the object based on the identification of the object (at least paragraphs 0048 – 0053, First bar code on vial is identified (i.e. object identified) then multiple steps are carried out (i.e. generating a set of steps of stages of structured process designed to produce a specific output, note each step has its own specific process i.e. steps related to object identified) according to identified bar code; paragraph 0048; compounding assistance device 201 requires that the user present vial 204 to bar code scanner 402, so that the identifying bar code on vial 204 can be read, and the system can verify that the correct vial with the correct concentration has been provided. If not, then an error message is generated and the compounding task is stopped. The scanning process is illustrated in FIG. 5, along with an example prompt shown on screen 208. Compounding assistance device 201 may automatically recognize that the barcode has been detected, and may move to the next step. Alternatively, an acknowledgment from the user may be required, in this and other steps); and generating a notification on an electronic display based on the workflow (paragraph; 0007, 0048, 0156; controller is programmed to guide a user of the compounding assistance device through a pharmaceutical compounding task using one or more prompts shown on the display; also figures 5 – 9, 12 - 13).
However, Trovato fails to teach trained machine learning models and machine learning image analysis. LIN, on the other hand teaches trained machine learning models and machine learning image analysis.
More specifically, LIN teaches trained machine learning models and machine learning image analysis (paragraphs 0013, 0031, 0033 - 0034, and 0043 – 0045; machine learning image analysis).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate the teachings of LIN with the teachings of Trovato because at least in paragraphs 0031, 0033, and 0043 LIN teaches that using the invention CNN of the present invention can be trained and revised periodically from the server side for continue improving the object recognition and classification capability, As a result, the performance of the identification module can be improved constantly, thereby improving the image processing of Trovato.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Trovato (US PgPub No. 2020/0179605) teaches a camera system with object detection and processing.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Usman A Khan whose telephone number is (571)270-1131. The examiner can normally be reached on M - Th 5:30 AM - 2 PM, F 5:30 AM - Noon.
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, Sinh Tran can be reached on (571)272-7564. 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.
Usman Khan
/USMAN A KHAN/Primary Examiner, Art Unit 2637
02/12/2026