Product obsolescence forecast system and method
AssigneeArchitecture Technology Corporation
InventorsDrew Sullivan, Evan Eaves, William Colligan
Life of this patent
Estimating the term…
Abstract
A product obsolescence forecast system includes machine instructions stored in a non-transitory computer readable storage medium, the machine instructions. A processor executes the instructions to receive an identity of a first product and identities of one or more second products similar to the first product, each of the second products having gone obsolete; receive a determinant of obsolescence of one or more of the obsolete second products; generate one or more observations related to the first product by inputting each received determinant to a trained network; and generate a statistical analysis of the one or more observations to provide an expected value of an actual obsolescence date for the first product.
Claims17
A method for predicting supply-chain obsolescence of products, each product comprising one or more components supplied through one or more supply chains, wherein one or more monitors are connected to each product, each product having an initially-determined life cycle, the method, comprising:
- a processor determining that a current life cycle of a first product remains as initially determined and identifies an end of life for the first product;
- the processor identifying, within a description of the first product, a first component having a time to live shorter than the time to live of the first product, the first component supplied through a first supply chain;
- the processor identifying one or more second products similar to the first product, each of the similar products having identified obsolescent supply chains, each of the second products having gone obsolete;
- the processor identifying a determinant of obsolescence of one or more obsolete second products, comprising the processor:
- extracting from a database of data records related to the obsolete second products, a plurality of second product data elements defining components having gone obsolescent because of obsolescence of a second supply chain, generating a second product data element similarity matrix for each of the second products using one or more of the extracted second product data elements, comparing each second data element similarity matrix to a corresponding first product data element similarity matrix, and based on the comparing, selecting as one or more determinants of second product supply chain obsolescence, second product data elements from the second product data element similarity matrix;
- the processor receiving a selected determinant of second product supply chain obsolescence;
- the processor correlating the first supply chain and the second supply chain, wherein the processor:
- generates one or more observations related to the first product by inputting a received determinant into a trained neural network, the observations comprising a forecast supply chain obsolescence date for the first product, determines, based on the forecast, a probability that the first supply chain will be unable to provide a replacement component for use in the first product before the forecast supply chain obsolescence date, and generates a statistical analysis of the one or more observations to provide an expected value of an actual supply chain obsolescence date for the first product;
- and
- the processor issuing an advisory comprising the expected value, and one or more component replacement actions.
A system for predicting supply-chain obsolescence of products, each product comprising one or more components supplied through one or more supply chains, wherein one or more monitors are connected to each product, each product having an initially-determined life cycle, the system comprising a non-transitory computer-readable storage mechanism having encoded thereon, machine instructions, and a processor, wherein a processor executes the machine instructions to:
- determine that a current life cycle of a first product remains as initially determined and identifies an end of life for the first product;
- identify, within a description of the first product, a first component having a time to live shorter than the time to live of the first product, the first component supplied through a first supply chain;
- identify one or more second products similar to the first product, each of the similar products having identified obsolescent supply chains, each of the second products having gone obsolete;
- identify a determinant of obsolescence of one or more obsolete second products, comprising, wherein the processor:
- extracts from a database of data records related to the obsolete second products, a plurality of second product data elements defining components having gone obsolescent because of obsolescence of a second supply chain,
- generates a second product data element similarity matrix for each of the second products using one or more of the extracted second product data elements, compares each second data element similarity matrix to a corresponding
- first product data element similarity matrix, and based on a comparison, selects as one or more determinants of second product supply chain obsolescence, second product data elements from the second product data element similarity matrix;
- receive a selected determinant of second product supply chain obsolescence;
- correlate the first supply chain and the second supply chain, wherein the processor:
- generates one or more observations related to the first product by inputting the received determinant into a trained neural network, the observations comprising a forecast supply chain obsolescence date for the first product, determines, based on the forecast, a probability that the first supply chain will be unable to provide a replacement component for use in the first product before the forecast supply chain obsolescence date, and
- generates a statistical analysis of the one or more observations to provide an expected value of an actual supply chain obsolescence date for the first product;
- and issue an advisory comprising the expected value, and one or more component replacement actions.
A non-transitory computer-readable storage medium having encoded thereon, machine instructions for predicting supply-chain obsolescence of products, each product comprising one or more components supplied through one or more supply chains, wherein one or more monitors are connected to each product, each product having an initially-determined life cycle, wherein a processor executes the machine instructions to:
- invoke a monitoring network associated with a first product:
- receive, from the first product through the monitoring network, first product
- operational data, the first product operational data comprising operational data
- indicative of a time to live for one or more of the first product components;
- identify a first component having a time to live shorter than a time to live of the first product, the first component supplied through a first supply chain;
- identify one or more second products similar to the first product, each of the similar products having identified supply chains, each of the second products having gone obsolete;
- identify a determinant of obsolescence of one or more obsolete second products, wherein the processor:
- extracts from a database of data records related to the obsolete second products, a plurality of second product data elements defining components having gone obsolescent because of obsolescence of a second supply chain,
- generates a second product data element similarity matrix for each of the second products using one or more of the extracted second product data elements, compares each second data element similarity matrix to a corresponding
- first product data element similarity matrix, and based on a comparison, selects as one or more determinants of second product supply chain obsolescence, second product data elements from the second product data element similarity matrix;
- receive a determinant of obsolescence of one or more of the obsolete second products, the determinant consisting of supply chain obsolescence;
- correlate the first supply chain and the second supply chain, wherein the processor:
- generates one or more observations related to the first product by inputting a received determinant into a trained neural network, the observations comprising a forecast supply chain obsolescence date for the first product,
- determines, based on the forecast, a probability that the first supply chain will be unable to provide a replacement component for use in the first product before the forecast supply chain obsolescence date, and generates a statistical analysis of the one or more observations to provide an expected value of an actual supply chain obsolescence date for the first product;
- and
- issue an advisory comprising the expected value, and one or more component replacement actions.
Dependencies are inferred from the claim text.