US20120158633A1 - Knowledge graph based search system - Google Patents

Knowledge graph based search system Download PDF

Info

Publication number
US20120158633A1
US20120158633A1 US13/404,109 US201213404109A US2012158633A1 US 20120158633 A1 US20120158633 A1 US 20120158633A1 US 201213404109 A US201213404109 A US 201213404109A US 2012158633 A1 US2012158633 A1 US 2012158633A1
Authority
US
United States
Prior art keywords
entity
data
table
context
software
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US13/404,109
Inventor
Jeffrey Scott Eder
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Square Halt Solutions LLC
Original Assignee
Asset Reliance Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to US43228302P priority Critical
Priority to US46483703P priority
Priority to US10/717,026 priority patent/US7401057B2/en
Priority to US56661404P priority
Priority to US11/094,171 priority patent/US7730063B2/en
Priority to US12/497,656 priority patent/US20090271342A1/en
Priority to US13/404,109 priority patent/US20120158633A1/en
Application filed by Asset Reliance Inc filed Critical Asset Reliance Inc
Assigned to ASSET RELIANCE, INC. reassignment ASSET RELIANCE, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: EDER, JEFF
Publication of US20120158633A1 publication Critical patent/US20120158633A1/en
Assigned to SQUARE HALT SOLUTIONS, LIMITED LIABILITY COMPANY reassignment SQUARE HALT SOLUTIONS, LIMITED LIABILITY COMPANY ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: ASSET RELIANCE, INC. DBA ASSET TRUST, INC.
Assigned to ASSET RELIANCE, INC. DBA ASSET TRUST, INC. reassignment ASSET RELIANCE, INC. DBA ASSET TRUST, INC. NUNC PRO TUNC ASSIGNMENT (SEE DOCUMENT FOR DETAILS). Assignors: EDER, JEFFREY SCOTT
Application status is Abandoned legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computer systems using knowledge-based models
    • G06N5/02Knowledge representation
    • G06N5/022Knowledge engineering; Knowledge acquisition
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H15/00ICT specially adapted for medical reports, e.g. generation or transmission thereof
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders

Abstract

Methods, computer program products and systems for developing and implementing a Knowledge Based Search System for an entity. Entity related data are analyzed as required to develop an entity knowledge and one or more knowledge graphs. The knowledge graphs are used to support the retrieval of relevant search results.

Description

    CONTINUATION, RELATED PROVISIONAL APPLICATIONS AND PATENT APPLICATIONS
  • This application is a continuation of U.S. patent application Ser. No. 12/497,656 filed Mar. 31, 2005 the disclosure of which is incorporated herein by reference. application Ser. No. 12/497,656 is a continuation of U.S. patent application Ser. No. 11/094,171 filed Mar. 31, 2005 which matured into U.S. Pat. No. 7,730,063 the disclosures of which are both incorporated herein by reference. application Ser. No. 11/094,171 was a continuation in part of U.S. patent application Ser. No. 10/717,026 which matured into U.S. Pat. No. 7,401,057 and a non provisional application of U.S. Provisional Patent Application No. 60/566,614 filed on Apr. 29, 2004 the disclosures of which are all also incorporated herein by reference. application Ser. No. 10/717,026 claimed priority from provisional application No. 60/432,283 filed on Dec. 10, 2002 and provisional application No. 60/464,837 filed on Apr. 23, 2003 the disclosures of which are both also incorporated herein by reference. This application is also related to U.S. Pat. No. 5,615,109 issued Mar. 25, 1997, U.S. Pat. No. 6,321,205 issued Nov. 20, 2001, U.S. Pat. No. 7,523,065 issued Apr. 21, 2009, U.S. Pat. No. 7,970,640 issued Jun. 28, 2011, U.S. patent application Ser. No. 10/237,021 filed Sep. 9, 2002, U.S. patent application Ser. No. 11/262,146 filed Oct. 28, 2005, U.S. patent application Ser. No. 12/114,784 filed May 4, 2008, U.S. patent application Ser. No. 12/370,574 filed Feb. 12, 2009, U.S. patent Ser. No. 12/684,954 filed Jan. 10, 2010, U.S. patent application Ser. No. 12/910,829 filed Oct. 24, 2010 and U.S. patent application Ser. No. 13/300,605 filed Nov. 20, 2011 the disclosures of which are all incorporated herein by reference.
  • BACKGROUND OF THE INVENTION
  • This invention relates to methods, program storage devices and systems for developing a Personalized Medicine Service (100) for an individual or group of individuals that can support the operation, customization and coordination of computer systems, software, products, services, data, entities and/or devices.
  • SUMMARY OF THE INVENTION
  • It is a general object of the present invention to provide a novel, useful system that develops and maintains one or more individual and/or group contexts in a systematic fashion and uses the one or more contexts to develop a Personalized Medicine Service (100) that supports the operation and coordination of software including a Complete Context™ Suite of services (625), a Complete Context™ Development System (610) and a plurality of Complete Context™ Bots (650), one or more external services (9), one or more narrow systems (4), entities and/or one or more devices (3).
  • The innovative system of the present invention supports the development and integration of any combination of data, information and knowledge from systems that analyze, monitor, support and/or are associated with entities in three distinct areas: a social environment area (1000), a natural environment area (2000) and a physical environment area (3000). Each of these three areas can be further subdivided into domains. Each domain can in turn be divided into a hierarchy or group. Each member of a hierarchy or group is a type of entity.
  • The social environment area (1000) includes a political domain hierarchy (1100), a habitat domain hierarchy (1200), an intangibles domain group (1300), an interpersonal domain group (1400), a market domain hierarchy (1500) and an organization domain hierarchy (1600). The political domain hierarchy (1100) includes a voter entity type (1101), a precinct entity type (1102), a caucus entity type (1103), a city entity type (1104), a county entity type (1105), a state/province entity type (1106), a regional entity type (1107), a national entity type (1108), a multi-national entity type (1109) and a global entity type (1110). The habitat domain hierarchy includes a household entity type (1202), a neighborhood entity type (1203), a community entity type (1204), a city entity type (1205) and a region entity type (1206). The intangibles domain group (1300) includes a brand entity type (1301), an expectations entity type (1302), an ideas entity type (1303), an ideology entity type (1304), a knowledge entity type (1305), a law entity type (1306), a intangible asset entity type (1307), a right entity type (1308), a relationship entity type (1309), a service entity type (1310) and a securities entity type (1311). The interpersonal group includes (1400) includes an individual entity type (1401), a nuclear family entity type (1402), an extended family entity type (1403), a clan entity type (1404), an ethnic group entity type (1405), a neighbors entity type (1406) and a friends entity type (1407). The market domain hierarchy (1500) includes a multi entity type organization entity type (1502), an industry entity type (1503), a market entity type (1504) and an economy entity type (1505). The organization domain hierarchy (1600) includes team entity type (1602), a group entity type (1603), a department entity type (1604), a division entity type (1605), a company entity type (1606) and an organization entity type (1607). These relationships are summarized in Table 1.
  • TABLE 1 Social Environment Domains Members (lowest level to highest for hierarchies) Political voter (1101), precinct (1102), caucus (1103), city (1100) (1104), county (1105), state/province (1106), regional (1107), national (1108), multi-national (1109), global (1110) Habitat household (1202), neighborhood (1203), community (1200) (1204), city (1205), region (1206) Intangibles brand (1301), expectations (1302), ideas (1303), Group (1300) ideology (1304), knowledge (1305), law (1306), intangible assets (1307), right (1308), relationship (1309), service (1310), securities (1311) Interpersonal individual (1401), nuclear family (1402), extended Group (1400) family (1403), clan (1404), ethnic group (1405), neighbors (1406), friends (1407) Market (1500) multi-entity organization (1502), industry (1503), market (1504), economy (1505) Organization team (1602), group (1603), department (1604), (1600) division (1605), company (1606), organization (1607)
  • The natural environment area (2000) includes a biology domain hierarchy (2100), a cellular domain hierarchy (2200), an organism domain hierarchy (2300) and a protein domain hierarchy (2400) as shown in Table 2. The biology domain hierarchy (2100) contains a species entity type (2101), a genus entity type (2102), a family entity type (2103), an order entity type (2104), a class entity type (2105), a phylum entity type (2106) and a kingdom entity type (2107). The cellular domain hierarchy (2200) includes a macromolecular complexes entity type (2202), a protein entity type (2203), a rna entity type (2204), a dna entity type (2205), an x-ylation** entity type (2206), an organelles entity type (2207) and cells entity type (2208). The organism domain hierarchy (2300) contains a structures entity type (2301), an organs entity type (2302), a systems entity type (2303) and an organism entity type (2304). The protein domain hierarchy contains a monomer entity type (2400), a dimer entity type (2401), a large oligomer entity type (2402), an aggregate entity type (2403) and a particle entity type (2404). These relationships are summarized in Table 2.
  • TABLE 2 Natural Environment Domains Members (lowest level to highest for hierarchies) Biology (2100) species (2101), genus (2102), family (2103), order (2104), class (2105), phylum (2106), kingdom (2107) Cellular* (2200) macromolecular complexes (2202), protein (2203), rna (2204), dna (2205), x-ylation** (2206), organelles (2207), cells (2208) Organism (2300) structures (2301), organs (2302), systems (2303), organism (2304) Protein (2400) monomer (2400), dimer (2401), large oligomer (2402), aggregate (2403), particle (2404) *includes viruses **x = methyl, phosphor, etc.

    The physical environment area (3000) contains a chemistry group (3100), a geology domain hierarchy (3200), a physics domain hierarchy (3300), a space domain hierarchy (3400), a tangible goods domain hierarchy (3500), a water group (3600) and a weather group (3700) as shown in Table 3. The chemistry group (3100) contains a molecules entity type (3101), a compounds entity type (3102), a chemicals entity type (3103) and a catalysts entity type (3104). The geology domain hierarch contains a minerals entity type (3202), a sediment entity type (3203), a rock entity type (3204), a landform entity type (3205), a plate entity type (3206), a continent entity type (3207) and a planet entity type (3208). The physics domain hierarchy (3300) contains a quark entity type (3301), a particle zoo entity type (3302), a protons entity type (3303), a neutrons entity type (3304), an electrons entity type (3305), an atoms entity type (3306), and a molecules entity type (3307). The space domain hierarchy contains a dark matter entity type (3402), an asteroids entity type (3403), a comets entity type (3404), a planets entity type (3405), a stars entity type (3406), a solar system entity type (3407), a galaxy entity type (3408) and universe entity type (3409). The tangible goods hierarchy contains a money entity type (3501), a compounds entity type (3502), a minerals entity type (3503), a components entity type (3504), a subassemblies entity type (3505), an assemblies entity type (3506), a subsystems entity type (3507), a goods entity type (3508) and a systems entity type (3509). The water group (3600) contains a pond entity type (3602), a lake entity type (3603), a bay entity type (3604), a sea entity type (3605), an ocean entity type (3606), a creek entity type (3607), a stream entity type (3608), a river entity type (3609) and a current entity type (3610). The weather group (3700) contains an atmosphere entity type (3701), a clouds entity type (3702), a lightning entity type (3703), a precipitation entity type (3704), a storm entity type (3705) and a wind entity type (3706).
  • TABLE 3 Physical Environment Domains Members (lowest level to highest for hierarchies) Chemistry Group molecules (3101), compounds (3102), chemicals (3100) (3103), catalysts (3104) Geology minerals (3202), sediment (3203), rock (3204), (3200) landform (3205), plate (3206), continent (3207), planet (3208) Physics quark (3301), particle zoo (3302), protons (3303), (3300) neutrons (3304), electrons (3305), atoms (3306), molecules (3307) Space dark matter (3402), asteroids (3403), comets (3404), (3400) planets (3405), stars (3406), solar system (3407), galaxy (3408), universe (3409) Tangible Goods money (3501), compounds (3502), minerals (3503), (3500) components (3504), subassemblies (3505), assemblies (3506), subsystems (3507), goods (3508), systems (3509) Water Group pond (3602), lake (3603), bay (3604), sea (3605), (3600) ocean (3606), creek (3607), stream (3608), river (3609), current (3610) Weather Group atmosphere (3701), clouds (3702), lightning (3703), (3700) precipitation (3704), storm (3705), wind (3706)

    Individual entities are items of one or more entity type. The analysis of the health of an individual or group can be linked together with a plurality of different entities to support an analysis that extends across several domains. Entities and patients can also be linked together to follow a chain of events that impacts one or more patients and/or entities. These chains can be recursive. The domain hierarchies and groups shown in Tables 1, 2 and 3 can be organized into different areas and they can also be expanded, modified, extended or pruned in order to support different analyses.
  • Data, information and knowledge from these seventeen different domains can be integrated and analyzed in order to support the creation of one or more health contexts for the subject individual or group. The one or more contexts developed by this system focus on the function performance (note the terms behavior and function performance will be used interchangeably) of a single patient as shown in FIG. 2A, a group of two or more patients as shown in FIG. 2B and/or a patient-entity system in one or more domains as shown in FIG. 2C. FIG. 2A shows an entity (900) and a function impact network diagram for a location (901), a project (902), an event (903), a virtual location (904), a factor (905), a resource (906), an element (907), an action/transaction (908/909), a function measure (910), a process (911), a subject mission (912), constraint (913) and a preference (914). FIG. 2B shows a collaboration (925) between two entities and the function impact network diagram for locations (901), projects (902), events (903), virtual locations (904), factors (905), resources (906), elements (907), action/transactions (908/909), a joint measure (915), processes (911), a joint mission (916), constraints (913) and preferences (914). For simplicity we will hereinafter use the terms patient or subject with the understanding that they refer to a patient (900) as shown in FIG. 2A, a group of two or more patients (925) as shown in FIG. 2B or a patient-entity system (950) as shown in FIG. 2C. While only two entities are shown in FIG. 2B and FIG. 2C it is to be understood that the subject can contain more than two patients and/or entities.
  • After one or more contexts are developed for the subject, they can be combined, reviewed, analyzed and/or applied using one or more of the context-aware services in a Complete Context™ Suite (625) of services. These services are optionally modified to meet user requirements using a Complete Context™ Development System (610). The Complete Context™ Development System (610) supports the maintenance of the services in the Complete Context™ Suite (625), the creation of newly defined stand-alone services, the development of new services and/or the programming of context-aware bots.
  • The system of the present invention systematically develops the one or more complete contexts for distribution in a Personalized Medicine Service (100). These contexts are in turn used to support the comprehensive analysis of subject performance, develop one or more shared contexts to support collaboration, simulate subject performance and/or turn data into knowledge. Processing in the Personalized Medicine Service (100) is completed in three steps:
      • 1. subject definition and measure specification;
      • 2. context and contextbase (50) development, and
      • 3. Complete Context™ service development and distribution.
        The first processing step in the Personalized Medicine Service (100) defines the subject that will be analyzed, prepares the data from devices (3), entity narrow system databases (5), partner narrow system databases (6), external databases (7), the World Wide Web (8), external services (9) and/or the Complete Context™ Input System (601) for use in processing and then uses these data to specify subject functions as well as function and/or mission measures.
  • As part of the first stage of processing, the user (40) identifies the subject by using existing hierarchies and groups, adding a new hierarchy or group or modifying the existing hierarchies and/or groups in order to fully define the subject. As discussed previously, each subject comprises one of three types. These definitions can be supplemented by identifying actions, constraints, elements, events, factors, preferences, processes, projects, risks and resources that impact the subject. For example, a white blood cell entity is an item with the cell entity type (2208) and an element of the circulatory system and auto-immune system (2303). In a similar fashion, entity Jane Doe could be an item within the organism entity type (2300), an item within the voter entity type (1101), an element of a team entity (1602), an element of a nuclear family entity (1402), an element of an extended family entity (1403) and an element of a household entity (1202). This individual would be expected to have one or more functions and function and/or mission measures for each entity type she is associated with. Separate systems that tried to analyze the six different roles of the individual in each of the six hierarchies would probably save some of the same data six separate times and use the same data in six different ways. At the same time, all of the work to create these six separate systems might provide very little insight because the complete context for behavior of this subject at any one period in time is a blend of the context associated with each of the six different functions she is simultaneously performing in the different domains. Predefined templates for the different entity types can be used at this point to facilitate the specification of the subject (these same templates can be used to accelerate learning by the system of the present invention). This specification can include an identification of other subjects that are related to the entity. For example, the individual could identity her friends, family, home, place of work, church, car, typical foods, hobbies, favorite malls, etc. using one of these predefined templates. The user could also indicate the level of impact of each of these entities has on different function and/or mission measures. These weightings can in turn be verified by the system of the present invention.
  • After the subject definition is completed, structured data and information, transaction data and information, descriptive data and information, unstructured data and information, text data and information, geo-spatial data and information, image data and information, array data and information, web data and information, video data and video information, device data and information, and/or service data and information are made available for analysis by converting data formats before mapping these data to a contextbase (50) in accordance with a common schema or ontology. The automated conversion and mapping of data and information from the existing devices (3) narrow computer-based system databases (5 & 6), external databases (7), the World Wide Web (8) and external services (9) to a common schema or ontology significantly increases the scale and scope of the analyses that can be completed by users. This innovation also gives users (40) the option to extend the life of their existing narrow systems (4) that would otherwise become obsolete. The uncertainty associated with the data from the different systems is evaluated at the time of integration. Before going further, it should be noted that the Personalized Medicine Service (100) is also capable of operating without completing some or all narrow system database (5 & 6) conversions and integrations as it can directly accept data that complies with the common schema or ontology. The Personalized Medicine Service (100) is also capable of operating without any input from narrow systems (4). For example, the Complete Context™ Input Service (601) (and any other application capable of producing xml documents) is fully capable of providing all data directly to the Personalized Medicine Service (100).
  • The Personalized Medicine Service (100) supports the preparation and use of data, information and/or knowledge from the “narrow” systems (4) listed in Tables 4, 5, 6 and 7 and devices (3) listed in Table 8.
  • TABLE 4 Biomedical affinity chip analyzer, array systems, biochip systems, bioinformatic systems, Systems biological simulation systems, blood chemistry systems, blood pressure systems, body sensors, clinical management systems, diagnostic imaging systems, electronic patient record systems, electrophoresis systems, electronic medication management systems, enterprise appointment scheduling, enterprise practice management, fluorescence systems, formulary management systems, functional genomic systems, galvanic skin sensors, gene chip analysis systems, gene expression analysis systems, gene sequencers, glucose test equipment, information based medical systems, laboratory information management systems, liquid chromatography, mass spectrometer systems, microarray systems, medical testing systems, microfluidic systems, molecular diagnostic systems, nano-string systems, nano-wire systems, peptide mapping systems, pharmacoeconomic systems, pharmacogenomic data systems, pharmacy management systems, practice management systems, protein biochip analysis systems, protein mining systems, protein modeling systems, protein sedimentation systems, protein sequencer, protein visualization systems, proteomic data systems, stentennas, structural biology systems, systems biology applications, x*-ylation analysis systems *x = methyl, phosphor,
  • TABLE 5 Personal appliance management systems, automobile management Systems systems, blogs, contact management applications, credit monitoring systems, gps applications, home management systems, image archiving applications, image management applications, folksonomies, lifeblogs, media archiving applications, media applications, media management applications, personal finance applications, personal productivity applications (word processing, spreadsheet, presentation, etc.), personal database applications, personal and group scheduling applications, social networking applications, tags, video applications
  • TABLE 6 Scientific accelerometers, atmospheric survey systems, geological Systems survey systems, ocean sensor systems, seismographic systems, sensors, sensor grids, sensor networks, smart dust
  • TABLE 7 Management accounting systems**, advanced financial systems, alliance management Systems systems, asset and liability management systems, asset management systems, battlefield systems, behavioral risk management systems, benefits administration systems, brand management systems, budgeting/financial planning systems, building management systems, business intelligence systems, call management systems, cash management systems, channel management systems, claims management systems, command systems, commodity risk management systems, content management systems, contract management systems, credit-risk management systems, customer relationship management systems, data integration systems, data mining systems, demand chain systems, decision support systems, device management systems document management systems, email management systems, employee relationship management systems, energy risk management systems, expense report processing systems, fleet management systems, foreign exchange risk management systems, fraud management systems, freight management systems, geological survey systems, human capital management systems, human resource management systems, incentive management systems, information lifecycle management systems, information technology management systems, innovation management systems, instant messaging systems, insurance management systems, intellectual property management systems, intelligent storage systems, interest rate risk management systems, investor relationship management systems, knowledge management systems, litigation tracking systems, location management systems, maintenance management systems, manufacturing execution systems, material requirement planning systems, metrics creation system, online analytical processing systems, ontology systems, partner relationship management systems, payroll systems, performance dashboards, performance management systems, price optimization systems, private exchanges, process management systems, product life-cycle management systems, project management systems, project portfolio management systems, revenue management systems, risk management information systems, sales force automation systems, scorecard systems, sensors (includes RFID), sensor grids (includes RFID), service management systems, simulation systems, six-sigma quality management systems, shop floor control systems, strategic planning systems, supply chain systems, supplier relationship management systems, support chain systems, system management applications, taxonomy systems, technology chain systems, treasury management systems, underwriting systems, unstructured data management systems, visitor (web site) relationship management systems, weather risk management systems, workforce management systems, yield management systems and combinations thereof **these typically include an accounts payable system, accounts receivable system, inventory system, invoicing system, payroll system and purchasing system
  • TABLE 8 Devices personal digital assistants, phones, watches, clocks, lab equipment, personal computers, televisions, radios, personal fabricators, personal health monitors, refrigerators, washers, dryers, ovens, lighting controls, alarm systems, security systems, hvac systems, gps devices, smart clothing (aka clothing with sensors), personal biomedical monitoring devices, personal computers

    After data conversions have been identified the user (40) is asked to specify entity functions. The user can select from pre-defined functions for each subject or define new functions using narrow system data. Examples of predefined subject functions are shown in Table 9.
  • TABLE 9 Entity type Example Functions Organism (2300) reproduction, killing germs, maintaining blood sugar levels

    Pre-defined quantitative measures can be used if pre-defined functions were used in defining the entity. Alternatively, new measures can be created using narrow system data for one or more subjects and/or the Personalized Medicine Service (100) can identify the best fit measures for the specified functions. The quantitative measures can take any form. For example, Table 10 shows three measures for a medical organization entity—patient element health, patient element longevity and organization financial break even. The Personalized Medicine Service (100) incorporates the ability to use other pre-defined measures including each of the different types of risk—alone or in combination—as well as sustainability.
  • After the data integration, subject definition and measure specification are completed, processing advances to the second stage where context layers for each subject are developed and stored in a contextbase (50). Each context for a subject can be divided into eight or more types of context layers. Together, these eight layers identify: actions, constraints, elements, events, factors, preferences, processes, projects, risks, resources and terms that impact entity performance for each function; the magnitude of the impact actions, constraints, elements, events, factors, preferences, processes, projects, risks, resources ad terms have on entity performance of each function; physical and/or virtual coordinate systems that are relevant to entity performance for each function and the magnitude of the impact location relative to physical and/or virtual coordinate systems has on entity performance for each function. These eight layers also identify and quantify subject function and/or mission measure performance. The eight types of layers are:
      • 1. A layer that defines and describes the element context over time, i.e. we store widgets (a resource) built (an action) using the new design (an element) with the automated lathe (another element) in our warehouse (an element). The lathe (element) was recently refurbished (completed action) and produces 100 widgets per 8 hour shift (element characteristic). We can increase production to 120 widgets per 8 hour shift if we add complete numerical control (a feature). This layer may be subdivided into any number of sub-layers along user specified dimensions such as tangible elements of value, intangible elements of value, processes, agents, assets and combinations thereof;
      • 2. A layer that defines and describes the resource context over time, i.e. producing 100 widgets (a resource) requires 8 hours of labor (a resource), 150 amp hours of electricity (another resource) and 5 tons of hardened steel (another resource). This layer may be subdivided into any number of sub-layers along user specified dimensions such as lexicon (what resources are called), resources already delivered, resources with delivery commitments and forecast resource requirements;
      • 3. A layer that defines and describes the environment context over time (the entities in the social (1000), natural (2000) and/or physical environment (3000) that impact entity function and/or mission measure performance, i.e. the volatility in the market for steel increased 50% last year, standard deviation on monthly shipments is 24% and analysts expect 30% growth in revenue this quarter. This layer may be subdivided into any number of sub-layers along user specified dimensions;
      • 4. A layer that defines and describes the transaction context (also known as tactical/administrative context) over time, i.e. Acme owes us $30,000 for prior sales, we have made a commitment to ship 100 widgets to Acme by Tuesday and need to start production by Friday. This layer may be subdivided into any number of sub-layers along user specified dimensions such as historical transactions, committed transactions, forecast transactions, historical events, forecast events and combinations thereof;
      • 5. A layer that defines and describes the relationship context over time, i.e. Acme is also a key supplier for the new product line, Widget X, that is expected to double our revenue over the next five years. This layer may be subdivided into any number of sub-layers along user specified dimensions;
      • 6. A layer that defines and describes the measurement context over time, i.e. the price per widget is $100 and the cost of manufacturing widgets is $80 so we make $20 profit per unit (for most businesses this would be a short term profit measure for the value creation function). Also, Acme is one of our most valuable customers and they are a valuable supplier to the international division (value based measures). This layer may be subdivided into any number of sub-layers along user specified dimensions. For example, the instant, five year and lifetime impact of certain medical treatments may be of interest. In this instance, three separate measurement layers could be created to provide the desired context. The risks associated with each measure can be integrated within each measurement layer or they can be stored in separate layers. For example, value measures for organizations integrate the risk and the return associated with measure performance. Measures associated with other entities can be included in this layer. This capability enables the use of the difference between the subject measure and the measures of other entities as measures;
      • 7. A layer that optionally defines the relationship of one or more of the first six layers of entity context to one or more reference systems over time. A spatial reference coordinate system will be used for most entities. Pre-defined spatial reference coordinates available for use in the system of the present invention include the major organs in a human body, each of the continents, the oceans, the earth and the solar system. Virtual reference coordinate systems can also be used to relate each entity to other entities. For example, a virtual coordinate system could be a network such as the Internet, an intranet, a local are network network, a wi-fi network, a wimax network and/or social network. The genome of different entities can also be used as a reference coordinate system. This layer may also be subdivided into any number of sub-layers along user specified dimensions and would identify system or application context if appropriate;
      • 8. A layer that defines and describes the lexicon of the subject—this layer may be broken into sub-layers to define the lexicon associated with each of the previous context layers.
        Different combinations of context layers from different subjects and/or entities are relevant to different analyses and decisions. For simplicity, we will generally refer to eight types of context layers or eight context layers while recognizing that the number of context layers can be greater or less than eight. It is worth noting at this point that the layers may be combined for ease of use, to facilitate processing and/or as entity requirements dictate. Before moving on to discuss context frames—which are defined by one or more entity function and/or mission measures and the portion of each of the eight context layers that impacts the one or more entity function and/or mission measures—we need to define each context layer in more detail. Before we can do this, we need to define key terms that we will use in more fully defining the Personalized Medicine Service (100) of the present invention:
      • 1. Entity type—any member or combination of members of a hierarchy or group (see Tables 1, 2 and 3 for examples of hierarchies and groups);
      • 2. Entity—a discrete unit of an entity type that has one or more functions, these functions can support the completion of a mission;
      • 3. Context—defines and describes the situation of an entity vis a vis the drivers of subject function performance as shown in FIG. 2A, FIG. 2B or FIG. 2C. It includes but is not limited to the data, information and knowledge that defines and describes the eight context layers identified previously for a valid context space;
      • 4. User context—defines and describes the users situation vis a vis drivers of user function performance—note: user may or may not be the subject;
      • 5. Subject—patient (900), combination of patients (925) or a patient—entity system (950) as shown in FIG. 2A, FIG. 2B or FIG. 2C respectively with one or more defined functions;
      • 6. Function—behavior or performance of the subject, can include creation, production, growth, improvement, destruction, diminution and/or maintenance of a component of context and/or one or more entities. Examples: maintaining body temperature at 98.6 degrees Fahrenheit, destroying cancer cells, improving muscle tone and producing insulin;
      • 7. Mission—what an entity intends to do or achieve (i.e. a goal), functions can support the completion of an entity mission;
      • 8. Characteristic—numerical or qualitative indication of entity status—examples: temperature, color, shape, distance weight, and cholesterol level (descriptive data are the typical source of data about characteristics) and the acceptable range for these characteristics (aka a subset of constraints);
      • 9. Event—something that takes place in a defined point in space time, the events of interest are generally those that are recorded and have an impact on the components of context and/or measure performance of a subject and/or change the characteristics of an entity;
      • 10. Project—action or series of actions that produces one or more lasting changes. Change can include: changes a characteristic, changes a constraint, produces one or more new components of context, changes one or more components of context, produces one or more new entities or some combination thereof. Said changes impact entity function performance/mission and are analyzed using same method, system and media described for event and extreme event analysis;
      • 11. Action—acquisition, consumption, destruction, production or transfer of resources, elements and/or entities in a defined point in space time—examples: blood cells transfer oxygen to muscle cells and an assembly line builds a product. Actions are a subset of events and are generally completed by a process;
      • 12. Data—anything that is recorded—includes transaction data, descriptive data, content, information and knowledge;
      • 13. Information—data with context of unknown completeness;
      • 14. Knowledge—data with the associated complete context—all eight types of layers are defined and complete to the extent possible given uncertainty;
      • 15. Transaction—anything that is recorded that isn't descriptive data. Transactions generally reflect events and/or actions for one or more entities over time (transaction data are generally the source);
      • 16. Measure—quantitative indication of one or more subject functions and/or missions—examples: cash flow, patient survival rate, bacteria destruction percentage, shear strength, torque, cholesterol level, and pH maintained in a range between 6.5 and 7.5;
      • 17. Element—also known as a context element these are tangible and intangible entities that participate in and/or support one or more subject actions and/or functions without normally being consumed by the action—examples: land, heart, Sargasso sea, relationships, wing and knowledge;
      • 18. Element combination—two or more elements that share performance drivers to the extent that they need to be analyzed as a single element;
      • 19. Item—an item is an instance within an element. For example, an individual salesman would be an “item” within the sales department element (or entity). In a similar fashion a gene would be an item within a dna entity. While there are generally a plurality of items within an element, it is possible to have only one item within an element;
      • 20. Item variables are the transaction data and descriptive data associated with an item or related group of items;
      • 21. Indicators (also known as item performance indicators and/or factor performance indicators) are data derived from data related to an item or a factor;
      • 22. Composite variables for a context element or element combination are mathematical combinations of item variables and/or indicators, logical combinations of item variables and/or indicators and combinations thereof;
      • 23. Element variables or element data are the item variables, indicators and composite variables for a specific context element or sub-context element;
      • 24. Subelement—a subset of all items in an element that share similar characteristics;
      • 25. Asset—subset of elements that support actions and are usually not transferred to other entities and/or consumed—examples: brands, customer relationships, information and equipment;
      • 26. Agent—subset of elements that can participate in an action. Six distinct kinds of agents are recognized—initiator, negotiator, closer, catalyst, regulator, messenger. A single agent may perform several agent functions—examples: customers, suppliers and salespeople;
      • 27. Resource—entities that are routinely transferred to other entities and/or consumed—examples: raw materials, products, information, employee time and risks;
      • 28. Subresource—a subset of all resources that share similar characteristics;
      • 29. Process—combination of elements actions and/or events that are used to complete an action or event—examples: sales process, cholesterol regulation and earthquake. Processes are a special class of element;
      • 30. Commitment—an obligation to complete a transaction in the future—example: contract for future sale of products and debt;
      • 31. Competitor—subset of factors, an entity that seeks to complete the same actions as the subject, competes for elements, competes for resources or some combination thereof;
      • 32. Priority—relative importance assigned to actions and measures;
      • 33. Requirement—minimum or maximum levels for one or more elements, element characteristics, actions, events, processes or relationships, may be imposed by user (40), laws (1306) or physical laws (i.e. force=mass times acceleration);
      • 34. Surprise—variability or events that improve or increase subject performance;
      • 35. Risk—variability or events that reduce or degrade subject performance;
      • 36. Extreme risk—caused by variability or extreme events that reduce subject performance by producing permanent changes in the impact of one or more components of context on the subject;
      • 37. Critical risk—extreme risks that can terminate a subject;
      • 38. Competitor risk—risks that are a result of actions by an entity that competes for resources, elements, actions or some combination thereof;
      • 39. Factor—entities external to subject that have an impact on subject performance—examples: commodity markets, weather, earnings expectation—as shown in FIG. 2A factors are associated with subjects that are outside the box. All higher levels in the hierarchy of a subject are also defined as factors.
      • 40. Composite factors are numerical indicators of: external entities that influence performance, conditions external to the subject that influence performance, conditions of the entity compared to external expectations of entity conditions or the performance of the entity compared to external expectations of entity performance;
      • 41. Factor variables are the transaction data and descriptive data associated with context factors;
      • 42. Factor performance indicators (also known as indicators) are data derived from factor related data;
      • 43. Composite factors (also known as composite variables) for a context factor or factor combination are mathematical combinations of factor variables and/or factor performance indicators, logical combinations of factor variables and/or factor performance indicators and combinations thereof;
      • 44. External Services (9) are services available from systems that are not part of the system of the present invention (100) via a network (wired or wireless) connection. They include search services (google, yahoo!, etc.), map services (mapquest, yahoo!, etc.), rating services (zagat's, fodor's, etc.), weather services and services particular to a location or site (projection services, presence detection services, voice transcription services, traffic status reports, tour guide information, etc.);
      • 45. A layer is software and/or information that gives an application, system, service, device or layer the ability to interact with another layer, device, system, service, application or set of information at a general or abstract level rather than at a detailed level;
      • 46. Context frames include all information relevant to function measure performance for a defined combination of context layers, subject and subject functions. In one embodiment, each context frame is a series of pointers that are stored within a separate table;
      • 47. Complete context is a shorthand way of noting that all eight types of context layers have been defined for an subject function (note: it is also used as a proprietary trade-name designation for applications or services with a context quotient of 200);
      • 48. Complete Entity Context—complete context for all entity functions;
      • 49. Components of Context—any combination of location (901), projects (902), events (903), virtual location (904), factors (905), resources (906, elements (907), actions (908), transactions (909), function measures (910), processes (911), mission measures (912), constraints (913), preferences (914) and factors (1000, 2000 and 3000) that have a relationship to and/or impact on a subject;
      • 50. Contextbase is a database that organizes data and information by context for one or more subject entities. In one embodiment the contextbase is a virtual database. The contextbase can also be a relational database, a flat database, a storage area network and/or some combination thereof;
      • 51. Total risk is the sum of all variability risks and event risks for a subject.
      • 52. Variability risk is a subset of total risk. It is the risk of reduced or impaired performance caused by variability in one or more components of context. Variability risk is quantified using statistical measures like standard deviation. The covariance and dependencies between different variability risks are also determined because simulations use quantified information regarding the inter-relationship between the different risks to perform effectively;
      • 53. Event risk is a subset of total risk. It is the risk of reduced or impaired performance caused by the occurrence of an event. Event risk is quantified by combining a forecast of event frequency with a forecast of event impact on subject components of context and the entity itself.
      • 54. Contingent liabilities are a subset of event risk where the impact of an event occurrence is known;
      • 55. Uncertainty measures the amount of subject function measure performance that cannot be explained by the components of context and their associated risk that have been identified by the system of the present invention. Sources of uncertainty include model error and data error.
      • 56. Real options are defined as options the entity may have to make a change in its behavior/performance at some future date—these can include the introduction of new elements or resources, the ability to move processes to new locations, etc. Real options are generally supported by the elements of an entity;
      • 57. The efficient frontier is the curve defined by the maximum function and/or mission measure performance an entity can expect for a given level of total risk; and
      • 58. Services are self-contained, self-describing, modular pieces of software that can be published, located, queried and/or invoked across a World Wide Web, network and/or a grid. In one embodiment all services are SOAP compliant. Bots and agents can be functional equivalents to services. In one embodiment all applications are services, However, the system of the present invention can function using: bots (or agents), client server architecture, and integrated software application architecture and/or combinations thereof.
        We will use the terms defined above and the keywords that were defined previously when detailing one embodiment of the present invention. In some cases key terms may be defined by the Upper Ontology or an industry organization such as the Plant Ontology Consortium, the Gene Ontology Consortium or the ACORD consortium (for insurance). In a similar fashion the Global Spatial Data Infrastructure organization and the Federal Geographic Data Committee are defining a reference model for geographic information that can be used to define the spatial reference standard for geographic information. The United Nations is similarly defining the United Nations Standard Product and Services Classification which can also be used for reference. The element definitions, descriptive data, lexicon and reference frameworks from these sources can supplement or displace the pre-defined metadata included within the contextbase (50) as appropriate. Because the system of the present invention identifies and quantifies the impact of different actions, constraints, elements, events, factors, preferences, processes, projects, risks and resources as part of its normal processing, the relationships defined by standardized ontologies are generally not utilized. However, they can be used as a starting point for system processing and/or to supplement the results of processing.
  • In any event, we can now use the key terms to better define the eight types of context layers and identify the typical source for the data and information as shown below.
      • 1. The element context layer identifies and describes the entities that impact subject function and/or mission measure performance by time period. The element description includes the identification of any sub-elements and preferences. Preferences may be important characteristics for process elements that have more than one option for completion. Elements are initially identified by the chosen subject hierarchy (elements associated with lower levels of a hierarchy are automatically included) whereas transaction data identifies others as do analysis and user input. These elements may be identified by item or sub-element. The sources of data can include devices (3), narrow system databases (5), partner narrow system databases (6), external databases (7), the World Wide Web (8), external services (9), xml compliant applications, the Complete Context™ Input Service (601) and combinations thereof.
      • 2. The resource context layer identifies and describes the resources that impact subject function and/or mission measure performance by time period. The resource description includes the identification of any sub-resources. The sources of data can include narrow system databases (5), partner narrow system databases (6), external databases (7), the World Wide Web (8), external services (9), xml compliant applications, the Complete Context™ Input Service (601) and combinations thereof.
      • 3. The environment context layer identifies and describes the factors in the social, natural and/or physical environment that impact subject function and/or mission measure performance by time period. The relevant factors are determined via analysis. The factor description includes the identification of any sub-factors. The sources of data can include devices (3), narrow system databases (5), partner narrow system databases (6), external databases (7), the World Wide Web (8) and external services (9), xml compliant applications, the Complete Context™ Input Service (601) and combinations thereof.
      • 4. The transaction context layers identifies and describes the events, actions, action priorities, commitments and requirements of the subject and each entity in the element context layer by time period. The description identifies the elements and/or resources that are associated with the event, action, action priority, commitment and/or requirement. The sources of data can include narrow system databases (5), partner narrow system databases (6), external databases (7), the World Wide Web (8), external services (9), xml compliant applications, the Complete Context™ Input Service (601) and combinations thereof.
      • 5. The relationship context layer defines the relationships between the first three layers (elements, resources and/or factors) and the fourth layer (events and/or actions) by time period. These impacts can be identified by user input (i.e. process maps and procedures), analysis, narrow system databases (5), partner narrow system databases (6), external databases (7), the World Wide Web (8), external services (9), xml compliant applications, the Complete Context™ Input Service (601) and combinations thereof.
      • 6. The measure context layer(s) identifies and quantifies the impact of actions, events, elements, factors, resources and processes (combination of elements) on each entity function measure by time period. The impact of risks and surprises can be kept separate or integrated with other element/factor measures. The impacts are generally determined via analysis. However, the analysis can be supplemented by input from simulation programs, the user (40), a subject matter expert (42) and/or a collaborator (43), narrow system databases (5), partner narrow system databases (6), external databases (7), the World Wide Web (8), external services (9), xml compliant applications, the Complete Context™ Input Service (601) and combinations thereof.
      • 7. Reference context layer (optional)—the relationship of the first six layers to a specified real or virtual coordinate system. These relationships can be identified by user input (i.e. maps), input from a subject matter expert (42) and/or a collaborator (43), narrow system databases (5), partner narrow system databases (6), external databases (7), the World Wide Web (8), external services (9), xml compliant applications, the Complete Context™ Input Service (601), analysis and combinations thereof; and
      • 8. Lexical context layer—defines the terminology used to define and describe the components of context in the other seven layers. These lexicon can be identified by user input, input from a subject matter expert (42) and/or a collaborator (43), narrow system databases (5), partner narrow system databases (6), external databases (7), the World Wide Web (8), external services (9), xml compliant applications, the Complete Context™ Input Service (601), analysis and combinations thereof.
        The eight context layers define a complete context for entity performance for a specified function by time period. We can use the more precise definition of context to define what it means to be knowledgeable. Our revised definition would state that an individual that is knowledgeable about a subject has information from all eight context layers for the one or more functions he, she or it is considering. This is important because, once the complete context is known and modeled any disease can be managed and/or cured. The knowledgeable individual would be able to use the information from the eight context layers to:
      • 1. identify the range of contexts where models of subject function performance are applicable; and
      • 2. accurately predict subject actions in response to events and/or actions in contexts where the context is applicable.
        The accuracy of the prediction created using the eight types of context layers reflects the level of knowledge. For simplicity we will use the R squared (R2) statistic as the measure of knowledge level. R2 is the fraction of the total squared error that is explained by the model—other statistics can be used to provide indications of the entity model accuracy including entropy measures and root mean squared error. The gap between the fraction of performance explained by the model and 100% is uncertainty, errors in the model and errors in the data. Table 10 illustrates the use of the information from six of the eight layers in analyzing a sample personalized medicine context.
  • TABLE 10 1. Mission: patient health & longevity, financial break even measures 2. Environment: malpractice insurance is increasingly costly 3. Measure: survival rate is 99% for procedure A and 98% for procedure B; treatment in first week improves 5 year survival 18%, 5 year recurrence rate is 7% higher for procedure A 4. Relationship: Dr. X has a commitment to assist on another procedure Monday 5. Resource: operating room A time available for both procedures 6. Transaction: patient should be treated next week, his insurance will cover operation 7. Element: operating room, operating room equipment, Dr. X

    In addition to defining context, context layers are useful in developing management tools. One use of the layers is establishing budgets and/or alert levels for data within a layer or combinations of layers. Using the sample situation illustrated in Table 10, an alert could be established for survival rates that drop below 99% in the measure layer. Control can be defined and applied at the transaction and measure levels by assigning priorities to actions and measures. Using this approach the system of the present invention has the ability to analyze and optimize performance using user specified priorities, historical measures or some combination of the two.
  • Some analytical applications are limited to optimizing the instant (short-term) impact given the elements, resources and the transaction status. Because these systems generally ignore uncertainty and the impact, reference, environment and long term measure portions of a complete context, the recommendations they make are often at odds with common sense decisions made by line managers that have a more complete context for evaluating the same data. This deficiency is one reason some have noted that “there is no intelligence in business intelligence applications”. One reason some existing systems take this approach is that the information that defines three important parts of complete context (relationship, environment and long term measure impact) are not readily available and must generally be derived. A related shortcoming of some of these systems is that they fail to identify the context or contexts where the results of their analyses are valid.
  • In one embodiment, the Personalized Medicine Service (100) provides the functionality for integrating data from all narrow systems (4), creating a contextbase (50), developing a Personalized Medicine Service (100) and supporting the Complete Context™ Suite (625) as shown in FIG. 13. Over time, the narrow systems (4) can be eliminated and all data can be entered directly into the Personalized Medicine Service (100) as discussed previously. In an alternate mode, the Personalized Medicine Service (100) would work in tandem with a Process Integration System (99) such as an application server, laboratory information management system, middleware application, extended operating system, data exchange or grid to integrate data, create the contextbase (50), develop a Personalized Medicine Service (100) and support the Complete Context™ Suite (625) as shown in FIG. 14. In either mode, the system of the present invention supports the development and storage of all eight types of context layers in order to create a contextbase (50).
  • The contextbase (50) also enables the development of new types of analytical reports including a sustainability report and a controllable performance report. The sustainability report combines the element lives, factor lives, risks and an entity context to provide an estimate of the time period over which the current subject performance level can be sustained. There are three paired options for preparing the report—dynamic or static mode, local or indirect mode, risk adjusted or pre-risk mode. In the static mode, the current element and factor mix is “locked-in” and the sustainability report shows the time period over which the current inventory will be depleted. In the dynamic mode the current element and factor inventory is updated using trended replenishment rates to provide a dynamic estimate of sustainability. The local perspective reflects the sustainability of the subject in isolation while the indirect perspective reflects the impact of the subject on another entity. The indirect perspective is derived by mapping the local impacts to some other entity. The risk adjusted (aka “risk”) and pre-risk modes (aka “no risk”) are self explanatory as they simply reflect the impact of risks on the expected sustainability of subject performance. The different possible combinations of these three options define eight modes for report preparation as shown in Table 11.
  • TABLE 11 Mode Static or Dynamic Local or Indirect Risk or No Risk 1 Static Local Risk 2 Static Local No Risk 3 Static Indirect Risk 4 Static Indirect No Risk 5 Dynamic Local Risk 6 Dynamic Local No Risk 7 Dynamic Indirect Risk 8 Dynamic Indirect No Risk

    The sustainability report reflects the expected impact of all context elements and factors on subject performance over time. It can be combined with the Complete Context™ Forecast Service (603), described below, to produce unbiased reserve estimates. Context elements and context factors are influenced to varying degrees by the subject. The controllable performance report identifies the relative contribution of the different context elements and factors to the current level of entity performance. It then puts the current level of performance in context by comparing the current level of performance with the performance that would be expected if some or all of the elements and factors were all at the mid-point of their normal range—the choice of which elements and factors to modify could be a function of the control exercised by the subject. Both of these reports are pre-defined for display using the Complete Context™ Review Service (607) described below.
  • The Complete Context™ Review Service (607) and the other services in the Complete Context™ Suite (625) use context frames and sub-context frames to support the analysis, forecast, review and/or optimization of entity performance. Context frames and sub-context frames are created from the information provided by the Personalized Medicine Service (100) created by the system of the present invention (100). The ID to frame table (165) identifies the context frame(s) and/or sub-context frame(s) that will be used by each user (40), manager (41), subject matter expert (42), and/or collaborator (43). This information is used to determine which portion of the Personalized Medicine Service (100) will be made available to the devices (3) and narrow systems (4) that support the user (40), manager (41), subject matter expert (42), and/or collaborator (43) via the Complete Context™ API (application program interface). As detailed later, the system of the present invention can also use other methods to provide the required context information.
  • Context frames are defined by the entity function and/or mission measures and the context layers associated with the entity function and/or mission measures. The context frame provides the data, information and knowledge that quantifies the impact of actions, constraints, elements, events, factors, preferences, processes, projects, risks and resources on entity performance. Sub-context frames contain information relevant to a subset of one or more function measure/layer combinations. For example, a sub-context frame could include the portion of each of the context layers that was related to an entity process. Because a process can be defined by a combination of elements, events and resources that produce an action, the information from each layer that was associated with the elements, events, resources and actions that define the process would be included in the sub-context frame for that process. This sub-context frame would provide all the information needed to understand process performance and the impact of events, actions, element change and factor change on process performance.
  • The services in the Complete Context™ Suite (625) are “context aware” (with context quotients equal to 200) and have the ability to process data from the Personalized Medicine Service (100) and its contextbase (50). Another novel feature of the services in the Complete Context™ Suite (625) is that they can review entity context from prior time periods to generate reports that highlight changes over time and display the range of contexts under which the results they produce are valid. The range of contexts where results are valid will be hereinafter be referred to as the valid context space.
  • The services in the Complete Context™ Suite (625) also support the development of customized applications or services. They do this by:
      • 1. providing ready access to the internal logic of the service while at the same time protecting this logic from change; and
      • 2. using the universal context specification (see FIG. 17) to define standardized Application Program Interfaces (API's) for all Complete Context™ Services—these API's allow the specification of the different context layers using text information, numerical information and/or graphical representations of subject context in a format similar to that shown in FIG. 2A, FIG. 2B. and FIG. 2C.
  • The first features allow users (40), partners and external services to get information tailored to a specific context while preserving the ability to upgrade the services at a later date in an automated fashion. The second feature allows others to incorporate the Complete Context™ Services into other applications and/or services. It is worth noting that this awareness of context is also used to support a true natural language interface (714)—one that understands the meaning of the identified words—to each of the services in the Suite (625). It should be also noted that each of the services in the Suite (625) supports the use of a reference coordinate system for displaying the results of their processing when one is specified for use by the user (40). The software for each service in the suite (625) resides in an applet or service with the context frame being provided by the Personalized Medicine Service (100). This software could also reside on the computer (110) with user access through a browser (800) or through the natural language interface (714) provided by the Personalized Medicine Service (100). Other features of the services in the Complete Context™ Suite (625) are briefly described below:
      • 1. Complete Context™ Analysis Service (602)—analyzes the impact of user (40) specified changes on a subject for a given context frame or sub-context frame by mapping the proposed change to the appropriate context layer(s) in accordance with the schema or ontology and then evaluating the impact of said change on the function and/or mission measures. Context frame information may be supplemented by simulations and information from subject matter experts (42) as appropriate. This service can also be used to analyze the impact on changes on any “view” of the entity that has been defined and pre-programmed for review. For example, accounting profit using three different standards or capital adequacy can be analyzed using the same rules defined for the Complete Context™ Review Service (607) to convert the context frame analysis to the required reporting format.
      • 2. Complete Context™ Auditing Service (624)—is a modified Complete Context™ Review Service (607) that uses a rules engine to completely re-process all relevant transactions and compare the resulting values with the information in a report presented by management. The Complete Context™ Auditing Service then combines this information with the information stored in the Context Base (50) to complete an automated audit of all the numbers in a report—including reserve estimates—as well as producing a list of risk factors in order of importance. After the various calculations are completed, the system of the present invention produces a discrepancy report where the reported values in a report is compared to the value computed using the method and system detailed above.
      • 3. Complete Context™ Bridge Service (624)—is a service that identifies the differences between two context frames and the best mode for bringing the frames into alignment or congruence. This service can be very useful in breaking down barriers to communication and facilitating negotiations.
      • 4. Complete Context™ Browser (628)—supports browsing through the contextbase (50) with a focus on one or more dimensions of the Universal Context Specification for the user (40) and/or a subject.
      • 5. Complete Context™ Capture and Collaboration Service (622)—guides one or more subject matter experts (42) and/or collaborators (43) through a series of steps in order to capture information, refine existing knowledge and/or develop plans for the future using existing knowledge. The one or more subject matter experts (42) and/or collaborators (43) will provide information and knowledge by selecting from a template of pre-defined elements, resources, events, factors, actions and entity hierarchy graphics that are developed from the subject schema table (157). The one or more subject matter experts (42) and/or collaborators (43) also have the option of defining new elements, events, factors, actions and hierarchies. The one or more subject matter experts (42) and/or collaborators (43) are first asked to define what type of information and knowledge will be provided. The choices will include each of the eight types of context layers as well as element definitions, factor definitions, event definitions, action definition, impacts, processes, uncertainty and scenarios. On this same screen, the one or more subject matter experts (42) and/or collaborators (43) will also be asked to decide whether basic structures or probabilistic structures will provided in this session, if this session will require the use of a time-line and if the session will include the lower level subject matter. The selection regarding type of structures will determine what type of samples will be displayed on the next screen. If the use of a time-line is indicated, then the user will be prompted to: select a reference point—examples would include today, event occurrence, when I started, etc.; define the scale being used to separate different times—examples would include seconds, minutes, days, years, light years, etc.; and specify the number of time slices being specified in this session. The selection regarding which type of information and knowledge will be provided determines the display for the last selection made on this screen. There is a natural hierarchy to the different types of information and knowledge that can be provided by a one or more subject matter experts (42) and/or collaborators (43). For example, measure level knowledge would be expected to include input from the impact, element, transaction and resource context layers. If the one or more subject matter experts (42) and/or collaborators (43) agrees, the service will guide the one or more subject matter experts (42) and/or collaborators (43) to provide knowledge for each of the “lower level” knowledge areas by following the natural hierarchies. Summarizing the preceding discussion, the one or more subject matter experts (42) and/or collaborators (43) has used the first screen to select the type of information and knowledge to be provided (measure layer, impact layer, transaction layer, resource layer, environment layer, element layer, reference layer, event risk or scenario). The one or more subject matter experts (42) and/or collaborators (43) has also chosen to provide this information in one of four formats: basic structure without timeline, basic structure with timeline, relational structure without timeline or relational structure with timeline. Finally, the one or more subject matter experts (42) and/or collaborators (43) has indicated whether or not the session will include an extension to capture “lower level” knowledge. Each selection made by the one or more subject matter experts (42) and/or collaborators (43) will be used to identify the combination of elements, events, actions, factors and entity hierarchy chosen for display and possible selection. This information will be displayed in a manner that is somewhat similar to the manner in which stencils are made available to Visio® users for use in the workspace. The next screen displayed by the service will depend on which combination of information, knowledge, structure and timeline selections that were made by the one or more subject matter experts (42) and/or collaborators (43). In addition to displaying the sample graphics to the one or more subject matter experts (42) and/or collaborators (43), this screen will also provide the one or more subject matter experts (42) and/or collaborators (43) with the option to use graphical operations to change impacts, define new impacts, define new elements, define new factors and/or define new events. The thesaurus table (164) in the contextbase (50) provides graphical operators for: adding an element or factor, acquiring an element, consuming an element, changing an element, factor or event risk values, adding a impact, changing the strength of a impact, identifying an event cycle, identifying a random impact, identifying commitments, identifying constraints and indicating preferences. The one or more subject matter experts (42) and/or collaborators (43) would be expected to select the structure that most closely resembles the knowledge that is being communicated or refined and add it to the workspace being displayed. After adding it to the workspace, the one or more subject matter experts (42) and/or collaborators (43) will then edit elements, factors, resources and events and add elements, factors, resources events and descriptive information in order to fully describe the information or knowledge being captured from the context frame represented on the screen. If relational information is being specified, then the one or more subject matter experts (42) and/or collaborators (43) will be given the option of using graphs, numbers or letter grades to communicate the information regarding probabilities. If a timeline is being used, then the next screen displayed will be the screen for the same perspective from the next time period in the time line. The starting point for the next period knowledge capture will be the final version of the knowledge captured in the prior time period. After completing the knowledge capture for each time period for a given level, the Service (622) will guide the one or more subject matter experts (42) and/or collaborators (43) to the “lower level” areas where the process will be repeated using samples that are appropriate to the context layer or area being reviewed. At all steps in the process, the information in the contextbase (50) and the knowledge collected during the session will be used to predict elements, resources, actions, events and impacts that are likely to be added or modified in the workspace. These “predictions” are displayed using flashing symbols in the workspace. The one or more subject matter experts (42) and/or collaborators (43) is given with the option of turning the predictive prompting feature off. After the information and knowledge has been captured, the graphical results are converted to data base entries and stored in the appropriate tables (141, 142, 143, 144, 145, 149, 154, 156, 157, 158, 162 or 168) in the contextbase (50). Data from simulation programs can also be added to the contextbase (50) to provide similar information or knowledge. This Service (622) can also be used to verify the veracity of some new assertion by mapping the new assertion to the subject model and quantifying any reduction in explanatory power and/or increase in uncertainty of the entity performance model.
      • 6. Complete Context™ Customization Service (621)—service for analyzing and optimizing the impact of data, information, products, projects and/or services by customizing the features included in or expressed by an offering for a subject for a given context frame or sub-context frame. The context frame or sub-context frame may be provided by the Complete Context™ Summary Service (617). Some of the products and services that can be customized with this service include medicine, medical treatments, medical tests, software, technical support, equipment, computer hardware, devices, services, telecommunication equipment, living space, buildings, advertising, data, information and knowledge. Other customizations may rely on the Complete Context™ Optimization Service (604) working alone or in combination with the Complete Context™ Search Service (609). Context frame information may be supplemented by simulations and information from subject matter experts (42) as appropriate.
      • 7. Complete Context™ Display Service (614)—manages the availability and display of data, information, and knowledge related to one or more context frames and/or sub context frames to a user (40), manager (41), subject matter expert (42), and/or collaborator (43) on a continuous basis using a portal (11), service (9), device (3), computer (110) and/or other display. To support this effort the Complete Context™ Display Service (614) supports RSS feeds, manages one or more caches (119) that support projections and display(s) utilizing the caches and/or data feeds. The priority assigned to the data and information made available is determined via a randomized algorithm that blends frequency of use, recency of use, cost to retrieve and time to retrieve measures with a relevance measure for each of the one or more context frames and/or sub context frames being supported (see Complete Context™ Scout Service (616) for a discussion of relevance measure computation). As the user (40), manager (41), subject matter expert (42), and/or collaborator (43) context changes (for example when location changes or the World Trade Center collapses), the relevance measure will change which will in turn drive this Service (614) to change the mix in the cache, RSS feed or projection in order to ensure that data and/or information that is most relevant to the new context is readily available. This Service (614) can be combined with the Complete Context™ Optimization Service (604) to ensure that messages, emails, network traffic, computer resources and related devices are providing the optimal support for a given context. In a similar fashion it can be combined with the Complete Context™ Capture and Collaboration Service (622) to ensure that the one or more subject matter experts (42) and/or collaborators (43) have the data, information and knowledge they need to complete their input to the system of the present invention. The service can be used to purge data, information and knowledge that is no longer relevant to the given context. In an interactive commerce setting this application can be used to: identify the content that is most relevant to a customer's context and/or display an ad or technical support information relevant to said context. In this same setting it can be combined with other services in the suite (625) complete a sale using the Complete Context™ Exchange Service (608), purchase content that has a value in excess of its cost in the current context using the Complete Context™ Exchange Service (608), customize and buy an offering using the Complete Context™ Customization Service (621) in conjunction with the Complete Context™ Exchange Service (608), and/or customize and sell an offering using the Complete Context™ Customization Service (621) in conjunction with the Complete Context™ Exchange Service (608).
      • 8. Complete Context™ Exchange Service (608)—identifies desirable exchanges of resources, elements, commitments, data and information with other entities in an automated fashion. This service calls on Complete Context™ Analysis Service (602) in order to review proposed prices. In a similar manner the service calls on the Complete Context™ Optimization Service (604) to determine the optimal parameters for an exchange before completing a transaction. For partners or customers that provide access to their data that is sufficient to define a shared context, the exchange service can use the other services from the Complete Context™ Suite (625) to analyze and optimize the exchange for the combined parties. The actual transactions are completed by the Complete Context™ Input Service (601).
      • 9. Complete Context™ Forecast Service (603)—forecasts the value of specified variable(s) using data from all relevant context layers. Completes a tournament of forecasts for specified variables and defaults to a multivalent combination of forecasts from the tournament using methods similar to those first described in cross referenced U.S. Pat. No. 5,615,109. In addition to providing the forecast, this service will provide the confidence interval associated with the forecast and provide the user (40) with the ability to identify the data that needs to be collected in order improve the confidence associated with a given forecast which will make the process of refining forecasts more efficient.
      • 10. Complete Context™ Indexing Service (619)—service for developing composite and covering indices for data, information and knowledge in contextbase (50) using the impact cutoff and node depth specified by the user (40) in the system settings table (162) for contexts and combination of contexts.
      • 11. Complete Context™ Input Service (601)—service for recording actions and commitments into the contextbase (50). The interface for this service is a template accessed via a browser (800) or the natural language interface (714) provided by the Medicine Service (100) that identifies the available element, transaction, resource and measure data for inclusion in a transaction. After the user has recorded a transaction the service saves the information regarding each action or commitment to the contextbase (50). Other services such as Complete Context™ Analysis (602), Planning (605) or Optimization (604) Services can interface with this service to generate actions, commitments and/or transactions in an automated fashion. Complete Context™ Bots (650) can also be programmed to provide this functionality.
      • 12. Complete Context™ Journal Service (630) (aka the “daily me”)—uses natural language generation to automatically develop and deliver a prioritized summary of news and information in any combination of formats covering a specified time period (hourly, daily, weekly, etc.) that is relevant to a given subject context or context frame. Relevance is determined in a manner identical to that described previously for the Complete Context™ Scout Service (616) save for the fact that the user (40) is free to modify the node depth, subject entity definition and/or impact cutoff used for evaluating relevance using a wizard.
      • 13. Complete Context™ Metrics and Rules Service (611)—tracks and displays the causal performance indicators for context elements, resources and factors for a given context frame as well as the rules used for segmenting context components into smaller groups for more detailed analysis. Rules and patterns can be discovered using an algorithm tournament that includes the Apriori algorithm, the sliding window algorithm; differential association rule mining, beam-search, frequent pattern growth and decision trees.
      • 14. Complete Context™ Optimization Service (604)—simulates entity performance and identifies the optimal mix of actions, events and/or context components for operating a specific context frame or sub context frame given the constraints, uncertainty and the defined function and/or mission measures. A tournament is used to select the best algorithm from the group consisting of genetic algorithms, the calculus of variations, constraint programming, game theory, mixed integer linear programming, multi-criteria maximization, linear programming, semi-definite programming, smoothing and highly optimized tolerance. Because most entities have more than one function (and more than one measure), the genetic algorithm and multi-criteria maximizations are used most frequently. This service can also be used to optimize Complete Context™ Review Service (607) measures using the same rules defined for the Complete Context™ Review Service (607) to define context frames in the required format before optimization.
      • 15. Complete Context™ Planning Service (605)—service that is used to: establish measure priorities, establish action priorities, and establish expected performance levels (aka budgets) for actions, events, elements resources and measures. These priorities and performance level expectations are saved in the corresponding layer in the contextbase (50). For example, measure priorities are saved in the measure layer table (145). This service also supports collaborative planning when context frames that include one or more partners are created (see FIG. 2B).
      • 16. Complete Context™ Profiling Service (615)—service for developing the best estimate of complete entity context from available subject related data and information. If a complete context has been developed for a similar entity, then the Complete Context™ Profiling Service (615) will identify: the portion of behavior that is generally explained by the level of detail in the profile, differences from the similar entity, expected ranges of behavior and sources of data that are generally used to produce a more complete context before completing an analysis of the available data. The contexts developed by this service (615) can be used to.
      • 17. Complete Context™ Project Service (606)—service for analyzing and optimizing the impact of a project or a group of projects on a context frame. Project is broadly defined to include any development or diminution of any components of context and/or entities. Context frame information may be supplemented by simulations and information from subject matter experts (42) as appropriate.
      • 18. Complete Context™ Review Service (607)—service for reviewing components of context and measures alone or in combination. These reviews can be completed with or without the use of a reference layer. This service uses a rules engine to transform contextbase (50) historical information into standardized reports that have been defined by different entities. Other standardized, non-financial performance reports have been developed for medical entities, military operations and educational institutions. The sustainability and controllable performance reports described previously are also pre-defined for calculation and display. The rules engine produces each of these reports on demand for review and optional publication.
      • 19. Complete Context™ Scout Service (616)—service that works with the Complete Context™ Indexing Service (619) to proactively identify data, information and/or knowledge regarding choices the subject will be making in the near future using the time frame or time frames defined by user (40) in system settings table (162). The Complete Context™ Scout (616) uses process maps, preferences and the Complete Context™ Forecast Service (603) to identify the choices that it expects the subject to make in the near future. It then uses weight of evidence/satisfaction algorithms including banburismus to determine which choices need additional data, information and/or knowledge to support an informed decision within parameters selected by the user (40) in the system settings table (162). It of course, also determines which choices are already supported by sufficient data, information and/or knowledge. The relative priority given to the data, information and/or knowledge selected by the Complete Context™ Scout (616) is a blended function of the relevance rankings produced by several measures of relevance including ontology alignment measures, semantic alignment measures, cover density rankings, vector space model measurements, okapi similarity measurements, node rankings (as described in U.S. Pat. No. 6,285,999, which is incorporated herein by reference) which can be obtained from Google, three level relevance scores and hypertext induced topic selection algorithm scores. The relevance measure detailed in cross referenced application Ser. No. 10/237,021 can also be used to identify relevance. The Complete Context™ Scout Service (616) evaluates relevance by utilizing the relationships and impacts that define a complete entity context to the node depth and impact cutoff specified by the user in the system settings table (162) as the basis for scoring using the techniques outlined above. The node depth identifies the number of node connections that are used to identify components of context to be considered in determining the relevance score. For example, if a single entity (as shown in FIG. 2A) was expected to need information about a resource (906) and a node depth of one had been selected, then the relevance rankings would consider the components of context that are linked to resources by a single link. Using this approach data, information and/or knowledge that contains and/or is closely linked to a similar mix of context components will receive a higher ranking. As shown in FIG. 2A, this would include locations (901), projects (902), events (903), virtual locations (904), elements (907), actions (908), transactions (909) and processes (911) that had an impact greater than or equal to the impact cutoff. The Complete Context™ Scout Service (616) has the ability to use word sense disambiguation algorithms to clarify the terms being selected for search, normalizes the terms selected for search using the Porter Stemming algorithm or an equivalent and uses collaborative filtering to learn the combination of ranking methods that are generally preferred for identifying relevant data, information and/or knowledge given the choices being faced by the subject for each context and/or context frame.
      • 20. Complete Context™ Search Service (609)—service for locating the most relevant data, information, services and/or knowledge for a given context frame or sub context frame in one of two modes—direct or indirect. In the direct mode, the relevant data, information and/or services are identified and presented to the user (40). In the indirect mode, candidate data, information and/or services are identified using publicly available search engine results that are re-analyzed before presentation to the user (40). This service can be combined with the Complete Context™ Customization Service (621) to identify and provide customized ads and/or other information related to a given context frame as relevance increases (through movement relative to a reference frame, external changes, etc.). Relevance is determined in a manner identical to that described previously for the Complete Context™ Scout (616) save for the fact that the user (40) is free to modify the node depth, subject definition and/or impact cutoff used for evaluating relevance using a wizard. Any indices associated with the revised subject definitions would automatically be changed by the Complete Context™ Index Service (619) as required to support the changed definition. The user (40) could choose to change the subject definition for any number of reasons. For example, he or she may wish to focus on only one entity context for a vertical search. Another reason for changing the definition would be to incorporate one or more contexts from other entities in a new definition. For example, an employee could choose to search for information relevant to a combination of one or more of his or her contexts (for example, his or her employee context) and one or more contexts of the employer/company (for example, the context of his project or division). As part of its processing, the Complete Context™ Search Engine (609) identifies the relationship between the requested information and other information by using the relationships and measure impacts identified in the contextbase (50). It uses this information to display the related data and/or information in a graphical format similar to the formats used in FIG. 2A, FIG. 2B and/or FIG. 2C. Again, the node depth cutoff is used to determine how “deep” into the graph the search is performed. The user (40) has the option of focusing on any block in a graphical summary of relevant information using the Complete Context™ Browser (628), for example the user (40) could choose to retrieve information about the resources (906) that support an entity (900). As discussed previously (see definitions), the subject may not be the user (40). If this is the case, then the user's context is considered as part of normal processing. Information obtained from the natural language interface (714) could be part of this context;
      • 21. Complete Context™ Summary Service (617)—develops a summary of entity context using the Universal Context Specification (see FIG. 17) in an rdf format that contains the portion of the specification approved for release by the user (40) for use by other applications, services and/or entities. For example, the user (40) could send a summary of two contexts (family member and church-member) to a financial planner for use in establishing a portfolio that will help the user (40) realize his or her goals with respect to these two contexts. This Complete Context™ Summary can be used by others providing goods, services and information (such as other search engines) to tailor their offerings to the portion of context that has been revealed.
      • 22. Complete Context™ Underwriting Service (620)—analyzes a context frame or sub-context frame for an entity in order to: evaluate entity liquidity, evaluate entity creditworthiness, evaluate entity risks and/or complete valuations. It can then use this information to support the: transfer of liquidity to or from said entity, transfer of risks to or from said entity, securitization one or more entity risks, underwriting of entity related securities, packaging of entity related securities into funds or portfolios with similar characteristics (i.e. sustainability, risk, uncertainty equivalent, value, etc.) and/or package entity related securities into funds or portfolios with dissimilar characteristics (i.e. sustainability, risk, uncertainty equivalent, value, etc.). As part of securitizing entity risks the Complete Context™ Underwriting Service (620) identifies an uncertainty equivalent for the risks being underwritten. This innovative analysis combines quantified uncertainty by type with the securitized risks to give investors a more complete picture of the risk they are assuming when they buy a risk security. All of these analyses can rely on the measure layer information stored in the contextbase (50), the sustainability reports, the controllable performance reports and any pre-defined review format. Context frame information may be supplemented by simulations and information from subject matter experts as appropriate.
        The services within the Complete Context™ Suite (625) can be combined in any combination and/or joined together in any combination in order to complete a specific task. For example, the Complete Context™ Review Service (607), the Complete Context™ Forecast Service (603) and the Complete Context™ Planning Service (605) can be joined together to process a series of calculations. The Complete Context™ Analysis Service (602) and the Complete Context™ Optimization Service (604) are also joined together frequently to support performance improvement activities. In a similar fashion the Complete Context™ Optimization Service (604) and the Complete Context™ Capture and Collaboration Service (622) are often combined to support knowledge transfer and simulation based training. The services in the Complete Context™ Suite (625) will hereinafter be referred to as the standard services or the services in the Suite (625).
  • The Personalized Medicine Service (100) utilizes a novel software and system architecture for developing the complete entity context used to support entity related systems and services. Narrow systems (4) generally try to develop and use a picture of how part of an entity is performing (i.e. supply chain, heart functionality, etc.). The user (40) is then left with an enormous effort to integrate these different pictures—often developed from different perspectives—to form a complete picture of entity performance. By way of contrast, the Personalized Medicine Service (100) develops complete pictures of entity performance for every function using a common format (i.e. see FIG. 2A, FIG. 2B and FIG. 2C) before combining these pictures to define the complete entity context and a contextbase (50) for the subject. The detailed information from the complete entity context is then divided and recombined in a context frame or sub-context frame that is used by the standard services in any variety of combinations for analysis and performance management.
  • The contextbase (50) and entity contexts are continually updated by the software in the Personalized Medicine Service (100). As a result, changes are automatically discovered and incorporated into the processing and analysis completed by the Personalized Medicine Service (100). Developing the complete picture first, instead of trying to put it together from dozens of different pieces can allow the system of the present invention to reduce IT infrastructure complexity by orders of magnitude while dramatically increasing the ability to analyze and manage subject performance. The ability to use the same software services to analyze, manage, review and optimize performance of entities at different levels within a domain hierarchy and entities from a wide variety of different domains further magnifies the benefits associated with the simplification enabled by the novel software and system architecture of the present invention.
  • The Personalized Medicine Service (100) provides several other important features, including:
      • 1. the system learns from the data which means that it supports the management of new aspects of entity performance as they become important without having to develop a new system;
      • 2. the user is free to specify any combination of functions and measures for analysis; and
      • 3. support for the automated development and use of bots and other independent software applications (such as services) that can be used to, among other things, initiate actions, complete actions, respond to events, seek information from other entities and provide information to other entities in an automated fashion.
        To illustrate the use of the Personalized Medicine Service (100), a description of the use of the services in the Complete Context™ Suite (625) to support a small clinic (an organization entity) in treating a patient (an organism entity that becomes an element of the clinic entity) will be provided. The clinic has the same measures described in table 10 for a medical facility. An overview of the one embodiment of a system to support this clinic is provided in FIG. 16. The patient comes to the clinic complaining of blood in the urine. After arriving at the clinic, he fills out a form that details his medical history. After the form is filled out, the patient has his weight and blood pressure checked by an aide before seeing a doctor. The doctor reviews the patient's information, examines the patient and prescribes a treatment before moving on to see the next patient. In the narrative that follows, the support provided by the Personalized Medicine Service (100) for each step in the patient visit and the subsequent follow up will be described. The narrative assumes that the system was installed some time ago and has completed the processing used to develop a complete ontology and contextbase (50) for the clinic along with the associated process maps.
  • Process maps define the expected sequence and timing of events, commitments and actions as treatment progresses. If the timing or sequence of events fail to follow the expected path, then the alerts built into the tactical layer will notify designated staff (element). Process maps also identify the agents, assets and resources that will be used to support the treatment process. FIG. 15 shows a sample process map. Process maps can be established centrally in accordance with guidelines or they can be established by individual clinicians in accordance with organization policy. In all cases they are stored in the relationship layer. Before selecting a process map, the doctor could activate the Complete Context™ Analysis Service (602) to review the expected instant impacts and outcomes from different combinations of procedures and treatments that are available under the current formulary. This information could be used to support the development of a new process map (if organization policy permits this). In any event, after the doctor selects a process map for the treatment of the specified diagnosis, the associated process commitments and alerts are associated with the patient and stored in the tactical layer. The required paperwork is automatically generated by the process map and signed as required by the doctor.
  • If the clinic is small, the history information from the clinic can be supplemented with data provided by external sources (such as the AMA, NIH, insurance companies, HMOs, drug companies, etc.) to provide data for a sufficient population to complete the processing to establish expected ranges for the expected mix of patients and diseases.
    Data entry can be completed in a number of ways for each step in the visit. The most direct route would be to use the Complete Context™ Input Service (601) or any xml compliant application (such as newer Microsoft Office and Adobe applications) with a device such as a pc or personal digital assistant to capture information obtained during the visit using the natural language interface (714) or a pre-defined form. Once the data are captured it is integrated with the contextbase (50) in an automated fashion. A paper form could be used for facilities that do not have the ability to provide pc or pda access to patients. This paper form can be transcribed or scanned and converted into an xml document where it could be integrated with the contextbase (50) in an automated fashion. If the patient has used a Personalized Medicine Service (100) that stored data related to his or her health, then this information could be communicated to the Medicine Service (100) in an automated fashion via wireless connectivity, wired connectivity or the transfer of files from the patient's Medicine Service (100) to a recordable media. Recognizing that there are a number of options for completing data entry we will simply say that “data entry is completed” when describing each step.
    Step 1—the patient details prior medical history and data entry is completed. Because the patient is new, a new element for the patient will automatically be created within the ontology and contextbase (50) for the clinic. The medical history will be associated with the new element for the patient in the element layer. Any information regarding insurance will be tagged and stored in the tactical layer which would determine eligibility by communicating with the appropriate insurance provider. The measure layer will in turn use this information to determine the expected margin and/or generate a flag if the patient is not eligible for insurance.
    Step 2—weight and blood pressure are checked by an aide and data entry is completed. The medical history data are used to generate a list of possible diagnoses based on the proximity of the patient's history to previously defined disease clusters and pathways by the analytics that support the instant impact and outcome layers. Any data that is out of the normal range for the cluster will be flagged for confirmation by the doctor. The Personalized Medicine Service (100) would also query external data providers to see if the out of range data correlates with any new clusters that may have been identified since the clinic's contextbase (50) and ontology were established. The analytics in the relationship layer would then identify the tests that should be conducted to validate or invalidate possible diagnoses. Preference would be given to the tests that provide information that is relevant to the highest number of potential diagnoses for the lowest cost. If the patient's history documented the diagnostic imaging history, then consideration would also be given to cumulative radiation levels when recommending tests.
    Step 3—the doctor refers the patient to a diagnostic imaging center using the process map for a pet scan (to look for tumors on the patient's kidneys). He also refers the patient for genetic testing with a new process map that assesses the patients likely response to a new type of chemotherapy.
    Step 4—The images and genetic tests are completed in accordance with the specified process maps. As part of this process, the Personalized Medicine Service (101) in the imaging center highlights any probable tumors before displaying the image to the radiologist for diagnosis. The Personalized Medicine Service (102) in the genetic testing center would determine if the test array displayed the biomarkers (indicators) that indicated a likely favorable response to the new chemotherapy before having the results analyzed by a technician. In both cases the results of the analyses are sent to the Personalized Medicine Service (100) in the clinic for automated integration with the patient's medical history. At this point, the Personalized Medicine Service (100) in the clinic would automatically update the list of likely diagnoses to reflect the newly gathered information.
    Step 5—the doctor reviews the information for the patient from the contextbase (50) using the Complete Context™ Review Service (607) on a device (3) such as a pda or personal computer. The doctor will have the ability to define the exact format of the display by choosing the mix of graphical and text information that will be displayed. At this point, the doctor determines that the patient probably has kidney cancer and refers the patient to a surgeon for further treatment. He activates the process map for a surgical referral, among other things this process map sends the patients medical history to the surgeon's context service system (103) in an automated fashion.
    Step 6—the surgeon examines the medical records and the patient before scheduling surgery for a hospital where he has privileges. He then activates the kidney surgery process map which forwards the medical records to the hospital context service system (104).
    Step 7—the surgeon completes a biopsy that confirms the presence of a malignant tumor before scheduling and completing the required surgery. After the surgery is completed, the surgeon then activates the pre-defined process map for the new chemotherapy (as noted previously, the patient's genetic biomarkers indicated that he would likely respond well to this new treatment). As information is added to the patient's medical history in the hospital context service (104), it is also communicated back to the Personalized Medicine Service (100) in the clinic for inclusion in the patient's medical history in an automated fashion and to the relevant insurance company.
    Step 8—follow up. The chemotherapy process map the doctor selected is used to identify the expected sequence of events that the patient will use to complete his treatment. If the patient fails to complete an event within the specified time range or in the specified order, then the alerts built into the tactical layer will generate email messages to the doctor and/or case worker assigned to monitor the patient for follow-up and possible corrective action. Bots could be used to automate some aspects of routine follow-up like sending reminders or requests for status via email or regular mail. This functionality could also be used to collect information about long-term outcomes from patients in an automated fashion.
    The process map follow-up processing continues automatically until the process ends, a clinician changes the process map for the patient or the patient visits the facility again and the process described above is repeated.
    In short, the services in the Complete Context™ Suite (625) work together with the Personalized Medicine Service (100) to provide knowledgeable support to anyone trying to analyze, manage and/or optimize actions, processes and outcomes for any subject. The contextbase (50) supports the services in the Complete Context™ Suite (625) as described above. The contextbase (50) provides six important benefits:
      • 1. By directly supporting entity performance, the system of the present invention guarantees that the contextbase (50) will provide a tangible benefit to the entity.
      • 2. The measure focus allows the system to partition the search space into two areas with different levels of processing. Data and information that is known to be relevant to the defined functions and/or measures as well as data that are not thought to be relevant. The system does not ignore data that is not known to be relevant; however, it is processed less intensely. This information can also be used to identify data for archiving or disposal.
      • 3. The processing completed in contextbase (50) development defines and maintains the relevant schema or ontology for the entity. This schema or ontology can be flexibly matched with other ontologies in order to interact with other entities that have organized their information using a different ontology. This functionality also enables the automated extraction and integration of data from the semantic web.
      • 4. Defining the complete subject context allows every piece of data that is generated to be placed “in context” when it is first created. Traditional systems generally treat every piece of data in an undifferentiated fashion. As a result, separate efforts are often required to find the data, define a context and then place the data in context.
      • 5. The contextbase (50) includes robust models of the components of context that drive action and event frequency as well as levels to vary. This capability is very useful in developing action plans to improve measure performance.
      • 6. The focus on primary subject functions also ensures the longevity of the contextbase (50) as entity primary functions rarely change. For example, the primary function of each cell in the human body has changed very little over the last 10,000 years.
  • Some of the important features of the patient centric approach are summarized in Table 13.
  • TABLE 13 Characteristic Personalized Medicine Service (100) Tangible benefit Built-in Computation/ Partitioned Search Space Ontology development Automated and maintenance Ability to analyze new Automatic—learns from data element, resource or factor Measures in alignment Automatic Data in context Automatic Service longevity Equal to longevity of definable measure(s)
  • To facilitate its use as a tool for improving performance, the Personalized Medicine Service (100) produces reports in formats that are graphical and highly intuitive. By combining this capability with the previously described capabilities (developing context, flexibly defining robust performance measures, optimizing performance, reducing IT complexity and facilitating collaboration) the Personalized Medicine Service (100) gives individuals, groups and clinicians the tools they need to model, manage and improve the performance of any subject.
  • BRIEF DESCRIPTION OF DRAWINGS
  • These and other objects, features and advantages of the present invention will be more readily apparent from the following description of one embodiment of the invention in which:
  • FIG. 1 is a block diagram showing the major processing steps of the present invention;
  • FIG. 2A, FIG. 2B and FIG. 2C are block diagrams showing a relationship between constraints, elements, events, factors, locations, measures, missions, processes and subject actions/behavior;
  • FIG. 3 shows a relationship between an entity and other entities, processes and groups;
  • FIG. 4 is a diagram showing the tables in the contextbase (50) of the present invention that are utilized for data storage and retrieval during the processing;
  • FIG. 5 is a block diagram of an implementation of the present invention;
  • FIG. 6A, FIG. 6B and FIG. 6C are block diagrams showing the sequence of steps in the present invention used for specifying system settings, preparing data for processing and specifying the subject measures;
  • FIG. 7A, FIG. 7B, FIG. 7C, FIG. 7D, FIG. 7E, FIG. 7F, FIG. 7G and FIG. 7H are block diagrams showing the sequence of steps in the present invention used for creating a contextbase (50) for a subject;
  • FIG. 8A and FIG. 8B are block diagrams showing the sequence in steps in the present invention used in propagating a Personalized Medicine Service, creating bots, services and performance reports;
  • FIG. 9 is a diagram showing the data windows that are used for receiving information from and transmitting information via the interface (700);
  • FIG. 10 is a block diagram showing the sequence of processing steps in the present invention used for identifying, receiving and transmitting data with narrow systems (4);
  • FIG. 11 is a diagram showing how the Personalized Medicine Service (100) develops and supports a natural language interface (714);
  • FIG. 12 is a sample report showing the efficient frontier for Entity XYZ and the current position of XYZ relative to the efficient frontier;
  • FIG. 13 is a diagram showing one embodiment of a Personalized Medicine Service (100) for a clinic;
  • FIG. 14 is a diagram showing how the Personalized Medicine Service (100) for a clinic can be used in conjunction with an integration platform or exchange (99);
  • FIG. 15 is a diagram showing a portion of a process map for treating a mental health patient;
  • FIG. 16 is a diagram showing an embodiment of the Personalized Medicine Service (100) for a clinic that is connected with a Personalized Medicine Service (107) for a patient, a a Personalized Medicine Service (106) for a health plan and an exchange (99); and
  • FIG. 17 shows a universal context specification format.
  • DETAILED DESCRIPTION OF ONE PREFERRED EMBODIMENT
  • FIG. 1 provides an overview of the processing completed by the innovative system for developing a Personalized Medicine Service (100). In accordance with the present invention, an automated system and method for developing a contextbase (50) that supports the development of a Personalized Medicine Service (100) is provided. In one preferred embodiment the contextbase (50) contains context layers for each subject measure. Processing starts in this Medicine Service (100) when the data preparation portion of the application software (200) extracts data from a narrow system database (5); an external database (7); a world wide web (8), external services (9) and optionally, a partner narrow system database (6) via a network (45). The connection to the network (45) can be via a wired connection, a wireless connection or a combination thereof. It is to be understood that the World Wide Web (8) also includes the semantic web that is being developed. Data may also be obtained from a Complete Context™ Input Service (601) or other applications that can provide xml output. For example, newer versions of Microsoft® Office and Adobe® Acrobat® can be used to provide data input to the Medicine Service (100) of the present invention.
  • After data are prepared, entity functions are defined and subject measures are identified, as part of contextbase (50) development in the second part of the application software (300). The contextbase (50) is then used to create a Personalized Medicine Service (100) in the third stage of processing. The processing completed by the Personalized Medicine Service (100) may be influenced by a user (40) or a manager (41) through interaction with a user-interface portion of the application software (700) that mediates the display, transmission and receipt of all information to and from the Complete Context™ Input Service (601) or browser software (800) such as the Mozilla or Opera browsers in an access device (90) such as a phone, personal digital assistant or personal computer where data are entered by the user (40). The user (40) and/or manager (41) can also use a natural language interface (714) provided by the Personalized Medicine Service (100).
  • While only one database of each type (5, 6 and 7) is shown in FIG. 1, it is to be understood that the Medicine Service (100) can process information from all narrow systems (4) listed in Tables 4, 5, 6 and/or 7 as well as the devices (3) listed in Table 8 for each entity being supported. In one embodiment, all functioning narrow systems (4) associated with each entity will provide data access to the Medicine Service (100) via the network (45). It should also be understood that it is possible to complete a bulk extraction of data from each database (5, 6 and 7), the World Wide Web (8) and external service (9) via the network (45) using peer to peer networking and data extraction applications. In one embodiment, the data extracted via the network (45) are tagged in a virtual database that leaves all data in the original databases where it can be retrieved and optionally converted for use in calculations by the analysis bots over a network (45). In alternate embodiments, the data could also be stored in a database, datamart, data warehouse, a cluster (accessed via GPFS), a virtual repository or a storage area network where the analysis bots could operate on the aggregated data.
  • The operation of the system of the present invention is determined by the options the user (40) and manager (41) specify and store in the contextbase (50). As shown in FIG. 4, the contextbase (50) contains tables for storing data by context layer including: a key terms table (140), a element layer table (141), a transaction layer table (142), an resource layer table (143), a relationship layer table (144), a measure layer table (145), a unassigned data table (146), an internet linkages table (147), a causal link table (148), an environment layer table (149), an uncertainty table (150), a context space table (151), an ontology table (152), a report table (153), a reference layer table (154), a hierarchy metadata table (155), an event risk table (156), a subject schema table (157), an event model table (158), a requirement table (159), a context frame table (160), a context quotient table (161), a system settings table (162), a bot date table (163), a Thesaurus table (164), an id to frame table (165), an impact model table (166), a bot assignment table (167), a scenarios table (168), a natural language table (169), a phoneme table (170), a word table (171) and a phrase table (172). The system of the present invention has the ability to accept and store supplemental or primary data directly from user input, a data warehouse, a virtual database, a data preparation system or other electronic files in addition to receiving data from the databases described previously. The system of the present invention also has the ability to complete the necessary calculations without receiving data from one or more of the specified databases. However, in the embodiment described herein all information used in processing is obtained from the specified data sources (5, 6, 7, 8, 9 and 601) for the subject and made available using a virtual database.
  • As shown in FIG. 5, one embodiment of the present invention is a computer Medicine Service (100) illustratively comprised of a computer (110). The computer (110) is connected via the network (45) to an Internet browser appliance (90) that contains Internet software (800) such as a Mozilla browser or an Opera browser. The browser (800) will support RSS feeds.
  • In one embodiment, the computer (110) has a read/write random access memory (111), a hard drive (112) for storage of a contextbase (50) and the application software (200, 300, 400 and 700), a keyboard (113), a communication bus (114), a display (115), a mouse (116), a CPU (117), a printer (118) and a cache (119). As devices (3) become more capable, they be used in place of the computer (110). Larger entities may require the use of a grid or cluster in place of the computer (110) to support Complete Context™ Service processing requirements. In an alternate configuration, all or part of the contextbase (50) can be maintained separately from a device (3) or computer (110) and accessed via a network (45) or grid.
  • The application software (200, 300, 400 and 700) controls the performance of the central processing unit (117) as it completes the calculations used to support Complete Context™ Service development. In the embodiment illustrated herein, the application software program (200, 300, 400 and 700) is written in a combination of Java and C++. The application software (200, 300, 400 and 700) can use Structured Query Language (SQL) for extracting data from the databases and the World Wide Web (5, 6, 7 and 8). The user (40) and manager (41) can optionally interact with the user-interface portion of the application software (700) using the browser software (800) in the browser appliance (90) or through a natural language interface (714) provided by the Medicine Service (100) to provide information to the application software (200, 300, 400 and 700).
  • The computers (110) shown in FIG. 5 is a personal computer that is widely available for use with Linux, Unix or Windows operating systems. Typical memory configurations for client personal computers (110) used with the present invention include more than 1024 megabytes of semiconductor random access memory (111) and a hard drive (112).
  • As discussed previously, the Personalized Medicine Service (100) completes processing in three distinct stages. As shown in FIG. 6A, FIG. 6B and FIG. 6C the first stage of processing (block 200 from FIG. 1) identifies and prepares data from narrow system databases (5); external databases (7); the world wide web (8), external services (9) and optionally, a partner narrow system database (6) for processing. This stage also identifies the entity and entity function and/or mission measures. As shown in FIG. 7A, FIG. 7B, FIG. 7C, FIG. 7D, FIG. 7E, FIG. 7F, FIG. 7G and FIG. 7H, the second stage of processing (block 300 from FIG. 1) develops and then continually updates a contextbase (50) for each subject measure. As shown in FIG. 8A and FIG. 8B, the third stage of processing (block 400 from FIG. 1) identifies the valid context space before developing and distributing one or more entity contexts via a Personalized Medicine Service (100). The third stage of processing also prepares and prints optional reports. If the operation is continuous, then the processing steps described are repeated continuously. As described below, one embodiment of the software is a bot or agent architecture. Other architectures including a service architecture, an n-tier client server architecture, an integrated application architecture and combinations thereof can be used to the same effect.
  • ENTITY DEFINITION
  • The flow diagrams in FIG. 6A, FIG. 6B and FIG. 6C detail the processing that is completed by the portion of the application software (200) that defines the subject, identifies the functions and measures for said subject, prepares data for use in processing and accepts user (40) and management (41) input. As discussed previously, the system of the present invention is capable of accepting data from and transmitting data to all the narrow systems (4) listed in Tables 4, 5, 6 and 7. It can also accept data from and transmit data to the devices listed in Table 8. Data extraction, processing and storage are normally completed by the Personalized Medicine Service (100). This data extraction, processing and storage can be facilitated by a separate data integration layer in an operating system or middleware application as described in cross referenced application Ser. No. 10/748,890. Operation of the Personalized Medicine Service (100) will be illustrated by describing the extraction and use of structured data from a narrow system database (5) for supply chain management and an external database (7). A brief overview of the information typically obtained from these two databases will be presented before reviewing each step of processing completed by this portion (200) of the application software.
  • Supply chain systems are one of the narrow systems (4) identified in Table 7. Supply chain databases are a type of narrow system database (5) that contain information that may have been in operation management system databases in the past. These systems provide enhanced visibility into the availability of resources and promote improved coordination between subject entities and their supplier entities. All supply chain systems would be expected to track all of the resources ordered by an entity after the first purchase. They typically store information similar to that shown below in Table 14.
  • TABLE 14 Supply chain system information 1. Stock Keeping Unit (SKU) 2. Vendor 3. Total quantity on order 4. Total quantity in transit 5. Total quantity on back order 6. Total quantity in inventory 7. Quantity available today 8. Quantity available next 7 days 9. Quantity available next 30 days 10. Quantity available next 90 days 11. Quoted lead time 12. Actual average lead time
  • External databases (7) are used for obtaining information that enables the definition and evaluation of words, phrases, context elements, context factors and event risks. In some cases, information from these databases can be used to supplement information obtained from the other databases and the World Wide Web (5, 6 and 8). In the system of the present invention, the information extracted from external databases (7) includes the data listed in Table 15.
  • TABLE 15 External database information 1. Text information such as that found in the Lexis Nexis database 2. Text information from databases containing past issues of specific publications 3. Multimedia information such as video and audio clips 4. Idea market prices indicate likelihood of certain events occurring 5. Event risk data including information about risk probability and magnitude for weather and geological events 6. Known phonemes and phrases
  • System processing of the information from the different data sources (3, 4, 5, 6, 7, 8 and 9) described above starts in a block 202, FIG. 6A. The software in block 202 prompts the user (40) via the system settings data window (701) to provide system setting information. The system setting information entered by the user (40) is stored in the system settings table (162) in the contextbase (50). The specific inputs the user (40) is asked to provide at this point in processing are shown in Table 16.
  • TABLE 16 1. Continuous, if yes, calculation frequency? (by minute, hour, day, week, etc.) 2. Subject (patient, group or patient-entity multi domain system) 3. SIC Codes 4. Names of primary competitors by SIC Code (if applicable) 5. Base account structure 6. Base units of measure 7. Base currency 8. Risk free interest rate 9. Program bots or applications? (yes or no) 10. Process measurements? (yes or no) 11. Probabilistic relational models? (yes or no) 12. Knowledge capture and/or collaboration? (yes or no) 13. Natural language interface? (yes, no or voice activated) 14. Video data extraction? (yes or no) 15. Image data extraction? (yes or no) 16. Internet data extraction? (yes or no) 17. Reference layer? (yes or no, if yes specify coordinate system(s)) 18. Text data analysis? 19. Geo-coded data? (if yes, then specify standard) 20. Maximum number of clusters (default is six) 21. Management report types (text, graphic or both) 22. Default missing data procedure (chose from selection) 23. Maximum time to wait for user input 24. Maximum number of subelements 25. Most likely scenario, normal, extreme or mix (default is normal) 26. System time period (days, month, years, decades, light years, etc.) 27. Date range for history-forecast time periods (optional) 28. Uncertainty level and source by narrow system type (optionally, default is zero) 29. Weight of evidence cutoff level (by context) 30. Time frame(s) for proactive search (hours, days, weeks, etc.) 31. Node depth for scouting and/or searching for data, information and knowledge 32. Impact cutoff for scouting and/or searching for data, information and knowledge

    The system settings data are used by the software in block 202 to establish context layers. As described previously, there are generally eight types of context layers for the subject. The application of the remaining system settings will be further explained as part of the detailed explanation of the system operation. The software in block 202 also uses the current system date and the system time period saved in the system settings table (162) to determine the time periods (generally in months) where data will be sought to complete the calculations. The user (40) also has the option of specifying the time periods that will be used for system calculations. After the date range is stored in the system settings table (162) in the contextbase (50), processing advances to a software block 203.
  • The software in block 203 prompts the user (40) via the entity data window (702) to identify the subject, identify subject functions and identify any extensions to the subject hierarchy or hierarchies specified in the system settings table (162). For example if the organism hierarchy (2300) was chosen, the user (40) could extend the hierarchy by specifying a join with the cellular hierarchy (2200). As part of the processing in this block, the user (40) is also given the option to modify the subject hierarchy or hierarchies. If the user (40) elects to modify one or more hierarchies, then the software in the block will prompt the user (40) to provide information for use in modifying the pre-defined hierarchy metadata in the hierarchy metadata table (155) to incorporate the modifications. The user (40) can also elect to limit the number of separate levels that are analyzed below the subject in a given hierarchy. For example, an organization could choose to examine the impact of their divisions on organization performance by limiting the context elements to one level below the subject. After the user (40) completes the specification of hierarchy extensions, modifications and limitations, the software in block 203 selects the appropriate metadata from the hierarchy metadata table (155) and establishes the hierarchy metadata (155) and stores the ontology (152) and entity schema (157). The software in block 203 uses the extensions, modifications and limitations together with three rules for establishing the entity schema:
      • 1. the members of the entity hierarchy that are above the subject are factors;
      • 2. hierarchies that could be used to extend the entity hierarchy that are not selected will be excluded; and
      • 3. all other hierarchies and groups will be potential factors.
        After subject schema is developed, the user (40) is asked to define process maps and procedures. The maps and procedures identified by the user (40) are stored in the relationship layer table (144) in the contextbase (50). The information provided by the user (40) will be supplemented with information developed later in the first stage of processing. It is also possible to obtain relationship layer information concerning process maps and procedures in an automated fashion by analyzing transaction patterns or reverse engineering narrow systems (4) as they often codify the relationship between different context elements, factors, events, resources and/or actions. The Complete Context™ Capture and Collaboration Service (622) can also be used here to supplement the information provided by the user (40) with information from subject matter experts (42). After data storage is complete, processing advances to a software block 204.
  • The software in block 204 prompts a context interface window (715) to communicate via a network (45) with the different devices (3), systems (4), databases (5, 6, 7), the World Wide Web (8) and external services (9) that are data sources for the Personalized Medicine Service (100). As shown on FIG. 10 the context interface window (715) contains a multiple step operation where the sequence of steps depends on the nature of the interaction and the data being provided to the Medicine Service (100). In one embodiment, a data input session would be managed by the a software block (720) that identifies the data source (3, 4, 5, 6, 7, 8 or 9) using standard protocols such as UDDI or xml headers, maintains security and establishes a service level agreement with the data source (3, 4, 5, 6, 7, 8 or 9). The data provided at this point could include transaction data, descriptive data, imaging data, video data, text data, sensor data, geospatial coordinate data, array data, virtual reference coordinate data and combinations thereof. The session would proceed to a software block (722) for pre-processing such as discretization, transformation and/or filtering. After completing the pre-processing in software block 722, processing would advance to a software block (724). The software in that block would determine if the data provided by the data source (3, 4, 5, 6, 7, 8 or 9) complied with the entity schema or ontology using pair-wise similarity measures on several dimensions including terminology, internal structure, external structure, extensions, hierarchical classifications (see Tables 1, 2 and 3) and semantics. If it did comply, then the data would not require alignment and the session would advance to a software block (732) where any conversions to match the base units of measure, currency or time period specified in the system settings table (162) would be identified before the session advanced to a software block (734) where the location of this data would be mapped to the appropriate context layers and stored in the contextbase (50). Establishing a virtual database in this manner eliminates the latency that can cause problems for real time processing. The virtual database information for the element layer for the subject and context elements is stored in the element layer table (141) in the contextbase (50). The virtual database information for the resource layer for the subject resources is stored in the resource layer table (143) in the contextbase (50). The virtual database information for the environment layer for the subject and context factors is stored in the environment layer table (149) in the contextbase (50). The virtual database information for the transaction layer for the subject, context elements, actions and events is stored in the transaction layer table (142) in the contextbase (50). The processing path described in this paragraph is just one of many paths for processing data input.
  • As shown FIG. 10, the context interface window (715) has provisions for an alternate data input processing path. This path is used if the data are not in alignment with the entity schema (157) or ontology (152). In this alternate mode, the data input session would still be managed by the session management software in block (720) that identifies the data source (3, 4, 5, 6, 7, 8 or 9) maintains security and establishes a service level agreement with the data source (3, 4, 5, 6, 7, 8 or 9). The session would proceed to the pre-processing software block (722) where the data from one or more data sources (3, 4, 5, 6, 7, 8 or 9) that requires translation and optional analysis is processed before proceeding to the next step. The software in block 722 has provisions for translating, parsing and other pre-processing of audio, image, micro-array, transaction, video and unformatted text data formats to schema or ontology compliant formats (xml formats in one embodiment). The audio, text and video data are prepared as detailed in cross referenced patent application Ser. No. 10/717,026. Image translation involves conversion, registration, segmentation and segment identification using object boundary models. Other image analysis algorithms can be used to the same effect. Other pre-processing steps can include discretization and stochastic resonance processing. After pre-processing is complete, the session advances to a software block 724. The software in block 724 determine whether or not the data was in alignment with the ontology (152) or schema (157) stored in the contextbase (50) using pair wise comparisons as described previously. Processing then advances to the software in block 736 which uses the mappings identified by the software in block 724 together with a series of matching algorithms including key properties, similarity, global namespace, value pattern and value range algorithms to align the input data with the entity schema (157) or ontology (152). Processing, then advances to a software block 738 where the metadata associated with the data are compared with the metadata stored in the subject schema table (157). If the metadata are aligned, then processing is completed using the path described previously. Alternatively, if the metadata are still not aligned, then processing advances to a software block 740 where joins, intersections and alignments between the two schemas or ontologies are completed in an automated fashion. Processing then advances to a software block 742 where the results of these operations are compared with the schema (157) or ontology (152) stored in the contextbase (50). If these operations have created alignment, then processing is completed using the path described previously. Alternatively, if the metadata are still not aligned, then processing advances to a software block 746 where the schemas and/or ontologies are checked for partial alignment. If there is partial alignment, then processing advances to a software block 744. Alternatively, if there is no alignment, then processing advances to a software block 747 where the data are tagged for manual review and stored in the unassigned data table (146). The software in block 744 cleaves the data in order to separate the portion that is in alignment from the portion that is not in alignment. The portion of the data that is not in alignment is forwarded to software block 747 where it is tagged for manual alignment and stored in the unassigned data table (146). The portion of the data that is in alignment is processed using the path described previously. Processing advances to a block 748 where the user (40) reviews the unassigned data table (146) using the review window (703) to see if the entity schema should be modified to encompass the currently unassigned data and the changes in the schema (157) and/or ontology (152)—if any—are saved in the contextbase (50).
  • After context interface window (715) processing is completed for all available data from the devices (3), systems (4), databases (5, 6 and 7), the World Wide Web (8), and external services (9), processing advances to a software block 206 where the software in block 206 optionally prompts the context interface window (715) to communicate via a network (45) with the Complete Context™ Input Service (601). The context interface window (715) uses the path described previously for data input to map the identified data to the appropriate context layers and store the mapping information in the contextbase (50) as described previously. After storage of the Complete Context™ Input Service (601) data are complete, processing advances to a software block 207.
  • The software in block 207 prompts the user (40) via the review data window (703) to optionally review the context layer data that has been stored in the first few steps of processing. The user (40) has the option of changing the data on a one time basis or permanently. Any changes the user (40) makes are stored in the table for the corresponding context layer (i.e. transaction layer changes are saved in the transaction layer table (142), etc.). As part of the processing in this block, an interactive GEL algorithm prompts the user (40) via the review data window (703) to check the hierarchy or group assignment of any new elements, factors and resources that have been identified. Any newly defined categories are stored in the relationship layer table (144) and the subject schema table (157) in the contextbase (50) before processing advances to a software block 208.
  • The software in block 208 prompts the user (40) via the requirement data window (710) to optionally identify requirements for the subject. Requirements can take a variety of forms but the two most common types of requirements are absolute and relative. For example, a requirement that the level of cash should never drop below $50,000 is an absolute requirement while a requirement that there should never be less than two months of cash on hand is a relative requirement. The user (40) also has the option of specifying requirements as a subject function later in this stage of processing. Examples of different requirements are shown in Table 17.
  • TABLE 17 Entity Requirement (reason) Individual (1401) Stop working at 67 (retirement) Keep blood pressure below 155/95 (health) Available funds > $X by Jan. 1, 2014 (college for daughter) Government Foreign currency reserves > $X (IMF requirement) Organization (1607) 3 functional divisions on standby (defense) Pension assets > liabilities (legal) Circulatory System Cholesterol level between 120 and 180 (2304) Pressure between 110/75 and 150/100

    The software in this block provides the ability to specify absolute requirements, relative requirements and standard “requirements” for any reporting format that is defined for use by the Complete Context™ Review Service (607).
  • After requirements are specified, they are stored in the requirement table (159) in the contextbase (50) by entity before processing advances to a software block 211.
  • The software in block 211 checks the unassigned data table (146) in the contextbase (50) to see if there are any data that has not been assigned to an entity and/or context layer. If there are no data without a complete assignment (entity and element, resource, factor or transaction context layer constitutes a complete assignment), then processing advances to a software block 214. Alternatively, if there are data without an assignment, then processing advances to a software block 212. The software in block 212 prompts the user (40) via the identification and classification data window (705) to identify the context layer and entity assignment for the data in the unassigned data table (146). After assignments have been specified for every data element, the resulting assignments are stored in the appropriate context layer tables in the contextbase (50) by entity before processing advances to a software block 214.
  • The software in block 214 checks the element layer table (141), the transaction layer table (142) and the resource layer table (143) and the environment layer table (149) in the contextbase (50) to see if data are missing for any specified time period. If data are not missing for any time period, then processing advances to a software block 218. Alternatively, if data for one or more of the specified time periods identified in the system settings table (162) for one or more items is missing from one or more context layers, then processing advances to a software block 216. The software in block 216 prompts the user (40) via the review data window (703) to specify the procedure that will be used for generating values for the items that are missing data by time period. Options the user (40) can choose at this point include: the average value for the item over the entire time period, the average value for the item over a specified time period, zero or the average of the preceding item and the following item values and direct user input for each missing value. If the user (40) does not provide input within a specified interval, then the default missing data procedure specified in the system settings table (162) is used. When the missing time periods have been filled and stored for all the items that were missing data, then system processing advances to a block 218.
  • The software in block 218 retrieves data from the element layer table (141), the transaction layer table (142), the resource layer table (143) and the environment layer table (149). It uses this data to calculate indicators for the data associated with each element, resource and environmental factor. The indicators calculated in this step are comprised of comparisons, regulatory measures and statistics. Comparisons and statistics are derived for: appearance, description, numeric, shape, shape/time and time characteristics. These comparisons and statistics are developed for different types of data as shown below in Table 18.
  • TABLE 18 Characteristic/ Appear- Shape- Data type ance Description Numeric Shape Time Time audio X X X coordinate X X X X X image X X X X X text X X X transaction X X video X X X X X X = comparisons and statistics are developed for these characteristic/data type combinations

    Numeric characteristics are pre-assigned to different domains. Numeric characteristics include amperage, area, concentration, density, depth, distance, growth rate, hardness, height, hops, impedance, level, mass to charge ratio, nodes, quantity, rate, resistance, similarity, speed, tensile strength, voltage, volume, weight and combinations thereof. Time characteristics include frequency measures, gap measures (i.e. time since last occurrence, average time between occurrences, etc.) and combinations thereof. The numeric and time characteristics are also combined to calculate additional indicators. Comparisons include: comparisons to baseline (can be binary, 1 if above, 0 if below), comparisons to external expectations, comparisons to forecasts, comparisons to goals, comparisons to historical trends, comparisons to known bad, comparisons to known good, life cycle comparisons, comparisons to normal, comparisons to peers, comparisons to regulations, comparison to requirements, comparisons to a standard, sequence comparisons, comparisons to a threshold (can be binary, 1 if above, 0 if below) and combinations thereof. Statistics include: averages (mean, median and mode), convexity, copulas, correlation, covariance, derivatives, Pearson correlation coefficients, slopes, trends and variability. Time lagged versions of each piece of data, statistic and comparison are also developed. The numbers derived from these calculations are collectively referred to as “indicators” (also known as item performance indicators and factor performance indicators). The software in block 218 also calculates mathematical and/or logical combinations of indicators called composite variables (also known as composite factors when associated with environmental factors). These combinations include both pre-defined combinations and derived combinations. The AQ program is used for deriving combinations. It should be noted that other attribute derivation algorithms, such as the LINUS algorithms, may be used to generate the combinations. The indicators and the composite variables are tagged and stored in the appropriate context layer table—the element layer table (141), the resource layer table (143) or the environment layer table (149)—before processing advances to a software block 220.
  • The software in block 220 checks the bot date table (163) and deactivates pattern bots with creation dates before the current system date and retrieves information from the system settings table (162), the element layer table (141), the transaction layer table (142), the resource layer table (143) and the environment layer table (149). The software in block 220 then initializes pattern bots for each layer to identify patterns in each layer. Bots are independent components of the application software of the present invention that complete specific tasks. In the case of pattern bots, their tasks are to identify patterns in the data associated with each context layer. In one embodiment, pattern bots use Apriori algorithms identify patterns including frequent patterns, sequential patterns and multi-dimensional patterns. However, a number of other pattern identification algorithms including the sliding window algorithm; differential association rule, beam-search, frequent pattern growth, decision trees and the PASCAL algorithm can be used alone or in combination to the same effect. Every pattern bot contains the information shown in Table 19.
  • TABLE 19 1. Unique ID number (based on date, hour, minute, second of creation) 2. Creation date (date, hour, minute, second) 3. Storage location 4. Entity type(s) 5. Entity 6. Context Layer 7. Algorithm

    After being initialized, the bots identify patterns for the data associated with elements, resources, factors and combinations thereof. Each pattern is given a unique identifier and the frequency and type of each pattern is determined. The numeric values associated with the patterns are indicators. The values are stored in the appropriate context layer table before processing advances to a software block 222.
  • The software in block 222 uses causal association algorithms including LCD, CC and CU to identify causal associations between indicators, composite variables, element data, factor data, resource data and events, actions, processes and measures. The software in this block uses semantic association algorithms including path length, subsumption, source uncertainty and context weight algorithms to identify associations. The identified associations are stored in the causal link table (148) for possible addition to the relationship layer table (144) before processing advances to a software block 224.
  • The software in block 224 uses a tournament of petri nets, time warping algorithms and stochism algorithms to identify probable subject processes in an automated fashion. Other pathway identification algorithms can be used to the same effect. The identified processes are stored in the relationship layer table (144) before processing advances to a software block 226.
  • The software in block 226 prompts the user (40) via the review data window (703) to optionally review the new associations stored in the causal link table (148) and the newly identified processes stored in the relationship layer table (144). Associations and/or processes that have already been specified or approved by the user (40) will not be displayed automatically. The user (40) has the option of accepting or rejecting each identified association or process. Any associations or processes the user (40) accepts are stored in the relationship layer table (144) before processing advances a software block 242.
  • The software in block 242 checks the measure layer table (145) in the contextbase (50) to determine if there are current models for all measures for every entity. If all measure models are current, then processing advances to a software block 252. Alternatively, if all measure models are not current, then the next measure for the next entity is selected and processing advances to a software block 244.
  • The software in block 244 checks the bot date table (163) and deactivates event risk bots with creation dates before the current system date. The software in the block then retrieves the information from the transaction layer table (142), the relationship layer table (144), the event risk table (156), the subject schema table (157) and the system settings table (162) in order to initialize event risk bots for the subject in accordance with the frequency specified by the user (40) in the system settings table (162). Bots are independent components of the application software that complete specific tasks. In the case of event risk bots, their primary tasks are to forecast the frequency and magnitude of events that are associated with negative measure performance in the relationship layer table (144). In addition to forecasting risks that are traditionally covered by insurance such as fires, floods, earthquakes and accidents, the system of the present invention also uses the data to forecast standard, “non-insured” event risks such as the risk of employee resignation and the risk of customer defection. The system of the present invention uses a tournament forecasting method for event risk frequency and duration. The mapping information from the relationship layer is used to identify the elements, factors, resources and/or actions that will be affected by each event. Other forecasting methods can be used to the same effect. Every event risk bot contains the information shown in Table 20.
  • TABLE 20 1. Unique ID number (based on date, hour, minute, second of creation) 2. Creation date (date, hour, minute, second) 3. Mapping information 4. Storage location 5. Hierarchy or group 6. Entity 7. Event (fire, flood, earthquake, tornado, accident, defection, etc.)

    After the event risk bots are initialized they activate in accordance with the frequency specified by the