FIELD OF INVENTION

This invention relates to natural language understanding and interpretation by a computer system. It relates in general to tools and methods for computational linguistics. In particular, the present invention relates to a framework and system to infer entity-state and activity-state with the larger aim to enable natural language understanding in machines.

BACKGROUND
The contemporary Natural Language Processing(NLP) systems use Neural Networks(NN) or other statistical methods to process Natural Language Inputs (NLI). These systems can only extract information that exists in the NLI. However Natural Language communication relies on commonly known implicit information which is assumed to be part the readers knowledge. The relation between various entities is not explicitly mentioned. Meaning of each action, its effect on the entities is also not mentioned in the NLI. These relations and effects are to be inferred by the reader with their previous common knowledge. However, without extracting and inferring these relations, the understanding of natural language is not complete and may lead to errors.
The inability of the current day system to process each individual sentence separately and carry forward the understanding from one sentence to the next, limits the system capabilities and exponentially increases the complexity of the system.
Therefore, a methodology is required, using which a system can infer the entity-state and activity-state before, during, and after each sentence. This will empower the machines with the capability to achieve effective and operational natural language understanding.

References:-
U.S. Patent Documents
Patent Number Date Inventor
5721938
February 1998 Stuckey
5752052
May 1998 Richardson
9110883
August 2015 Ghannam
2003/0233224
December 2003 Marchisio
2004/0220796
November 2004 Parkinson
2006/0217963
September 2006 Masuichi
2007/0016398
January 2007 Buchholz
10,503,769
December 2019 Ghannam
9934465
April 2018 Hunt
10474647
Nov 2019 Sweeney
5794050
Aug 1998 Kathleen Dahlgren
7840400
November 2010 Ofer Lavi

OBJECTIVE
There is a pressing need to have the capability to infer entity-state and activity-state from NLI to achieve effective natural language understanding. The current statistical and rule-based systems fall short of the desired results as has been discussed in the background section.
The principal object of this invention is to infer the entity-state and activity-state through knowledge based, intelligent reasoning system. The principal object is achieved by formulating rules and developing software engines to firstly extract entities and activities, and thereafter inferring the states of extracted entities and activities.
A further objective of this invention is to develop rules to transfer the extracted and inferred entity-state and activity-state across multiple sentences. This objective leads to a coherent, logical and explainable story built by tracking the state(s) over time.
AUI Systems has developed a solution framework based on proprietary technology which provides meaning interpretation and a robust universal knowledge system. It combines linguistics, general and domain knowledge, common sense, and reasoning through multiple subsystems to infer entity-state and activity-state, to enable natural language understanding in machines.
Before we elaborate the subsystems, it would be prudent to qualify the entity-state and activity-state. Let us examine the usage of some critical terminologies pertinent to this claim.
1. Entity. An entity is any physical, non-physical, tangible, or non-tangible concept. Entities are the primary participants in information sharing.
2. Property. Each entity can have many properties associated with it. These properties define some aspect of the entity. They can be simple attributes or its relationship with other entities.
3. Entity-State: It is the set of all the properties an entity has at a given point of time.
4. Activity. An activity is the action which an entity or multiple entities perform.
5. Activity-Role. These are important participants involved in an Activity, state of that Activity or the relation of the Activity to other activities.
6. Role-Performing-Entity/ Role-Performing-Activity. This is the Entity/Activity which will be taking a particular Activity-Role in an activity.
7. Activity-State. Activity-state is the set of all roles associated with the activity at a given point in time.
Entity-state and activity-state Inferencing System
As the principal objective of the invention, AUI has developed a proprietary system consisting of the following subsystems to extract and infer entity-state and activity-state to achieve understanding in computer systems. Please refer Figure 1.
• Knowledge base. AUI has developed a knowledge-based system to capture the real-world knowledge (or common worldly knowledge) along with all the supporting rules. The Knowledge base consists of the following: -
o Symbol Index. This index stores all the symbols that are used in the systems. Please refer Annexure 1.
o Taxonomy. This is the relationship which classifies all the symbols into an interlinked hierarchy. Please refer Annexure 2.
o Meaning Store. This captures all the rules and facts that are required to perform natural language understanding.
• Knowledge for Inferencing. AUI has developed specific knowledge variants(types) required for each specific task. Knowledge types have specific pattern which helps the system infer the required state. Each of these can be extended by adding more rules to cover wider input. The Knowledge-types are as follows. Hierarchical Taxonomy is used to compress the number of rules required in each case.
o The Entity-State Extraction Rules before processing a sentence: -
? Adjective-Noun rules. These rules define the entity-state of an entity when it is preceded by an adjective. Please refer Annexure 3.
? Noun-Noun rules. These rules define the entity relation of entities when two Nouns are used one after the other in a sentence. Please refer Annexure 4.
? Noun-Preposition-Noun rules. These rules define the Entity relation of the entities when two Nouns are used with a preposition in between. Please refer Annexure 5.
o Activity-State Extraction Rules: -
? Verb-Subject-Object rules. These rules uniquely define the entities that are used along with a verb and extract the Entity-State and Activity-State. Please refer Annexure 6.
? Activity-Preposition/Conjunction-Activity rules. When multiple verbs are used in a sentence, there is a unique way these verbs influence each other. This rule captures the relation between the extracted activities and their parent verbs and the inter-relation between various activities. Please refer Annexure 7.
? Adverb-Verb rules. The Adverb Verb rules captures the change in the activity-state and entity-state when an adverb interacts with a verb in a sentence. Please refer Annexure 8.
o Entity-State Inferencing rules. These rule captures the effect of one entity-state on to the other entities and their state(s). It also identifies the rules for transferring the Entity-State from one sentence to another. Please refer Annexure 9.
o Activity-State Inferencing rules. The information of all the roles in an activity generally does not come in a single sentence. These rules specify the methodology to complete the activity-state by inferencing the roles from other preceding sentences and from the associated entity state. Please refer Annexure 10.
• Each of these Knowledge types require specific knowledge processing logic and engine (Please refer Figure 2). The following Knowledge processing engines have been developed for processing these Knowledge types: -
o The Entity-State Extraction is achieved by processing a sentence through the following engines: -
? Adjective-Noun Relation Extraction Engine
? Noun-Noun Relation Extraction Engine
? Noun-Preposition-Relation Extraction Engine
o Activity-State Extraction is achieved by processing a sentence through the following engines: -
? Verb-Subject-Object state change Extraction Engine
? Activity-preposition/conjunction-Activity Relation Extraction Engine
? Adverb-Verb Relation Extraction Engine
o Entity-State Inferencing Engine
o Activity-State Inferencing Engine

To elaborate the invention, we will take an example and explain the process through the example. Let's consider the following Natural Language Input (NLI): -
• John withdrew 500 Rs.
• He booked an Uber cab.
• He went to market.
• He bought a basket of Apples for 400 Rs.

A system is required to perform the following: -
1. Extract entity-state of all entities in a sentence as it existed prior to the performance of activities in the sentence. This entails identification of entity properties which are defined in the sentence at a time just prior to the performance of activity mentioned in that sentence. These relations come in the form of Adjective-Noun/ Noun-Noun or Noun-Preposition-Noun combinations (noun phrases)

John withdrew 500 Rs.
Entity-State before sentence Entity: John
• No further state deducible
Entity: Rs
• has value=500
He booked an Uber cab.
Entity-State before sentence Entity: John (He) (Co-reference Resolution done)
• No further state deducible
Entity: Cab
• has aggregator = Uber
He went to market.
Entity-State before sentence Entity: John (He) (Co-reference Resolution done)
• No further state deducible
Entity: Market
• No further state deducible
He bought a basket of Apples for 400 Rs.
Entity-State before sentence Entity: John (He) (Co-reference Resolution done)
• No further state deducible
Entity: Basket
• has items = apples
Entity: Rs
• has value= 400

2. Extract Activity-State of all activities being performed in the sentence. Every sentence will have at least one verb. Sometimes the verb in the sentences are just helper verbs or the main activity comes as a noun. Firstly, there is a requirement to identify the main activity which is being performed in the sentence. Once, the activity has been identified, the knowledge of that activity is used along with the pre-created knowledge in the Knowledge Base for understanding the verb. With this knowledge, the system identifies all the activities along with the roles from the input sentence.
John withdrew 500 Rs.
Entity-State before sentence Entity: John
• No further state deducible
Entity: Rs
• has value=500
Activity-State Activity: Withdraw
• Performer: John
• Amount: 500 Rs
He booked an Uber cab.
Entity-State before sentence Entity: John (He)
• No further state deducible
Entity: Cab
• has aggregator = Uber
Activity-State Activity: Book-Transport
• Performer: John (He)
• Type of Vehicle: Cab
• Aggregator: Uber
• Source: unknown
• Destination: unknown
He went to market.
Entity-State before sentence Entity: John (He)
• No further state deducible
Entity: market
• No further state deducible
Activity-State Activity: Change-Of-Location
• Performer: John (He)
• Mode of transport: unknown
• Source: unknown
• Destination: market
He bought a basket of Apples for 400 Rs.
Entity-State before sentence Entity: John (He)
• No further state deducible
Entity: Basket
• has items = apples
Entity: Rs
• has value= 400
Activity-State Activity: Sell-Item
• Seller: Unknown
• Buyer: John (He)
• Item: Basket of Apples
• Cost: 400 Rs

3. Entity-State of all entities in a sentence after all the activities in the sentence have been performed is identified. By virtue of performing an activity, the relation between the entities in the sentence change. The rules required to understand this Entity-State change are created in knowledge base. This knowledge is applied and the Entity-State change of the participating entities in the sentences are evaluated.
John withdrew 500 Rs.
Entity-State before sentence Entity: John
• No further state deducible
Entity: Rs
• has value=500
Activity-State Activity: Withdraw
• Performer: John
• Amount: 500 Rs
Entity-State after sentence Entity: John
• has possession = 500 Rs
He booked an Uber cab.
Entity-State before sentence Entity: John (He)
• No further state deducible
Entity: Cab
• has aggregator = Uber
Activity-State Activity: Book-Transport
• Performer: John (He)
• Type of Vehicle: Cab
• Aggregator: Uber
• Source: unknown
• Destination: unknown
Entity-State after sentence No Change in entity state
He went to market.
Entity-State before sentence Entity: John (He)
• No further state deducible
Entity: market
• No further state deducible
Activity-State Activity: Change-Of-Location
• Performer: John (He)
• Mode of transport: unknown
• Source: unknown
• Destination: market
Entity-State after sentence Entity: John (He)
• has location = Market
He bought a basket of Apples for 400 Rs.
Entity-State before sentence Entity: John (He)
• No further state deducible
Entity: Basket
• has items = apples
Entity: Rs
• has value= 400
Activity-State Activity: Sell-Item
• Seller: Unknown
• Buyer: John (He)
• Item: Basket of Apples
• Cost: 400 Rs
Entity-State after sentence Entity: John (He)
• has possession = Basket of apples
• has possession = (-)400 Rs
Entity: Basket
• has items = apples
• has cost = 400 Rs

4. Transfer of Entity-State to the next sentence. The Entity-State is persistant and requires to be carried forward. There is a requirement of transferring the Entity-State from one sentence to another. The rules of transferring the Entity-State are created in the Knowledge base.
John withdrew 500 Rs.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John
• No further state deducible
Rs
• has value=500
No Transfer of state. However, known persistent information of the entities can be initialized here.
Activity-State Activity: Withdraw
• Performer: John
• Amount: 500 Rs
Entity-State after sentence John
• has possession = 500 Rs
He booked an Uber cab.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John (He)
• No further state deducible
• has possession = 500 Rs
Entity: Cab
• has aggregator = Uber
Activity-State Activity: Book-Transport
• Performer: John (He)
• Type of Vehicle: Cab
• Aggregator: Uber
• Source: unknown
• Destination: unknown
Entity-State after sentence No Change in entity state
He went to market.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John (He)
• No further state deducible
• has possession = 500 Rs
Entity: market
• No further state deducible
Activity-State Activity: Change-Of-Location
• Performer: John (He)
• Mode of transport: unknown
• Source: unknown
• Destination: market
Entity-State after sentence Entity: John (He)
• has location = Market
He bought a basket of Apples for 400 Rs.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John (He)
• No further state deducible
• has possession = 500 Rs
• has location = Market
Entity: Basket
• has items = apples
Entity: Rs
• has value= 400
Activity-State Activity: Sell-Item
• Seller: Unknown
• Buyer: John (He)
• Item: Basket of Apples
• Cost: 400 Rs
Entity-State after sentence Entity: John (He)
• has possession = Basket of apples
• has possession = -400 Rs
Entity: Basket
• has items = apples
• has cost = 400 Rs

5. Perform reasoning on the Activity-State to infer more roles. All the roles of an activity do not come from the same sentence. Hence, the activity template Knowledge created is used to infer all the possible roles of an activity.
John withdrew 500 Rs.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John
• No further state deducible
Entity: Rs
• has value=500
Activity-State +
Reasoning on the Activity-State Activity: Withdraw
• Performer: John
• Amount: 500 Rs
Entity-State after sentence Entity: John
• has possession = 500 Rs
He booked an Uber cab.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John (He)
• No further state deducible
• has possession = 500 Rs
Entity: Cab
• has aggregator = Uber
Activity-State +
Reasoning on the Activity-State Activity: Book-Transport
• Performer: John (He)
• Type of Vehicle: Cab
• Aggregator: Uber
• Source: unknown
• Destination: market
Entity-State after sentence No Change in entity state
He went to market.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John (He)
• No further state deducible
• has possession = 500 Rs
Entity: market
• No further state deducible
Activity-State +
Reasoning on the Activity-State Activity: Change-Of-Location
• Performer: John (He)
• Mode of transport: Cab
• Source: unknown
• Destination: market
Entity-State after sentence Entity: John (He)
• has location = Market
He bought a basket of Apples for 400 Rs.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John (He)
• No further state deducible
• has possession = 500 Rs
• has location = Market
Entity: Basket
• has items = apples
Entity: Rs
• has value= 400
Activity-State +
Reasoning on the Activity-State Activity: Sell-Item
• Seller: Unknown
• Buyer: John (He)
• Item: Basket of Apples
• Cost: 400 Rs
Entity-State after sentence Entity: John (He)
• has possession = Basket of apples
• has possession = -400 Rs
Entity: Basket
• has items = apples
• has cost = 400 Rs

6. Perform reasoning on the Entity-State to infer more relations. Finally based on the Entity-State before the sentence, Activity-State and Entity-State after the sentence, the final Entity-State for each entity is inferred.
John withdrew 500 Rs.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John
• No further state deducible
Entity: Rs
• has value=500
Activity-State +
Reasoning on the Activity-State Activity: Withdraw
• Performer: John
• Amount: 500 Rs
Entity-State after sentence +
Entity-State Inference Entity: John
• has possession = 500 Rs
He booked an Uber cab.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John (He)
• No further state deducible
• has possession = 500 Rs
Entity: Cab
• has aggregator = Uber
Activity-State +
Reasoning on the Activity-State Activity: Book-Transport
• Performer: John (He)
• Type of Vehicle: Cab
• Aggregator: Uber
• Source: unknown
• Destination: market
Entity-State after sentence +
Entity-State Inference No Change in entity state
He went to market.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John (He)
• No further state deducible
• has possession = 500 Rs
Entity: market
• No further state deducible
Activity-State +
Reasoning on the Activity-State Activity: Change-Of-Location
• Performer: John (He)
• Mode of transport: Cab
• Source: unknown
• Destination: market
Entity-State after sentence +
Entity-State Inference Entity: John (He)
• has location = Market
• has possession = 500 Rs
Entity: Cab
• has Location = Market
He bought a basket of Apples for 400 Rs.
Entity-State before sentence + Entity-State Transferred from previous sentence Entity: John (He)
• No further state deducible
• has possession = 500 Rs
• has location = Market
Entity: Basket
• has items = apples
Entity: Rs
• has value= 400
Activity-State +
Reasoning on the Activity-State Activity: Sell-Item
• Seller: Unknown
• Buyer: John (He)
• Item: Basket of Apples
• Cost: 400 Rs
Entity-State after sentence +
Entity-State Inference Entity: John (He)
• has possession = Basket of apples
• has possession = -400 Rs
• has possession = 500 Rs
• has location = Market
• Has possession= 100 Rs

Entity: Basket
• has items = apples
• has cost = 400 Rs

7. Repeat Step 2 to 6 till the end of input.

The Overall System Integration
The subsystems and the Knowledge above forms part of the bigger NLU framework of AUI. The knowledge is created along with common, and domain specific knowledge required by the NLU framework. Each of the processing engine is integrated with the overall NLU framework to achieve Natural Language Understanding in machines.

SUMMARY
The AUI Entity-state and activity-state system forms the basic enabler for the AUI Natural Language Understanding system. This system breaks down a complex sentence into its explicit and implicit ingredients, connects the obvious, implied and unsaid in the light of previously/elsewhere stated information and common knowledge. Thus, the system can identify the actors(entities) and actions(activities) and the changes in over the shared textual information. Thus, a story is created in terms of the evolving data. This time referenced evolving data enables syntactic and semantic interpretation by a machine thus enabling to achieve understanding which is explainable and auditable. The example under ‘Objective’ section illustrates the core concept, inputs, and outputs at all intermediate stages of the system through the use of four simple interconnected sentences.

CLAIMS

We claim: -
1. A framework and inherent method of extracting and inferring the entity and Activity-States from unstructured text. The steps involve extracting the entities and activities and their state based on knowledge-based rules by the software engines. The extracted entity-state and activity-state are contextually inferred in the light of stated information and unstated common knowledge by software-based inference engines based on the editable logic stated in the inferencing rules. Thus, existing common worldly knowledge and domain specific knowledge is collated and codified to convert unstructured text into semantic data which can be analyzed and interpreted by machines / software engines.

2. A framework and inherent method of entity-state tracking and activity-state tracking. This is achieved by logically transferring the extracted and inferred entity-state and activity-state from previous sentence(s) to the current sentence by applying knowledge-based rules by the software engines. As a result of this capability, information is logically collated and corelated irrespective of its location in an unstructured text. The entity-state and activity-state evolution as per the stated information is captured in a proprietary machine query-able format for analysis and interpretations.

Annexure 1
SYMBOL INDEX
The Symbol Index gives a unique ID to every Sense in the Knowledge base. The important information stored for each sense is as follows: -
• Unique ID. This ID is an unambiguous Identity for the sense in the entire Knowledge World
• Sense Name. This is the Human readable word/words which represent the sense.
• Parts of Speech Tag. This gives the Part of speech of the sense.
• Tense. The tense of the sense if POS=Verb
• Plurality. Defines the Plurality of a sense if the POS=noun
• Lemme. Points to the Sense which the Lemme of this sense

The following Table is a sample of some of the senses that are used in the example in the document
Unique ID Sense Name Parts of Speech Tag Tense Plurality Lemme
1 John Proper Noun
2 Withdraw Verb Present
3 withdrew Verb Past Withdraw
4 Rs Noun
5 He Pronoun
6 Book Verb Present
7 Booked Verb Past Book
8 an Article
9 Uber Proper Noun
10 cab Noun
11 Go Verb Present
12 went Verb Past Go
13 To Preposition
14 market Noun
15 Buy Verb Present
16 bought Verb Past Buy
17 A Article
18 Basket Noun
19 Of Preposition
20 Apple Noun
21 Apples Noun Plural Apple
22 for Preposition

Annexure 2

TAXONOMY

Every Sense in the Knowledge base is organized in a hierarchical tree structure. The hierarchy starts with a notional node called Knowledge Root. The first level of children of the Knowledge Root are the POS tag nodes. Then each of the sense is populated into its tree. Each sense can also have multiple parents. Each child inherits all the properties and rules defined for the parent.
A sample Taxonomy if as below: -

Annexure 3

Adjective-Noun rules
The Adjective-Noun Rules can be defined for any Adjective (both leaf and in-between nodes in the Hierarchy of Adjectives). The Adjective-Noun Rules will be of the following Format:-
Rule: Number Noun
Inference: Noun has Value = Number
The methodology of application: -
Whenever a pattern with a number followed by any noun comes in the Natural Language Input, The Rule will match. This will result in application of the Inference corresponding to this rule. For Example: -
In the input “John withdrew 500 Rs”, 500 Rs matches the rule (500 is number, Rs is a Noun). Hence the resulting Inferences will be
• Creation of an Entity called Rs
• Adding of the property “Value” in the Entity Rs as Rs has Value = 500

Annexure 4

NOUN-NOUN RULES
The Noun-Noun Rules can be defined for any Noun (both leaf and in-between nodes in the Hierarchy of Nouns). The Noun-Noun Rules will be of the following Format: -
Rule: Organization Vehicle
Inference: Vehicle has Aggregator = Organization
The methodology of application: -
Whenever a pattern with an organization followed by any Vehicle comes in the Natural Language Input, The Rule will match. This will result in application of the Inference corresponding to this rule. For Example: -
In the input “He booked an Uber cab”, Uber cab matches the rule (Uber is an organization, Cab is a Vehicle). Hence the resulting Inferences will be
• Creation of Entities Uber and Cab
• Adding of the property “Aggregator” in the Entity Uber as Uber has Aggregator = Cab

Annexure 5

NOUN-PREPOSITION-NOUN RULES
The Noun-Preposition-Noun Rules can be defined for any Preposition when a pair of Nouns come in-between a preposition in a Sentence that has a logical meaning (both leaf and in-between nodes in the Hierarchy of Nouns). The Noun-Preposition-Noun Rules will be of the following Format: -
Rule: Container Of Fruit
Inference: Container has Items = Fruit
The methodology of application: -
Whenever a pattern with any Container followed by the preposition ‘Of’ followed by any fruit comes in the Natural Language Input, The Rule will match. This will result in application of the Inference corresponding to this rule. For Example: -
In the input “He bought a basket of Apples for 400 Rs”, basket of Apples matches the rule (Basket is a Container, Apples is a fruit). Hence the resulting Inferences will be
• Creation of Entities Basket and Apples
• Adding of the property “Items” in the Entity Basket as Basket has Items = Apples

Annexure 6

VERB-SUBJECT-OBJECT RULES
The Verb-Subject-Object Rules can be defined for any verb. Any Sentence with a Verb will have the following format:-
[Subject] [Verb] [Direct Object] {Preposition Noun-Phrase}
The {Preposition Noun-Phrase} can come zero or more than Zero number of times in the sentence. The Verb-Subject-Object Rules will be of the following Format: -
Rule: [Human] [Buy] [Noun] {for Currency} {from human/organization}
Inference:
• Activity : Sell-Item
• Role : Seller , Role-Performing-Entity/ Role-Performing-Activity : Human (Subject)
• Role : Buyer , Role-Performing-Entity/ Role-Performing-Activity : Human/organization (3rd object)
• Role : Item , Role-Performing-Entity/ Role-Performing-Activity : Noun (Direct object which is also the first object)
• Role : Cost , Role-Performing-Entity/ Role-Performing-Activity : Currency (Which is the 2nd object)
The methodology of application: -
Whenever a pattern with
• Any Human as the subject
• Followed by verb ‘Buy’ (or any other tense of buy)
• Followed by the direct object of type Noun (optional)
• Followed by preposition ‘for’ and any currency (optional)
• Followed by Preposition ‘from’ and any Human/Organization (optional)
comes in the Natural Language Input, The Rule will match. This rule is matched even if zero or more than zero objects match. This will result in application of the Inference corresponding to this rule. For Example: -
In the input “He bought a basket of Apples for 400 Rs”, The matches are as follows: -
• Subject : John is a human hence matches the subject
• Verb : Bought is the past tense of Buy hence match
• Direct Object (first Object): Basket is a Noun. Matches the direct object
• 2nd Object : ‘for’ and ‘Rs’ matches the 2nd object
• 3rd Object : No Match. Ignored.
The Inference will be applied as follows: -
• Creation of Activity Sell-Item
• Adding Role-Performing-Entity John to the role “Buyer”.
• Adding Role-Performing-Entity Basket to the role “Item”.
• Adding Role-Performing-Entity Rs to the role “Cost”.
Note: Basket will have Apples as part of its Entity-State and Rs will have 500 as part of its entity state
Annexure 7

ACTIVITY-PREPOSITION/CONJUNCTION-ACTIVITY RULES
The Activity-Preposition/Conjunction-Activity rules can be defined for any Preposition/ Conjunction. This is for handling the relation between two activities which are generated by processing a complex sentence with more than one verb.
For Example, John went to market to buy Apples. This sentence is broken into two simple sentences with one verb in each simple sentence like below :-
• John went to market
• buy Apples
These two simple sentences are connected by the preposition ‘to’. The first simple sentence will generate the Activity ‘Travel’ and the 2nd simple sentence will generate the Activity ‘Sell-Item’ with their corresponding roles and role performing agents as below:-
Travel
• Performer: John
• Destination: Market
Sell-Item
• Buyer: John
• Item: Apples
The Activity-Preposition/Conjunction-Activity Rules will be of the following Format: -
Rule: Movement to Commercial-Activity
Inference: Movement
Role= Purpose, Role-performing-Activity = Commercial-Activity
The methodology of application: -
Here Travel is of type Movement and Sell-Item is of type Commercial-Activity which are interconnected by the preposition ‘to’. Hence the rule matches and the state of activity Travel changes as follows: -
Travel
• Performer : John
• Destination: Market
• Purpose : Sell-Item (The Sell-Item will be referring the complete Activity Sell-Item with its roles Buyer and Item)

Annexure 8

ADVERB-VERB RULES

The Adverb-Verb rules can be defined for any Adverb when it accompanies a Verb in a sentence. The adverb may be adjacent to the verb or somewhere in the simple sentence. The Adverb-Verb rules will be of the following Format: -

Rule: Occurrence Verb
Inference: Verb has Frequency = Occurrence

The methodology of application: -
Whenever a adverb is encountered in a Simple sentence, the adverb is paired with the Verb and if the adverb and the verb matches the rule, the corresponding inference is applied. Later, when the verb is converted into and activity, the inference is further transferred to the Activity. For Example: -
In the input “John paid rent monthly”, monthly is an Occurrence and Pay is a verb and hence matches the rule. Hence the resulting Inferences will be
Activity: Pay
Role: Payee, Role-performing-Entity: John
Role: Purpose, Role-performing-Entity: Rent
Role: Frequency, Role-performing-Entity: Monthly

Annexure 9

ENTITY-STATE INFERENCING RULES

There are three kinds of Entity-State Inferencing rules. They are as follows: -
1. Intra Entity-State Inferencing. These rules are made to carry out inference between the properties of the same entity.
Rule: Entity has Possession currency1 AND Entity has Possession currency2 (The same entity has two possession properties with value of type Currency)
Inference: Entity has Possession currency1+currenct2 (perform the addition operation on the value of the currency)
Example: John has possession = (-)400 Rs and John has possession = 500 Rs
Result: John has possession = 100 Rs
2. Inter Entity-State Inferencing. These rules are made to carry out inference between the properties of the different entities which are connected by some property.
Rule: Entity1 has Possession Entity2 AND Entity1 has Location Entity3
Inference: Entity2 has Location Entity 3
Example: John has possession = Apple and John has Location = Paris
Result: Apple has Location = Paris
3. Property Transfer between Sentence for the same entity. These Rules are used to transfer a property of an Entity from one sentence to the other sentence. Primarily properties are defined as single valued and multi valued properties. When an Entity gets a property in one sentence which is single valued, the property is transferred to the same entity in the next sentence only if the same property change has not occurred in the next sentence. If the property is multi valued, and if the same property gets changed in two sentences, both properties are kept with the entity.
Example 1: Multi Valued Properties
Sentence 1: John bought an apple.
State: John has possession = apple.
Sentence 2: John bought an orange.
State: John has possession = orange.
State after Property Transfer
John
has possession = apple
has possession = orange
Example 2: Single Valued Properties
Sentence 1: John went to Paris.
State: John has location = Paris.
Sentence 2: John flew to London.
State: John has location = London.
State after Property Transfer
John
has location = London
Annexure 10

ACTIVITY-STATE INFERENCING RULES

The Activity-State Inferencing rules helps to complete the roles of an activity based on other related activities and entities.
For Example, we have
“John booked a uber cab” which results in an Activity
Activity: Book-Transport
• Performer: John (He)
• Type of Vehicle: Cab
• Aggregator: Uber
• Source: unknown
• Destination: Unknown
“John went to market” results in an entity state
John (He)
• has location = Market
We can build a Role completion rule as follows: -
Rule: Movement has role=performer and Role-performing-Entity=Human &&
This Human has Location=X
Inference: Movement has role= Destination and Role-performing-Entity=X
Applying this rule, the above ‘Movement’ Activity will look like this after the Inference
Activity: Book-Transport
• Performer: John (He)
• Type of Vehicle: Cab
• Aggregator: Uber
• Source: unknown
• Destination: market

Claims:We claim: -
1. A framework and inherent method of extracting and inferring the entity and Activity-States from unstructured text. The steps involve extracting the entities and activities and their state based on knowledge-based rules by the software engines. The extracted entity-state and activity-state are contextually inferred in the light of stated information and unstated common knowledge by software-based inference engines based on the editable logic stated in the inferencing rules. Thus, existing common worldly knowledge and domain specific knowledge is collated and codified to convert unstructured text into semantic data which can be analyzed and interpreted by machines / software engines.

2. A framework and inherent method of entity-state tracking and activity-state tracking. This is achieved by logically transferring the extracted and inferred entity-state and activity-state from previous sentence(s) to the current sentence by applying knowledge-based rules by the software engines. As a result of this capability, information is logically collated and corelated irrespective of its location in an unstructured text. The entity-state and activity-state evolution as per the stated information is captured in a proprietary machine query-able format for analysis and interpretations.