DESC:FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:

SYSTEMS AND METHODS FOR GENERATING RESPONSE TO INTERACTIVE USER QUERIES BASED UPON REAL-TIME LEARNING

Applicant

Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India

The following specification particularly describes the invention and the manner in which it is to be performed.


CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY

[001] The present application claims priority to Indian provisional Application No. (201821015372), filed in India on 23th of April, 2018.
TECHNICAL FIELD
[002] The disclosure herein generally relates to a self-learning method and a system for responding to request query, and, more particularly, to systems and methods for generating response to interactive user queries based upon real-time learning.

BACKGROUND
[003] With advances in artificial intelligence and machine learning capabilities in recent years, robots have been extensively used in interaction, communication, and even co- working with human users in a variety of application areas.
[004] Social robots are being proposed and developed for robot systems and their processors including robotic chat- or chatter-bots or bots are used to interact and communicate with human users in a variety of application areas such as child and elderly care, receptionist, greeter, and guide applications, and multiple-capability home assistant etc. A variety of techniques have been applied to processors or bots to simulate intelligent conversation with one or more users. The intelligent conversation between the user and the bot may be carried out via various methods such as sensory methods or textual methods. Users can request queries and receive relevant responses to queries from a bot during the chat session.
[005] The relevant responses that a user receives from a bot are often obtained from the bot’s preprogrammed knowledge base. In response to the user’s query the bot identifies a relevant response from its knowledge base and can thereafter responds with the identified relevant response.
[006] While bots have proven useful in many scenarios, their acceptance has generally been limited because the existing bots are tightly scripted applications, which are dependent on their respective knowledge base to carry out communication. Hence if relevant response to a user’s query is not present in the bot’s knowledge base, then the existing bot system fails to provide required information. However knowledge database is generally updated and modified offline to enhance the bot’s knowledge base and handle newly trained queries.
[007] The existing bots are also restricted in their ways of expressing themselves in natural language, due to which the response to user’s query is often incoherent or unsatisfactory as it includes responses that are obvious, inconsistent or conflicting.

SUMMARY
[008] Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a method for generating response to interactive user queries based upon real-time learning, the method comprising: receiving, by one or more hardware processors, at least one query from a user; identifying, by implementing one or more cognitive intent identification and classification techniques, whether a relevant response to the query is present in a learning module; and performing, based upon the identifying of the relevant response, one of: generating, by implementing one or more response mapping techniques, the relevant response to the user on the query from the learning module upon determining a presence of the relevant response in the learning module; and learning in a real-time, from a plurality of sources, an another response to the query upon determining an absence of the relevant response in the learning module, wherein the another response is learnt by implementing one or more cognitive insight generation techniques, and wherein the plurality of sources comprise at least one of a human, a machine, a robot and a knowledge base; identifying, from the relevant response in the learning module, an appropriate intent and an appropriate entity corresponding to the relevant response by implementing the one or more cognitive intent identification and classification techniques; and performing, via a response module, a mapping of an intent and an entity, and wherein the intent and the entity are extracted from the another response by implementing the one or more response mapping techniques.
[009] In another aspect, there is provided a system for generating response to interactive user queries based upon real-time learning, the system comprising a memory storing instructions; one or more communication interfaces; and one or more hardware processors coupled to the memory via the one or more communication interfaces, wherein the one or more hardware processors are configured by the instructions to: receive at least one query from a user; identify, by implementing one or more cognitive intent identification and classification techniques, whether a relevant response to the query is present in a learning module; perform, based upon the identifying of the relevant response, one of: generate, by implementing one or more response mapping techniques, the relevant response to the user on the query from the learning module upon determining a presence of the relevant response in the learning module; and learn in a real-time, from a plurality of sources, an another response to the query upon determining an absence of the relevant response in the learning module, wherein the another response is learnt by implementing one or more cognitive insight generation techniques, and wherein the plurality of sources comprise at least one of a human, a machine, a robot and a knowledge base; generate the relevant response by identifying, from the relevant response in the learning module, an appropriate intent and an appropriate entity corresponding to the relevant response by implementing the one or more cognitive intent identification and classification techniques; and perform, via a response module, a mapping of an intent and an entity, and wherein the intent and the entity are extracted from the another response by implementing the one or more response mapping techniques.
[010] In yet another aspect, there is provided one or more non-transitory machine readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors causes the one or more hardware processors to perform a method for generating response to interactive user queries based upon real-time learning, the method comprising: receiving at least one query from a user; identifying, by implementing one or more cognitive intent identification and classification techniques, whether a relevant response to the query is present in a learning module; and performing, based upon the identifying of the relevant response, one of: generating, by implementing one or more response mapping techniques, the relevant response to the user on the query from the learning module upon determining a presence of the relevant response in the learning module; and learning in a real-time, from a plurality of sources, an another response to the query upon determining an absence of the relevant response in the learning module, wherein the another response is learnt by implementing one or more cognitive insight generation techniques, and wherein the plurality of sources comprise at least one of a human, a machine, a robot and a knowledge base; identifying, from the relevant response in the learning module, an appropriate intent and an appropriate entity corresponding to the relevant response by implementing the one or more cognitive intent identification and classification techniques; and performing, via a response module, a mapping of an intent and an entity, and wherein the intent and the entity are extracted from the another response by implementing the one or more response mapping techniques.
[011] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS
[012] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles.
[013] FIG. 1 is a block diagram of a system for generating response to interactive user queries based upon real-time learning, in accordance with some embodiments of the present disclosure.
[014] FIG. 2 is an architectural diagram depicting components and flow of the system for generating the response to interactive user queries based upon the real-time learning, in accordance with some embodiments of the present disclosure.
[015] FIG. 3 is a flow diagram illustrating steps involved in a method for generating the response to interactive user queries based upon the real-time learning, in accordance with some embodiments of the present disclosure.
[016] FIG. 4 illustrates a used case example wherein, intents and entities are extracted from user’s request in a learning module, in accordance with some embodiments of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS
[017] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims.
[018] The embodiments herein provide systems and methods for generating response to interactive user queries based upon real-time learning. Cognitive techniques provide for real-time data / response generation by combining various aspects of artificial intelligence, natural language processing, dynamic learning, and hypothesis generation to render vast quantities of intelligible data to assist humans in making better decisions. As such, cognitive systems can be characterized as having the ability to interact naturally with people to extend what either humans, or machines, could do on their own. Furthermore, they are typically able to process natural language, multi-structured data, and experience much in the same way as humans. Moreover, they are also typically able to learn a knowledge domain based upon the best available data and get better, and more immersive, over time.
[019] However, the traditional systems and methods implementing the cognitive techniques may fail to generate any response, if a pre-defined response is not present in database(s) and / or knowledge base(s). The method disclosed attempts to overcome the limitations faced by the traditional systems and methods. For example, the method disclosed provides for a real-time learning of response(s) from experts to provide answer to interactive user queries upon determining an absence of a pre-response appropriate in the database(s) and / or knowledge base(s).
[020] Referring now to the drawings, and more particularly to FIG. 1 through 4, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
[021] FIG. 1 illustrates an exemplary block diagram of a system 100 for generating a response to interactive user queries based upon a real-time learning, in accordance with an embodiment of the present disclosure. In an embodiment, the system 100 includes one or more processors 104, communication interface device(s) or input/output (I/O) interface(s) 106, and one or more data storage devices or memory 102 operatively coupled to the one or more processors 104. The one or more processors 104 that are hardware processors can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor(s) is configured to fetch and execute computer-readable instructions stored in the memory 102. In an embodiment, the system 100 can be implemented in a variety of computing systems, such as laptop computers, notebooks, hand-held devices, workstations, mainframe computers, servers, a network cloud and the like.
[022] The memory 102 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. In an embodiment, the memory 102 can be configured to store any data that is associated with the generating of response to interactive user queries based upon the real-time learning. In an embodiment, the information pertaining to user queries, intent and entity mapping, response generated for the user queries is stored in the memory 102. Further, all information (inputs, outputs and so on) pertaining to the generating of response to interactive user queries based upon the real-time learning, may also be stored in the database, as history data, for reference purpose.
[023] The I/O interface device(s) 106 can include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like and can facilitate multiple communications within a wide variety of networks N/W and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. In an embodiment, the I/O interface device(s) can include one or more ports for connecting a number of devices to one another or to another server.
[024] According to an embodiment of the disclosure, by referring to FIG. 2, the architecture and flow of the system 100 for generating the response to interactive user queries based upon the real-time learning may be considered in detail. By referring to FIG. 2 again, it may be noted that the architecture comprises a User Interface 202, an Interactive Query Response Module 204, further comprising of a Response Module 206 and a Learning Module 208, a Database 210, a Memory Module 212, and an Expert 214.. The system 100, receives a request query or request from the user interface 202.
[025] The user interface 202 is configured to be operated by a user, that may be a machine or human that sends out a request to the interactive query response module 204. The request may be sensory or textual in nature. Upon reception of the request the interactive query response module 204 tries to identify if a relevant response is present its knowledge base such as the learning module 208. Further, if the relevant response is identified, the relevant response is shared with the user by the response module 206, in case the relevant response is not identified in its learning module 208, the interactive query response module 204 requests assistance of an Expert 214, wherein the expert 214 could be a machine, processor or human. A Database 210 stores all relevant information / data corresponding to generating the response to interactive user queries. A Memory Module 212 facilitates storing of response fetched from the expert 214 in the learning module 208 and / or in the database 210.
[026] The expert 214 shares an another response to the interactive query response module’s 204 request. Upon receiving the another response from the expert 214 for the request, the interactive query response module 204 dynamically trains itself at real-time in the learning module 208. The response of the expert 214 that is dynamically learnt is saved in the interactive query response module’s 204 learning module 208 for further reference. The saved another response is also shared with the user, who had requested for it. Hence the proposed system and method performs dynamic cognitive learning in interactive query response system at real-time.
[027] FIG. 3, with reference to FIG. 1 and FIG. 2, is a flow diagram illustrating steps involved in a method for generating the response to interactive user queries based upon the real-time learning, in accordance with some embodiments of the present disclosure. In an embodiment the system 100 comprises one or more data storage devices of the memory 102 operatively coupled to the one or more hardware processors 104 and is configured to store instructions for execution of steps of the method by the one or more processors 104. The steps of the method of the present disclosure will now be explained with reference to the components of the system 100 as depicted in FIG. 1 and the flow diagram. In the embodiments of the present disclosure, the hardware processors 104 when configured the instructions performs one or more methodologies described herein.
[028] According to an embodiment of the present disclosure, at step 302, the one or more hardware processors 104 are configured to receive at least one from a user by implementing the user interface 202. The user interface 202 is configured to be operated by the user, that may be a machine or human that sends out a request to the interactive query response module 204. The user query may be received in the form of a natural language or as a text or any combination thereof. Considering an example scenario, the query may be received as “Does organization X has expertise in Drones solutions?; Tell me about the organization X Drone solution?; What are capabilities of the organization X in drones?; and What is organization's X UAV solution?
[029] According to an embodiment of the present disclosure, at step 304, the one or more hardware processors 104 are configure to identify, via a bot (not shown in the figure), whether the relevant response to the query is present in the learning module 208, wherein the relevant response is identified by implementing one or more cognitive intent identification and classification techniques. The bot tries to identify if the relevant response is present its knowledge base or the learning module 208. The learning module 208 identifies the relevant response after it understands the user’s request. The learning module 208 understands the user query by identifying an appropriate intent and an appropriate entity using algorithms based on the one or more cognitive intent identification and classification techniques, for example, Cognitive Natural Language Processing (NLP).
[030] As is known in the art, cognitive intent identification and classification techniques are used to classify user queries to intent intentions. For example, if the user has a query like “How much is balance in my saving account”; “How much do I have in checking account”; “tell me the balance in my account”; and “show me account balance”, by implementing the cognitive intent identification and classification techniques, the intent may be generated as a “Balance enquiry” intent.
[031] By referring to FIG. 4, a used case example of the identification of the appropriate intent and the appropriate entity may be referred, wherein the first column represents the user’s query, the second column is represents the corresponding identified appropriate intent and the appropriate entity as “Intent – OrganizationXCapabilities”; and “Entity – Drones”.
[032] According to an embodiment of the present disclosure, at step 306, the one or more hardware processors 104 are initially configured to generate, by implementing one or more response mapping techniques, the relevant response to the user on the query from the learning module 208 upon determining a presence of the relevant response in the learning module 208. As is known in the art, a response mapping technique is generally used to find out response(s) to be provided to user for identified intentions, wherein such response(s) may be known or fetched by integrating with any enterprise service.
[033] Considering the same example scenario as discussed in steps 302 and 304 above, upon identifying of the appropriate intent and the appropriate entity, the relevant response may be generated as “Organization X cognitive transformation framework powers many solutions such as cognitive information retrieval, cognitive data extraction cognitive warehouse tracking and cognitive transportation management”.
[034] According to an embodiment of the present disclosure, at step 306, if the relevant response is not identified in the learning module 208, the one or more hardware processors 104 are configured to generate the another response to the query, wherein the another response is generated upon facilitating the real-time learning of the another response from a plurality of sources, and wherein the another response is learnt by implementing one or more cognitive insight generation techniques. The process of the real-time learning by implementing the one or more cognitive insight generation techniques may now be considered in detail.
[035] In an embodiment, the interactive query response module 204 requests assistance of an expert 214. Further, the expert 214 could be a machine, a processor, a human, a robot, an existing knowledge base, an enterprise service or an enterprise process (or any combination thereof) who shares an another relevant response (that is, the another response) to the interactive query response module’s request 204. The expert 214 shares the another response to the interactive query response module’s 204 request. Upon receiving of the another response from the expert 214 for the request, the interactive query response module 204 dynamically trains itself at real-time in the learning module 208.
[036] The another response from the expert 214 that is dynamically learnt at real-time is saved in the interactive query response module’s 204 learning module 208 for further reference. Further, the response module 206 also maintains a mapping between intent, entity and response, wherein the intent and the entity are extracted from the another response by implementing the one or more response mapping techniques. Considering an example scenario, by implementing the one or more response mapping techniques, for intention "Balance enquiry" may fetch balance by querying to service exposed by banking application and will share that as a response to user.
[037] In an embodiment, the another response to the user’s query may be prepared in the response module 206 with the relevant response identified from the learning module 208. The response module 206 may thus be pre-trained, via the one or more response mapping techniques, to generate the learnt another response on the query. The relevant response is identified in the learning module 208 or if unknown, learnt from the expert 214 at real time by the learning module 208.
[038] The learning module 208 may thus be updated in a real-time with the learnt another response by implementing the one or more cognitive insight generation techniques. Considering an example scenario, by referring to FIG. 4 again, a used case example of the learnt another response from the expert 214 may be referred. Suppose the user query is received as “What is the type of screen iphone offers”; and “tell me about iphone screen”. The intent and the entity may be identified as “PartEnquiry” and “Screen” respectively. The another response may be learnt in real-time from the plurality of sources, comprising of the expert(s) 214 (for example, a robot, an iphone technical person) as “It has Super AMOLED capacitive touchscreen with 16M colors”.
[039] According to an embodiment of the present disclosure, advantages of the method disclosed may be considered in detail. The method disclosed provides for the real-time learning of the response from the expert 214, and thus saves time and efforts involved in an identification response(s) to answer to user queries. Further, since the response is learnt from the expert 214, it provides for providing an accurate response / answer to user queries. Finally, the learnt response is updated in real-time in the learning module 208.
[040] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
[041] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
[042] It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g. any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g. hardware means like e.g. an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g. an ASIC and an FPGA, or at least one microprocessor and at least one memory with software modules located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g. using a plurality of CPUs.
[043] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various modules described herein may be implemented in other modules or combinations of other modules. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[044] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
[045] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[046] It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.
,CLAIMS:

1. A method for generating response to interactive user queries based upon real-time learning, the method comprising a processor implemented steps of:
receiving, by one or more hardware processors, at least one query from a user (302);
identifying, by implementing one or more cognitive intent identification and classification techniques, whether a relevant response to the query is present in a learning module (304); and
performing, based upon the identifying of the relevant response, one of (306):
generating, by implementing one or more response mapping techniques, the relevant response to the user on the query from the learning module upon determining a presence of the response in the learning module; and
learning in a real-time, from a plurality of sources, an another response to the query upon determining an absence of the relevant response in the learning module, wherein the another response is learnt by implementing one or more cognitive insight generation techniques, and wherein the plurality of sources comprise at least one of a human, a machine, a robot and a knowledge base.

2. The method as claimed in claim 1, wherein the step of generating the relevant response is preceded by identifying, from the relevant response in the learning module, an appropriate intent and an appropriate entity corresponding to the relevant response by implementing the one or more cognitive intent identification and classification techniques.

3. The method as claimed in claim 1, wherein the step of learning the another response comprises performing, via a response module, a mapping of an intent and an entity, and wherein the intent and the entity are extracted from the another response by implementing the one or more response mapping techniques.

4. The method as claimed in claim 1, wherein the learning module is updated in a real-time with the learnt another response by implementing the one or more cognitive insight generation techniques.

5. The method as claimed in claim 3, wherein the response module is pre-trained, via the one or more response mapping techniques, to generate the learnt another response on the query.

6. A system (100) for generating response to interactive user queries based upon real-time learning, the system (100) comprising:
a memory (102) storing instructions;
one or more communication interfaces (106); and
one or more hardware processors (104) coupled to the memory (102) via the one or more communication interfaces (106), wherein the one or more hardware processors (104) are configured by the instructions to:
receive at least one query from a user;
identify, by implementing one or more cognitive intent identification and classification techniques, whether a relevant response to the query is present in a learning module (208);
perform, based upon the identifying of the relevant response, one of:
generate, by implementing one or more response mapping techniques, the relevant response to the user on the query from the learning module (208) upon determining a presence of the relevant response in the learning module (208); and
learn in a real-time, from a plurality of sources, an another response to the query upon determining an absence of the relevant response in the learning module (208), wherein the another response is learnt by implementing one or more cognitive insight generation techniques, and wherein the plurality of sources comprise at least one of a human, a machine, a robot and a knowledge base.

7. The system (100) as claimed in claim 6, wherein the one or more hardware processors (104) are configured to generate the relevant response by identifying, from the relevant response in the learning module (208), an appropriate intent and an appropriate entity corresponding to the relevant response by implementing the one or more cognitive intent identification and classification techniques.

8. The system (100) as claimed in claim 6, wherein the one or more hardware processors (104) are configured to perform, via a response module (206), a mapping of an intent and an entity, and wherein the intent and the entity are extracted from the another response by implementing the one or more response mapping techniques.

9. The system (100) as claimed in claim 6, wherein the learning module (208) is updated in a real-time with the learnt another response by implementing the one or more cognitive insight generation techniques.

10. The system (100) as claimed in claim 8, wherein the response module (206) is pre-trained, via the one or more response mapping techniques, to generate the learnt another response on the query.