Automated creation of semantically-enriched diagnosis models using time series data of temperatures collected by a network of sensors

• US 9,679,248 B2
• Filed: 12/30/2013
• Issued: 06/13/2017
• Est. Priority Date: 12/30/2013
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Lecue, Freddy, Ploennigs, Joern, Schumann, Anika
• Primary Examiner(s): Vincent, David
• Application Number:
  US14/143,840
• Publication Number:
  US 20150186777A1
• Time in Patent Office: 1,261 Days
• Field of Search: 706 12, 706 45, 706 62
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06N 5/025 Extracting rules from data

Abstract

A system, method and a computer program product may be provided for automatically creating and parameterizing a semantically-enriched diagnosis model for an entity. The system receives a list of data points, from sensors or a database, to be used to create a diagnosis model. The system automatically creates the diagnosis model based on the received list of data points and data stored in a database and parameterizes the diagnosis model. The parameterized diagnosis model reflects rules that determine one or more potential causes of one or more abnormalities of one or more physical conditions in the entity.

Claims

1. A method for automatically generating a semantic diagnosis model from a list of data points, the method comprising:

sensing, by using a network of sensors, a time series of temperatures of a room;

receiving, by a computer system, the time series of temperatures from the network of sensors, to be used to create a semantic diagnosis model;

automatically creating, by the computer system, the semantic diagnosis model based on the received time series of temperatures, the automatically created diagnosis model reflecting rules that determine one or more potential causes of one or more abnormalities associated with one or more conditions in the room, including

creating a plurality of models in sequence including said semantic diagnosis model, including creating a semantic data point model comprising the time series of temperatures semantically annotated, creating variables representing physical conditions indicated by the semantically annotated temperatures, generating from the semantic data point model and the created variables a semantic variable model comprising a data representation of the created variables, and using the semantic variable model in the creating said diagnosis model;

determining, by the computer system and based on the received time series of temperatures, that the room has an abnormal temperature; and

determining, by the computer system using the diagnosis model and said rules, one or more potential causes of the abnormal temperature, including mapping one of the created variables to said abnormal temperature, said one of the created variables being positively correlated in the diagnosis model with said abnormal temperature.

2. The method according to claim 1, further comprising:

semantically annotating the time series of temperatures from the network of sensors.

3. The method according to claim 1, wherein the creating variables representing physical conditions includes:

automatically creating semantic variables having values that represent conditions in the room.

4. The method according to claim 1, further comprising:

automatically deriving relationships between the variables.

5. The method according to claim 3, wherein the creating variables representing physical conditions includes:

creating semantic variables that represent normal and abnormal conditions of the room, the created diagnosis model computing the rules based on the created semantic variables.

6. The method according to claim 1, further comprising:

determining a relationship between the created variables and a dependency of the one or more potential causes of the one or more abnormalities associated with the one or more conditions.

7. The method of claim 1, further comprising:

providing and using a database that stores a plurality of pre-determined semantic concepts and rules.

27. The method according to claim 1, further comprising using the semantic diagnosis model to map one of the potential causes to one of the conditions in the system.

8. A method for automatically creating a parameterized, semantic diagnosis model, the method comprising:

sensing, by using a network of sensors, a real-time series of temperatures of a room;

receiving, by a computer system, the real-time time series of temperatures, from the network of sensors, associated with a diagnosis model;

creating, by the computer system, based on the received time series of temperatures, the semantic diagnosis model, including

creating a plurality of models in sequence including said semantic diagnosis model, including creating a semantic data point model comprising the time series of temperatures semantically annotated, creating variables representing physical conditions indicated by the semantically annotated temperatures, generating from the semantic data point model and the created variables a semantic variable model comprising a data representation of the created variables, and using the semantic variable model in the creating said diagnosis model,

parameterizing the diagnosis model, the parameterized diagnosis model mapping one or more potential causes or actual causes to a condition of the room and enabling, based on the mapping, a user or system to identify the one or more potential causes or the actual causes of the condition of the room;

determining, by the computer system and based on the received time series of temperatures, that the room has an abnormal temperature; and

determining, by the computer system using the diagnosis model and said rules, one or more potential causes of the abnormal temperature, including mapping one of the created variables to said abnormal temperature, said one of the created variables being positively correlated in the diagnosis model with said abnormal temperature.

9. The method according to claim 8, wherein the creating the diagnosis model further includes:

analyzing a real-time time series of temperatures to extract parameters of the diagnosis model using statistical or data mining.

10. An apparatus for automatically generating a semantic diagnosis model on a computer system from a list of data points, the apparatus comprising:

a memory device;

a processor coupled to the memory device,

wherein the processor is configured to perform;

receiving a time series of temperatures, from a network of sensors in a room, to be used to create a semantic diagnosis model; and

automatically creating the semantic diagnosis model on the computer system based on the received time series of temperatures, the automatically created diagnosis model reflecting rules that determine one or more potential causes of one or more abnormalities associated with one or more conditions in a system the room, including

creating a plurality of models in sequence including said semantic diagnosis model, including creating a semantic data point model comprising the time series of temperatures semantically annotated, creating variables representing physical conditions indicated by the semantically annotated temperatures, generating from the semantic data point model and the created variables a semantic variable model comprising a data representation of the created variables, and using the semantic variable model in the creating said diagnosis model;

determining, based on the received time series of temperatures, that the room has an abnormal temperature; and

determining, by using the diagnosis model and said rules, one or more potential causes of the abnormal temperature, including mapping one of the created variables to said abnormal temperature, said one of the created variables being positively correlated in the diagnosis model with said abnormal temperature.

11. The apparatus according to claim 10, wherein the processor is configured to perform:

automatically creating semantic variables having values that represent conditions in the room.

12. The apparatus according to claim 10, wherein the processor is configured to perform:

automatically deriving relationships between the variables.

13. The apparatus according to claim 10, wherein the processor is configured to perform:

creating semantic variables that represent normal and abnormal conditions of the room, the created diagnosis model computing the rules based on the created semantic variables.

14. The apparatus according to claim 10, wherein the processor is configured to perform:

determining a relationship between the created semantic variables and a dependency of the one or more potential causes of the one or more abnormalities associated with the one or more conditions.

15. The apparatus of claim 10, wherein the processor is configured to perform:

providing and using a database that stores a plurality of pre-determined semantic concepts and rules.

16. An apparatus for automatically creating a parameterized, semantic diagnosis model on a computer system, the apparatus comprising:

a memory device;

a processor coupled to the memory device,

wherein the processor is configured to perform;

receiving a real-time time series of temperatures, from a network of sensors in a room, associated with a semantic diagnosis model;

creating a plurality of models in sequence including said semantic diagnosis model, including creating a semantic data point model comprising the time series of temperatures semantically annotated, creating variables representing physical conditions indicated by the semantically annotated temperatures, generating from the semantic data point model and the created variables a semantic variable model comprising a data representation of the created variables, and using the semantic variable model in the creating said diagnosis model,

parameterizing the diagnosis model, the parameterized diagnosis model mapping one or more potential causes or actual causes to a condition of the room and enabling, based on the mapping, a user or system to identify the one or more potential causes or the actual causes of the condition of the room;

determining, based on the received time series of temperatures, that the room has an abnormal temperature; and

determining, by using the diagnosis model and said rules, one or more potential causes of the abnormal temperature, including mapping one of the created variables to said abnormal temperature, said one of the created variables being positively correlated in the diagnosis model with said abnormal temperature.

17. The apparatus according to claim 16, wherein the parameterizing the diagnosis model includes:

analyzing a real-time time series of temperatures to extract parameters of the diagnosis model using statistical or data mining.

18. A computer program product for automatically generating a semantic diagnosis model on a computer system from a list of data points, the computer program product comprising a storage medium that excludes a propagating signal, the storage medium readable by a processing circuit and storing instructions run by the processing circuit for performing a method, said method steps comprising:

receiving, by a computer system, a time series of temperatures, from a network of sensors in a room, to be used to create a semantic diagnosis model;

automatically creating, by the computer system, the semantic diagnosis model based on the received time series of temperatures, the automatically created diagnosis model reflecting rules that determine one or more potential causes of one or more abnormalities associated with one or more physical conditions in the room, including

creating a plurality of models in sequence including said semantic diagnosis model, including creating a semantic data point model comprising the time series of temperatures semantically annotated, creating variables representing physical conditions indicated by the semantically annotated temperatures, generating from the semantic data point model and the created variables a semantic variable model comprising a data representation of the created variables, and using the semantic variable model in the creating said diagnosis model;

determining, by the computer system and based on the received time series of temperatures, that the room has an abnormal temperature; and

determining, by the computer system using the diagnosis model and said rules, one or more potential causes of the abnormal temperature, including mapping one of the created variables to said abnormal temperature, said one of the created variables being positively correlated in the diagnosis model with said abnormal temperature.

19. The computer program product according to claim 18, wherein the method steps further comprises:

semantically annotating the time series of temperatures from the network of sensors.

20. The computer program product according to claim 18, wherein the method steps further comprises:

automatically creating semantic variables having values that represent conditions in the room.

21. The computer program product according to claim 18, wherein the method steps further comprises:

automatically deriving relationships between the variables.

22. The computer program product according to claim 18, wherein the creating variables representing physical conditions includes:

creating semantic variables that represent normal and abnormal conditions of the room, the created diagnosis model computing the rules based on the created semantic variables.

23. The computer program product according to claim 18, wherein the method steps further includes:

determining a relationship between the created semantic variables and a dependency of the one or more potential causes of the one or more abnormalities associated with the one or more conditions.

24. The computer program product according to claim 18, further comprising:

providing and using a database that stores a plurality of pre-determined semantic concepts and the rules.

26. The computer program product according to claim 24, wherein the creating the semantic diagnosis model further includes:

analyzing a real-time time series of temperatures to extract parameters of the diagnosis model using statistical or data mining.

25. A computer program product for automatically creating a parameterized, semantic diagnosis model on a computer system, the computer program product comprising a storage medium that excludes a propagating signal, the storage medium readable by a processing circuit and storing instructions run by the processing circuit for performing a method, said method steps comprising:

receiving, by a computer system, a real-time time series of temperatures, from a network of sensors in a room, associated with a semantic diagnosis model;

creating, by the computer system, based on the received real-time series of temperatures, the semantic diagnosis model on the computer system, including

creating a plurality of models in sequence including said semantic diagnosis model, including creating a semantic data point model comprising the time series of temperatures semantically annotated, creating variables representing physical conditions indicated by the semantically annotated temperatures, generating from the semantic data point model and the created variables a semantic variable model comprising a data representation of the created variables, and using the semantic variable model in the creating said diagnosis model,

parameterizing the diagnosis model, the parameterized diagnosis model mapping one or more potential causes or actual causes to a condition of the room and enabling, based on the mapping, a user or system to identify the one or more potential causes or the actual causes of the condition of the room;

determining, by the computer system and based on the received time series of temperatures, that the room has an abnormal temperature; and

determining, by the computer system using the diagnosis model and said rules, one or more potential causes of the abnormal temperature, including mapping one of the created variables to said abnormal temperature, said one of the created variables being positively correlated in the diagnosis model with said abnormal temperature.