Characterizing electronic designs via visual processing and data transformation
A cognitive, artificially intelligent system employs, in part, visual recognition and image processing to transform electronic design information, such as a schematic diagram, into a machine-readable data structure suitable for machine-based comparison of one data structure against another data structure of like kind. A comparison method identifies and quantifies similarities or equivalencies between the any such data structures, and hence between respectively corresponding electronic designs.
1. A computer-implemented method comprising:
receiving design information corresponding to a first device;
identifying, via a neural network, and based on standard electronic design symbology, a first component of the first device, and a first node of the first device;
generating a first data structure based on the design information for the first device, wherein the first data structure includes a first element corresponding to a combination of the first component and the first node;
receiving, from a database, a second data structure corresponding to a second device, wherein the second data structure includes a second element corresponding to a combination of a second component of the second device and a second node of the second device;
comparing the first component against the second component to generate a comparison dataset comprising a numerical degree of similarity, with respect to an electrical characteristic, between the first component and the second component, wherein the numerical degree of similarity takes into account a probability of value overlap of electrical characteristics respectively corresponding to the first component and the second component, wherein the first component and the second component have different nominal values;
sending the comparison dataset to a storage address; and
sending the first data structure to the database.
2. The method of claim 1 , wherein generating the first data structure comprises:
determining a first type of the first component of the first device;
determining a second type of the second component of the first device; and
determining that the first component and the second component are operationally coupled.
3. The method of claim 1 , wherein:
design information for the first device is selected from the group consisting of: a schematic diagram; an open American Standard Code for Information Interchange (ASCII) vector format for two-dimensional (2D) binary image file; component placement data; drill data; printed circuit board mask data; printed circuit board layup information; test data; circuit logic response data; circuit analog response data; and netlist data.
4. The method of claim 3 ; wherein generating the first data st re comprises:
applying a transformation formula to the first schematic diagram.
5. The method of claim 4 , wherein the transformation formula is formatted as a sum of products.
6. The method of claim 5 , wherein the transformation formula is N f(N) =C x1 (N y1 )+C x2 (N y2 )+ . . . +C xn (N yn );
wherein: N f(N) represents a given node, C xn represents a component connected to the given node, and N yn represents another node connected to component C xn .
7. A computer program product comprising a computer readable storage medium having stored thereon program instructions programmed to perform:
receiving design information corresponding to a first device;
identifying, via a neural network; and based on standard electronic design symbology; a first component of the first device, and a first node of the first device;
generating a first data structure based on the design information for the first device, wherein the first data structure includes a first element corresponding to a combination of the first component and the first node;
receiving, from a database, a second data structure corresponding to a second device, wherein the second data structure includes a second element corresponding to a combination of a second component of the second device and a second node of the second device;
comparing the first component against the second component to generate a comparison dataset comprising a numerical degree of similarity, with respect to an electrical characteristic, between the first component and the second component, wherein the numerical degree of similarity takes into account a probability of value overlap of electrical characteristics respectively corresponding to the first component and the second component, wherein the first component and the second component have different nominal values;
sending the comparison dataset to a storage address; and
sending the first data structure to the database.
8. The computer program product of claim 7 , wherein generating the first data structure comprises:
determining a first type of the first component of the first device;
determining a second type of the second component of the first device; and
determining that the first component and the second component are operationally coupled.
9. The computer program product of claim 7 , wherein:
design information for the first device is selected from the group consisting of: a schematic diagram; an open American Standard Code for Information Interchange (ASCII) vector format for two-dimensional (2D) binary image file; component placement data; drill data; printed circuit board mask data; printed circuit board layup information; test data; circuit logic response data; circuit analog response data; and netlist data.
10. The computer program product of claim 9 , wherein generating the first data structure comprises:
applying a transformation formula to the first schematic diagram.
11. The computer program product of claim 10 , wherein the transformation formula is formatted as a sum of products.
12. The computer program product of claim 11 ; wherein the transformation formula is N f(N) =C x1 (N y1 )=C x2 (N y2 )+ . . . +C xn (N yn );
wherein: N f(N) represents a given node, C xn represents a component connected to the given node, and N yn represents another node connected to component C xn .
13. A computer system comprising:
a processor set; and
a computer readable storage medium;
wherein the processor set is structured; located, connected and/or programmed to run program instructions stored on the computer readable storage medium; and the program instructions include instructions programmed to perform:
receiving design information corresponding to a first device;
identifying, via a neural network, and based on standard electronic design symbology, a first component of the first device; and a first node of the first device;
generating a first data structure based on the design information for the first device, wherein the first data structure includes a first element corresponding to a combination of the first component and the first node;
receiving, from a database, a second data structure corresponding to a second device, wherein the second data structure includes a second element corresponding to a combination of a second component of the second device and a second node of the second device;
comparing the first component against the second component to generate a comparison dataset comprising a numerical degree of similarity, with respect to an electrical characteristic, between the first component and the second component, wherein the numerical degree of similarity takes into account a probability of value overlap of electrical characteristics respectively corresponding to the first component and the second component, wherein the first component and the second component have different nominal values;
sending the comparison dataset to a storage address; and
sending the first data structure to the database.
14. The computer system of claim 13 , wherein generating the first data structure comprises:
determining a first type of the first component of the first device;
determining a second type of the second component of the first device; and
determining that the first component and the second component are operationally, coupled.
15. The computer system of claim 13 , wherein:
design information for the first device is selected from the group consisting of: a schematic diagram; an open American Standard Code for Information interchange (ASCII) vector format for two-dimensional (2D) binary image file; component placement data; drill data; printed circuit board mask data; printed circuit board layup information; test data; circuit logic response data; circuit analog response data; and netlist data.
16. The computer system of claim 15 , wherein generating the first data structure comprises:
applying a transformation formula to the first schematic diagram.
17. The computer system of claim 16 , wherein the transformation formula is formatted as a sum of products.
18. The computer system of claim 17 , wherein the transformation formula is N f(N) =C x1 (N y1 )+C x2 (N y2 )+ . . . +C xn (N yn );
wherein: N f(N) represents a given node, C xn represents a component connected to the given node, and N yn represents another node connected to component C xn .