AU2017200094B2

AU2017200094B2 - Systems of computerized agents and user-directed semantic networking

Info

Publication number: AU2017200094B2
Application number: AU2017200094A
Authority: AU
Inventors: Peter Joseph Sweeney
Original assignee: Primal Fusion Inc
Current assignee: Primal Fusion Inc
Priority date: 2010-06-22
Filing date: 2017-01-06
Publication date: 2018-10-25
Anticipated expiration: 2031-06-22
Also published as: CA2802887A1; JP5921536B2; WO2011160205A1; CA2802887C; IL223540A; JP2013536484A; AU2011269676A1; AU2017200094A1; AU2011269676B2

Abstract

A system, method and computer program product in which semi-autonomous agents interact with a semantic network. In a basic embodiment of the system, a data structure providing a semantic network is provided in a non-transitory, computer-readable medium 5 within a computer network. A plurality of computer-implemented agents are deployed within the computer network and interactive with the semantic network. A user interface is provided and configured to permit a user to create and/or modify the semantic network. The agents are configured to read and modify the semantic network without receiving explicit instructions from a user after their initial deployment, whereby the 10 agents operate as assistants to support the user's use of the network.

Description

The invention is limited only as defined by the following claims and the equivalents thereto.

8845390_1

2017200094 16 Mar 2017

Claims

CLAIMS:

1. A system employing a semantic network, the system comprising:

in a non-transitory, computer-readable medium within a computer network, a data 5 structure providing a semantic network including a representation of knowledge with edges representing semantic relations;

a plurality of computer-implemented agents deployed within said computer network, executing on one or more processors within the computer network, wherein the plurality of agents is configured to interact with the semantic network;

10 a user interface configured to permit at least a first user of a plurality of users to at least one of create or modify the semantic network by at least one of adding or deleting at least one of vertices or the edges from the semantic network, resulting in the semantic network being configured by the at least first user;

wherein, after initial deployment of the plurality of agents, the plurality of agents

15 is configured to read and modify the semantic network without receiving explicit instructions, the plurality of agents comprising:

a first agent configured to:

monitor behavior of at least one of the at least first user and/or a second user; and modify the semantic network based on the behavior of the at least one of the at

20 least first user and/or the second user; and a second agent configured to:

provide at least one content item based at least in part on the semantic network after being modified by at least one of the first agent and/or the at least first user.
2. The system of claim 1, wherein the second agent is configured to determine that

25 the at least one content item is likely to be of interest to the at least first user.

2017200094 16 Mar 2017
3. The system of claim 2, wherein the second agent is configured to extract at least one keyword and/or signature from the at least one content item, and determine that the at least one content item is likely to be of interest to the at least first user based at least in part on the semantic network and the at least one keyword and/or signature.

5 4. The system of any one of the preceding claims, wherein at least one of the plurality of agents is configured to notify the at least first user of the providing of the at least one content item.

5. The system of claim 4, wherein at least one of the plurality of agents is configured to determine whether the at least one content item was of interest to the at

10 least first user based on behavior of the at least first user after the notification.

6. The system of claim 5, wherein the at least one of the plurality of agents is further configured to modify the semantic network based on whether the at least one content item was determined to be of interest to the at least first user.

7. The system of claim 6, wherein modifying the semantic network based on 15 whether the at least one content item was determined to be of interest to the at least first user comprises adding or deleting at least one of nodes or the edges from the semantic network based on contents and/or attributes extracted from the at least one content item.

8. The system of claim 7, wherein the second agent is configured to retrieve at least one additional content item after the modifying the semantic network based on whether

20 the at least one content item was determined to be of interest to the at least first user.

9. The system of any one of the preceding claims, wherein the second agent is configured to retrieve the at least one content item without receiving explicit instructions from the at least first user.

10. The system of any one of the preceding claims, wherein the behavior of the at 25 least one of the at least first user and/or the second user comprises at least one of: a search query, selection of a search result, and/or viewing a content item.

11. The system of any one of the preceding claims, wherein the content items are retrieved from at least one of a local content source and/or a remote content source.

8845390_1

2017200094 16 Mar 2017

12. The system of any one of the preceding claims, wherein the at least one content items comprises at least one of a document, a collection of documents, an advertisement, text, music, images, and/or webpages.

13. The system of any one of the preceding claims, wherein the semantic network 5 includes at least two nodes that each represent a distinct concept and at least one edge that represents a semantic relationship between two distinct concepts.

14. A method comprising:

providing a semantic network in a non-transitory, computer-readable medium within a computer network, wherein the semantic network includes a representation of

10 knowledge with edges representing semantic relations;

providing a plurality of computer-implemented agents deployed within said computer network and configured to interact with the semantic network, the agents being configured, collectively, to read and modify the semantic network without receiving explicit instructions; and

15 providing a user interface configured to permit at least a first user of a plurality of users to at least one of create and/or modify the semantic network by at least one of adding or deleting at least one of vertices or the edges from the semantic network, resulting in the semantic network being configured by the at least first user;

wherein a first agent of the plurality of computer-implemented agents is

20 configured to:

monitor behavior of at least one of the at least first user and/or a second user; and modify the semantic network based on the behavior of the at least one of the at least first user and/or the second user, and wherein a second agent of the plurality of computer-implemented agents is

25 configured to:

provide at least one content item based at least in part on the semantic network after being modified by at least one of the first agent and/or the at least first user.

8845390_1

2017200094 16 Mar 2017

15. The method of claim 14, further comprising notifying the at least first user of the providing of the at least one content item.

16. The method of claim 15, further comprising determining whether the at least one content item was of interest to the at least first user based on behavior of the at least first

5 user after the notification.

17. The method of claim 16, further comprising modifying the semantic network by adding or deleting at least one of nodes or the edges from the semantic network based on contents and/or attributes extracted from the at least one content item.

18. The method of claim 17, further comprising retrieving at least one additional 10 content item after the modifying the semantic network based on whether the at least one content item was determined to be of interest to the at least first user.

19. At least one non-transitory computer-readable medium encoded with a plurality of computer-executable instructions that includes:

a semantic network module configured to provide a data structure that includes a 15 semantic network, the semantic network including a representation of knowledge with edges representing semantic relations;

an agent-interface module configured to allow interaction between a plurality of computer-implemented agents and the semantic network; and a user-editing module configured to permit, through a user interface, modification 20 of the semantic network by a first user of a plurality of users, the modification comprising at least one of adding or deleting at least one of vertices or the edges from the semantic network, resulting in the semantic network being configured by the first user;

wherein a first agent of the plurality of computer-implemented agents is configured to:

25 monitor behavior of at least one of the at least first user and/or a second user; and modify the semantic network based on the behavior of the at least one of the at least first user and/or the second user, and

8845390_1

2017200094 16 Mar 2017 wherein a second agent of the plurality of computer-implemented agents is configured to:

provide at least one content item based at least in part on the semantic network after being modified by at least one of the first agent and/or the at least first user.

8845390_1

WO 2011/160205

PCT/CA2011/000719

2017200094 06 Jan 2017

1/20

Editor/

Interface

Semantic ► Network Builcer

i............................................7' i j 30

0 0 (I ' 0 'o

0 ' ti χ·-.

Agent

50i j Agent I 50₂

Agent

50_N

FIG. 1

WO 2011/160205

PCT/CA2011/000719

2017200094 06 Jan 2017

2/20

FIG. 2

WO 2011/160205

PCT/CA2011/000719

2017200094 06 Jan 2017

3/20

FIG. 3

WO 2011/160205

PCT/CA2011/000719

2017200094 06 Jan 2017

WO 2011/160205

PCT/CA2011/000719

5/20

2017200094 06 Jan 2017

Connectors iff

FIG. 5

WO 2011/160205

PCT/CA2011/000719

6/20

2017200094 06 Jan 2017

Volatile Memory _r

Non-Volatile

Memory

Executable

Instructions

1102 1101 z'

Processing Unit

1105

X

Storage

Data Sets

1106

FIG. 6 yHOO

S'

1110

Network Interface

Communication

Network

1120

WO 2011/160205

PCT/CA2011/000719

2017200094 06 Jan 2017

7/20

SUBSTITUTE SHEET (RULE 26)

WO 2011/160205

PCT/CA2011/000719

8/20

2017200094 06 Jan 2017

ILLUSTRATIVE RELATION CAR

h Honda Civic Red 1800 500 t₂ Honda Odyssey Blue 1500 300 ^3 Jeep Liberty Black 5200 700 h Jeep Wrangler Red 5000 600 Ford Focus Black 5100 600 t₆ Ford Mustang White 1700 400

FIG. 8

WO 2011/160205

PCT/CA2011/000719

2017200094 06 Jan 2017

9/20

FIG. 9

SUBSTITUTE SHEET (RULE 26)

WO 2011/160205

PCT/CA2011/000719

10/20

2017200094 06 Jan 2017

ILLUSTRATIVE SCOPES OBTAINED FROM RELATION CAR

Rj; Select* from R where Make=‘Honda’ /' --- - v \

R< Select from R where Make- Ford' R,i h--J... Λ ;R R₃: Select^5: from R where Colors‘Red VA h VY XYt-\ X

R₄: Select * from R where Color-‘Black' X”'’ χ V X A X R₅: Select from R where Price > 2000 ³\ ί t4 J \..X- -^Jj Re: Select * from R where Price < 2000 -FIG. 10

WO 2011/160205

PCT/CA2011/000719

2017200094 06 Jan 2017

11/20

ILLUSTRATIVE SCOPE COMPARATORS fl,2 /7 (ti.Price <t2.Price) return 1 else if (ti. Price > t2. Price) return -1 else return ίδ,β if (te.Color = 'Red’^Λ t6.Color = ‘Blue’) return 1 e/se//(t6.Make = ‘Ford’) return -1 else return -¹-

FIG.

SUBSTITUTE SHEET (RULE 26)

WO 2011/160205

PCT/CA2011/000719

12/20

2017200094 06 Jan 2017

CONJOINT PREFERENCES EXAMPLE

Color

Red Blue Honda 1 3 Toyota 2 4

Make-Color preferences

Price

<=2000 >2000 Honda 1 3 Toyota 2 4

Make-Price preferences

Color

Red (50) Blue (35} Honda (40] 1 (90) 3 (75) Toyota (30) 2 (SO) 4 (55)

Make-Color utilities

Price

<=2000 >2000 (30) (10) Honda (40) 1 (70) 3 (50) Toyota (30) 2 (60) 4 (40)

Make-Price utilities

FIG. 12

WO 2011/160205

PCT/CA2011/000719

13/20

2017200094 06 Jan 2017

ILLUSTRATIVE MAPPING OF A PARTIAL ORDER TO LINEAR EXTENSIONS

FIG. 13 (A ·Λ./.) Ά <A -/2-/4 ·//>

WO 2011/160205

PCT/CA2011/000719

2017200094 06 Jan 2017

14/20

ILLUSTRATIVE REFERENCE GRAPH

FIG. 14

SUBSTITUTE SHEET (RULE 26)

WO 2011/160205

PCT/CA2011/000719

2017200094 06 Jan 2017

15/20

Prioritized Comparators f

ILLUSTRATIVE COMPUTATION OF EDGE WEIGHTS FOR DIFFERENT TYPES OF SECOND-ORDER PREFERENCES

Partial Order

FIG. 15

SUBSTITUTE SHEET (RULE 26)

WO 2011/160205

PCT/CA2011/000719

16/20

2017200094 06 Jan 2017

ILLUSTRATIVE PAGERANK-BASED MATRIX FOR PRIORITIZED COMPARATORS

/ V. ' ί ί J ¹ 0 0 0.25 0 0.25 0 / *>t \ il /-1 1/6 ‘Λ 0 0 0.25 0 0.25 0.5 Y: 1/6 I .i = a 0 0 0 0 0 0 £ + (1- a) 1/6 V i 4 0.5 1.0 0.25 1.0 0.25 0.5 n 1/6 Is 0 0 0 0 0 0 h 1/6 I ) 0.5 0 0.25 0 0.25 0 , c/e J 1/6

FIG. 16

WO 2011/160205

PCT/CA2011/000719

17/20

2017200094 06 Jan 2017

ILLUSTRATIVE WEIGHTED PREFRENCE GRAPH AND DERIVED TOURNAMENTS ⁴ 1.0 ’ _A ’ t₂^ θ'-S -0.4 if

T,: 0.09 i T,: 0.21

T,: 0.06
4· r₄: 0.14 u·T<. o.os t,

T,:0.21

T₇: 0.06

17:0,14

FIG. 17

WO 2011/160205

PCT/CA2011/000719

18/20

2017200094 06 Jan 2017

ILLUSTRATIVE PROCESS FOR INTERACTIVE PREFERENCE SPECIFICATION

FIG. 18

WO 2011/160205

PCT/CA2011/000719

2017200094 06 Jan 2017

19/20

Primal’s AKRM Technology

Reference corpora

Knowledge Generation f·'·*³!· : ' ^: Rules s/S:

Sample complex semantics

FIG. 19

WO 2011/160205

PCT/CA2011/000719

20/20

2017200094 06 Jan 2017 fb-i'-j’s Τ;·,Ή -'logy

.............................. Λ

Reference corpora

Complex uQcabul*rs&s

Sample complex semantics i

Sitnpie ' /j-J 'CH ' sP'l,

Context/qucry ______________irpm end-user s/apps

/) ·”*♦> n,_Fuc complex

Sample complex semanoc *»

FIG. 20