SUPPLY CHAIN FORECASTING SYSTEM

• US 20200134545A1
• Filed: 10/31/2018
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: APPEL, ANA PAULA, Oliveira, Igor Cerqueira, Vasconcelos, Marisa Affonso, Vieira Borges Franco, Ricardo
• Granted Patent: US 11,126,957 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/0635 Risk analysis of enterprise or organisation activities
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders

Abstract

Systems and methods are described for supply chain vulnerability forecasting using external event data is described. The method may include identifying historic data from each entity of a plurality of entities connected in a supply chain, aggregating temporal-based information relating to the entities and to relations among the entities into one or more time periods based on the historic data, training a cognitive prediction model using the aggregated temporal-based information, generating a vulnerability score for each entity, generating a recommendation for at least one entity if the vulnerability score for the at least one entity is above a preset threshold, retraining the cognitive prediction model using changed data of the at least one entity, and adjusting the vulnerability score based on the retraining.

Claims

1. A method for supply chain vulnerability forecasting, comprising:

identifying historic data from each entity of a plurality of entities connected in a supply chain;

aggregating temporal-based information relating to the entities and to relations among the entities into one or more time periods based on the historic data;

training a cognitive prediction model using the aggregated temporal-based information;

generating a vulnerability score for each entity;

generating a recommendation for at least one entity if the vulnerability score for the at least one entity is above a preset threshold;

retraining the cognitive prediction model using changed data of the at least one entity; and

adjusting the vulnerability score based on the retraining.

2. The method of claim 1, wherein:

the historic data comprises at least one of weather information or market information corresponding to a selected time interval.

3. The method of claim 1, further comprising:

generating a network comprising a plurality of nodes and a plurality of edges, wherein the plurality of nodes represent the plurality of entities and the plurality of edges represent the relations among the entities; and

assigning a weight to each of the plurality of edges based at least in part on the aggregation.

4. The method of claim 1, wherein:

the retraining is based on additional temporal-based information corresponding to a subsequent time interval after a selected time interval of the temporal-based information.

5. The method of claim 1, wherein:

the cognitive prediction model includes a neural network.

6. The method of claim 1, wherein:

the cognitive prediction model includes a machine learning model.

7. The method of claim 1, wherein:

the vulnerability score corresponds to a selected time interval in the future.

8. The method of claim 1, wherein:

the historic data is processed by text mining algorithms.

9. The method of claim 1, further comprising:

processing remote sensing data using geo-referential tools and databases.

10. The method of claim 1, wherein:

the aggregating includes use of internet of things (IoT) sensor data.

11. The method of claim 1, wherein:

the changed data is based at least in part on the recommendation.

12. An apparatus for supply chain vulnerability forecasting, comprising:

a processor and a memory storing instructions and in electronic communication with the processor, the processor being configured to execute the instructions to;

identify historic data from each entity of a plurality of entities connected in a supply chain;

aggregate temporal-based information relating to the entities and to relations among the entities into one or more time periods based on the historic data;

train a cognitive prediction model using the aggregated temporal-based information;

generate a vulnerability score for each entity;

generate a recommendation for at least one entity if the vulnerability score for the at least one entity is above a preset threshold;

retrain the cognitive prediction model using changed data of the at least one entity; and

adjust the vulnerability score based on the retraining.

13. The apparatus of claim 12, wherein:

the historic data comprises at least one of weather information or market information corresponding to a selected time interval.

14. The apparatus of claim 12, the processor being further configured to execute the instructions to:

generate a network comprising a plurality of nodes and a plurality of edges, wherein the plurality of nodes represent the plurality of entities and the plurality of edges represent the relations among the entities; and

assign a weight to each of the plurality of edges based at least in part on the aggregation.

15. The apparatus of claim 12, wherein:

the retraining is based on additional temporal-based information corresponding to a subsequent time interval after a selected time interval of the temporal-based information.

16. The apparatus of claim 12, wherein:

the cognitive prediction model includes a neural network.

17. A non-transitory computer readable medium storing code for supply chain vulnerability forecasting, the code comprising instructions executable by a processor to:

identifying historic input data and historic vulnerability data for a plurality of entities in a supply chain;

assigning time periods to the historic input data and the historic vulnerability data;

training a cognitive prediction model using the historic input data and the historic vulnerability data based on the assigned time periods;

generating one or more vulnerability scores for at least one of the plurality of entities in the supply chain using the cognitive prediction model, wherein each of the one or more vulnerability scores corresponds to a future time period.

18. The non-transitory computer-readable medium of claim 17, the code further comprising instructions executable by the processor to:

determining that the one or more vulnerability scores exceed a threshold; and

generating a mitigation recommendation based at least in part on the determination that the one or more vulnerability scores exceed the threshold.

19. The non-transitory computer-readable medium of claim 17, the code further comprising instructions executable by the processor to:

generate a network comprising a plurality of nodes and a plurality of edges, wherein the plurality of nodes represent the plurality of entities and the plurality of edges represent the relations among the entities; and

assign a weight to each of the plurality of edges based at least in part on the aggregation.

20. The non-transitory computer-readable medium of claim 17, wherein the training is based on additional temporal-based information corresponding to a subsequent time interval after a selected time interval of the temporal-based information.