Reasoning engine services

• US 10,255,552 B2
• Filed: 11/15/2016
• Issued: 04/09/2019
• Est. Priority Date: 03/22/2011
• Status: Active Grant

• Current Assignee: Nant Holdings IP, LLC (NantWorks, LLC)
• Original Assignee: Patrick Soon-Shiong
• Inventors: Soon-Shiong, Patrick
• Primary Examiner(s): Hill, Stanley K.
• Application Number:
  US15/352,532
• Publication Number:
  US 20170061303A1
• Time in Patent Office: 875 Days
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/041 Abduction
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06T 9/00 Image coding bandwidth or redundancy reduction for static pictures H04N1/41; coding or decoding of static colour picture signals H04N1/64; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00
• CPC Class Codes: G06V 20/00 Scenes; Scene-specific elements control of digital cameras H04N23/60
• CPC Class Codes: G16H 20/00 ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A reasoning engine is disclosed. Contemplated reasoning engines acquire data relating to one or more aspects of various environments. Inference engines within the reasoning engines review the acquire data, historical or current, to generate one or more hypotheses about how the aspects of the environments might be correlated, if at all. The reasoning engine can attempt to validate the hypotheses through controlling acquisition of the environment data.

Claims

1. A medical computer-based cognitive inference engine comprising:

an inquiry interface configured to receive an inquiry over a network;

a medical knowledge database configured to store medical data objects, wherein each one of the medical data objects has data object attributes; and

at least one server coupled with the inquiry interface and that is, upon execution of software instructions stored in a non-transitory computer readable memory by at least one processor, configurable to;

receive, via the inquiry interface, the inquiry, wherein the inquiry relates to at least one patient;

search the medical knowledge database to satisfy at least a portion of the inquiry, wherein the search identifies medical data objects related to the inquiry;

select one or more reasoning rules sets from a plurality of reasoning rules sets as a function of data object attributes of the medical data objects related to the inquiry;

generate a plurality of hypotheses comprising at least one of a recommended change to a treatment protocol or a likely response to a treatment protocol for the at least one patient by (1) applying the one or more reasoning rule sets to the data object attributes of the medical data objects related to the inquiry, and (2) determining correlations among the medical data objects related to the inquiry, wherein applying the one or more reasoning rule sets comprises mapping the data object attributes to a namespace related to known medical concepts, and weighting the mapped data object attributes based on medical reasoning criteria;

assign merit scores for the plurality of hypotheses that account for one or more aspects of the data object attributes related to the inquiry and the one or more reasoning rule sets, wherein each merit score comprises a measure of validity of a hypothesis of the plurality of hypotheses; and

rank at least some of the plurality of hypotheses by comparing at least some of the merit scores, wherein the at least some of the plurality of hypotheses are configured to be presented on a display of a computing device according to the ranking.

2. The engine of claim 1, wherein the network comprises at least one of the Internet and a wireless network.

3. The engine of claim 1, wherein one or more reasoning rule sets comprise inference chaining rules.

4. The engine of claim 3, wherein inference chaining rules comprise forward chaining reasoning.

5. The engine of claim 4, wherein inference chaining rules comprise backward chaining reasoning.

6. The engine of claim 1, wherein the inquiry comprises at least one of text data, audio data, image data, video data, and sensor data.

7. The engine of claim 1, wherein the at least one server comprises a cloud-based service.

8. The engine of claim 1, wherein the plurality of hypotheses includes at least one hypothesis that the at least one patient belongs to a group that responds to the treatment protocol.

9. The engine of claim 1, wherein at least one of the plurality of hypotheses includes a recommended treatment.

10. The engine of claim 9, wherein the recommended treatment includes at least one of a surgery, a prescription, a chemotherapy, a blood analysis, and a family history review.

11. The engine of claim 1, wherein the server is further configurable to request, via the inquiry interface, updated data associated with the plurality of hypotheses and according to a validation plan.

12. The engine of claim 1, wherein the server is further configurable to change the merit scores as a function of updates to the related medical data objects.

13. The engine of claim 1, wherein the server is further configurable to change the plurality of hypotheses as a function of updates to the medical data objects related to the inquiry.

14. The engine of claim 1, wherein the inquiry interface comprises a mobile device interface.

15. The engine of claim 14, wherein the mobile device interface comprises at least one of a mobile phone, a portable computer, and a computing tablet.

16. The engine of claim 1, wherein the inquiry interface is configured to support an application program interface.

17. The engine of claim 1, wherein the medical data objects related to the inquiry include at least one of experimental data, biometric data, medical data, genomic data, identity data, demographic data, and sensor data.

18. The engine of claim 1, wherein the medical data objects related to the inquiry comprise an observed change in an observed medical characteristic.

19. The engine of claim 18, wherein the observed medical characteristic includes at least one of a pressure point, an airway patency, a respiration, a blood pressure, a perspiration, a body fluid, and a perfusion.

20. The engine of claim 1, wherein the data object attributes adhere to at least one namespace.

21. The engine of claim 20, wherein the data object attributes adhere to at least two namespaces.

22. The engine of claim 20, wherein the at least one namespace comprises an ontology.

23. The engine of claim 1, wherein the presentation includes reasons or additional information supporting at least one hypothesis of the plurality of hypotheses.

24. The engine of claim 23, wherein the reasons include a type of reasoning or reason steps supporting the at least one hypothesis.

25. The engine of claim 24, wherein the type of reasoning includes at least one of deductive reasoning, adductive reasoning, inductive reasoning, amplitative reasoning, case-based reasoning, metaphorical mapping, forward chaining reasoning, backward chaining reasoning, analogical reasoning, cause-and-effect reasoning, defeasible or indefeasible reasoning, comparative reasoning, conditional reasoning, decompositional reasoning, exemplar reasoning, modal logic, set-base reasoning, systemic reasoning, syllogistic reasoning, probabilistic reasoning, and paraconsistent reasoning.

26. The engine of claim 1, wherein the presentation comprises a web page within a browser operating on the computing device.

27. The engine of claim 1, wherein the presentation changes in time as a function of changes in merit scores.

28. The engine of claim 1, wherein each one of the merit scores comprises at least one value.

29. The engine of claim 28, wherein the at least one value represents a relevance to a medical diagnosis.

30. The engine of claim 1, wherein each one of the merit scores represents a confidence that a corresponding hypothesis is valid.

31. The engine of claim 1, wherein the medical data objects related to the inquiry comprise treatments and outcomes from treatments.

32. The engine of claim 31, wherein the outcomes from treatments include at least one of a positive outcome from a treatment and a negative outcome from a treatment.

33. The engine of claim 1 wherein the server generates the plurality of hypotheses in real-time relative to changes in the medical data objects related to the inquiry.