Predictive System for Deploying Enterprise Applications
Predictive systems for deploying 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 . A system for predicting a sequence of operations for an enterprise application, the system comprising:
a memory that stores computer instructions for predicting the sequence of operations;
hierarchical temporal memories that store data and predict one or more next operations based on input data transmitted from a user and the stored 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 communicate to the user the predicted one or more next operations that are received from the hierarchical temporal memories.
2 . The system of claim 1 , wherein the hierarchical temporal memories comprise a hierarchy of levels having memory nodes, and wherein the memory nodes receive information from lower levels of memory nodes as inputs.
3 . The system of claim 2 , wherein the memory nodes identify combinations of the inputs often received as causes and store the identified combinations of the inputs in spatial memory.
4 . The system of claim 3 , wherein the 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 , where a stored database of causes and temporal groups can be fed into the hierarchical temporal memories.
6 . The system of claim 4 , wherein the 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 memory nodes at lower levels enter memory nodes at higher levels as inputs.
8 . The system of claim 7 , wherein the 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 data stored at the hierarchical temporal memories is dynamic.
10 . The system of claim 1 , wherein the data stored at the hierarchical temporal memories is associated with learned behaviors of the user.
11 . The system of claim 1 , wherein the hierarchical temporal memories further predict based on a current state and a user's input.
12 . The system of claim 1 , further presenting the one or more next operations to a user as a sequence of steps for monitoring an application.
13 . The system of claim 1 , further presenting the one or more next operations to a user as a sequence of steps for managing an application.
14 . The system of claim 13 , wherein the inputs are associated with one or more of a profile of a user, a department, a company, and an enterprise application.
15 . The system of claim 8 , further presenting the one or more next operations to a user as a sequence of steps for deploying an application.
16 . The system of claim 15 , wherein the hierarchical temporal memories predict based on model topologies.
17 . The system of claim 15 , wherein the hierarchical temporal memories predict based on composite models, further wherein the hierarchical temporal memories comprise a space for temporal patterns and a space for spatial patterns.
18 . The system of claim 15 , wherein the hierarchical temporal memories predict based on composite model components, further wherein the hierarchical temporal memories comprise a space for temporal patterns and a space for spatial patterns.
19 . An enterprise application runtime deployment system for predicting a sequence of operations for deploying an enterprise application, the system comprising:
a memory that stores computer instructions for deploying the sequence of operations;
hierarchical temporal memories that store data and predict one or more next operations based on input data transmitted from a user and the stored 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 deploy the enterprise application in accordance with the predicted one or more next operations that are received from the hierarchical temporal memories.
20 . The system of claim 19 , wherein the hierarchical temporal memories predict based on model topologies.
21 . The system of claim 19 , wherein the hierarchical temporal memories predict based on composite models, further wherein the hierarchical temporal memories comprise a space for temporal patterns and a space for spatial patterns.
22 . The system of claim 19 , wherein the hierarchical temporal memories predict based on composite model components, further wherein the hierarchical temporal memories comprise a space for temporal patterns and a space for spatial patterns.
23 . A method for predicting a sequence of operations of an enterprise application, the method comprising:
converting behavior associated with enterprise applications to data representative of the behavior;
storing the data representative of the behavior of hierarchical temporal memories; and
predicting one or more next operations based on input data transmitted from a user and the data stored at the hierarchical temporal memories.
24 . The method of claim 23 , wherein the hierarchical temporal memories comprise a hierarchy of levels having memory nodes, and wherein the memory nodes receive information from lower levels of memory nodes as inputs.
25 . The method of claim 24 , wherein the memory nodes identify combinations of the inputs often received as causes and store the identified combinations of the inputs in spatial memory.
26 . The method of claim 25 , wherein the 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.
27 . The method of claim 26 , where a stored database of causes and temporal groups can be fed into the hierarchical temporal memories.
28 . The method of claim 26 , 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.
29 . The method of claim 28 , wherein beliefs output from memory nodes at lower levels enter memory nodes at higher levels as inputs.
30 . The method of claim 29 , 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.
31 . The method of claim 23 , wherein the data stored at the hierarchical temporal memories is dynamic.
32 . The method of claim 23 , wherein the data stored at the hierarchical temporal memories is associated with learned behaviors of the user.
33 . The method of claim 23 , wherein the predicting is further based on a current state and a user's input.
34 . The method of claim 23 , further comprising presenting the one or more next operations to a user as a sequence of steps for managing an application.
35 . The method of claim 23 , further comprising presenting the one or more next operations to a user as a sequence of steps for monitoring an application.
36 . The method of claim 35 , wherein data representative of the behavior comprises one or more of behavior associated with a profile of a user, a department, a company, and an enterprise application.
37 . The method of claim 30 , further comprising presenting the one or more next operations to a user as a sequence of steps for deploying an application.
38 . The method of claim 37 , wherein the hierarchical temporal memories predict based on model topologies.
39 . The method of claim 37 , wherein the hierarchical temporal memories predict based on composite models, further wherein the hierarchical temporal memories comprise a space for temporal patterns and a space for spatial patterns.
40 . The method of claim 37 , wherein the hierarchical temporal memories predict based on composite model components, further wherein the hierarchical temporal memories comprise a space for temporal patterns and a space for spatial patterns.