METHOD AND SYSTEM FOR ELECTRIC VEHICLE ADOPTION SIMULATION WITH REASONING

• US 20130124441A1
• Filed: 11/15/2012
• Published: 05/16/2013
• Est. Priority Date: 11/16/2011
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Quaile, James Patrick, Garifullin, Maxim V., Cline, Jerrold Allen, Wang, Shanshan
• Granted Patent: US 8,949,163 B2
• Time in Patent Office: Days
• US Class Current: 706/46
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A method and system for an agent-based evidential reasoning decision computer system for determining an adoption rate of a trend is provided. The system includes a plurality of nodes arranged in a tree structure. The plurality of nodes define an evidential reasoning algorithm where lower level nodes receive factors to be considered in the decision and each node assigns a likelihood of an outcome of the received factors, and generates an output to a subsequent higher level node or root of the tree structure. The system also includes a plurality of agent models organized in a hierarchical structure, each agent model comprising a respective set of the plurality of nodes and an output of the agent model, each agent model representing a member of a population, and an aggregator algorithm configured to combine the outputs of the plurality of agent models to generate an output representing an adoption rate.

Claims

1. An agent-based evidential reasoning decision computer system for determining an adoption rate of a trend, the system comprising a processor and a computer-readable storage device having encoded thereon computer-executable instructions that are executable by the processor to perform functions, the system further comprising:

a plurality of nodes arranged in a tree structure, a topology of the tree structure determined by a subject matter expert in an area of the decision, the topology defining a hierarchy of the tree structure and an interconnection of the nodes, the plurality of nodes defining an evidential reasoning algorithm where lower level nodes receive factors to be considered in the decision, each node assigns a likelihood of an outcome of the received factors, and generates an output to a subsequent higher level node or root of the tree structure;

a plurality of agent models organized in a hierarchical structure, each agent model comprising a respective set of the plurality of nodes and an output of the agent model, each agent model representing at least one of a member of a population and a subset of the population; and

an aggregator algorithm configured to combine the outputs of the plurality of agent models to generate an output representing an adoption rate.

2. The computer system of claim 1, wherein said aggregator algorithm comprises a Bass diffusion model.

3. The computer system of claim 2, wherein the elements of the Bass diffusion model include at least one of financial payback, age of existing vehicle, commute distance of user, availability of charger infrastructure, and manufacturing supply constraints

4. The computer system of claim 1, wherein the evidential reasoning algorithm is used to assign a belief in the decision at each node where additional factors are considered, the belief represented by a certainty factor that ranges from absolute belief to absolute disbelief

5. A computer-implemented method for determining an adoption rate of a trend by a plurality of potential adopters defining a population, the adoption rate defining a rate of the spread of the trend through the population, the trend relating to a pattern of a change in usage of a technology area by the population, the method implemented using a computer device coupled to a memory device, the method comprising:

receiving a set of factors, determined by an expert in the technology area, the received set of factors representing facts to be considered in determining the adoption rate;

applying the set of factors to a plurality of agent models, each agent model representing one or more of the users, each of the agent models including a hierarchical reasoning algorithm including a plurality of decision nodes, each algorithm configured to generate a score for the hierarchical reasoning algorithm based on the applied set of factors;

applying the generated scores to an adoption forecasting model configured to combine the scores of the agent models to generate an adoption rate for the population based on the applied set of factors; and

outputting the generated adoption rate to a user.

6. The method of claim 5 wherein each of the plurality of nodes of the hierarchical reasoning algorithm is configured to evaluate the applied set of factors at respective nodes through the hierarchical algorithm to generate the score.

7. The method of claim 5, wherein the adoption forecasting model comprises a Riccati equation.

8. The method of claim 7, wherein the Riccati equation comprises a Bass diffusion model that includes a plurality of elements.

9. The method of claim 8, wherein the elements of the Bass diffusion model include at least one of financial payback, age of existing vehicle, commute distance of user, availability of charger infrastructure, and manufacturing supply constraints.

10. The method of claim 5, wherein the agent models each comprise a hierarchical reasoning algorithm.

11. The method of claim 10, wherein the hierarchical reasoning algorithm comprises an example based evidential reasoning (EBER) algorithm.

12. A method in accordance with claim 5 wherein the score represents a likelihood of that agent adopting the trend.

13. One or more non-transitory computer-readable storage media having computer-executable instructions embodied thereon, wherein when executed by at least one processor, the computer-executable instructions cause the processor to:

receive a set of factors, determined by an expert in the technology area, the received set of factors representing facts to be considered in determining the adoption rate;

apply the set of factors to a plurality of agent models, each agent model representing one or more of the users, each of the agent models including a hierarchical reasoning algorithm including a plurality of decision nodes, each algorithm configured to generate a score for the hierarchical reasoning algorithm based on the applied set of factors;

apply the generated scores to an adoption forecasting model configured to combine the scores of the agent models to generate an adoption rate for the population based on the applied set of factors; and

output the adoption rate.

14. The computer-readable storage media of claim 13, wherein each of the plurality of nodes of the hierarchical reasoning algorithm is configured to evaluate the applied set of factors at respective nodes through the hierarchical algorithm to generate the score.

15. The computer-readable storage media of claim 13, wherein the adoption forecasting model comprises a Riccati equation.

16. The computer-readable storage media of claim 15, wherein the Riccati equation comprises a Bass diffusion model that includes a plurality of elements.

17. The computer-readable storage media of claim 16, wherein the elements of the Bass diffusion model include at least one of financial payback, age of existing vehicle, commute distance of user, availability of charger infrastructure, and manufacturing supply constraints.

18. The computer-readable storage media of claim 13, wherein the agent models each comprise a hierarchical reasoning algorithm.

19. The computer-readable storage media of claim 18, wherein the hierarchical reasoning algorithm comprises an example based evidential reasoning (EBER) algorithm.

20. The computer-readable storage media of claim 13, wherein the score represents a likelihood of that agent adopting the trend.