Configuration Price Quote with Enhanced Approval Control
AssigneeOracle International Corporation
InventorsJeffrey WILKINS, Re LAI, Ellen BERES
Life of this patent
Estimating the term…
Loading patent…
AssigneeOracle International Corporation
InventorsJeffrey WILKINS, Re LAI, Ellen BERES
Estimating the term…
Embodiments operate a configurator that generates a quote for a product or service configuration, the quote including a quote workflow that includes at least one required quote approval and the quote includes a plurality of quote attributes that define the quote. Embodiments input the plurality of quote attributes into a first neural network model and a second neural network model and generate with a gradient descent a likelihood that the quote will be approved and a time required for the quote to be approved. Embodiments generate one or more attributes with the largest gradient values for the likelihood that the quote will be approved and the time required for the quote to be approved. Embodiments receive a change to one or more of the attributes and regenerate the likelihood that the quote will be approved and/or the time required for the quote to be approved based on the change.
A method of operating a configurator comprising:
A non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, cause the processor to provide a configuration comprising:
The non-transitory computer readable medium 8, wherein quote approvals of the quote comprise a graph of nodes.
The non-transitory computer readable medium 8, wherein the quote attributes comprise at least one categorical attribute and at least one numeric attribute.
The non-transitory computer readable medium 8, wherein the first neural network model comprises three layers, wherein two of the layers comprise linear neurons and a final layer comprises a sigmoid activation function.
The non-transitory computer readable medium 11, wherein the first neural network model comprises f(x)=1/(1+e{circumflex over ( )}(Mx)) having a gradient comprising f′(x)=f(x)*(1−f(x))*M
The non-transitory computer readable medium 8, wherein the second neural network model comprises three layers having a first input layer comprising non-linear components and a second and third layer comprising linear components.
The non-transitory computer readable medium 10, wherein the numeric attributes are normalized to be between 0 and 1 and the categorical attributes are transformed into one hot encoded vectors.
A product configurator comprising:
Dependencies are inferred from the claim text.