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 .
1. Claims 1-15 are presented for examination.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
2 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.
2.1 Claim(s) 1-6 and 8-9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yeoh (US 20200353678 A1) in view of Anand (US 20170372480 A1).
Regarding claim 1, Yeoh discloses determining a graph representation of a three-dimensional (3D) object based on a voxel representation of the 3D object ([0020], [0026], providing a desired 3D structure inserting an input material into a stitch additive manufacturing machine, and arranging the input material into the desired 3D structure),
wherein the graph representation comprises nodes corresponding to voxels of the voxel representation and edges associated with the nodes ([0130], [0364], Fig. 64, Fig. 66, Nodes in the sample topography may be represented by a voxel database or other data formats, edge).
Yeoh fails to discloses predicting, using a machine learning model, a sintering state of the 3D object based on the graph representation.
However, Anand discloses predicting, using a machine learning model, a sintering state of the 3D object based on the graph representation ([0181]-[0182], [0225],[0232], [0209], the sintering area and the sintering time calculator are validated on the CAD model in the geometry using the output of the AM process simulation used to create the datasets for the ANN model training. These surface data used by the ANN model to train on/learn the direction and magnitude of deformation. The trained network may then be used on the CAD model geometry to generate the modified geometry).
Yeoh and Anand are analogous art. They relate to additive manufacturing.
Therefore, before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify the pre- and post-processing in additive manufacturing, taught by Anand, incorporated with create a three-dimensional structure, taught by Yeoh, in order to modified topology optimization algorithm with manufacturing constraint for support structure volume.
Regarding claim 2, Yeah discloses the graph representation comprises a global factor ([0312], a product of manufacture constructed of the treated working yarn).
Regarding claim 3, Yeoh discloses determining the graph representation comprises filtering voxel vertices to produce the nodes ([0364] [0339], the generation of voxels, to tessellation of 3D volumes, and to the generation of 3D filled meshes using a Kalman filtering. The nodes in the sample topography represented by a 3D mesh, 3D matrix, voxel database or other data formats).
Regarding claim 4, Yeoh discloses determining the graph representation comprises determining a node attribute value for each of the nodes ([0364], the Nodes in the sample topography represented by a 3D mesh, 3D matrix, voxel database or other data formats).
Regarding claim 5, Yeoh discloses the node attribute value indicates node mobility ([0364], Nodes 5301, corresponding to e.g. stitches, physical locations, fiducials, or other identifiable features on the work in progress) including node position, node connections, node relations to adjacent nodes, node velocity and acceleration, connection elasticity and flexibility, and other node information).
Regarding claim 6, Anand discloses determining the graph representation comprises determining the edges based on a threshold distance ([0101], [0192], Fig. 5-8, Fig. 17, the captured sectional snapshot may be converted to a binary image using binary thresholding operation or the Corner and edge detection algorithm).
Regarding claim 8, Anand discloses updating the graph representation over a time increment of a sintering procedure ([0073], [0093], [0140], [0181]-[0182], create a modified part geometry which helps counteract the thermal deformations and shrinkages that occur during some of the AM processes. The segmented image and 2D bounding box data from previous analysis may be also used to calculate a sintering area and time for each layer. The applied geometric modifications help compensate for thermal shrinkage and deformations during the AM process); and
predicting, using the machine learning model, a second sintering state of the 3D object based on the updated graph representation ([0181]-[0182], [0208],[0209], [0225],[0213], Sintering area the area hatched by the laser during any laser sintering additive processes or area traversed by the nozzle for deposition based additive processes. Sintering time as the time taken to perform either hatching or deposition operation. Sintering time assumed to be linearly proportional to the hatch area and the effect. Using an ANN model for making direct modifications to the geometry of a given part CAD model. Continuously evaluated and updated, as the data instances are input to the network, and this process includes network training).
Regarding claim 9, Anand discloses voxelizing a 3D object model to produce the voxel representation of the 3D object ([00252], Fig. 5-8, part surface point voxels are input at the ANN input layer, which are then provided to the ANN hidden layer, and CAD surface point voxels are output at the ANN output layer, where the target is a CAD surface with point voxels. A voxel matching approach used to create ANN training data in FIG. 66).
2.2 Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Anand (US 20170372480 A1) in view of Yeoh (US 20200353678 A1).
Regarding claim 10, Anand discloses apparatus, comprising: a memory (memory 7008 and 7010); a processor in electronic communication with the memory, wherein the processor is to ([0013],[0014], Fig. 70, a processor coupled to the memory, where the processor may be configured to receive a model of the object. The processor may be further configured to extract nodes representing a surface of the object, each node having a position):
simulate sintering of voxels to produce an initial simulated sintering state (Fig. 1-5, Fig. 53], [0092],[0093],[0157-0154], [0182], [0229], The first stages simulation into a total sintering area and total sintering time which may prove useful in process planning. an analytical model based on a ray tracing approach to simulate the effect of laser energy in the SLS process. the model was used to simulate the laser sintering of Ti6A14V powder for generating the required surface data for the manufactured part. The trained neural network trained with previous object fabrication simulations),
determine a graph based on the initial simulated sintering state (Fig. 22, Fig. 27, Fig. 65, [0093], [0153], [0154], [0181], [0182], The image processing approach can also be used for calculation of the total sintering area and total sintering time which may prove useful in process planning),
predict a subsequent sintering state based on the graph ([0093], [0254], [0092], prediction a sintering parameters calculator and sintering area, a time calculation report and the trained network used on the STL file of the part CAD model to impart the required geometrical compensations to the part design).
Anand fails to disclose the graph comprises nodes and edges.
However, Yeoh discloses the graph comprises nodes and edges (Abstract, identifying an edge indicative of a connection between the respective node and a second node of the plurality of nodes).
Yeoh and Anand are analogous art. They relate to additive manufacturing.
Therefore, before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify the pre- and post-processing in additive manufacturing, taught by Anand, incorporated with create a three-dimensional structure, taught by Yeoh, in order to modified topology optimization algorithm with manufacturing constraint for support structure volume.
2.3 Claim(s) 7 and 11-12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yeoh (US 20200353678 A1) in view of Anand (US 20170372480 A1) further in view of Kanza (US 20180006897 A1).
Regarding claims 7 and 11-12, the combination of Yeoh and Anand disclose the limitations of claims 1 and 10, but fail to disclose the limitations of claims 7 and 11-12. However, Kanza discloses the limitations of claims 7 and 11-12 as follow:
Regarding claim 7, Kanza discloses determining the graph representation comprises determining an edge attribute value for each of the edges ([0008]-[0010], plurality of edge data structures based on the edges and creating a graph database comprising a layered graph based on the node data structures and the edge data structures).
Regarding claim 11, Kanza discloses each of the nodes comprises an attribute value indicating a node type ([0035], detecting a plurality of nodes in network 100. Nodes may be any network entities, whether implemented in software, hardware, or a combination thereof).
Regarding claim 12, Kanza discloses the processor is to predict the subsequent sintering state using a machine learning model trained with an anchoring loss ([0011], [0012], [0191], the operations may also include determining an anchor set based on at least one of the pathway variables and identifying an evaluation order based on the anchor set, autonomous learning of peer transport layer addresses by one or more of the network nodes).
Kanza, Yeoh and Anand are analogous art. They relate to additive manufacturing.
Therefore, before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify layered graph based on data structures, taught by Kanza, incorporated with the teaching of Anand and Yeoh, as state above, in order to modify the object in accordance with the changes in positions, said trained neural network trained with previous object fabrication simulations. Moreover, the processor may output a modified model of the object.
2.4 Claim(s) 13-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Anand (US 20170372480 A1) in view of Kanza (US 20180006897 A1) further in view of Yeoh (US 20200353678 A1).
Regarding claim 13, Anand discloses a non-transitory tangible computer-readable medium comprising instructions when executed cause a processor of an electronic device to ([0011]-[0013] a non-transitory computer readable medium embodying computer-executable instructions, that when executed by a processor, may cause the processor to execute operations):
a plurality of nodes of a first graph corresponding to a first time ([0012], [0013], [0237], Fig. 56, comprise extracting nodes representing a surface of the object, each node having a position and fabrication occurring across a time frame);
determine a plurality of node attributes for the plurality of nodes (Fig. 56, [0013], determining changes in the positions of the extracted nodes across the time frame); and
predict, using a graph neural network, a second graph based on the first graph, wherein the second graph indicates a sintering state corresponding to a second time ([0093], [0254], [0092], prediction a sintering parameters calculator and sintering area, a time calculation report and the trained network used on the STL file of the part CAD model to impart the required geometrical compensations to the part design).
Anand fails to disclose generate a plurality of edges of the first graph, determine a plurality of edge attributes for the plurality of edges, and generate, based on voxels representing a three-dimensional.
However, Kanza discloses generate a plurality of edges of the first graph ([0010], [0032], Fig. 2, data structures may comprise the plurality of edge data structures); and determine a plurality of edge attributes for the plurality of edges (Abstract, [0010], identifying an edge indicative of a connection between the respective node and a second node of the plurality of nodes, and instantiating a plurality of edge data structures based on the edges).
Kanza and Anand are analogous art. They relate to the data structures comprising the plurality of node.
Therefore, before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify graph database comprising a layered graph based on data structures, taught by Kanza, incorporated with defined design space, taught by Anand, in order to modify the object in accordance with the changes in positions, said trained neural network trained with previous object fabrication simulations. Moreover, the processor may output a modified model of the object.
The combination of Anand and Kanza fail to disclose generate, based on voxels representing a three-dimensional (3D) object model.
However, Yeoh discloses generate, based on voxels representing a three-dimensional (3D) object model ([0339], generation of voxels, to tessellation of 3D volumes, and to the generation of 3D filled meshes).
Kanza, Yeoh and Anand are analogous art. They relate to the data structures comprising the plurality of node.
Therefore, before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify create a three-dimensional structure, taught by Yeoh, incorporated with the teaching of Anand and Kanza, as state above, in order to modified topology optimization algorithm with manufacturing constraint for support structure volume.
Regarding claim 14, Yeoh discloses the graph neural network is trained based on a deformation loss and a stress loss ([0203], [0359], [0444], Fig. 19C, Fig. 52 neural network 5207C training datasets comprising actual and/or simulated system inputs and outputs deformation, to monitor e.g. stress and strain distribution, contact profile, temperature distribution, and physical or other metrics).
2.5 Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Anand (US 20170372480 A1) in view of Kanza (US 20180006897 A1) further in view of Yeoh (US 20200353678) and further in view of Dai et al. (US 20190251449 A1).
Regarding claim 15, the combination of Anand, Kanza and Yeoh disclose the limitations claims 13-14, but fail to disclose the limitation of claim 15. However, Dai discloses the limitations of claim 15 as follow:
Regarding claim 15, Dai discloses the graph neural network is trained based on an anchoring loss ([0032], Fig. 1 and 2, determined by training the neural network with a loss function that includes at least one auxiliary loss in addition to a main supervised loss, using auxiliary losses and anchor points in a recurrent neural network).
Kanza, Dai, Yeoh and Anand are analogous art. They relate to node connection with machine learning or neural network.
Therefore, before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify recurrent neural networks by adding an unsupervised auxiliary loss, taught by Dai, incorporated with the teaching of Kanza, Yeoh and Anand, as state above, in order to achieved by gradient descent and backpropagation through time (BPTT) with recurrent networks.
Citation Pertinent prior art
3. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Urtasun et al. (US20210009163A1) discloses an object detection model and a graph neural network including a plurality of nodes and a plurality of edges.
WATTYN (US 20200353675 A1) discloses an apparatus for generating a three-dimensional structure using a solidifiable material (M) includes a support structure configured for providing a support surface, wherein the support surface may be formed by a substrate intended to be part of the three-dimensional structure to be generated or by a support not intended to be part of the three-dimensional structure to be generated.
A reference to specific paragraphs, columns, pages, or figures in a cited prior art reference is not limited to preferred embodiments or any specific examples. It is well settled that a prior art reference, in its entirety, must be considered for allthat it expressly teaches and fairly suggests to one having ordinary skill in the art. Stated differently, a prior art disclosure reading on a limitation of Applicant's claim cannot be ignored on the ground that other embodiments disclosed wereinstead cited. Therefore, the Examiner's citation to a specific portion of a single prior art reference is not intended to exclusively dictate, but rather, to demonstrate an exemplary disclosure commensurate with the specific limitations being addressed. In re Heck, 699 F.2d 1331, 1332-33,216 USPQ 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1 009, 158 USPQ 275, 277 (CCPA 1968)). In re: Upsher-Smith Labs. v. Pamlab, LLC, 412 F.3d 1319, 1323, 75 USPQ2d 1213, 1215 (Fed. Cir. 2005); In re Fritch, 972 F.2d 1260, 1264, 23 USPQ2d 1780, 1782 (Fed. Cir. 1992); Merck& Co. v. Biocraft Labs., Inc., 874 F.2d804, 807, 10 USPQ2d 1843, 1846 (Fed. Cir. 1989); In re Fracalossi, 681 F.2d 792,794 n.1, 215 USPQ 569, 570 n.1 (CCPA 1982); In re Lamberti, 545 F.2d 747, 750, 192 USPQ 278, 280 (CCPA 1976); In re Bozek, 416 F.2d 1385, 1390, 163USPQ 545, 549 (CCPA 1969).
Conclusion
4. Any inquiry concerning this communication or earlier communications from the examiner should be directed Kidest Worku whose telephone number is 571-272-3737. If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Ali Mohammad can be reached on 571-272-4105. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Examiner interviews are available via telephone 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.
Information regarding the status of an application may be obtained from the Patent Application information Retrieval IPAIRI system. Status information for published applications may be obtained from either Private PMR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAG system, contact the Electronic Business Center (EBC) at 866-217- 9197.
/KIDEST WORKU/Primary Examiner, Art Unit 2119