Predictive system for designing enterprise applications
Predictive systems for designing enterprise applications include memory structures that output predictions to a user. The predictive system may include an HTM structure that comprises a tree-shaped hierarchy of memory nodes, wherein each memory node has a learning and memory function, and is hierarchical in space and time that allows them to efficiently model the structure of the world. The memory nodes learn causes, predicts with probability values, and form beliefs based on the input data, where the learning algorithm stores likely sequence of patterns in the nodes. By combining memory of likely sequences with current input data, the nodes may predict the next event. The predictive system may employ an HHMM structure comprising states, wherein each state is itself an HHMM. The states of the HHMM generate sequences of observation symbols for making predictions.
1. An enterprise application design system for predicting a sequence of operations for designing an enterprise application, the system comprising:
a memory that stores computer instructions for designing or predicting the sequence of operations;
hierarchical temporal memories configured to:
store modeling data related to models of previously designed enterprise applications;
receive input data related to designing the enterprise application; and
predict one or more next operations based on the input data and the modeling data; and
a processor in communication with the memory and with the hierarchical temporal memories, the processor operable to execute the computer instructions and to design the enterprise application in accordance with the predicted one or more next operations.
2. The system of claim 1 , wherein the hierarchical temporal memories comprise a hierarchy of levels each comprising one or more memory nodes, wherein higher level memory nodes receive information from lower level memory nodes as inputs.
3. The system of claim 2 , wherein the one or more memory nodes identify combinations of the inputs received as causes and store the identified combinations of the inputs in spatial memory.
4. The system of claim 3 , wherein the one or more memory nodes further identify sequential combinations of the inputs often received as temporal groups and store the identified sequential combinations of the inputs in temporal memory.
5. The system of claim 4 , wherein a stored database of causes and temporal groups is received by the hierarchical temporal memories.
6. The system of claim 4 , wherein the one or more memory nodes generate probability information as beliefs that one or more of the inputs are associated with one or more of the causes and with one or more of the temporal groups.
7. The system of claim 6 , wherein beliefs output from lower level memory nodes enter higher level memory nodes as inputs.
8. The system of claim 7 , wherein the one or more memory nodes output a pre-specified number of beliefs based on the probability information, wherein the pre-specified number of beliefs comprises causes and temporal groups with the highest probabilities at a highest level of the temporal hierarchical memories.
9. The system of claim 1 , wherein the modeling data or the input data is associated with one or more of a task and a link used for creating a business process.
10. The system of claim 1 , wherein the hierarchical temporal memories predict based on topology patterns.
11. The system of claim 1 , wherein the hierarchical temporal memories predict based on process patterns or process component patterns, further wherein the hierarchical temporal memories comprise a space for temporal patterns and a space for spatial patterns.
12. The system of claim 1 , wherein the modeling data stored at the hierarchical temporal memories is dynamic.
13. The system of claim 1 , wherein the modeling data stored at the hierarchical temporal memories is associated with learned behaviors.
14. The system of claim 1 , wherein the hierarchical temporal memories further predict based on a current state.
15. A method for predicting a sequence of operations of an enterprise application design system, the method comprising:
storing, in a memory, computer instructions for predicting the sequence of operations;
storing, in one or more hierarchical temporal memories, modeling data related to models of previously designed enterprise applications;
receiving, at the one or more hierarchical temporal memories, input data related to an enterprise application; and
predicting one or more next operations based on the input data and the modeling data.
16. The method of claim 15 , wherein the hierarchical temporal memories comprise a hierarchy of levels each comprising one or more memory nodes, wherein higher level memory nodes receive information from lower level memory nodes as inputs.
17. The method of claim 16 , wherein the one or more memory nodes identify combinations of the inputs received as causes and store the identified combinations of the inputs in spatial memory.
18. The method of claim 17 , wherein the one or more memory nodes further identify sequential combinations of the inputs received as temporal groups and store the identified sequential combinations of the inputs in temporal memory.
19. The method of claim 18 , wherein a stored database of causes and temporal groups is received by the hierarchical temporal memories.
20. The method of claim 18 , further comprising:
generating probability information as beliefs that one or more of the inputs are associated with one or more of the causes and with one or more of the temporal groups.
21. The method of claim 20 , wherein beliefs output from lower level memory nodes enter higher level memory nodes as inputs.
22. The method of claim 21 , further comprising outputting a pre-specified number of beliefs based on the probability information,
wherein the pre-specified number of beliefs comprises causes and temporal groups with the highest probabilities at a highest level of the temporal hierarchical memories.
23. The method of claim 15 , wherein the input data or the modeling data comprises one or more of behavior associated with a task and a link used for creating a business process.
24. The method of claim 15 , wherein the hierarchical temporal memories predict based on topology patterns.
25. The method of claim 15 , wherein the hierarchical temporal memories predict based on process patterns or process component patterns, further wherein the hierarchical temporal memories comprise a space for temporal patterns and a space for spatial patterns.
26. The method of claim 15 , wherein the modeling data stored at the hierarchical temporal memories is dynamic.
27. The method of claim 15 , wherein the modeling data stored at the hierarchical temporal memories is associated with learned behaviors.
28. The method of claim 15 , wherein the predicting is further based on a current state.
29. The system of claim 1 , wherein the modeling data comprises data related to models of previously deployed enterprise applications or data related to components of the models of the previously deployed enterprise applications.
30. The method of claim 15 , wherein the modeling data comprises data related to models of previously deployed enterprise applications or data related to components of the models of the previously deployed enterprise applications.
31. The system of claim 1 , wherein the hierarchical temporal memories predict based on at least one of model topologies, composite models, and composite model components.
32. The system of claim 1 , wherein the hierarchical temporal memories comprise at least one of a space for temporal patterns and a space for spatial patterns.
33. The system of claim 1 , wherein storing the modeling data further comprises storing modeling data related to models of previously deployed enterprise applications, wherein receiving the input data further comprises receiving input data related to deploying the enterprise application, and wherein the processor is further operable to deploy the enterprise application in accordance with the predicted one or more next operations.
34. The method of claim 15 , wherein the hierarchical temporal memories predict based on at least one of model topologies, composite models, and composite model components.
35. The method of claim 15 , wherein the hierarchical temporal memories comprise a space for temporal patterns and a space for spatial patterns.
36. The method of claim 15 , wherein storing the modeling data further comprises storing modeling data related to models of previously deployed enterprise applications.