Self-Organizing Neural Network Approach to the Automatic Layout of Business Process Diagrams

Patent metadata

Field	Value
Publication number	US-2016180263-A1
Application number	US-201414579338-A
Country	US
Kind code	A1
Filing date	Dec 22, 2014
Priority date	Dec 22, 2014
Publication date	Jun 23, 2016
Grant date	—

Abstract

A method, system, and/or computer program product generates self-organizing layouts of process diagrams. Initial weight vectors are distributed uniformly within boundaries of regions in the process diagram. A spatial input vector is randomly generated within the boundaries of each region. In each region in the process diagram, a closest graphical node is found, and a position of a winning graphical node that is the closest graphical node to the random input vector is adjusted. Positions of all non-immutable graphical objects, w i , in a topographical neighborhood N(k) of a closest graphical node w c that can cross a boundary of one or more regions from the multiple regions are adjusted. The spatial input vector is recursively generated, the closest graphical node is recursively located, and the positions of all non-immutable graphical objects, w i , in the topographical neighborhood N(k) are recursively adjusted until a maximum number of iterations, k max is reached.

First claim

1 - 8 . (canceled)

9 . A computer program product for generating self-organizing layouts of process diagrams, the computer program product comprising a computer readable storage medium having program code embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, and wherein the program code is readable and executable by a processor to perform a method comprising:
randomly selecting initial spatial position vectors, w i , for all graphical nodes in a process diagram; distributing the initial spatial position vectors, w i , uniformly within boundaries of multiple regions in the process diagram; in each region in the process diagram, randomly generating a spatial input vector, x, within the boundaries of each region; in each region in the process diagram, finding a closest graphical node w c , to a random input vector generated in said each region; in each region in the process diagram, adjusting a position of a winning graphical node that is the closest graphical node to the random input vector generated in said each region, wherein said adjusting the position of the winning graphical node brings the winning graphical node closer to the random input vector; adjusting a weight vector of each immutable closest graphical node in the process diagram, wherein each immutable closest graphical node w c has a fixed location on the process diagram; adjusting positions of all non-immutable graphical objects in a topographical neighborhood N(k) of the closest graphical node w c that can cross a boundary of one or more regions from the multiple regions; and randomly generating the spatial input vector x, locating the closest graphical node w c , adjusting the position of the winning graphical node, adjusting the position of the immutable closest graphical node w c , and adjusting positions of all non-immutable graphical objects in the topographical neighborhood N(k) recursively until a maximum number of iterations, k max is reached.

10 . The computer program product claim 9 , wherein the closest graphical node w c is determined by:
minimizing a Euclidean distance between x and w i such that:
μ x−w c ∥=min i ∥x−w i ∥.

11 . The computer program product claim 9 , wherein w c is not immutable, wherein w c is from a set of non-immutable graphical nodes, w c , in an interconnected neighborhood N(k), wherein nodes from w c can cross the regional boundaries in the process diagram, and wherein spatial adjustment of nodes in the process diagram is calculated by:
Δ w i =α( k ) h ( n c , n i ) [ x−wi], n i εN ( k )
where α(k) is an adaption rate, having a value between 0 and 1, that diminishes with every iteration k; h(n c , n i ) is a neighborhood function, having a value between 0 and 1, that diminishes as a topographical distance increases between the winning graphical node and other nodes n i in the neighborhood N(k) and wherein N(k) defines a neighborhood boundary during an iteration k and decreases over a span of the iterations, such that n i εN(k) refers to every k iteration of output nodes n in the neighborhood N(k).

12 . The computer program product claim 11 , wherein the method further comprises:
determining α(k) h(n c , n i ):

α


(
k
)

=

α
max



e

-

c


(

k

k
max

)

where α max , is a maximum adaption parameter (between 0 and 1), and c is a cooling parameter that determines a rate of decline in the adaption rate.

13 . The computer program product claim 9 , wherein the method further comprises:
recursively randomly generating the spatial input vector x, locating the closest graphical node w c , and adjusting the position of the immutable closest graphical node w c , until a weight adaption rate drops below a predefined threshold.

14 . The computer program product claim 9 , wherein the method further comprises setting boundaries for each region R in the process diagram by implementing an algorithm:

w

i

k
+
1

=

w
i

+

Δ




w
i

=

(

w

i

k
+
1


x

,

w

i

k
+
1


y

)

such that:
if w i k+1 x >x max R then w i k+1 x =x max R
if w i k+1 x <x min R then w i k+1 x =x min R
if w i k+1 y >y max R then w i k+1 y =y max R
if w i k+1 y <y min R then w i k+1 y =y min R .

15 . The computer program product claim 9 , wherein the method further comprises determining w c , by implementing an algorithm:

h


(

n
c

,

n
i

)

=

{

1

Assignees

• IBM

Inventors

• Mourra John

Classifications

• G06F3/04817

  using icons (graphical or visual programming using iconic symbols G06F8/34) · CPC title

• G06Q10/067 Primary

  Enterprise or organisation modelling · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title