WO2017199074A1 - Method of generating knowledge based data and an embedded cognitive processing system thereof - Google Patents

Method of generating knowledge based data and an embedded cognitive processing system thereof Download PDF

Info

Publication number
WO2017199074A1
WO2017199074A1 PCT/IB2016/054977 IB2016054977W WO2017199074A1 WO 2017199074 A1 WO2017199074 A1 WO 2017199074A1 IB 2016054977 W IB2016054977 W IB 2016054977W WO 2017199074 A1 WO2017199074 A1 WO 2017199074A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
processing system
processed data
embedded
cognitive processing
Prior art date
Application number
PCT/IB2016/054977
Other languages
French (fr)
Inventor
Naveen SRINIVAS
Original Assignee
Srinivas Naveen
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
Application filed by Srinivas Naveen filed Critical Srinivas Naveen
Publication of WO2017199074A1 publication Critical patent/WO2017199074A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models

Definitions

  • the present invention generally relates to processing data and more particularly to a method of processing data to generate knowledge based data and an embedded cognitive processing system thereof.
  • Data processing is a method generally used to process data in order to generate meaningful information.
  • the data available today from different sources is typically large, complex and difficult to process.
  • a number of data processing technologies are commonly in use to process large amounts of the data. Examples of different frameworks or the data processing technologies in use to process the data and achieve intelligence include, but are not limited to, hadoop, graphdb, and the like.
  • Such data processing technologies are inefficient in combining hardware and software to build general purpose artificial intelligence in systems to accommodate and solve problems.
  • Specific developmental architectures for example big data and other forms of expert systems, are also being used to solve specific problems. Such developmental architectures, however, are unable to work on data of different sizes and is difficult to modify.
  • An example of a computer-implemented method of generating knowledge based data includes receiving pre-processed data by an embedded cognitive processing system.
  • the pre-processed data includes n-dimensional data pre-processed from one or more data sources.
  • the method also includes analysing, by the embedded cognitive processing system, the pre- processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data.
  • the at least one multi-level contextual response is provided to a user in response to a query of the user.
  • Another example of a computer-implemented method of generating knowledge based data includes receiving, by an embedded cognitive processing system, pre-processed data.
  • the pre-processed data includes n-dimensional data pre-processed from one or more data sources.
  • the method also includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data.
  • the method further includes providing, by the embedded cognitive processing system, the at least one multi-level contextual response to a user in response to a query of the user.
  • the at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system.
  • Another example of a computer-implemented method of generating knowledge based data includes pre-processing, by an embedded cognitive processing system, n- dimensional data from one or more data sources to generate pre-processed data.
  • the method also includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data.
  • the method further includes providing, by the embedded cognitive processing system, the at least one multi-level contextual response to a user in response to a query of the user.
  • the at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system.
  • An example of an embedded cognitive processing system for generating knowledge based data includes a communication interface in electronic communication with at least one user device of a user.
  • the embedded cognitive processing system also includes a memory that stores instructions.
  • the embedded cognitive processing system further includes a processor responsive to the instructions.
  • the processor includes a learning module and a response module.
  • the learning module is configured to analyse pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data.
  • the response module is coupled to the learning module and is configured to provide the at least one multi-level contextual response to the user in response to a query of the user.
  • the at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system.
  • FIG. 1 is an example representation of an environment, in accordance with an embodiment
  • FIG. 2 is an example representation of an embedded cognitive processing system, in accordance with an embodiment
  • FIG. 3 illustrates an example flow diagram of a method for delivering advertisements to user devices, in accordance with an embodiment
  • FIG. 4 illustrates an example flow diagram of a method for delivering advertisements to user devices, in accordance with another embodiment
  • FIG. 5 illustrates an example flow diagram of a method for delivering advertisements to user devices, in accordance with yet another embodiment
  • FIG. 6 illustrates a block diagram of an electronic device, in accordance with one embodiment.
  • FIG. 1 is an example representation of an environment 100, in accordance with an embodiment.
  • the environment 100 includes a plurality of data sources, for example a data source 105, a data source 110, and a data source 115, a network 120, and an embedded cognitive processing system 125.
  • the embedded cognitive processing system' 125 refers to a parallel distributable data system that is configured to store, classify, analyse or learn, and respond to information or data.
  • the embedded cognitive processing system 125 is also referred to as an evolving big data system, an evolving knowledge base system, or a general purpose artificial intelligence system.
  • the embedded cognitive processing system 125 is implemented as a compact device that operates at moderate conditions, consumes around 60 Watts power, and is modular and distributable.
  • the embedded cognitive processing system 125 can be distributed across geography as an offline unit or an online unit.
  • the data source 105, the data source 110, and the data source 115 communicate with the embedded cognitive processing system 125 through the network 120.
  • the plurality of data sources include, but are not limited to, computer systems, mobile devices, tablets, laptops, palmtops, handheld devices, telecommunication devices, personal digital assistants (PDAs), television broadcasting devices, medical equipment, infrastructures associated with cities, sensor-equipped buildings and factories, transportation systems, and the like.
  • PDAs personal digital assistants
  • a 'data source' refers to a device that is configured to provide or display information or data.
  • Examples of the network 120 includes, but are not limited to, a Local Area Network (LAN), a Wireless Local Area Network (WLAN), a Wide Area Network (WAN), internet, a Small Area Network (SAN), and the like.
  • the embedded cognitive processing system 125 is configured to generate knowledge based data by processing data.
  • the 'knowledge based data' refers to optimized data that is obtained by applying one or more data aggregation methods and logical elements to the data.
  • the embedded cognitive processing system 125 receives pre-processed data from one or more data sources, for example from the data source 105, the data source 110, and the data source 115.
  • the 'pre-processed data' includes n-dimensional data (for example, text files, audio files, video files, and the like) that is pre-processed using one or more methods.
  • the n- dimensional data includes, but is not limited to, presentations, logs, documents, spreadsheets, sensor data, web content, online activities, enterprise applications, internet of things, processes, knowledge bases, tweets, posts, videos, audio, location information, wiki feeds, news feeds, social media feeds, or any other form of unstructured and asynchronous data.
  • the embedded cognitive processing system 125 can further analyze the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data.
  • the at least one multi-level contextual response is provided to a user in response to a query of the user.
  • the embedded cognitive processing system 125 including one or more components is described in detail with reference to FIG. 2.
  • the embedded cognitive processing system 125 includes a communication interface 205 and a processor 210.
  • the communication interface 205 is a network interface unit.
  • the network interface unit can transfer data at a speed of 1000 megabits per second (Mbps).
  • the embedded cognitive processing system 125 is powered by a power unit 215.
  • the power unit 215 can operate at 60 Watts.
  • the power unit 215 further provides 12 Volt (V) to the communication interface 205 and 5V to the processor 215.
  • the processor 210 includes a pre-processor module 220, a learning module 225, and a response module 230.
  • the processor 210 operates using distributed computing.
  • the pre-processor module 220, the learning module 225, and the response module 230 are enabled as low powered and low computing units that communicate with each other.
  • each low computing unit includes a random access memory (RAM) of 2 Gigabytes (GB), a processor memory of 16 GB, and operates at a frequency of 1.3 Giga Hertz (GHz).
  • RAM random access memory
  • GB Gigabytes
  • GHz Giga Hertz
  • the low computing units are organized or clustered similar to neurons in a human brain.
  • the pre-processor module 220 is coupled to the learning module 225.
  • the learning module 225 is further coupled to the response module 230.
  • the pre-processor module 220 is configured to pre-process the n-dimensional data from one or more data sources (the data source 105— the data source 115 of FIG. 1) to generate the pre-processed data.
  • the n-dimensional data is pre-processed using multiple methods.
  • the pre-processor module 220 receives image data from one or more image data sources.
  • the image data from the image data sources include unstructured image data.
  • the pre-processor module 220 detects an auto layout in the image data.
  • the term 'auto layout' refers to a representation of data.
  • the pre-processor module 220 further converts the image data to structured text.
  • OCR optical character recognition
  • a language processing method is applied to the structured text to subsequently generate the pre-processed data.
  • the pre-processed data is arranged in a semantic format. For instance, a newspaper image can be received by the preprocessor module 220. Layout of different topics and content in the newspaper image is identified. The newspaper image is then converted to text and digitized. A natural language processing method is applied to the text and the pre-processed text thus obtained is semantically arranged.
  • the pre-processor module 220 receives textual data from one or more textual data sources, for example a word document.
  • the textual data from the image data sources include unstructured textual data.
  • the pre-processor module 220 detects an auto layout in the textual data.
  • the pre-processor module 220 further converts the textual data to structured text.
  • a language processing method is applied to the structured text to subsequently generate the pre-processed data that is arranged in the semantic format.
  • the learning module 225 is configured to analyse the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data.
  • the learning module 225 receives the pre-processed data from the pre-processor module 220.
  • the learning module 225 implements a plurality of cognitive rules on the pre-processed data.
  • the plurality of cognitive rules is determined based on a data dimension parameter.
  • the learning module 225 determines complementary data in relation to the pre-processed data.
  • the term 'complementary data' refers to data similar to the pre-processed data.
  • the learning module 225 further multiplies the pre- processed data by pairing the pre-processed data with the complementary data.
  • such multiplication of the pre-processed data is similar to multiplication of deoxyribonucliec acid (DNA) found in various living organisms.
  • the pre-processed data is paired with the complementary data in a cognitive eco- system of the embedded cognitive processing system 125.
  • the term 'cognitive eco-system' refers to a digital environment that supports growth and multiplication of the pairing of the pre-processed data with the complementary data using the plurality of cognitive rules.
  • the response module 230 is configured to provide the at least one multi-level contextual response to the user in response to a query of the user.
  • the at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system 125.
  • the response module 230 can go offline after the analysing by the learning module 225.
  • the response module 230 can be 1/10 of size of the learning module 225, making the response module 230 robust and mobile.
  • a plurality of response modules can be present as per application areas and corresponding pre-processed data. For instance, a response module associated with healthcare, a response module associated with banking, a response module associated with automotive, and the like.
  • the embedded cognitive processing system 125 does not include the pre-processor module 220.
  • the pre-processed data is received by the embedded cognitive processing system 125 from an external pre-processor module.
  • the embedded cognitive processing system 125 does not include the response module 230.
  • the learning module 210 is configured to provide the at least one multi-level contextual response to the user in absence of the response module.
  • FIG. 3 illustrates an example flow diagram of a method 300 for generating knowledge based data, in accordance with an embodiment.
  • the method 300 includes receiving pre-processed data.
  • the pre-processed data can be received by an embedded cognitive processing system, for example the embedded cognitive processing system 125 of FIG. 1.
  • the pre-processed data includes n-dimensional data pre-processed from one or more data sources. Examples of the n-dimensional data includes, textual data, image data, video data, and the like.
  • the pre-processed data can be received from an external pre-processor module.
  • the method 300 includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data.
  • the pre-processed data is analysed by a learning module, for example the learning module 225 of FIG. 2.
  • the at least one multi-level contextual response is provided to a user in response to a query of the user, by the leaning module.
  • the at least one multi-level contextual response is provided to the user in one of an online state and an offline state of the embedded cognitive processing system.
  • the pre-processed data is first received by the embedded cognitive processing system.
  • a plurality of cognitive rules is further implemented on the pre-processed data.
  • the plurality of cognitive rules are determined based on a data dimension parameter.
  • Complementary data in relation to the pre-processed data is subsequently determined.
  • the pre-processed data is then multiplied by pairing the pre-processed data with the complementary data.
  • the pre-processed data is paired with the complementary data in a cognitive eco-system of the embedded cognitive processing system.
  • the method of analysing the pre-processed data by the learning module is explained with reference to FIG. 2 and is not explained herein for sake of brevity. Another example method for generating the knowledge based data is explained with reference to FIG. 4.
  • FIG. 4 illustrates an example flow diagram of a method 400 for generating knowledge based data, in accordance with an embodiment.
  • the method 400 includes receiving pre-processed data.
  • the pre-processed data is received by an embedded cognitive processing system, for example the embedded cognitive processing system 125 of FIG. 1.
  • the pre-processed data includes n-dimensional data that is pre-processed from one or more data sources. Examples of the n-dimensional data includes, but is not limited to, textual data, image data, video data, and the like.
  • the pre-processed data is received from an external pre-processor module.
  • the method 400 includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data.
  • the pre-processed data is analysed by a learning module, for example the learning module 225 of FIG. 2.
  • the at least one multi-level contextual response is built in response to a query of a user, by the leaning module.
  • the pre-processed data is first received by the embedded cognitive processing system.
  • a plurality of cognitive rules is further implemented on the pre-processed data.
  • the plurality of cognitive rules are determined based on a data dimension parameter.
  • Complementary data in relation to the pre-processed data is subsequently determined.
  • the pre-processed data is then multiplied by pairing the pre-processed data with the complementary data.
  • the pre-processed data is paired with the complementary data in a cognitive eco-system of the embedded cognitive processing system.
  • the method of analysing the pre-processed data by the learning module is explained with reference to FIG. 2 and is not explained herein for sake of brevity.
  • the method 400 includes providing, by the embedded cognitive processing system, the at least one multi-level contextual response to a user in response to the query of the user.
  • the at least one multi-level contextual response is provided by a response module, for example the response module 230 of FIG. 2.
  • the at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system.
  • FIG. 5 illustrates an example flow diagram of a method 500 for generating knowledge based data, in accordance with an embodiment.
  • the method 500 includes pre-processing, by an embedded cognitive processing system, n-dimensional data from one or more data sources to generate pre- processed data.
  • the pre-processing is performed by a pre-processor module, for example the pre-processor module 220 of FIG. 2.
  • the pre-processing of the n-dimensional data includes receiving image data from one or more image data sources.
  • the image data includes unstructured image data.
  • An auto layout is then detected in the image data.
  • the image data is then converted to structured text.
  • a language processing method is applied to the structured text to generate the pre-processed data.
  • a natural language processing method is applied to the structured text to generate the pre-processed data.
  • the pre-processed data is further arranged in a semantic format.
  • textual data is received by the pre-processor module from one or more textual data sources.
  • the textual data from the image data sources includes unstructured textual data.
  • the auto layout is then detected in the textual data.
  • the textual data is converted to the structured text.
  • the language processing method is further applied to the structured text to subsequently generate the pre-processed data that is arranged in the semantic format.
  • the method 500 includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data.
  • the pre-processed data is analysed by a learning module, for example the learning module 225 of FIG. 2.
  • the method of analysing the pre-processed data by the learning module is explained with reference to FIG. 4 and is not explained herein for sake of brevity.
  • the method 500 includes providing, by the embedded cognitive processing system, the at least one multi-level contextual response to a user in response to a query of the user.
  • the at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system.
  • the at least one multi-level contextual response is provided by a response module, for example the response module 230 of FIG. 2.
  • FIG. 6 illustrates a block diagram of an electronic device 600, which is representative of a hardware environment for practicing the present invention.
  • the electronic device 600 can include a set of instructions that can be executed to cause the electronic device 600 to perform any one or more of the methods disclosed.
  • the electronic device 600 may operate as a standalone device or can be connected, for example using a network, to other electronic devices or peripheral devices.
  • the electronic device 600 may operate in the capacity of a data source, for example the data source 105, a data source 110, and a data source 115 of FIG. 1, and an embedded cognitive processing system, for example the embedded cognitive processing system 125 of FIG. 1, in a server-client user network environment, or as a peer electronic device in a peer-to-peer (or distributed) network environment.
  • a data source for example the data source 105, a data source 110, and a data source 115 of FIG. 1
  • an embedded cognitive processing system for example the embedded cognitive processing system 125 of FIG.
  • the electronic device 600 can also be implemented as or incorporated into various devices, such as a personal computer (PC), a tablet PC, a personal digital assistant (PDA), a mobile device, a palmtop computer, a laptop computer, a desktop computer, a communications device, a wireless telephone, a land-line telephone, a control system, a camera, a scanner, a facsimile machine, a printer, a pager, a personal trusted device, a web appliance, a network router, switch or bridge, or any other machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine.
  • the term "device” shall also be taken to include any collection of systems or sub-systems that individually or jointly execute a set, or multiple sets, of instructions to perform one or more computer functions.
  • the electronic device 600 can include a processor 605, for example a central processing unit (CPU), a graphics processing unit (GPU), or both.
  • the processor 605 can be a component in a variety of systems.
  • the processor 605 can be part of a standard personal computer or a workstation.
  • the processor 605 can be one or more general processors, digital signal processors, application specific integrated circuits, field programmable gate arrays, servers, networks, digital circuits, analog circuits, combinations thereof, or other now known or later developed devices for analyzing and processing data.
  • the processor 605 can implement a software program, such as code generated manually (for example, programmed).
  • the electronic device 600 can include a memory 610, such as a memory 610 that can communicate via a bus 615.
  • the memory 610 can include a main memory, a static memory, or a dynamic memory.
  • the memory 610 can include, but is not limited to, computer readable storage media such as various types of volatile and non-volatile storage media, including but not limited to, random access memory, read-only memory, programmable readonly memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like.
  • the memory 610 includes a cache or random access memory for the processor 605.
  • the memory 610 is separate from the processor 605, such as a cache memory of a processor, the system memory, or other memory.
  • the memory 610 can be an external storage device or database for storing data. Examples include a hard drive, compact disc (“CD”), digital video disc (“DVD”), memory card, memory stick, floppy disc, universal serial bus (“USB”) memory device, or any other device operative to store data.
  • the memory 610 is operable to store instructions executable by the processor 605. The functions, acts or tasks illustrated in the figures or described can be performed by the programmed processor 605 executing the instructions stored in the memory 610.
  • processing strategies can include multiprocessing, multitasking, parallel processing and the like.
  • the electronic device 600 can further include a display unit 620, for example a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid state display, a cathode ray tube (CRT), a projector, a printer or other now known or later developed display device for outputting determined information.
  • the display 620 can act as an interface for a user to see the functioning of the processor 605, or specifically as an interface with the software stored in the memory 610 or in a drive unit 625.
  • the electronic device 600 can include an input device 630 configured to allow the user to interact with any of the components of the electronic device 600.
  • the input device 630 can include a stylus, a number pad, a keyboard, or a cursor control device, for example a mouse, or a joystick, touch screen display, remote control or any other device operative to interact with the electronic device 600.
  • the electronic device 600 can also include the drive unit 625.
  • the drive unit 625 can include a computer-readable medium 635 in which one or more sets of instructions 640, for example software, can be embedded.
  • the instructions 640 can embody one or more of the methods or logic as described.
  • the instructions 640 can reside completely, or at least partially, within the memory 610 or within the processor 605 during execution by the electronic device 600.
  • the memory 610 and the processor 605 can also include computer-readable media as discussed above.
  • the present invention contemplates a computer-readable medium that includes instructions 640 or receives and executes the instructions 640 responsive to a propagated signal so that a device connected to a network 645 can communicate voice, video, audio, images or any other data over the network 645. Further, the instructions 645 can be transmitted or received over the network 645 via a communication port or communication interface 650 or using the bus 615.
  • the communication interface 650 can be a part of the processor 605 or can be a separate component.
  • the communication interface 650 can be created in software or can be a physical connection in hardware.
  • the communication interface 650 can be configured to connect with the network 645, external media, the display 620, or any other components in the electronic device 600 or combinations thereof.
  • connection with the network 645 can be a physical connection, such as a wired Ethernet connection or can be established wirelessly as discussed later.
  • additional connections with other components of the electronic device 600 can be physical connections or can be established wirelessly.
  • the network 645 can alternatively be directly connected to the bus 615.
  • the network 645 can include wired networks, wireless networks, Ethernet AVB networks, or combinations thereof.
  • the wireless network can include a cellular telephone network, an 802.11, 802.16, 802.20, 802.1Q or WiMax network.
  • the network 645 can be a public network, such as the Internet, a private network, such as an intranet, or combinations thereof, and can utilize a variety of networking protocols now available or later developed including, but not limited to TCP/IP based networking protocols.
  • dedicated hardware implementations such as application specific integrated circuits, programmable logic arrays and other hardware devices, can be constructed to implement various parts of the electronic device 600.
  • One or more examples described can implement functions using two or more specific interconnected hardware modules or devices with related control and data signals that can be communicated between and through modules, or as portions of an application-specific integrated circuit. Accordingly, the present system encompasses software, firmware, and hardware implementations.
  • the system described can be implemented by software programs executable by an electronic device. Further, in a non-limited example, implementations can include distributed processing, component/object distributed processing, and parallel processing. Alternatively, virtual electronic device processing can be constructed to implement various parts of the system.
  • the system is not limited to operation with any particular standards and protocols.
  • standards for Internet and other packet switched network transmission for example, TCP/IP, UDP/IP, HTML, HTTP
  • Such standards are periodically superseded by faster or more efficient equivalents having essentially the same functions. Accordingly, replacement standards and protocols having the same or similar functions as those disclosed are considered equivalents thereof.
  • Various embodiments disclosed herein provide numerous advantages by providing a method and of generating knowledge based data and an embedded cognitive processing system thereof.
  • the present invention provides learning of pre-processed data similar to human learning.
  • the present invention builds high level contextual understanding on the data and makes unsupervised relations and associations.
  • the embedded cognitive processing system is intelligent, and includes low powered and low computing units with low memory and RAM.
  • the embedded cognitive processing system is hence more cost efficient. Further, due to low form factor the embedded cognitive processing system can be deployed across geography in various environments.
  • the cognitive eco-system of the embedded cognitive processing system allows solving of different problems or a same problem.
  • the present invention is modifiable to suit to problem solving and can work on any size of data.
  • the present invention is further suitable for use in defence field activities and intelligence.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The present invention relates to a method and of generating knowledge based data and an embedded cognitive processing system thereof. The method includes receiving pre-processed data by the embedded cognitive processing system. The pre-processed data includes n-dimensional data pre-processed from one or more data sources. The method also includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data. The at least one multi-level contextual response is provided to a user in response to a query of the user.

Description

METHOD OF GENERATING KNOWLEDGE BASED DATA AND AN EMBEDDED COGNITIVE PROCESSING SYSTEM THEREOF
FIELD OF THE INVENTION:
[0001] The present invention generally relates to processing data and more particularly to a method of processing data to generate knowledge based data and an embedded cognitive processing system thereof.
BACKGROUND TO THE INVENTION:
[0002] Data processing is a method generally used to process data in order to generate meaningful information. However, the data available today from different sources is typically large, complex and difficult to process. A number of data processing technologies are commonly in use to process large amounts of the data. Examples of different frameworks or the data processing technologies in use to process the data and achieve intelligence include, but are not limited to, hadoop, graphdb, and the like. Such data processing technologies are inefficient in combining hardware and software to build general purpose artificial intelligence in systems to accommodate and solve problems. Specific developmental architectures, for example big data and other forms of expert systems, are also being used to solve specific problems. Such developmental architectures, however, are unable to work on data of different sizes and is difficult to modify.
SUMMARY OF THE INVENTION:
[0003] This summary is provided to introduce a selection of concepts in a simplified format that are further described in the detailed description of the invention. This summary is not intended to identify key or essential inventive concepts of the subject matter, nor is it intended for determining the scope of the invention.
[0004] An example of a computer-implemented method of generating knowledge based data includes receiving pre-processed data by an embedded cognitive processing system. The pre-processed data includes n-dimensional data pre-processed from one or more data sources. The method also includes analysing, by the embedded cognitive processing system, the pre- processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data. The at least one multi-level contextual response is provided to a user in response to a query of the user. [0005] Another example of a computer-implemented method of generating knowledge based data includes receiving, by an embedded cognitive processing system, pre-processed data. The pre-processed data includes n-dimensional data pre-processed from one or more data sources. The method also includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data. The method further includes providing, by the embedded cognitive processing system, the at least one multi-level contextual response to a user in response to a query of the user. The at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system.
[0006] Another example of a computer-implemented method of generating knowledge based data includes pre-processing, by an embedded cognitive processing system, n- dimensional data from one or more data sources to generate pre-processed data. The method also includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data. The method further includes providing, by the embedded cognitive processing system, the at least one multi-level contextual response to a user in response to a query of the user. The at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system.
[0007] An example of an embedded cognitive processing system for generating knowledge based data includes a communication interface in electronic communication with at least one user device of a user. The embedded cognitive processing system also includes a memory that stores instructions. The embedded cognitive processing system further includes a processor responsive to the instructions. The processor includes a learning module and a response module. The learning module is configured to analyse pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data. The response module is coupled to the learning module and is configured to provide the at least one multi-level contextual response to the user in response to a query of the user. The at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system.
[0008] To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended figures. It is appreciated that these figures depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying figures.
BRIEF DESCRIPTION OF THE FIGURES:
[0009] The invention will be described and explained with additional specificity and detail with the accompanying figures in which:
[0010] FIG. 1 is an example representation of an environment, in accordance with an embodiment;
[0011] FIG. 2 is an example representation of an embedded cognitive processing system, in accordance with an embodiment;
[0012] FIG. 3 illustrates an example flow diagram of a method for delivering advertisements to user devices, in accordance with an embodiment;
[0013] FIG. 4 illustrates an example flow diagram of a method for delivering advertisements to user devices, in accordance with another embodiment;
[0014] FIG. 5 illustrates an example flow diagram of a method for delivering advertisements to user devices, in accordance with yet another embodiment; and
[0015] FIG. 6 illustrates a block diagram of an electronic device, in accordance with one embodiment.
[0016] Further, skilled artisans will appreciate that elements in the figures are illustrated for simplicity and may not have been necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the figures with details that will be readily apparent to those of ordinary skill in the art having benefit of the description herein.
DESCRIPTION OF THE INVENTION:
[0017] For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates.
[0018] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be restrictive thereof.
[0019] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by "comprises... a" does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.
[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.
[0021] Embodiments of the present invention will be described below in detail with reference to the accompanying figures.
[0022] FIG. 1 is an example representation of an environment 100, in accordance with an embodiment. The environment 100 includes a plurality of data sources, for example a data source 105, a data source 110, and a data source 115, a network 120, and an embedded cognitive processing system 125. Herein, the embedded cognitive processing system' 125 refers to a parallel distributable data system that is configured to store, classify, analyse or learn, and respond to information or data. In an example, the embedded cognitive processing system 125 is also referred to as an evolving big data system, an evolving knowledge base system, or a general purpose artificial intelligence system. In an example, the embedded cognitive processing system 125 is implemented as a compact device that operates at moderate conditions, consumes around 60 Watts power, and is modular and distributable. The embedded cognitive processing system 125 can be distributed across geography as an offline unit or an online unit.
[0023] The data source 105, the data source 110, and the data source 115 communicate with the embedded cognitive processing system 125 through the network 120. Examples of the plurality of data sources include, but are not limited to, computer systems, mobile devices, tablets, laptops, palmtops, handheld devices, telecommunication devices, personal digital assistants (PDAs), television broadcasting devices, medical equipment, infrastructures associated with cities, sensor-equipped buildings and factories, transportation systems, and the like. Herein, a 'data source' refers to a device that is configured to provide or display information or data. Examples of the network 120 includes, but are not limited to, a Local Area Network (LAN), a Wireless Local Area Network (WLAN), a Wide Area Network (WAN), internet, a Small Area Network (SAN), and the like.
[0024] The embedded cognitive processing system 125 is configured to generate knowledge based data by processing data. Herein, the 'knowledge based data' refers to optimized data that is obtained by applying one or more data aggregation methods and logical elements to the data. In order to generate the knowledge based data, the embedded cognitive processing system 125 receives pre-processed data from one or more data sources, for example from the data source 105, the data source 110, and the data source 115. Herein, the 'pre-processed data' includes n-dimensional data (for example, text files, audio files, video files, and the like) that is pre-processed using one or more methods. In an example, the n- dimensional data includes, but is not limited to, presentations, logs, documents, spreadsheets, sensor data, web content, online activities, enterprise applications, internet of things, processes, knowledge bases, tweets, posts, videos, audio, location information, wiki feeds, news feeds, social media feeds, or any other form of unstructured and asynchronous data. The embedded cognitive processing system 125 can further analyze the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data. The at least one multi-level contextual response is provided to a user in response to a query of the user.
[0025] The embedded cognitive processing system 125 including one or more components is described in detail with reference to FIG. 2.
[0026] Referring now to FIG. 2, the embedded cognitive processing system 125 is illustrated, in accordance with an embodiment. The embedded cognitive processing system 125 includes a communication interface 205 and a processor 210. In an example, the communication interface 205 is a network interface unit. The network interface unit can transfer data at a speed of 1000 megabits per second (Mbps). The embedded cognitive processing system 125 is powered by a power unit 215. In an example, the power unit 215 can operate at 60 Watts. The power unit 215 further provides 12 Volt (V) to the communication interface 205 and 5V to the processor 215.
[0027] The processor 210 includes a pre-processor module 220, a learning module 225, and a response module 230. The processor 210 operates using distributed computing. In some embodiments, the pre-processor module 220, the learning module 225, and the response module 230 are enabled as low powered and low computing units that communicate with each other. In an example, each low computing unit includes a random access memory (RAM) of 2 Gigabytes (GB), a processor memory of 16 GB, and operates at a frequency of 1.3 Giga Hertz (GHz). In an example, the low computing units are organized or clustered similar to neurons in a human brain.
[0028] The pre-processor module 220 is coupled to the learning module 225. The learning module 225 is further coupled to the response module 230. The pre-processor module 220 is configured to pre-process the n-dimensional data from one or more data sources (the data source 105— the data source 115 of FIG. 1) to generate the pre-processed data. The n-dimensional data is pre-processed using multiple methods. In one example, the pre-processor module 220 receives image data from one or more image data sources. The image data from the image data sources include unstructured image data. The pre-processor module 220 detects an auto layout in the image data. Herein, the term 'auto layout' refers to a representation of data. The pre-processor module 220 further converts the image data to structured text. In an example, optical character recognition (OCR) methods are used to convert the image data to the structured text. A language processing method is applied to the structured text to subsequently generate the pre-processed data. The pre-processed data is arranged in a semantic format. For instance, a newspaper image can be received by the preprocessor module 220. Layout of different topics and content in the newspaper image is identified. The newspaper image is then converted to text and digitized. A natural language processing method is applied to the text and the pre-processed text thus obtained is semantically arranged. [0029] In another example, the pre-processor module 220 receives textual data from one or more textual data sources, for example a word document. The textual data from the image data sources include unstructured textual data. The pre-processor module 220 detects an auto layout in the textual data. The pre-processor module 220 further converts the textual data to structured text. A language processing method is applied to the structured text to subsequently generate the pre-processed data that is arranged in the semantic format.
[0030] The learning module 225 is configured to analyse the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data. In one example, the learning module 225 receives the pre-processed data from the pre-processor module 220. The learning module 225 implements a plurality of cognitive rules on the pre-processed data. The plurality of cognitive rules is determined based on a data dimension parameter. The learning module 225 determines complementary data in relation to the pre-processed data. Herein, the term 'complementary data' refers to data similar to the pre-processed data. The learning module 225 further multiplies the pre- processed data by pairing the pre-processed data with the complementary data. In an example, such multiplication of the pre-processed data is similar to multiplication of deoxyribonucliec acid (DNA) found in various living organisms. The pre-processed data is paired with the complementary data in a cognitive eco- system of the embedded cognitive processing system 125. Herein, the term 'cognitive eco-system' refers to a digital environment that supports growth and multiplication of the pairing of the pre-processed data with the complementary data using the plurality of cognitive rules.
[0031] The response module 230 is configured to provide the at least one multi-level contextual response to the user in response to a query of the user. The at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system 125. In some embodiments, the response module 230 can go offline after the analysing by the learning module 225. In an example, the response module 230 can be 1/10 of size of the learning module 225, making the response module 230 robust and mobile.
[0032] In some embodiments, a plurality of response modules can be present as per application areas and corresponding pre-processed data. For instance, a response module associated with healthcare, a response module associated with banking, a response module associated with automotive, and the like.
[0033] In some embodiments, the embedded cognitive processing system 125 does not include the pre-processor module 220. In such embodiments, the pre-processed data is received by the embedded cognitive processing system 125 from an external pre-processor module.
[0034] In some embodiments, the embedded cognitive processing system 125 does not include the response module 230. In such embodiments, the learning module 210 is configured to provide the at least one multi-level contextual response to the user in absence of the response module.
[0035] An example method for generating the knowledge based data from the data is explained with reference to FIG. 3.
[0036] FIG. 3 illustrates an example flow diagram of a method 300 for generating knowledge based data, in accordance with an embodiment. At step 305, the method 300 includes receiving pre-processed data. The pre-processed data can be received by an embedded cognitive processing system, for example the embedded cognitive processing system 125 of FIG. 1. The pre-processed data includes n-dimensional data pre-processed from one or more data sources. Examples of the n-dimensional data includes, textual data, image data, video data, and the like. In an example, the pre-processed data can be received from an external pre-processor module.
[0037] At step 310, the method 300 includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data. In an example, the pre-processed data is analysed by a learning module, for example the learning module 225 of FIG. 2. The at least one multi-level contextual response is provided to a user in response to a query of the user, by the leaning module.
[0038] In some embodiments, the at least one multi-level contextual response is provided to the user in one of an online state and an offline state of the embedded cognitive processing system.
[0039] The pre-processed data is first received by the embedded cognitive processing system. A plurality of cognitive rules is further implemented on the pre-processed data. The plurality of cognitive rules are determined based on a data dimension parameter. Complementary data in relation to the pre-processed data is subsequently determined. The pre-processed data is then multiplied by pairing the pre-processed data with the complementary data. In an example, the pre-processed data is paired with the complementary data in a cognitive eco-system of the embedded cognitive processing system. The method of analysing the pre-processed data by the learning module is explained with reference to FIG. 2 and is not explained herein for sake of brevity. Another example method for generating the knowledge based data is explained with reference to FIG. 4.
[0040] FIG. 4 illustrates an example flow diagram of a method 400 for generating knowledge based data, in accordance with an embodiment. At step 405, the method 400 includes receiving pre-processed data. The pre-processed data is received by an embedded cognitive processing system, for example the embedded cognitive processing system 125 of FIG. 1. The pre-processed data includes n-dimensional data that is pre-processed from one or more data sources. Examples of the n-dimensional data includes, but is not limited to, textual data, image data, video data, and the like. In an example, the pre-processed data is received from an external pre-processor module.
[0041] At step 410, the method 400 includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data. In an example, the pre-processed data is analysed by a learning module, for example the learning module 225 of FIG. 2. The at least one multi-level contextual response is built in response to a query of a user, by the leaning module.
[0042] The pre-processed data is first received by the embedded cognitive processing system. A plurality of cognitive rules is further implemented on the pre-processed data. The plurality of cognitive rules are determined based on a data dimension parameter. Complementary data in relation to the pre-processed data is subsequently determined. The pre-processed data is then multiplied by pairing the pre-processed data with the complementary data. In an example, the pre-processed data is paired with the complementary data in a cognitive eco-system of the embedded cognitive processing system. The method of analysing the pre-processed data by the learning module is explained with reference to FIG. 2 and is not explained herein for sake of brevity.
[0043] At step 415, the method 400 includes providing, by the embedded cognitive processing system, the at least one multi-level contextual response to a user in response to the query of the user. In an example, the at least one multi-level contextual response is provided by a response module, for example the response module 230 of FIG. 2. The at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system.
[0044] Another example method for generating the knowledge based data is explained with reference to FIG. 5.
[0045] FIG. 5 illustrates an example flow diagram of a method 500 for generating knowledge based data, in accordance with an embodiment.
[0046] At step 505, the method 500 includes pre-processing, by an embedded cognitive processing system, n-dimensional data from one or more data sources to generate pre- processed data. In an example, the pre-processing is performed by a pre-processor module, for example the pre-processor module 220 of FIG. 2. In an example, the pre-processing of the n-dimensional data includes receiving image data from one or more image data sources. The image data includes unstructured image data. An auto layout is then detected in the image data. The image data is then converted to structured text. A language processing method is applied to the structured text to generate the pre-processed data. In an example, a natural language processing method is applied to the structured text to generate the pre-processed data. The pre-processed data is further arranged in a semantic format.
[0047] In another example, textual data is received by the pre-processor module from one or more textual data sources. The textual data from the image data sources includes unstructured textual data. The auto layout is then detected in the textual data. The textual data is converted to the structured text. The language processing method is further applied to the structured text to subsequently generate the pre-processed data that is arranged in the semantic format.
[0048] At step 510, the method 500 includes analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data. In an example, the pre-processed data is analysed by a learning module, for example the learning module 225 of FIG. 2. The method of analysing the pre-processed data by the learning module is explained with reference to FIG. 4 and is not explained herein for sake of brevity.
[0049] At step 515, the method 500 includes providing, by the embedded cognitive processing system, the at least one multi-level contextual response to a user in response to a query of the user. The at least one multi-level contextual response is provided in one of an online state and an offline state of the embedded cognitive processing system. In an example, the at least one multi-level contextual response is provided by a response module, for example the response module 230 of FIG. 2.
[0050] Referring to FIG. 6, illustrates a block diagram of an electronic device 600, which is representative of a hardware environment for practicing the present invention. The electronic device 600 can include a set of instructions that can be executed to cause the electronic device 600 to perform any one or more of the methods disclosed. The electronic device 600 may operate as a standalone device or can be connected, for example using a network, to other electronic devices or peripheral devices.
[0051] In a networked deployment of the present invention, the electronic device 600 may operate in the capacity of a data source, for example the data source 105, a data source 110, and a data source 115 of FIG. 1, and an embedded cognitive processing system, for example the embedded cognitive processing system 125 of FIG. 1, in a server-client user network environment, or as a peer electronic device in a peer-to-peer (or distributed) network environment. The electronic device 600 can also be implemented as or incorporated into various devices, such as a personal computer (PC), a tablet PC, a personal digital assistant (PDA), a mobile device, a palmtop computer, a laptop computer, a desktop computer, a communications device, a wireless telephone, a land-line telephone, a control system, a camera, a scanner, a facsimile machine, a printer, a pager, a personal trusted device, a web appliance, a network router, switch or bridge, or any other machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine. Further, while a single electronic device 600 is illustrated, the term "device" shall also be taken to include any collection of systems or sub-systems that individually or jointly execute a set, or multiple sets, of instructions to perform one or more computer functions.
[0052] The electronic device 600 can include a processor 605, for example a central processing unit (CPU), a graphics processing unit (GPU), or both. The processor 605 can be a component in a variety of systems. For example, the processor 605 can be part of a standard personal computer or a workstation. The processor 605 can be one or more general processors, digital signal processors, application specific integrated circuits, field programmable gate arrays, servers, networks, digital circuits, analog circuits, combinations thereof, or other now known or later developed devices for analyzing and processing data. The processor 605 can implement a software program, such as code generated manually (for example, programmed).
[0053] The electronic device 600 can include a memory 610, such as a memory 610 that can communicate via a bus 615. The memory 610 can include a main memory, a static memory, or a dynamic memory. The memory 610 can include, but is not limited to, computer readable storage media such as various types of volatile and non-volatile storage media, including but not limited to, random access memory, read-only memory, programmable readonly memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like. In one example, the memory 610 includes a cache or random access memory for the processor 605. In alternative examples, the memory 610 is separate from the processor 605, such as a cache memory of a processor, the system memory, or other memory. The memory 610 can be an external storage device or database for storing data. Examples include a hard drive, compact disc ("CD"), digital video disc ("DVD"), memory card, memory stick, floppy disc, universal serial bus ("USB") memory device, or any other device operative to store data. The memory 610 is operable to store instructions executable by the processor 605. The functions, acts or tasks illustrated in the figures or described can be performed by the programmed processor 605 executing the instructions stored in the memory 610. The functions, acts or tasks are independent of the particular type of instructions set, storage media, processor or processing strategy and can be performed by software, hardware, integrated circuits, firm-ware, microcode and the like, operating alone or in combination. Likewise, processing strategies can include multiprocessing, multitasking, parallel processing and the like.
[0054] As shown, the electronic device 600 can further include a display unit 620, for example a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid state display, a cathode ray tube (CRT), a projector, a printer or other now known or later developed display device for outputting determined information. The display 620 can act as an interface for a user to see the functioning of the processor 605, or specifically as an interface with the software stored in the memory 610 or in a drive unit 625.
[0055] Additionally, the electronic device 600 can include an input device 630 configured to allow the user to interact with any of the components of the electronic device 600. The input device 630 can include a stylus, a number pad, a keyboard, or a cursor control device, for example a mouse, or a joystick, touch screen display, remote control or any other device operative to interact with the electronic device 600.
[0056] The electronic device 600 can also include the drive unit 625. The drive unit 625 can include a computer-readable medium 635 in which one or more sets of instructions 640, for example software, can be embedded. Further, the instructions 640 can embody one or more of the methods or logic as described. In a particular example, the instructions 640 can reside completely, or at least partially, within the memory 610 or within the processor 605 during execution by the electronic device 600. The memory 610 and the processor 605 can also include computer-readable media as discussed above.
[0057] The present invention contemplates a computer-readable medium that includes instructions 640 or receives and executes the instructions 640 responsive to a propagated signal so that a device connected to a network 645 can communicate voice, video, audio, images or any other data over the network 645. Further, the instructions 645 can be transmitted or received over the network 645 via a communication port or communication interface 650 or using the bus 615. The communication interface 650 can be a part of the processor 605 or can be a separate component. The communication interface 650 can be created in software or can be a physical connection in hardware. The communication interface 650 can be configured to connect with the network 645, external media, the display 620, or any other components in the electronic device 600 or combinations thereof. The connection with the network 645 can be a physical connection, such as a wired Ethernet connection or can be established wirelessly as discussed later. Likewise, the additional connections with other components of the electronic device 600 can be physical connections or can be established wirelessly. The network 645 can alternatively be directly connected to the bus 615.
[0058] The network 645 can include wired networks, wireless networks, Ethernet AVB networks, or combinations thereof. The wireless network can include a cellular telephone network, an 802.11, 802.16, 802.20, 802.1Q or WiMax network. Further, the network 645 can be a public network, such as the Internet, a private network, such as an intranet, or combinations thereof, and can utilize a variety of networking protocols now available or later developed including, but not limited to TCP/IP based networking protocols.
[0059] In an alternative example, dedicated hardware implementations, such as application specific integrated circuits, programmable logic arrays and other hardware devices, can be constructed to implement various parts of the electronic device 600.
[0060] One or more examples described can implement functions using two or more specific interconnected hardware modules or devices with related control and data signals that can be communicated between and through modules, or as portions of an application- specific integrated circuit. Accordingly, the present system encompasses software, firmware, and hardware implementations.
[0061] The system described can be implemented by software programs executable by an electronic device. Further, in a non-limited example, implementations can include distributed processing, component/object distributed processing, and parallel processing. Alternatively, virtual electronic device processing can be constructed to implement various parts of the system.
[0062] The system is not limited to operation with any particular standards and protocols. For example, standards for Internet and other packet switched network transmission (for example, TCP/IP, UDP/IP, HTML, HTTP) can be used. Such standards are periodically superseded by faster or more efficient equivalents having essentially the same functions. Accordingly, replacement standards and protocols having the same or similar functions as those disclosed are considered equivalents thereof. [0063] Various embodiments disclosed herein provide numerous advantages by providing a method and of generating knowledge based data and an embedded cognitive processing system thereof. The present invention provides learning of pre-processed data similar to human learning. The present invention builds high level contextual understanding on the data and makes unsupervised relations and associations. The embedded cognitive processing system is intelligent, and includes low powered and low computing units with low memory and RAM. The embedded cognitive processing system is hence more cost efficient. Further, due to low form factor the embedded cognitive processing system can be deployed across geography in various environments. The cognitive eco-system of the embedded cognitive processing system allows solving of different problems or a same problem. The present invention is modifiable to suit to problem solving and can work on any size of data. The present invention is further suitable for use in defence field activities and intelligence.
[0064] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.
[0065] The figures and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.

Claims

WE CLAIM:
1. A computer- implemented method of generating knowledge based data, the method comprising:
receiving, by an embedded cognitive processing system, pre-processed data, the pre- processed data comprising n-dimensional data pre-processed from one or more data sources; and
analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data, the at least one multi-level contextual response being provided to a user in response to a query of the user.
2. The method as claimed in claim 1, wherein the at least one multi-level contextual response is provided to the user in one of an online state and an offline state of the embedded cognitive processing system.
3. The method as claimed in claim 1, wherein the pre-processed data is generated from one of image data and textual data.
4. The method as claimed in claim 1, wherein analysing the pre-processed data comprises:
receiving, by the embedded cognitive processing system, the pre-processed data; implementing, by the embedded cognitive processing system, a plurality of cognitive rules on the pre-processed data, the plurality of embedded cognitive rules being determined based on a data dimension parameter;
determining, by the embedded cognitive processing system, complementary data in relation to the pre-processed data; and
multiplying, by the embedded cognitive processing system, the pre-processed data by pairing the pre-processed data with the complementary data, the pre-processed data being paired with the complementary data in a cognitive eco- system of the embedded cognitive processing system.
5. A computer- implemented method of generating knowledge based data, the method comprising: receiving, by an embedded cognitive processing system, pre-processed data, the pre- processed data comprising n-dimensional data pre-processed from one or more data sources; analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data; and
providing, by the embedded cognitive processing system, the at least one multi-level contextual response to a user in response to a query of the user, the at least one multi-level contextual response being provided in one of an online state and an offline state of the embedded cognitive processing system.
6. The method as claimed in claim 5, wherein the pre-processed data is generated from one of image data and textual data.
7. The method as claimed in claim 5, wherein analysing the pre-processed data comprises:
receiving, by the embedded cognitive processing system, the pre-processed data; implementing, by the embedded cognitive processing system, a plurality of cognitive rules on the pre-processed data, the plurality of cognitive rules being determined based on a data dimension parameter;
determining, by the embedded cognitive processing system, complementary data in relation to the pre-processed data; and
multiplying, by the embedded cognitive processing system, the pre-processed data by pairing the pre-processed data with the complementary data, the pre-processed data being paired with the complementary data in a cognitive eco- system of the embedded cognitive processing system.
8. A computer- implemented method of generating knowledge based data, the method comprising:
pre-processing, by an embedded cognitive processing system, n-dimensional data from one or more data sources to generate pre-processed data;
analysing, by the embedded cognitive processing system, the pre-processed data to cognitively build at least one multi-level contextual response associated with the pre- processed data; and
providing, by the embedded cognitive processing system, the at least one multi-level contextual response to a user in response to a query of the user, the at least one multi-level contextual response being provided in one of an online state and an offline state of the embedded cognitive processing system.
9. The method as claimed in claim 8, wherein pre-processing the n-dimensional data comprises:
receiving, by the embedded cognitive processing system, image data from one or more image data sources, the image data comprising unstructured image data;
detecting, by the embedded cognitive processing system, an auto layout in the image data;
converting, by the embedded cognitive processing system, the image data to structured text; and
applying, by the embedded cognitive processing system, a language processing method to the structured text to generate the pre-processed data, the pre-processed data being arranged in a semantic format.
10. The method as claimed in claim 8, wherein pre-processing the n-dimensional data comprises:
receiving, by the embedded cognitive processing system, textual data from one or more textual data sources, the textual data comprising unstructured textual data;
detecting, by the embedded cognitive processing system, an auto layout in the textual data;
converting, by the embedded cognitive processing system, the textual data to structured text; and
applying, by the embedded cognitive processing system, a language processing method to the structured text to generate the pre-processed data, the pre-processed data being arranged in a semantic format.
11. The method as claimed in claim 8, wherein analysing the pre-processed data comprises:
receiving, by the embedded cognitive processing system, the pre-processed data; implementing, by the embedded cognitive processing system, a plurality of cognitive rules on the pre-processed data, the plurality of cognitive rules being determined based on a data dimension parameter; determining, by the embedded cognitive processing system, complementary data in relation to the pre-processed data; and
multiplying, by the embedded cognitive processing system, the pre-processed data by pairing the pre-processed data with the complementary data, the pre-processed data being paired with the complementary data in a cognitive eco- system of the embedded cognitive processing system.
12. A embedded cognitive processing system for generating knowledge based, the embedded cognitive processing system comprising:
a communication interface in electronic communication with at least one user device of a user;
a memory that stores instructions; and
a processor responsive to the instructions, the processor comprising:
a learning module configured to analyse pre-processed data to cognitively build at least one multi-level contextual response associated with the pre-processed data; and
a response module coupled to the learning module and configured to provide the at least one multi-level contextual response to the user in response to a query of the user, the at least one multi-level contextual response being provided in one of an online state and an offline state of the embedded cognitive processing system.
13. The embedded cognitive processing system as claimed in claim 12, wherein the processor further comprises:
a pre-processor module coupled to the learning module and configured to pre-process n-dimensional data from one or more data sources to generate the pre-processed data.
14. The embedded cognitive processing system as claimed in claim 13, wherein the preprocessor module is further configured to:
receive image data from one or more image data sources, the image data comprising unstructured image data;
detect an auto layout in the image data;
convert the image data to structured text; and
apply a language processing method to the structured text to generate the pre- processed data, the pre-processed data being arranged in a semantic format.
15. The embedded cognitive processing system as claimed in claim 13, wherein the preprocessor module is further configured to:
receive textual data from one or more textual data sources, the textual data comprising unstructured textual data;
detect an auto layout in the textual data;
convert the textual data to structured text; and
apply a language processing method to the structured text to generate the pre- processed data, the pre-processed data being arranged in a semantic format.
16. The embedded cognitive processing system as claimed in claim 13, wherein the learning module is further configured to:
receive the pre-processed data;
implement a plurality of cognitive rules on the pre-processed data, the plurality of cognitive rules being determined based on a data dimension parameter;
determine complementary data in relation to the pre-processed data; and
multiply the pre-processed data by pairing the pre-processed data with the complementary data, the pre-processed data being paired with the complementary data in a cognitive eco-system of the embedded cognitive processing system.
17. The embedded cognitive processing system as claimed in claim 12, wherein the learning module is configured to provide the at least one multi-level contextual response to the user in absence of the response module.
18. The embedded cognitive processing system as claimed in claim 12, wherein the communication interface comprises a network interface unit.
19. The embedded cognitive processing system as claimed in claim 12, wherein the processor operates based on distributed computing on low computing units.
PCT/IB2016/054977 2016-05-18 2016-08-19 Method of generating knowledge based data and an embedded cognitive processing system thereof WO2017199074A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IN201641017149 2016-05-18
IN201641017149 2016-05-18

Publications (1)

Publication Number Publication Date
WO2017199074A1 true WO2017199074A1 (en) 2017-11-23

Family

ID=60325760

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2016/054977 WO2017199074A1 (en) 2016-05-18 2016-08-19 Method of generating knowledge based data and an embedded cognitive processing system thereof

Country Status (1)

Country Link
WO (1) WO2017199074A1 (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2320358A2 (en) * 2005-04-08 2011-05-11 Definiens AG Computer-implemented method for automatic knowledge-based generation of user data

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2320358A2 (en) * 2005-04-08 2011-05-11 Definiens AG Computer-implemented method for automatic knowledge-based generation of user data

Similar Documents

Publication Publication Date Title
US10831345B2 (en) Establishing user specified interaction modes in a question answering dialogue
US20160196491A1 (en) Method For Recommending Content To Ingest As Corpora Based On Interaction History In Natural Language Question And Answering Systems
US9984050B2 (en) Ground truth collection via browser for passage-question pairings
WO2011126458A1 (en) Automatic frequently asked question compilation from community-based question answering archive
US9830316B2 (en) Content availability for natural language processing tasks
US10108661B2 (en) Using synthetic events to identify complex relation lookups
US10740570B2 (en) Contextual analogy representation
US20200150981A1 (en) Dynamic Generation of User Interfaces Based on Dialogue
CN113761220A (en) Information acquisition method, device, equipment and storage medium
US10558760B2 (en) Unsupervised template extraction
US10133736B2 (en) Contextual analogy resolution
US10229156B2 (en) Using priority scores for iterative precision reduction in structured lookups for questions
US20210173837A1 (en) Generating followup questions for interpretable recursive multi-hop question answering
US10303765B2 (en) Enhancing QA system cognition with improved lexical simplification using multilingual resources
US20170228438A1 (en) Custom Taxonomy
US9946762B2 (en) Building a domain knowledge and term identity using crowd sourcing
WO2017199074A1 (en) Method of generating knowledge based data and an embedded cognitive processing system thereof
US10318633B2 (en) Using multilingual lexical resources to improve lexical simplification
US10325025B2 (en) Contextual analogy representation
US10417053B2 (en) Adaptive cognitive agent
US11636391B2 (en) Automatic combinatoric feature generation for enhanced machine learning
US20230251834A1 (en) Method and system for library package management
Singh et al. Making machines think

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16902288

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16902288

Country of ref document: EP

Kind code of ref document: A1