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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/08/2025 has been entered.
Response to Arguments
Applicant's arguments, see Remarks, filed 12/08/2025, with respect to the rejection(s) of claims 1, 7, 13, 20, and 21 under 35 U.S.C. 101 have been fully considered but they are not persuasive. The claims relate to a generic magnetic sensor system which does not integrate the claims into practical application. It is also unclear from the claim what rotation angle is being measured and what errors are being reduced by the argued improvement. As seen in MPEP 2106.05 the claim must include the components or steps of the invention that provide the improvement described in the specification.
The deviation of the system data from a target state is a generic definition of error. It is unknown how that error relates to a particular sensor making some angular measurement of some unknown subject. The claimed sensor system and data amounts to generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h). The claimed processor amounts to using a computer as a tool.
Furthermore, MPEP 2106.05 describes that “A claim having broad applicability across many fields of endeavor may not provide meaningful limitations that integrate a judicial exception into a practical application or amount to significantly more.” Generic magnetic rotation angle sensors have broad applicability to many fields of endeavor, from health systems as seen in the Pour reference to mirrors as seen in the Kim reference.
The additional elements in the claim of magnetic sensors and processors do not amount to significantly more than the abstract idea. Those features are well known in the art. This amounts to simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the abstract ideas as seen in MPEP 2106.05.
Applicant’s arguments, see Remarks, filed 12/08/2025, with respect to the rejection(s) of claim(s) 1, 7, 13, 20, and 21 under 35 U.S.C. 103 in view of Pour (US 20210015634 A1) and Kim (US 20240039641 A1) have been fully considered and are persuasive. They do not explicitly teach “wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field, wherein the target state corresponds to an ideal state of the sensor system.” Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Pour (US 20210015634 A1) and Srivastava (US 20200372409 A1).
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1, 3-7, and 9-23 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
With respect to claim 1,
the limitations,
“receive system data about a sensor system for measuring a magnetic field to determine the rotation angle;
generate error data which includes at least one deviation of the system data from a target state of the sensor system or a magnetic field strength of a plurality of magnetic field components of a superimposed external magnetic field;
create training data using the system data and the error data;
determine, using the trained neural network, the rotation angle based on the sensor”
are directed to abstract ideas and would fall within the “Mental Process” and “Mathematical Concept” grouping of abstract ideas. Receiving sensor data can be practically performed in the human mind using observation. Generating error data by finding the deviation between two values is a well-known mathematical concept. Generating error data from magnetic field strength data can be practically performed in the human mind using observation, evaluation, judgement, and opinion. According to MPEP 2106.04 “The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011). As the Federal Circuit explained, "methods which can be performed mentally, or which are the equivalent of human mental work, are unpatentable abstract ideas the ‘basic tools of scientific and technological work’ that are open to all.’" 654 F.3d at 1371, 99 USPQ2d at 1694 (citing Gottschalk v. Benson, 409 U.S. 63, 175 USPQ 673 (1972)). See also Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 71, 101 USPQ2d 1961, 1965 (2012) ("‘[M]ental processes and abstract intellectual concepts are not patentable, as they are the basic tools of scientific and technological work’" (quoting Benson, 409 U.S. at 67, 175 USPQ at 675)); Parker v. Flook, 437 U.S. 584, 589, 198 USPQ 193, 197 (1978) (same). Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions.”
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements –
“A device for training a neural network for determining a rotation angle of an object, the device comprising: at least one processor configured to: and train the neural network using the training data. receive sensor data from the sensor system, the sensor data indicating measurements of the magnetic field by the sensor system; wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of a sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, or a distance between the sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system;”
Examiner views these limitations amount to generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h)
As such Examiner does NOT view that the claims
-Improve the functioning of a computer, or to any other technology or technical field
-Apply the judicial exception with, or by use of, a particular machine - see MPEP 2106.05(b)
-Effect a transformation or reduction of a particular article to a different state or thing - see MPEP 2106.05(c)
-Apply or use the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception - see MPEP 2106.05(e) and Vanda Memo.
Moreover, Examiner views the claims to be merely generally linking the use of the judicial exception to a processor for training a neural network with rotation sensor data. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “A device for training a neural network for determining a rotation angle of an object, the device comprising: at least one processor configured to: and train the neural network using the training data. receive sensor data from the sensor system, the sensor data indicating measurements of the magnetic field by the sensor system; wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of a sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, or a distance between the sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system;” amount to a generic computer or processor and a well-known process of training neural network based on rotation data from a well-known magnetic sensor. This is considered generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h). Furthermore, receiving data from a sensor can be seen as a limitation that amounts to necessary data gathering as seen in MPEP 2106.05.
Examiner further notes that such additional elements are viewed as well known, routine, and conventional as evidenced by
Pour (US 20210015634 A1)
Kather (US 20090267594 A1).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Considering the claim as a whole, one of ordinary skill in the art would not know the practical application of the present invention since the claims do not apply or use the judicial exception in some meaningful way. As currently claimed, Examiner views that the additional elements do not apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, because the claim fails to recite clearly how the judicial exception is applied in a manner that does not monopolize the exception because the limitations “A device for training a neural network for determining a rotation angle of an object, the device comprising: at least one processor configured to: and train the neural network using the training data. receive sensor data from the sensor system, the sensor data indicating measurements of the magnetic field by the sensor system; wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of a sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, or a distance between the sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system” just tie the claim to training a neural network to find rotation angles does not impose a meaningful limitation describing what problem is being remedied or solved.
With respect to claim 7,
the limitations,
“receive sensor data from a first sensor and a second sensor of a sensor system for measuring a magnetic field;
determine the rotation angle, wherein the trained neural network uses the sensor data of the first sensor and the second sensor as input data.
wherein the trained neural network has been trained using system data about the sensor system
and error data,
wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field,”
are directed to abstract ideas and would fall within the “Mental Process” and “Mathematical Concept” grouping of abstract ideas. Receiving sensor data can be practically performed in the human mind using observation. Determining the rotation angle from data from two sensors can be practically performed in the human mind using observation, evaluation, judgement, and opinion. According to MPEP 2106.04 “The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011). As the Federal Circuit explained, "methods which can be performed mentally, or which are the equivalent of human mental work, are unpatentable abstract ideas the ‘basic tools of scientific and technological work’ that are open to all.’" 654 F.3d at 1371, 99 USPQ2d at 1694 (citing Gottschalk v. Benson, 409 U.S. 63, 175 USPQ 673 (1972)). See also Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 71, 101 USPQ2d 1961, 1965 (2012) ("‘[M]ental processes and abstract intellectual concepts are not patentable, as they are the basic tools of scientific and technological work’" (quoting Benson, 409 U.S. at 67, 175 USPQ at 675)); Parker v. Flook, 437 U.S. 584, 589, 198 USPQ 193, 197 (1978) (same). Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions.”
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements –
“A device for determining a rotation angle of an object, the device comprising: a sensor interface and a trained neural network configured to determine the rotation angle wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of the first sensor, the second sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, a distance between the first sensor and the magnet or the encoder, or a distance between the second sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system.”
Examiner views these limitations amount to generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h)
As such Examiner does NOT view that the claims
-Improve the functioning of a computer, or to any other technology or technical field
-Apply the judicial exception with, or by use of, a particular machine - see MPEP 2106.05(b)
-Effect a transformation or reduction of a particular article to a different state or thing - see MPEP 2106.05(c)
-Apply or use the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception - see MPEP 2106.05(e) and Vanda Memo.
Moreover, Examiner views the claims to be merely generally linking the use of the judicial exception to a processor for training a neural network with rotation sensor data. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “A device for determining a rotation angle of an object, the device comprising: a sensor interface and a trained neural network configured to determine the rotation angle, wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of the first sensor, the second sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, a distance between the first sensor and the magnet or the encoder, or a distance between the second sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system” amount to a generic computer or processor and a well-known trained neural network. This is considered generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h). Examiner further notes that such additional elements are viewed as well known, routine, and conventional as evidenced by
Pour (US 20210015634 A1)
Kather (US 20090267594 A1).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Considering the claim as a whole, one of ordinary skill in the art would not know the practical application of the present invention since the claims do not apply or use the judicial exception in some meaningful way. As currently claimed, Examiner views that the additional elements do not apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, because the claim fails to recite clearly how the judicial exception is applied in a manner that does not monopolize the exception because the limitations “A device for determining a rotation angle of an object, the device comprising: a sensor interface and a trained neural network configured to determine the rotation angle wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of the first sensor, the second sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, a distance between the first sensor and the magnet or the encoder, or a distance between the second sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system” just tie the claim to a processing device, a sensor system form measuring rotation angles, and machine learning and does not impose a meaningful limitation describing what problem is being remedied or solved.
With respect to claim 13,
the limitations,
“receive sensor data from the at least one first sensor and the second sensor;
determine the rotation angle, wherein the trained neural network uses the sensor data of the at least one first sensor and the second sensor as input data
and wherein the trained neural network has been trained using system data about the sensor system and error data,
wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field,”
are directed to abstract ideas and would fall within the “Mental Process” and “Mathematical Concept” grouping of abstract ideas. Receiving sensor data can be practically performed in the human mind using observation. Determining the rotation angle from the data of two sensors can be practically performed in the human mind using observation, evaluation, judgement, and opinion. According to MPEP 2106.04 “The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011). As the Federal Circuit explained, "methods which can be performed mentally, or which are the equivalent of human mental work, are unpatentable abstract ideas the ‘basic tools of scientific and technological work’ that are open to all.’" 654 F.3d at 1371, 99 USPQ2d at 1694 (citing Gottschalk v. Benson, 409 U.S. 63, 175 USPQ 673 (1972)). See also Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 71, 101 USPQ2d 1961, 1965 (2012) ("‘[M]ental processes and abstract intellectual concepts are not patentable, as they are the basic tools of scientific and technological work’" (quoting Benson, 409 U.S. at 67, 175 USPQ at 675)); Parker v. Flook, 437 U.S. 584, 589, 198 USPQ 193, 197 (1978) (same). Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions.”
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements –
“A system for determining a rotation angle of an object, the system comprising: a sensor system configured to measure a magnetic field, the sensor system comprising at least one first sensor and a second sensor; a sensor interface and an integrated circuit comprising a trained neural network configured to determine the rotation angle, wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of the first sensor, the second sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, a distance between the first sensor and the magnet or the encoder, or a distance between the second sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system”
Examiner views these limitations amount to generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h)
As such Examiner does NOT view that the claims
-Improve the functioning of a computer, or to any other technology or technical field
-Apply the judicial exception with, or by use of, a particular machine - see MPEP 2106.05(b)
-Effect a transformation or reduction of a particular article to a different state or thing - see MPEP 2106.05(c)
-Apply or use the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception - see MPEP 2106.05(e) and Vanda Memo.
Moreover, Examiner views the claims to be merely generally linking the use of the judicial exception to a processor for training a neural network with rotation sensor data. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “A system for determining a rotation angle of an object, the system comprising: a sensor system configured to measure a magnetic field, the sensor system comprising at least one first sensor and a second sensor; a sensor interface and an integrated circuit comprising a trained neural network configured to determine the rotation angle, wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of the first sensor, the second sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, a distance between the first sensor and the magnet or the encoder, or a distance between the second sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system” amount to a generic computer or processor, a well-known trained neural network and well known magnetic sensors that are capable of measuring rotation angles. This is considered generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h). Examiner further notes that such additional elements are viewed as well known, routine, and conventional as evidenced by
Pour (US 20210015634 A1)
Kather (US 20090267594 A1).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Considering the claim as a whole, one of ordinary skill in the art would not know the practical application of the present invention since the claims do not apply or use the judicial exception in some meaningful way. As currently claimed, Examiner views that the additional elements do not apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, because the claim fails to recite clearly how the judicial exception is applied in a manner that does not monopolize the exception because the limitations “A system for determining a rotation angle of an object, the system comprising: a sensor system configured to measure a magnetic field, the sensor system comprising at least one first sensor and a second sensor; a sensor interface and an integrated circuit comprising a trained neural network configured to determine the rotation angle, wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of the first sensor, the second sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, a distance between the first sensor and the magnet or the encoder, or a distance between the second sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system” just tie the claim to a processing device, a sensor system form measuring rotation angles and machine learning and does not impose a meaningful limitation describing what problem is being remedied or solved.
With respect to claim 20,
the limitations,
“receiving system data about a sensor system for measuring a magnetic field in order to determine the rotation angle,
generate error data which includes at least one deviation of the system data from a target state of the sensor system or a magnetic field strength of a plurality of magnetic field components of a superimposed external magnetic field;
generating training data using the system data and the error data;
wherein the trained neural network has been trained using system data about the sensor system
and error data.”
are directed to abstract ideas and would fall within the “Mental Process” and “Mathematical Concept” grouping of abstract ideas. Receiving sensor data can be practically performed in the human mind using observation. Generating error data by finding the deviation between two values is a well-known mathematical concept. Generating error data from magnetic field strength Analyzing materials and comparing chemical compositions can be practically performed in the human mind using observation, evaluation, judgement, and opinion. According to MPEP 2106.04 “The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011). As the Federal Circuit explained, "methods which can be performed mentally, or which are the equivalent of human mental work, are unpatentable abstract ideas the ‘basic tools of scientific and technological work’ that are open to all.’" 654 F.3d at 1371, 99 USPQ2d at 1694 (citing Gottschalk v. Benson, 409 U.S. 63, 175 USPQ 673 (1972)). See also Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 71, 101 USPQ2d 1961, 1965 (2012) ("‘[M]ental processes and abstract intellectual concepts are not patentable, as they are the basic tools of scientific and technological work’" (quoting Benson, 409 U.S. at 67, 175 USPQ at 675)); Parker v. Flook, 437 U.S. 584, 589, 198 USPQ 193, 197 (1978) (same). Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions.”
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements –
“A method for training a neural network for determining a rotation angle of an object, comprising: and training the neural network using the training data, wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of a sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, or a distance between the sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system;”
Examiner views these limitations amount to generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h)
As such Examiner does NOT view that the claims
-Improve the functioning of a computer, or to any other technology or technical field
-Apply the judicial exception with, or by use of, a particular machine - see MPEP 2106.05(b)
-Effect a transformation or reduction of a particular article to a different state or thing - see MPEP 2106.05(c)
-Apply or use the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception - see MPEP 2106.05(e) and Vanda Memo.
Moreover, Examiner views the claims to be merely generally linking the use of the judicial exception to a processor for training a neural network with rotation sensor data. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “A method for training a neural network for determining a rotation angle of an object, comprising: and training the neural network using the training data, wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of a sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, or a distance between the sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system.” amount to a generic computer or processor and a well-known process of training neural network based on rotation data from a well-known magnetic sensor. This is considered generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h). Examiner further notes that such additional elements are viewed as well known, routine, and conventional as evidenced by
Pour (US 20210015634 A1)
Kather (US 20090267594 A1).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Considering the claim as a whole, one of ordinary skill in the art would not know the practical application of the present invention since the claims do not apply or use the judicial exception in some meaningful way. As currently claimed, Examiner views that the additional elements do not apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, because the claim fails to recite clearly how the judicial exception is applied in a manner that does not monopolize the exception because the limitations “A method for training a neural network for determining a rotation angle of an object, comprising: and training the neural network using the training data, wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of a sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, or a distance between the sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system” just tie the claim to training a neural network to find rotation angles and does not impose a meaningful limitation describing what problem is being remedied or solved.
With respect to claim 21,
the limitations,
“A method for determining a rotation angle of an object, comprising: receiving sensor data from a first sensor and a second sensor of a sensor system for measuring a magnetic field;
and determining the rotation angle, wherein the trained neural network has been trained using system data about the sensor system and error data,
and wherein the trained neural network has been trained using system data about the sensor system and error data,
wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field,”
are directed to abstract ideas and would fall within the “Mental Process” and “Mathematical Concept” grouping of abstract ideas. Receiving sensor data can be practically performed in the human mind using observation. Determining the rotation angle from data from two sensors can be practically performed in the human mind using observation, evaluation, judgement, and opinion. According to MPEP 2106.04 “The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011). As the Federal Circuit explained, "methods which can be performed mentally, or which are the equivalent of human mental work, are unpatentable abstract ideas the ‘basic tools of scientific and technological work’ that are open to all.’" 654 F.3d at 1371, 99 USPQ2d at 1694 (citing Gottschalk v. Benson, 409 U.S. 63, 175 USPQ 673 (1972)). See also Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 71, 101 USPQ2d 1961, 1965 (2012) ("‘[M]ental processes and abstract intellectual concepts are not patentable, as they are the basic tools of scientific and technological work’" (quoting Benson, 409 U.S. at 67, 175 USPQ at 675)); Parker v. Flook, 437 U.S. 584, 589, 198 USPQ 193, 197 (1978) (same). Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions.”
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements –
“using a trained neural network, wherein the trained neural network uses the sensor data of the first sensor and the second sensor as input data, wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of the first sensor, the second sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, a distance between the first sensor and the magnet or the encoder, or a distance between the second sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system.”
Examiner views these limitations amount to generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h)
As such Examiner does NOT view that the claims
-Improve the functioning of a computer, or to any other technology or technical field
-Apply the judicial exception with, or by use of, a particular machine - see MPEP 2106.05(b)
-Effect a transformation or reduction of a particular article to a different state or thing - see MPEP 2106.05(c)
-Apply or use the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception - see MPEP 2106.05(e) and Vanda Memo.
Moreover, Examiner views the claims to be merely generally linking the use of the judicial exception to a processor for training a neural network with rotation sensor data. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “using a trained neural network, wherein the trained neural network uses the sensor data of the first sensor and the second sensor as input data, wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of the first sensor, the second sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, a distance between the first sensor and the magnet or the encoder, or a distance between the second sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system” amount to a generic computer or processor and a well-known trained neural network based off of generic data from two generic magnetic sensors. This is considered generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h). Examiner further notes that such additional elements are viewed as well known, routine, and conventional as evidenced by
Pour (US 20210015634 A1)
Kather (US 20090267594 A1).
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Considering the claim as a whole, one of ordinary skill in the art would not know the practical application of the present invention since the claims do not apply or use the judicial exception in some meaningful way. As currently claimed, Examiner views that the additional elements do not apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, because the claim fails to recite clearly how the judicial exception is applied in a manner that does not monopolize the exception because the limitations “using a trained neural network, wherein the trained neural network uses the sensor data of the first sensor and the second sensor as input data, wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of the first sensor, the second sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, a distance between the first sensor and the magnet or the encoder, or a distance between the second sensor and the magnet or the encoder, and wherein the target state corresponds to an ideal state of the sensor system” just tie the claim to a processing device, a sensor system for measuring rotation angles, and machine learning and does not impose a meaningful limitation describing what problem is being remedied or solved.
Dependent claims 3-6, 9-12, 14-19, 22, and 23 when analyzed as a whole are held to be patent ineligible under 35 U.S.C. 101 because the additional recited limitation(s) fail(s) to establish that the claims are not directed to an abstract idea, as detailed below:
They amount to limiting the type of magnetic sensors to well-known devices, limiting the number of sensors, and training the neural network using known methods which amounts to adding insignificant extra-solution activity to the judicial exception - see MPEP 2106.05(g).
Therefore, there are no additional element(s) in the dependent claims that add a meaningful limitation to the abstract idea to make the claims significantly more than the judicial exception (abstract idea). Dependent claims 3-6, 9-12, 14-19, 22, and 23 further limit the abstract idea with an abstract idea and thus the claims are still directed to an abstract idea without significantly more.
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:
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, 5-7, 9, 13-17, and 19-22 are rejected under 35 U.S.C. 103 as being unpatentable over Pour (US 20210015634 A1) as modified by Srivastava (US 20200372409 A1).
Regarding claim 1,
Pour teaches,
A device for training a neural network for determining a rotation angle of an object, the device comprising: (Para. [0103] teaches “In addition to estimating the angle of the permanent magnet, the neural network may, for example, estimate the permanent magnet location with respect to the axis of rotation of the joint. This information can be used to determine whether the femoral head component and the acetabular liner component are in full contact. Moreover, the angle retrieval may still be accurate even if the location of the permanent magnet (with respect to the axis of rotation of the joint) changes due to fabrication inaccuracies.” Para. [0115] teaches “Further, determining the orientations of the femoral head component relative to the acetabular liner component may include inputting the magnetic field data, or data derived from the magnetic field data, to a trained neural network. The trained neural network may then output data indicative of the orientations of the femoral head component relative to the acetabular liner component.”)
at least one processor configured to: receive system data about a sensor system for measuring a magnetic field to determine the rotation angle; (Para. [0109] teaches “the method 800 may further include processing the magnetic field data to determine orientations of the femoral head component relative to the acetabular liner component, substantially in real time as the at least two magnetic sensors capture the sensor readings. This processing may be performed by, for example, the computing system 306 (e.g., processor 326).” Para. [0088] teaches “As the femoral head component 404 rotates on an acetabular liner component (e.g., acetabular liner component 302), the direction and intensity of the magnetic field 408 at different positions on the acetabular liner component surface changes. If the magnetic field 408 generated by the at least one permanent magnet 406 is strong enough, the rotation angle may be determined by measuring the direction and intensity of the magnetic field 408 at one or more locations on the surface of the acetabular liner component.”)
wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of a sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, or a distance between the sensor and the magnet or the encoder, (Para. [0054] teaches “Moreover, the array of magnetometers are positioned to reduce the sensitivity of the system to the intensity and positioning of the permanent magnet in the femoral head component.” (I.e. information about a magnet.))
create training data using the system data; and train, for the system, the neural network using the training data. (Para. [0081] teaches “The neural network may be trained in a supervised manner, for example, using magnetic field values (collected by acetabular liner component 300 and/or other similar components) with corresponding labels. The labels may be confirmed orientations/positions (e.g., as determined using conventional methods known in the art) that correspond to each set of magnetic field values.”)
receive sensor data from the sensor system, the sensor data indicating measurements of the magnetic field by the sensor system; and determine, using the trained neural network, the rotation angle based on the sensor data. (Para. [0081] teaches “These determinations may be performed at least by inputting the magnetic field data (from magnetic sensor array 308), or data derived from the magnetic field data, to a trained neural network implemented by the computer system 306. The trained neural network may process the magnetic field data to output data indicative of the orientations of the femoral head component 316 relative to the acetabular liner component 302.”)
Pour does not explicitly teach,
generate error data which includes at least one deviation of the system data from a target state of the sensor system or a magnetic field strength of a plurality of magnetic field components of a superimposed external magnetic field; create training data using the system data and the error data; wherein the target state corresponds to an ideal state of the sensor system; train, for the sensor system, the neural network using the training data.
Srivastava teaches,
generate error data which includes at least one deviation of the system data from a target state of the sensor system or a magnetic field strength of a plurality of magnetic field components of a superimposed external magnetic field; create training data using the system data and the error data; wherein the target state corresponds to an ideal state of the sensor system; train, for the sensor system, the neural network using the training data. (Para. [0013] teaches “In Example 9, the system of Example 8, wherein the training the machine learning dataset comprises determining a second error corresponding to a determined geometric spacing between a plurality of magnetic field detection sensors corresponding to the calibration device and an actual geometric spacing between the plurality of magnetic field detection sensors, wherein the determined geometric spacing is determined using the machine learning dataset, and updating the machine learning dataset based on the second error.” (i.e. the actual geometric spacing is viewed as the ideal state. Para. [0015] teaches “train the machine learning dataset based on the plurality of determined orientation measurements and predict an orientation of the medical device based on the machine learning dataset and the one or more EM field procedure measurements.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Pour with generate error data which includes at least one deviation of the system data from a target state of the sensor system or a magnetic field strength of a plurality of magnetic field components of a superimposed external magnetic field; create training data using the system data and the error data; wherein the target state corresponds to an ideal state of the sensor system; train, for the sensor system, the neural network using the training data such as that of Srivastava.
One of ordinary skill would have been motivated to modify Pour, because distortions caused by the spacing of the sensors and other effects can lead to measurements that are inaccurate or incorrect as seen in Para. [0004] of Srivastava. Furthermore, Pour teaches compensating for error in Para [0070]. Therefore, in order to ensure accuracy of the measurements one would train the machine learning model with error data.
Regarding claim 5,
Pour further teaches,
The device as claimed in claim 1,
wherein the at least one processor is configured to generate the training data based on a plurality of combinations of error data with respect to the system data to obtain sensor data and a rotation angle for each combination. (Para. [0081] teaches “The neural network may be trained in a supervised manner, for example, using magnetic field values (collected by acetabular liner component 300 and/or other similar components) with corresponding labels. The labels may be confirmed orientations/positions (e.g., as determined using conventional methods known in the art) that correspond to each set of magnetic field values.”)
Regarding claim 6,
Pour further teaches,
The device as claimed in claim 5, wherein the sensor data includes information about a magnetic field component of the magnetic field to be detected by sensors of the sensor system. (Para. [0082] teaches “To further refine the precision of the orientation determinations, the magnetic sensor array 308 may consist of at least two multi-axis magnetic sensors, each having an accuracy of at least 10 micro-Tesla.”)
Regarding claim 7,
Pour teaches,
A device for determining a rotation angle of an object, the device comprising: (Para. [0103] teaches “In addition to estimating the angle of the permanent magnet, the neural network may, for example, estimate the permanent magnet location with respect to the axis of rotation of the joint. This information can be used to determine whether the femoral head component and the acetabular liner component are in full contact. Moreover, the angle retrieval may still be accurate even if the location of the permanent magnet (with respect to the axis of rotation of the joint) changes due to fabrication inaccuracies.”)
a sensor interface configured to receive sensor data from a first sensor and a second sensor of a sensor system for measuring a magnetic field; (Para. [0082] teaches “To further refine the precision of the orientation determinations, the magnetic sensor array 308 may consist of at least two multi-axis magnetic sensors, each having an accuracy of at least 10 micro-Tesla. With these components, the orientations of the femoral head component 316 relative to the acetabular liner component 302 may be accurate to within 0.2 degrees in any direction along the inner concave surface”)
and a trained neural network configured to determine the rotation angle, wherein the trained neural network uses the sensor data of the first sensor and the second sensor as input data. (Para. [0081] teaches “These determinations may be performed at least by inputting the magnetic field data (from magnetic sensor array 308), or data derived from the magnetic field data, to a trained neural network implemented by the computer system 306. The trained neural network may process the magnetic field data to output data indicative of the orientations of the femoral head component 316 relative to the acetabular liner component 302.”)
wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of the first sensor, the second sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, a distance between the first sensor and the magnet or the encoder, or a distance between the second sensor and the magnet or the encoder, (Para. [0054] teaches “Moreover, the array of magnetometers are positioned to reduce the sensitivity of the system to the intensity and positioning of the permanent magnet in the femoral head component.” (I.e. information about a magnet.))
Pour does not explicitly teach,
and wherein the trained neural network has been trained using system data about the sensor system and error data, wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field, wherein the target state corresponds to an ideal state of the sensor system.
Srivastava teaches,
wherein the trained neural network has been trained using system data about the sensor system and error data, wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field, wherein the target state corresponds to an ideal state of the sensor system. ((Para. [0013] teaches “In Example 9, the system of Example 8, wherein the training the machine learning dataset comprises determining a second error corresponding to a determined geometric spacing between a plurality of magnetic field detection sensors corresponding to the calibration device and an actual geometric spacing between the plurality of magnetic field detection sensors, wherein the determined geometric spacing is determined using the machine learning dataset, and updating the machine learning dataset based on the second error.” (i.e. the actual geometric spacing is viewed as the ideal state. Para. [0015] teaches “train the machine learning dataset based on the plurality of determined orientation measurements and predict an orientation of the medical device based on the machine learning dataset and the one or more EM field procedure measurements.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Pour wherein the trained neural network has been trained using system data about the sensor system and error data, wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field, wherein the target state corresponds to an ideal state of the sensor system such as that of Srivastava.
One of ordinary skill would have been motivated to modify Pour, because distortions caused by the spacing of the sensors and other effects can lead to measurements that are inaccurate or incorrect as seen in Para. [0004] of Srivastava. Furthermore, Pour teaches compensating for error in Para [0070]. Therefore, in order to ensure accuracy of the measurements one would train the machine learning model with error data.
Regarding claim 9,
Pour further teaches,
The device as claimed in claim 7, wherein the sensor data is based on a measurement of magnetic field components of the magnetic field by means of the first and second sensors. (Para. [0082] teaches “To further refine the precision of the orientation determinations, the magnetic sensor array 308 may consist of at least two multi-axis magnetic sensors, each having an accuracy of at least 10 micro-Tesla.”)
Regarding claim 13,
A system for determining a rotation angle of an object, the system comprising: a sensor system configured to measure a magnetic field, the sensor system comprising at least one first sensor and a second sensor; (Para. [0081] teaches “These determinations may be performed at least by inputting the magnetic field data (from magnetic sensor array 308), or data derived from the magnetic field data, to a trained neural network implemented by the computer system 306. The trained neural network may process the magnetic field data to output data indicative of the orientations of the femoral head component 316 relative to the acetabular liner component 302.” (Para. [0082] teaches “To further refine the precision of the orientation determinations, the magnetic sensor array 308 may consist of at least two multi-axis magnetic sensors, each having an accuracy of at least 10 micro-Tesla. With these components, the orientations of the femoral head component 316 relative to the acetabular liner component 302 may be accurate to within 0.2 degrees in any direction along the inner concave surface” Para. [0103] teaches “In addition to estimating the angle of the permanent magnet, the neural network may, for example, estimate the permanent magnet location with respect to the axis of rotation of the joint. This information can be used to determine whether the femoral head component and the acetabular liner component are in full contact. Moreover, the angle retrieval may still be accurate even if the location of the permanent magnet (with respect to the axis of rotation of the joint) changes due to fabrication inaccuracies”)
a sensor interface configured to receive sensor data from the at least one first sensor and the second sensor; (Para. [0072] “cause the computer system 306 to receive the magnetic field data transmitted by the wireless transceiver 312, and process the received magnetic field data to determine orientations of the femoral head component 316 relative to the acetabular liner component 302.”)
and an integrated circuit comprising a trained neural network configured to determine the rotation angle, wherein the trained neural network uses the sensor data of the at least one first sensor and the second sensor as input data. (Para. [0081] teaches “These determinations may be performed at least by inputting the magnetic field data (from magnetic sensor array 308), or data derived from the magnetic field data, to a trained neural network implemented by the computer system 306. The trained neural network may process the magnetic field data to output data indicative of the orientations of the femoral head component 316 relative to the acetabular liner component 302.)
Pour does not explicitly teach,
wherein the trained neural network has been trained using system data about the sensor system and error data, wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field, wherein the target state corresponds to an ideal state of the sensor system. (However, Pour trains the neural network using training data that comes from sensor data. Para. [0081] teaches “The neural network may be trained in a supervised manner, for example, using magnetic field values (collected by acetabular liner component 300 and/or other similar components) with corresponding labels. The labels may be confirmed orientations/positions (e.g., as determined using conventional methods known in the art) that correspond to each set of magnetic field values”)
Srivastava teaches,
wherein the trained neural network has been trained using system data about the sensor system and error data, wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field, wherein the target state corresponds to an ideal state of the sensor system. ((Para. [0013] teaches “In Example 9, the system of Example 8, wherein the training the machine learning dataset comprises determining a second error corresponding to a determined geometric spacing between a plurality of magnetic field detection sensors corresponding to the calibration device and an actual geometric spacing between the plurality of magnetic field detection sensors, wherein the determined geometric spacing is determined using the machine learning dataset, and updating the machine learning dataset based on the second error.” (i.e. the actual geometric spacing is viewed as the ideal state. Para. [0015] teaches “train the machine learning dataset based on the plurality of determined orientation measurements and predict an orientation of the medical device based on the machine learning dataset and the one or more EM field procedure measurements.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Pour wherein the trained neural network has been trained using system data about the sensor system and error data, wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field, wherein the target state corresponds to an ideal state of the sensor system such as that of Srivastava.
One of ordinary skill would have been motivated to modify Pour, because distortions caused by the spacing of the sensors and other effects can lead to measurements that are inaccurate or incorrect as seen in Para. [0004] of Srivastava. Furthermore, Pour teaches compensating for error in Para [0070]. Therefore, in order to ensure accuracy of the measurements one would train the machine learning model with error data.
Regarding claim 14,
Pour further teaches,
The system as claimed in claim 13, further comprising: a magnet having an axis around which the magnet can be rotated, the axis being perpendicular to a sensor plane on which the at least one first sensor and the second sensor are arranged, the magnet being spaced apart from the sensor plane along the axis. (Fig(s). 5A, 5B, 6)
Regarding claim 15,
Pour further teaches,
The system as claimed in claim 13, wherein the sensor system further comprises a third sensor for measuring the magnetic field. (Para. [0032] teaches “are plots showing the error of the present system when compensating for the magnetic field of the earth, and when using three magnetic sensors, respectively.”)
Regarding claim 16,
Pour does not explicitly teach,
The system as claimed in claim 15, wherein the sensor system further comprises a fourth sensor for measuring the magnetic field.
However, Poor does teach,
“an artificial neural network to allow for real-time position calculation from the readings of the at least two magnetic sensors” (Para. [0055]) and “As shown in FIG. 7B, the three-sensor system can be roughly three times more accurate than the single-sensor system.” (Para. [0104])
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pour and Srivastava wherein the sensor system further comprises a fourth sensor for measuring the magnetic field.
One of ordinary skill would have been motivated to modify the combination of Pour and Srivastava because since it has been held that mere duplication of the essential working parts of a device involves only routine skill in the art. St. Regis Paper Co. v. Bemis Co., 193 USPQ 8. It would also fall under “Obvious to try" – choosing from a finite number of identified, predictable solutions, with a reasonable expectation of success; as seen in MPEP 2143.
Regarding claim 17,
Pour further teaches,
The system as claimed in 16, wherein the at least one first sensor, the second sensor, the third sensor, and the fourth sensor are each arranged on the sensor plane at an equal radial distance from the axis. (Fig. 5a and 5b show that the sensors are arranged on a sensor plane at an equal radial distance from the axis.)
Regarding claim 19,
Pour further teaches,
The system as claimed in claim 13, wherein the sensor interface, the integrated circuit comprising the trained neural network, and the sensor system are integrated in a common chip. (Fig. 3 shows that the user interface and processor are a part of the same computer system. Para. [0081] teaches that the neural network is also implemented on the device.)
Regarding claim 20,
A method for training a neural network for determining a rotation angle of an object, comprising: receiving system data about a sensor system for measuring a magnetic field in order to determine the rotation angle; (Para. [0103] teaches “In addition to estimating the angle of the permanent magnet, the neural network may, for example, estimate the permanent magnet location with respect to the axis of rotation of the joint. This information can be used to determine whether the femoral head component and the acetabular liner component are in full contact. Moreover, the angle retrieval may still be accurate even if the location of the permanent magnet (with respect to the axis of rotation of the joint) changes due to fabrication inaccuracies.” Para. [0109] teaches “the method 800 may further include processing the magnetic field data to determine orientations of the femoral head component relative to the acetabular liner component, substantially in real time as the at least two magnetic sensors capture the sensor readings. This processing may be performed by, for example, the computing system 306 (e.g., processor 326).”)
wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of a sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, or a distance between the sensor and the magnet or the encoder, (Para. [0054] teaches “Moreover, the array of magnetometers are positioned to reduce the sensitivity of the system to the intensity and positioning of the permanent magnet in the femoral head component.” (I.e. information about a magnet.))
Pour does not explicitly teach,
generating error data which includes at least one deviation of the system data from a target state of the sensor system or a magnetic field strength of a plurality of magnetic field components of a superimposed external magnetic field; wherein the target state corresponds to an ideal state of the sensor system; generating training data using the system data and the error data; train, for the sensor system, the neural network using the training data.
Srivastava teaches,
generating error data which includes at least one deviation of the system data from a target state of the sensor system or a magnetic field strength of a plurality of magnetic field components of a superimposed external magnetic field; wherein the target state corresponds to an ideal state of the sensor system; generating training data using the system data and the error data; train, for the sensor system, the neural network using the training data. (Para. [0013] teaches “In Example 9, the system of Example 8, wherein the training the machine learning dataset comprises determining a second error corresponding to a determined geometric spacing between a plurality of magnetic field detection sensors corresponding to the calibration device and an actual geometric spacing between the plurality of magnetic field detection sensors, wherein the determined geometric spacing is determined using the machine learning dataset, and updating the machine learning dataset based on the second error.” (i.e. the actual geometric spacing is viewed as the ideal state. Para. [0015] teaches “train the machine learning dataset based on the plurality of determined orientation measurements and predict an orientation of the medical device based on the machine learning dataset and the one or more EM field procedure measurements.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Pour with generating error data which includes at least one deviation of the system data from a target state of the sensor system or a magnetic field strength of a plurality of magnetic field components of a superimposed external magnetic field; wherein the target state corresponds to an ideal state of the sensor system; generating training data using the system data and the error data; train, for the sensor system, the neural network using the training data such as that of Srivastava.
One of ordinary skill would have been motivated to modify Pour, because distortions caused by the spacing of the sensors and other effects can lead to measurements that are inaccurate or incorrect as seen in Para. [0004] of Srivastava. Furthermore, Pour teaches compensating for error in Para [0070]. Therefore, in order to ensure accuracy of the measurements one would train the machine learning model with error data.
Regarding claim 21,
Pour teaches,
A method for determining a rotation angle of an object, comprising: receiving sensor data from a first sensor and a second sensor of a sensor system for measuring a magnetic field; (Para. [0082] teaches “To further refine the precision of the orientation determinations, the magnetic sensor array 308 may consist of at least two multi-axis magnetic sensors, each having an accuracy of at least 10 micro-Tesla. With these components, the orientations of the femoral head component 316 relative to the acetabular liner component 302 may be accurate to within 0.2 degrees in any direction along the inner concave surface”)
and determining the rotation angle using a trained neural network, wherein the trained neural network uses the sensor data of the first sensor and the second sensor as input data. (Para. [0103] teaches “In addition to estimating the angle of the permanent magnet, the neural network may, for example, estimate the permanent magnet location with respect to the axis of rotation of the joint. This information can be used to determine whether the femoral head component and the acetabular liner component are in full contact. Moreover, the angle retrieval may still be accurate even if the location of the permanent magnet (with respect to the axis of rotation of the joint) changes due to fabrication inaccuracies.”)
wherein the system data comprises at least information, for the sensor system, about a geometric arrangement of a sensor, a magnet or an encoder of the sensor system, a magnetic field of the magnet or the encoder, a shape of the magnet or the encoder, or a distance between the sensor and the magnet or the encoder, (Para. [0054] teaches “Moreover, the array of magnetometers are positioned to reduce the sensitivity of the system to the intensity and positioning of the permanent magnet in the femoral head component.” (I.e. information about a magnet.))
Pour does not explicitly teach,
wherein the trained neural network has been trained using system data about the sensor system and error data, wherein the error data comprises at least one deviation of the system data from a target state of the sensor system or a strength of a plurality of magnetic field components of a superimposed external magnetic field, and wherein the target state corresponds to an ideal state of the sensor system.
Srivastava teaches,
generating error data which includes at least one deviation of the system data from a target state of the sensor system or a magnetic field strength of a plurality of magnetic field components of a superimposed external magnetic field; wherein the target state corresponds to an ideal state of the sensor system; generating training data using the system data and the error data; train, for the sensor system, the neural network using the training data. (Para. [0013] teaches “In Example 9, the system of Example 8, wherein the training the machine learning dataset comprises determining a second error corresponding to a determined geometric spacing between a plurality of magnetic field detection sensors corresponding to the calibration device and an actual geometric spacing between the plurality of magnetic field detection sensors, wherein the determined geometric spacing is determined using the machine learning dataset, and updating the machine learning dataset based on the second error.” (i.e. the actual geometric spacing is viewed as the ideal state. Para. [0015] teaches “train the machine learning dataset based on the plurality of determined orientation measurements and predict an orientation of the medical device based on the machine learning dataset and the one or more EM field procedure measurements.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Pour with generating error data which includes at least one deviation of the system data from a target state of the sensor system or a magnetic field strength of a plurality of magnetic field components of a superimposed external magnetic field; wherein the target state corresponds to an ideal state of the sensor system; generating training data using the system data and the error data; train, for the sensor system, the neural network using the training data such as that of Srivastava.
One of ordinary skill would have been motivated to modify Pour, because distortions caused by the spacing of the sensors and other effects can lead to measurements that are inaccurate or incorrect as seen in Para. [0004] of Srivastava. Furthermore, Pour teaches compensating for error in Para [0070]. Therefore, in order to ensure accuracy of the measurements one would train the machine learning model with error data.
Regarding claim 22,
Pour teaches,
A non-transitory computer-readable medium comprising a computer program having a program code for causing a programmable processor to execute a method for training a neural network for determining a rotation angle of an object, the computer program comprising the steps of claim 20. (Para. [0072] teaches “The memory 324 (e.g., a solid-state memory, hard drive, or other suitable memory) may store instructions that, when executed by the processor 326 (e.g., one or more microprocessors), cause the computer system 306 to receive the magnetic field data transmitted by the wireless transceiver 312, and process the received magnetic field data to determine orientations of the femoral head component 316 relative to the acetabular liner component 302. The processing may be performed substantially in real time as the magnetic sensors of the sensor array 308 capture the sensor readings.”)
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Pour (US 20210015634 A1) and Srivastava (US 20200372409 A1) as applied to claim 1 above, and further in view of Kather (US 20090267594 A1).
Regarding claim 3,
Pour does not explicitly teach,
The device as claimed in claim 1, wherein the error data is generated within a tolerance range so that the deviation of the system data from the target state and the magnetic field strength of the plurality of magnetic field components of the external magnetic field do not exceed a corresponding critical limit.
Kather teaches
wherein the error data is generated within a tolerance range so that the deviation of the system data from the target state and the magnetic field strength of the plurality of magnetic field components of the external magnetic field do not exceed a corresponding critical limit. (Claim 11 “learning phase for each of the sensor elements the respective absolute value of the magnet field vector and the related magnetic field orientation for one or several predetermined relative positions as a data set belonging together, and during the actual operation determine from the measured magnetic field direction for the individual sensor elements an estimated absolute value of the magnetic field vector, and in case of a deviation between the estimated value and measured value exceeding a threshold value, to discard the measured value of the respective sensor output value as non-plausible.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pour and Srivastava wherein the error data is generated within a tolerance range so that the deviation of the system data from the target state and the magnetic field strength of the plurality of magnetic field components of the external magnetic field do not exceed a corresponding critical limit such as that of Kather.
One of ordinary skill would have been motivated to modify the combination of Pour and Srivastava, because if the value of the deviation were too great the system would be trained on data that is not plausible and would be superfluous as seen in claim 11 of Kather.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Pour (US 20210015634 A1) and Srivastava (US 20200372409 A1) as applied to claim 1 above, and further in view of Spitz (US 20220399845 A1).
Regarding claim 4,
Pour does not explicitly teach,
The device as claimed in claim 1, wherein the at least one processor is configured to generate the training data using a simulation model.
Spitz teaches,
wherein the at least one processor is configured to generate the training data using a simulation model. (Para. [0101] teaches “wherein the at least one processor is configured to generate the training data using a simulation model.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pour and Srivastava wherein the at least one processor is configured to generate the training data using a simulation model such as that of Kather.
One of ordinary skill would have been motivated to modify the combination of Pour and Srivastava, because according to Para. [0014] of Spitz “In particular, a very accurate forward model may be used. The model thus trained may thus carry out particularly accurate mapping, which significantly improves the control quality as a whole.”
Claims 10 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Pour (US 20210015634 A1) and Srivastava (US 20200372409 A1) as applied to claim 7 above, and further in view of Uzair (Effects of Hidden Layers on the Efficiency of Neural networks; 2020).
Regarding claim 10,
Pour does not explicitly teach,
The device as claimed in claim 7, wherein the trained neural network comprises four hidden layers between an input layer and an output layer, the input layer being configured to receive the sensor data of the sensor system and the output layer being configured to output an output for the determination of the rotation angle.
Uzair teaches,
wherein the trained neural network comprises four hidden layers between an input layer and an output layer, the input layer being configured to receive the sensor data of the sensor system and the output layer being configured to output an output for the determination of the rotation angle. (Pg. 2 Section 2: Literature review teaches “J. De Villiers, E. Barnad [10] used three and four hidden layers which are not only feasible for only small and linear type problems but these number of layers are also enough to handle large and very complex problems with larger number of data set. S. Seifollahi, J. Yearwood and B. Ofoghi [11] talks about ELM and suggests a binary classifier working on the single Hidden layer by using Radial basis function and sigmoid function in the hidden layer. They also suggest a new weight ca [11].”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pour and Srivastava wherein the trained neural network comprises four hidden layers between an input layer and an output layer, the input layer being configured to receive the sensor data of the sensor system and the output layer being configured to output an output for the determination of the rotation angle such as that of Uzair.
One of ordinary skill would have been motivated to modify the combination of Pour and Srivastava, because Pg. 2 Section 2: Literature Review of Uzair further teaches “It shows how much the results of the networks are accurate or near to real results. Networks having large number of hidden layers normally show high accuracy even for the large and complex problems. High accuracy can be achieved only if whole problem can be understood by the network without having any overfitting and underfitting conditions [15, 14, 20]. To gain good result in Neural network very large number of hidden layers and neurons are required [14, 21].” Also, since it has been held that where the general conditions of a claim are disclosed in the prior art, discovering the optimum or workable ranges involves only routine skill in the art. In re Aller, 105 USPQ 233.
Regarding claim 11,
Pour further teaches,
The device as claimed in claim 10, wherein the trained neural network has a feed-forward architecture. (Para. [0096] teaches “An artificial neural network with one hidden layer may then be used to fit this function, in some embodiments, due to the simplicity of the calculations once the network is trained using the theoretical forward model.”)
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Pour (US 20210015634 A1), Srivastava (US 20200372409 A1) and Uzair (Effects of Hidden Layers on the Efficiency of Neural networks; 2020) as applied to claim 10 above, and further in view of Cui (CN 111609872 A).
Regarding claim 12,
The combination of Pour and Uzair does not explicitly teach,
The device as claimed in claim 10, wherein the trained neural network is configured to determine the rotation angle by using the sensor data and applying an arc tangent function.
Cui teaches,
wherein the trained neural network is configured to determine the rotation angle by using the sensor data and applying an arc tangent function. (Para. [0103] teaches “According to the same or other embodiments, a processing unit (eg, a processing unit that may be provided on-chip or off-chip), or a position determination module loaded into and executed by a processing unit, may be configured to perform an inverse tangent operation to determine the rotation angle α.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pour, Srivastava, and Uzair wherein the trained neural network is configured to determine the rotation angle by using the sensor data and applying an arc tangent function such as that of Cui.
One of ordinary skill would have been motivated to modify the combination of Pour, Srivastava, and Uzair, because it is a known mathematical function which would allow the rotation angle to be found. It is akin to Applying a known technique to a known device (method, or product) ready for improvement to yield predictable results as seen in MPEP 2143.
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Pour (US 20210015634 A1) and Srivastava (US 20200372409 A1) as applied to claim 13 above, and further in view of Kantor (US 20170344878 A1).
Regarding claim 18,
Pour does not explicitly teach,
The system as claimed in claim 13, wherein the at least one first sensor and the second sensor are 3D Hall sensors or magnetoresistive sensors.
Kantor teaches,
wherein the at least one first sensor and the second sensor are 3D Hall sensors or magnetoresistive sensors. (Para. [0066] teaches “In the exemplary embodiment shown in FIG. 8, it is assumed that the target object itself is formed by a rotating permanent magnet 900 and that analogue magnetic field sensors 905-925 (for example based on the Hall effect, AMR or GMR) are arranged around this target object. Since the rotation of the magnetic target object 900 causes a periodic change to the output signals of the sensor elements and therefore the momentary angle of rotation of the target object can be derived in an inherently known manner from the sensor signals supplied to the input layer 930 of an ANN (not shown), a rotary encoder can be provided with the shown arrangement.” Para. [0036] teaches “A one-, two- or three-dimensional arrangement (array) of sensor elements which are essentially identical per se, wherein the individual sensor elements are arranged along a sensitive axis, a sensitive circle or arc of a circle, within a limited region, in a limited volume, or along an irregular surface or trajectory”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pour and Srivastava wherein the at least one first sensor and the second sensor are 3D Hall sensors or magnetoresistive sensors such as that of Kantor.
One of ordinary skill would have been motivated to modify the combination of Pour and Srivastava because Para. [0005] of Kantor teaches “This approach not only enables an electronic selection of individual Hall effect sensors, but an interpolation between the individual Hall effect sensors, whereby the number of the Hall effect sensors can be kept low with simultaneously high precision of the detection of the position.” Therefore, one would be motivated to combine the prior art in order to reduce the number of sensors while maintaining high precision.
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over Pour (US 20210015634 A1) and Srivastava (US 20200372409 A1) as applied to claim 13 above, and further in view of Timopheev (US 20220050151 A1).
With respect to claim 23,
Pour does not explicitly teach,
The system as claimed in claim 13, wherein the error data is generated within a tolerance range so that the deviation of the system data from the target state and the magnetic field strength of the plurality of magnetic field components of the superimposed external magnetic field do not exceed a corresponding critical limit.
Timopheev teaches,
wherein the error data is generated within a tolerance range so that the deviation of the system data from the target state and the magnetic field strength of the plurality of magnetic field components of the superimposed external magnetic field do not exceed a corresponding critical limit. (Para. [0012] teaches “The total angular error corresponds to a difference between the measured relative angle θ between the direction of the sense magnetization 210 and reference magnetization 230 (see FIG. 5) when an external magnetic field (H.sub.ext) is applied and an “ideal” relative angle, i.e., when the sense magnetization 210 is completely aligned in the direction of the external magnetic field H.sub.ext, and when the reference magnetization 230 is not deflected by the external magnetic field H.sub.ext.” Para. [0042] teaches “For example, such ratio can be selected to obtain a compensation effect that corresponds to the angular deviation (or error) being minimized within a predetermined range of external magnetic field 60. For example, the ratio can be selected such that the angular deviation is equal or less than 0.5° within a range of external magnetic field 60 of about 200 Oe with the central working point of 800 Oe (FIG. 10c).”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pour and Srivastava wherein the error data is generated within a tolerance range so that the deviation of the system data from the target state and the magnetic field strength of the plurality of magnetic field components of the superimposed external magnetic field do not exceed a corresponding critical limit such as that of Timopheev.
One of ordinary skill would have been motivated to modify the combination of Pour and Srivastava because, putting a limit could prevent catastrophic errors in measurement should the generated error get too large.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to JOSHUA L FORRISTALL whose telephone number is 703-756-4554. The examiner
can normally be reached Monday-Friday 8:30 AM- 5 PM.
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, Andrew Schechter can be reached on 571-272-2302. 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.
/JOSHUA L FORRISTALL/Examiner, Art Unit 2857
/ANDREW SCHECHTER/Supervisory Patent Examiner, Art Unit 2857
Prosecution Insights