CN112260930A

CN112260930A - System and method for creating global conversation threads across communication channels

Info

Publication number: CN112260930A
Application number: CN202010616941.3A
Authority: CN
Inventors: S·S·穆塔斯瓦米; S·达斯; Y·M·帕特奈克; N·V·拉文德拉
Original assignee: International Business Machines Corp
Current assignee: International Business Machines Corp
Priority date: 2019-07-02
Filing date: 2020-07-01
Publication date: 2021-01-22
Anticipated expiration: 2040-07-01
Also published as: CN112260930B; WO2021001735A1; JP2022539135A

Abstract

A system for creating a global conversation thread may include a processor that receives data associated with a plurality of conversation threads, each conversation thread including one or more conversations between the same person or the same role. The processor may identify overlapping conversation threads of the plurality of conversation threads based on the data and group the overlapping conversation threads based on a person or role within the conversation. The processor may apply the matching rules to identify relevant dialogs that include the target interest feature, and create a global dialog thread based on the identified relevant dialogs, the global dialog thread including dialog threads across different platforms.

Description

System and method for creating global conversation threads across communication channels

Technical Field

The present application relates generally to dialogs occurring on various platforms, and more particularly to creating a global conversation thread across different communication channels.

Background

The bank employees use various channels to communicate within the bank and with the customers (such as email, chat, voice). In situations that can be characterized as market abuse, the relevant communications typically occur over various channels and also between the parties. For example, John may talk to a corresponding person of another brokerage firm via email or text message to decide the price of the foreign exchange. Once they reach pricing, john can use his phone to call his front desk to order to purchase or sell a certain currency in bulk. To capture such a scenario, it is not sufficient to monitor the various channels separately.

Existing systems apply different techniques (such as clustering and topic modeling) to establish closely related conversations and group them together using metadata such as: message subject, participant, submission date, and message content. Most systems analyze different conversations within the same channel-e.g., review all emails to find related emails-and thus miss information that may exist on another communication channel. There is a need for a system that can detect conversation threads across different communication channels and different conversation threads within those communication channels in order to create a global conversation thread that can be evaluated for market abuse scenarios.

The present disclosure is directed to overcoming these and other problems of the prior art.

Disclosure of Invention

In some embodiments, a computer-implemented method for creating a global conversation thread in a data processing system is disclosed. The data processing system may include a processing device and a memory including instructions for execution by the processing device. The method can comprise the following steps: receiving data associated with a plurality of conversation threads, each conversation thread comprising one or more conversations between the same person or the same role; the method includes identifying overlapping conversation threads of a plurality of conversation threads based on data, grouping overlapping conversation threads based on people or roles within a conversation, applying matching rules to identify relevant conversations including target interest features, and creating a global conversation thread based on the identified relevant conversations, the global conversation thread including conversation threads across different platforms.

Additional embodiments may include systems and computer program products for creating a global conversation thread.

Drawings

The foregoing and other aspects of the present invention are best understood from the following detailed description when read with the accompanying drawing figures. For the purpose of illustrating the invention, there is shown in the drawings embodiments which are presently preferred, it being understood, however, that the invention is not limited to the specific instrumentalities disclosed. Included in the drawings are the following figures:

FIG. 1 depicts a schematic diagram of a global dialog system consistent with disclosed embodiments;

FIG. 2 is a block diagram of an example data processing system in which aspects of the illustrative embodiments may be implemented;

FIG. 3 is a flow diagram of an example process for creating a global conversation thread consistent with the disclosed embodiments;

FIG. 4 is a diagram of a first conversation between individuals consistent with the disclosed embodiments;

FIG. 5 is a diagram of a second conversation between individuals consistent with the disclosed embodiments;

FIG. 6 is a flow diagram of an example dialog linking process consistent with the disclosed embodiments; and

FIG. 7 is a diagram of a global conversation thread from first and second conversations, consistent with the disclosed embodiments.

Detailed Description

The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and procedural programming languages, such as Java, the "C" language, or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The present disclosure relates to systems and methods for creating a global conversation thread by connecting conversations across different communication channels (different communication modalities), wherein conversations across different communication channels are connected by linking conversations based on their content. The programmed system may look for certain information based on the content of the conversation in order to identify connected conversations that concern scenarios that may involve market abuse by the parties to the conversation or market abuse as the subject of the conversation.

FIG. 1 depicts a schematic diagram of one illustrative embodiment of a global dialog system 100. The global dialog system 100 comprises, for example, a central server 110 and a plurality of user devices 120 each associated with a user 130 and all connected via a network 140. The central server 110 and the plurality of user devices 120 are functionally represented as a single, separate component, but it should be understood that the disclosed embodiments are not so limited. Further, in some embodiments, devices may be combined. For example, the central server 110 and/or its components may be integrated into one or more of the user devices 120. User 130 is an individual, which may be interchangeably described herein as a participant in one or more personal conversations via user device 120, where such personal conversations may be combined into a global conversation through central server 110.

Fig. 1 shows three

user devices

120A, 120B, 120C (which make up a plurality of user devices 120) and three

corresponding users

130A, 130B, 130C (which make up user 130). It should be understood that this representation is exemplary, and other embodiments may include more (or fewer) user devices 120 and associated users 130. Furthermore, it is not necessary that each user device 120 only have one associated user 130. In some embodiments, a single user 130 may represent all of the participants associated with user device 120, such as multiple people assigned the same role within an organizational structure (e.g., administrators, assistants, attorney assistants, accountants, etc.).

The central server 110 may be implemented in hardware and/or software and may include various component (consistency) components. These components may include, for example, one or more processing devices, one or more memory devices, and/or one or more databases. The central server 110 is particularly configured as an information center (hub) configured to receive data from the user equipment 120 and to transmit data to the user equipment 120. For example, the central server 110 may be configured as a processing server that receives the session data from the user devices 120. In an embodiment, the central server 110 is a server, but is not limited to such embodiments.

The user device 120 is preferably a computing device configured to be operated by a user 130 and to deliver data to the global dialog system 100. The user device 120 may be, for example, a personal computer (e.g., laptop, desktop, etc.), a tablet, a smartphone, etc. User device 120 may include constituent components. These components may include, for example: an I/O device configured to collect data associated with user input; communication hardware for sending and receiving data to and from other components of the global dialog system 100; and a display device for displaying information to the user 130, such as a display screen configured to display a user interface. User device 120 is configured to support various platforms associated with conversations between users 130. For example, the user device 120 may support a communication platform, such as a platform associated with messaging programs, email programs, video feeds, audio feeds, camera inputs and other images, web browsers, social media, mobile applications, and so forth.

The users 130 may be individuals associated with the respective user devices 120. For example, user 130 may be an employee participating in a conversation in one or more companies. Users 130 are different people with different personal characteristics. Users 130 may be employees in different companies, departments, have different professions, and so on. Users 130 may include customers and employees, such as clients and financial professionals who manage the client's finances.

The network 140 may be a local or global network and may include wired and/or wireless components and functionality that enable communication between the central server 110 and the user devices 120. Network 140 may be implemented by the internet provided at least in part via cloud services, and/or may include one or more communication devices or systems that initiate data transfers to and from systems and components of central server 110 and user device 120.

According to some exemplary embodiments, the elements of the global dialog system 100 include logic implemented in dedicated hardware, software executing on hardware, or any combination of dedicated hardware and software executing on hardware for implementing the global dialog system 100. In some exemplary embodiments, the global dialog system 100 may be a network or a packageIncluding IBM Watson available from International Business machines corporation of Armonk, N.Y^TMA system that is enhanced with the mechanisms of the illustrative embodiments described hereinafter.

FIG. 2 is a block diagram of an example data processing system 200 in which aspects of the illustrative embodiments may be implemented. Data processing system 200 is an example of a computer, such as a server or a client, in which computer usable code or instructions implementing the processes for illustrative embodiments of the present invention may be located. In one embodiment, fig. 2 represents a server computing device, such as a central server 110, the central server 110 implementing the global dialog system 100 described herein.

In the depicted example, data processing system 200 may use a hub architecture including a north bridge and memory controller hub (NB/MCH)201 and a south bridge and input/output (I/O) controller hub (SB/ICH) 202. Processing unit 203, main memory 204, and graphics processor 205 may be connected to NB/MCH 201. Graphics processor 205 may be connected to NB/MCH 201 through an Accelerated Graphics Port (AGP).

In the depicted example, network adapter 206 connects to SB/ICH 202. Audio adapter 207, keyboard and mouse adapter 208, modem 209, Read Only Memory (ROM)210, Hard Disk Drive (HDD)211, optical drive (CD or DVD)212, Universal Serial Bus (USB) ports and other communications ports 213, and PCI/PCIe devices 214 may connect to SB/ICH 202 through bus system 216. PCI/PCIe devices 214 may include Ethernet adapters, add-in cards, and PC cards for notebook computers. ROM 210 may be, for example, a flash basic input/output system (BIOS). The HDD 211 and the optical drive 212 may use an Integrated Drive Electronics (IDE) or Serial Advanced Technology Attachment (SATA) interface. A super I/O (SIO) device 215 may connect to SB/ICH 202.

An operating system may run on processing unit 203. An operating system may coordinate and provide control of various components within data processing system 200. As a client, the operating system may be a commercially available operating system. Object-oriented program system (such as Java)^TMProgram system) may run in conjunction with an operating system and receive data fromAn object oriented program or application executing on processing system 200 provides calls to the operating system. As a server, data processing system 200 may be running a high-level inter-execution operating system or a Linux operating system

eServer^TM System

Data processing system 200 may be a Symmetric Multiprocessor (SMP) system including a plurality of processors in processing unit 203. Alternatively, a single processor system may be used.

Instructions for the operating system, the object-oriented program system, and applications or programs are located on storage devices, such as HDD 211, and are loaded into main memory 204 for execution by processing unit 203. The processes for embodiments of the global dialog system 100 may be performed by the processing unit 203 using computer usable program code, which may be located in a memory such as, for example, the main memory 204, the ROM 210, or in one or more peripheral devices.

The bus system 216 may include one or more buses. The bus system 216 may be implemented using any type of communication fabric or architecture that provides for a transfer of data between different components or devices attached to the fabric (fabric) or architecture. A communication unit, such as modem 209 or network adapter 206, may include one or more devices operable to transmit and receive data.

Those of ordinary skill in the art will appreciate that the hardware depicted in FIG. 2 may vary depending on the implementation. Other internal hardware or peripheral devices, such as flash memory, equivalent non-volatile memory, or optical disk drives and the like, may be used in addition to or in place of the hardware depicted. Moreover, data processing system 200 may take the form of any number of different data processing systems including, but not limited to: client computing devices, server computing devices, tablet computers, laptop computers, telephones or other communication devices, personal digital assistants, and the like. Essentially, data processing system 200 may be any known or later developed data processing system without architectural limitations.

Those of ordinary skill in the art will appreciate that the hardware depicted in FIG. 2 may vary depending on the implementation. For example, the data processing system 200 includes a number of components that will not be included directly in some embodiments of the global dialog system 100. However, it is to be understood that the global dialog system 100 may include one or more of the components and configurations of the data processing system 200 for performing the processing methods and steps in accordance with the disclosed embodiments.

Further, other internal hardware or peripheral devices, such as flash memory, equivalent non-volatile memory, or optical disk drives may be used in addition to or in place of the hardware depicted. Moreover, data processing system 200 may take the form of any number of different data processing systems including, but not limited to: client computing devices, server computing devices, tablet computers, laptop computers, telephones or other communication devices, personal digital assistants, and the like. Essentially, data processing system 200 may be any known or later developed data processing system without architectural limitations.

FIG. 3 is a flow diagram of an exemplary process 300 for creating a global conversation thread. In an exemplary embodiment, the central server 110 may perform one or more steps of the process 300. In step 310, the central server 110 receives conversation data, including identification details associated with one or more conversations from one or more user devices 120. The identification details may include: user information, dialog content, general details, specific details, etc.

In step 320, central server 110 may model each conversation thread. For example, the central server 110 may model each person as a node and each conversation between persons as a connector between nodes. In one example, a conversation may occur between two people. For example, a first employee may talk to a customer/client via email. Conversations may also occur between more than two people, such as in a teleconference. In another example, a conversation may occur only where one user is involved, such as through a memo, note, email itself, and so forth.

In step 330, the central server 110 may extract features from the conversation. For example, the central server 110 may extract personal information, and content features. The content features may include, for example, first level features and second level features. In other embodiments, the content features may include different classes of features (e.g., first-level-fourth-level features). First level features may include, for example, individuals and businesses, trade and non-trade, foreign exchange and equity (equity) to associate various categories and subcategories of communication. Second level features may be more specific and include, for example, an ticker (i.e., stock or asset identifier) in the case of equity or currency in the case of an outsourced transaction, a quantity of units of the ticker or currency, and a price tag associated with the conversation, among others. The second level features may include transaction details associated with the financial transaction. In other words, the first level features may be related to the generic recognition features of the dialog, and the second level features may be more particularly related to the content and/or intent of the dialog.

In step 340, the central server 110 may connect the relevant dialogs to create a global dialog thread. The conversation detected by the central server 110 may occur between different people via different user devices and involve different platforms for communication. However, each personal conversation may be related to one or more other personal conversations as part of a larger global conversation about the same topic. For example, two individuals may engage in a conversation related to market abuse, such as planned fraudulent activities. Conversations may occur across different platforms (e.g., chat-based platforms, email-based platforms, audio-based platforms, etc.), such as to attempt to avoid detection. The central server 110 is configured to link related conversations across different platforms and devices to identify global conversations, which may allow the central server 110 to identify global conversations related to market abuse scenarios.

Fig. 4 is an example model of a first conversation between two individuals "john" and "mary". The data associated with the first conversation may include metadata about each person, such as whether the person is an employee of a particular company, the person's potential identity, a customer/company identifier, the year of contact, and a communication profile (e.g., communication frequency and subject matter). If the individual (e.g., "John") is an employee, the personal information may include department, age of engagement, additional information about the position, and the like.

The data associated with the first conversation may also include metadata about the conversation (e.g., content data, background data, etc.). The content data may include first-level features such as general category information (e.g., business, trade, foreign exchange, etc.), participants, platforms/channels of conversation (e.g., text messaging, chat channels, email, phone, video conferencing, social media, etc.), dates, call duration, etc. The content data may also include, for example, second level features such as financial details, such as the amount, currency, ticker, etc. in question.

The central server 110 may be configured to perform natural language processing to create additional metadata features for the conversation. For example, the central server 110 may classify the conversation based on the words or phrases used, may determine the intent of the conversation, identify the subject matter of the conversation, and so on. The central server 110 may use a feedback/machine learning process to improve the process as more conversations are collected.

In some embodiments, details associated with a single conversation between "john" and "mary" may be grouped with other conversations between the same people as part of a grouped conversation thread. The conversation thread may also include details extracted by the central server 110, such as the intent of the conversation, the character mode, the conversation period, the number of conversations in the thread, and the like. In some aspects, a group conversation between two individuals may be considered a "global conversation thread" that provides details about the discussion between the two individuals.

FIG. 5 is an example model of a second conversation between two individuals "John" and "Joe". The conversation may be between two employees of a company, such as a member in the trading department and a foreground employee. The central server 110 may receive metadata about each person and content data about the conversation. The content data may include first-level and second-level features that generally and specifically describe the dialog. The central server 110 may track multiple conversations between "john" and "joe" and create a grouped conversation thread.

FIG. 6 is a flow diagram of an exemplary process 600 for linking personal dialogs to create a global conversation thread. For example, process 600 may include a process of linking a single conversation instance to another single conversation instance. In another example, process 600 may include linking a group conversation between two people to another group conversation between two other people (e.g., at least one different person). Central server 110 may perform one or more steps of process 600. Process 600 may be a step-wise filtering process that determines which dialogs are related. The central server 110 may target conversations on a particular topic, such as a market abuse scenario.

In step 610, the central server 110 may identify overlapping conversation threads. Step 610 may be an initial filtering mechanism based on certain characteristics (such as timing, intent, role patterns, etc.) to identify close/similar conversations. For example, the central server 110 may identify all conversations between particular people, characters, that involve particular words during a certain time. The central server 110 may use a simple rule model or a machine learning model to group conversations.

In some embodiments, the central server 110 may identify overlapping conversation threads by comparing the proximity of one or more features of the conversation. For example, the central server 110 may use timed proximity (e.g., how close the conversations occurred), intent proximity (e.g., how similar the intentions of the conversations are), or role mode proximity (e.g., what role an individual plays in a conversation and how similar the modes are). The use of timing proximity may include matching dialogs within a selected time period. In some embodiments, the use of intent proximity includes comparing similarity of topics of conversations within the conversation thread. The use of character pattern proximity may include comparing locations of entities in a conversation to identify similar patterns. The central server 110 may use a combination of timed proximity, intent proximity, and role pattern proximity to identify overlapping conversations between entities.

In step 620, the central server 110 may group the people and form a larger operational group. For example, the central server 110 may also filter conversations based on the people involved, departments within the company, roles of individuals, and so forth.

In step 630, the central server 110 may use the rules to target relevant conversations of interest. For example, the central server 110 may target conversations that include particular features, such as: financial terms, ticker, negotiation terms, conversation results, event triggers, and the like.

In some embodiments, the central server 110 may target related conversations based on the determined intent of the conversation. For example, the central server 110 may identify the roles of the participants in the personal conversation and the determined intent of the conversation to determine whether a pattern exists across multiple conversations. The central server 110 may use supervised machine learning models, such as fraud analysis models, to distinguish legitimate (e.g., typical work sessions) activities from illegitimate (e.g., fraudulent) activities.

In step 640, the central server 110 may collect the filtered conversations and create a global conversation thread. The global conversation thread may include collected data related to the global conversation thread. For example, the global conversation thread may include first-level features, such as categories of component conversations (e.g., business, trade, foreign exchange, order, purchase). The global conversation thread may also include second level features, such as communication modes and the like. Other data may include the time period of the overall conversation, the number of individual conversations, the average duration, etc.

In some embodiments, the global conversation thread may be analyzed for anomalies that may be of interest. For example, the central server 110 may provide a global conversation thread to a fraud detection system to determine whether the conversation includes or may include fraudulent or undesirable activity. A global conversation thread, which is a combination of conversations across different platforms, enables the detection system to have a more complete picture of interactions between entities (e.g., the same person, people in the same role) as opposed to those conversations occurring only on the same platform.

FIG. 7 is an example model of a global conversation thread formed by a first conversation and a second conversation. For example, the global conversation may be a combined conversation between "john" and "mary" and "joe". The central server 110 may store metadata related to the global conversation thread. The communication may be a user or group communication. Global conversations may be abstracted to roles rather than individuals. For example, instead of "joe," the identifier may be a role, such as "front receptionist.

An exemplary method for creating a global conversation thread includes: identifying dialogs across different communication channels and between parties, modeling each dialog using connected nodes, extracting basic and specific details of the dialog, and linking the modeled dialogs to each other based on the extracted information. The disclosed embodiments include features that allow linking of conversations, even though they are between different participants on different communication channels. As a potential result, the global dialog system may reliably detect market abuse by connecting dialogs across different communication channels. The system may include providing an alert when an anomaly is detected in the global conversation thread.

The description and claims may use the terms "a," "at least one of … …," and "one or more of … …" in relation to particular features and elements of the illustrative embodiments. It should be understood that these terms and phrases are intended to describe having at least one of the particular features or elements present in a particular illustrative embodiment, but that more than one may be present. That is, these terms/phrases are not intended to limit the specification or claims to the presence of a single feature/element or to require the presence of multiple such features/elements. Rather, these terms/phrases only require at least a single feature/element insofar as a plurality of such features/elements are possible within the scope of the specification and claims.

Additionally, it should be appreciated that the following description further illustrates example implementations of the illustrative embodiments and facilitates an understanding of mechanisms of the illustrative embodiments using a number of different examples for the various elements of the illustrative embodiments. These examples are intended to be non-limiting and non-exhaustive of the various possibilities for implementing the mechanisms of the illustrative embodiments. It will be apparent to those of ordinary skill in the art in view of this disclosure that there are many other alternative implementations for these various elements that can be used in addition to or in place of the examples provided herein without departing from the spirit and scope of the present invention.

The systems and processes of the drawings are non-exclusive. Other systems, processes, and functional tables may be derived in accordance with the principles of the embodiments described herein to achieve the same objectives. It is to be understood that the embodiments and variations shown and described herein are for illustration purposes only. Modifications to the current design may be implemented by those skilled in the art without departing from the scope of the embodiments. As described herein, the various systems, subsystems, agents, managers, and processes can be implemented using hardware components, software components, and/or combinations thereof. No claimed element will be understood under the terms of paragraph six of 35u.s.c.112 unless the element is explicitly recited using the phrase "means for … ….

Although the present invention has been described with reference to exemplary embodiments, the present invention is not limited thereto. It will be understood by those skilled in the art that many changes and modifications may be made to the preferred embodiment of the present invention and that such changes and modifications may be made without departing from the true spirit of the invention. It is therefore intended that the following appended claims be interpreted as covering all such equivalent variations as fall within the true spirit and scope of the invention.

Claims

1. A computer-implemented method for creating a global conversation thread in a data processing system, the data processing system including a processing device and a memory including instructions for execution by the processing device, the method comprising:

receiving data associated with a plurality of conversation threads, each conversation thread comprising one or more conversations between the same person or the same role;

identifying overlapping conversation threads of the plurality of conversation threads based on the data;

grouping overlapping session threads based on people or roles within the session;

applying matching rules to identify relevant dialogs that include the target interest feature; and

creating a global conversation thread based on the identified relevant conversations, the global conversation thread including conversation threads across different platforms.

2. The method of claim 1, wherein identifying overlapping conversation threads comprises comparing one or more of: timing proximity, intent proximity, or role mode proximity.

3. The method of claim 2, wherein comparing timing proximities comprises: matching the dialogs within the selected time period.

4. The method of claim 2, wherein comparing the intended proximity comprises: the subject matter of the conversations within the conversation threads is compared for similarity.

5. The method of claim 2, wherein comparing the persona pattern proximity comprises: the locations of entities in the conversation are compared.

6. The method of claim 2, wherein identifying overlapping conversation threads comprises: combinations of timing proximity, intent proximity, and role mode proximity are compared.

7. The method of claim 1, wherein the target interest characteristic is a financial transaction factor.

8. The method of claim 7, wherein the financial transaction factor is a transaction amount.

9. The method of claim 1, wherein the different platforms comprise: chat-based platforms, and email-based platforms.

10. The method of claim 8, wherein the different platforms comprise: text-based platforms, and audio-based platforms.

11. A system for creating a global conversation thread, comprising a processing device and a memory including instructions for execution by the processor to perform a method, the method comprising:

12. The system of claim 11, wherein identifying overlapping conversation threads comprises comparing one or more of: timing proximity, intent proximity, or role mode proximity.

13. The system of claim 12, wherein comparing timing proximities comprises: matching the dialogs within the selected time period.

14. The system of claim 12, wherein comparing the intended proximity comprises: the subject matter of the conversations within the conversation threads is compared for similarity.

15. The system of claim 12, wherein comparing the persona pattern proximity comprises: the locations of entities in the conversation are compared.

16. The system of claim 12, wherein identifying overlapping conversation threads comprises: combinations of timing proximity, intent proximity, and role mode proximity are compared.

17. The system of claim 11, wherein the target interest characteristic is a financial transaction factor.

18. The system of claim 17, wherein the financial transaction factor is a transaction amount.

19. The system of claim 11, wherein the different platforms comprise: chat-based platforms, and email-based platforms.

20. The system of claim 18, wherein the different platforms comprise: text-based platforms, and audio-based platforms.

21. A computer program product configured to create a global conversation thread, comprising a computer readable storage medium having computer readable program instructions stored thereon that, when read by a processor, cause the processor to perform steps encompassed by a process comprising:

22. A computer system comprising means for performing the steps of the method according to any one of claims 1-10, respectively.

23. A computer-implemented method for creating a global conversation thread in a data processing system, the data processing system including a processing device and a memory including instructions for execution by the processing device, the method comprising:

receiving, using one or more user devices, data associated with a plurality of personal conversations between one or more users;

modeling a personal conversation thread based on the data;

extracting features from the modeled conversation thread; and

linking the conversation based on the extracted features to create a global conversation thread,

wherein the personal conversation occurs on a different platform and the global conversation thread includes content from the different platform.

24. The method of claim 23, wherein the modeling the personal conversation thread comprises: entities are represented as nodes and connect entities that conduct a conversation.

25. The method of claim 24, wherein the extracted features comprise: basic features, and specific features.

26. The method of claim 25, wherein the base features comprise: a classification of the entity, or a topic of the conversation.

27. The method of claim 25, wherein the particular characteristic comprises transaction details.

28. The method of claim 24, wherein the entity is a person.

29. The method of claim 24, wherein the entity is a persona comprising a plurality of individuals.

30. The method of claim 23, wherein the extracted features comprise metadata.

31. The method of claim 30, wherein the metadata includes identification information of the user.

32. The method of claim 30, wherein the metadata comprises: the date and duration of the personal conversation.

33. A system for creating a global conversation thread, comprising a processing device and a memory including instructions for execution by the processing device to perform a method, the method comprising:

modeling a personal conversation thread based on the data;

extracting features from the modeled conversation thread; and

34. The system of claim 33, wherein the modeling of the personal conversation thread comprises: entities are represented as nodes and connect entities that conduct a conversation.

35. The system of claim 34, wherein the extracted features comprise: basic features, and specific features.

36. The system of claim 35, wherein the base features comprise: a classification of the entity, or a topic of the conversation.

37. The system of claim 35, wherein the specific characteristics include transaction details.

38. The system of claim 34, wherein the entity is a person.

39. The system of claim 34, wherein the entity is a persona comprising a plurality of individuals.

40. The system of claim 33, wherein the extracted features comprise metadata.

41. The system of claim 40, wherein the metadata includes identification information of the user.

42. The system of claim 40, wherein the metadata comprises a date and duration of the personal conversation.

43. A computer program product configured to create a global conversation thread, comprising a computer readable storage medium having computer readable program instructions stored thereon that, when read by a processor, cause the processor to perform steps encompassed by a process comprising:

modeling a personal conversation thread based on the data;

extracting features from the modeled conversation thread; and

44. A computer system comprising means for performing the steps of the method according to any one of claims 23-32, respectively.