DESC:FIELD
The present disclosure generally relates to two-way chat platforms. More particularly, the present disclosure relates to an omni-channel chat platform.
DEFINITION
As used in the present disclosure, the following terms are generally intended to have the meaning as set forth below, except to the extent that the context in which they are used indicate otherwise.

Omni-channel: The term “omni-channel” describes a multichannel approach that seeks to provide customers with a seamless experience. In omni-channel platform, the customers may start in one channel and move to another as they progress to a resolution.
BACKGROUND
The background information herein below relates to the present disclosure but is not necessarily prior art.
Nowadays, customers can easily ask queries online on a chat platform regarding a product or a service. However, with the availability of numerous communication channels like social media messenger, mobile application chat, web application chat, and the like, the customers tend to frequently switch from one communication channel to another channel. If a customer asks queries on one communication channel and then switches to another channel, he may have to refer to the previous channel for resuming the conversation, as the new channel may not have any conversation transferred from previous channel. The customer’s journey with contextual conversations and interactions with the business happening across multiple customer platforms with a chat platform is missing in the present scenario. The customer conversations on various channels can lead to loss of context when the customer switches from one channel to another. The redundancy of customer service requests and transactions is also not carried seamlessly from one channel to other, thus reducing end customer satisfaction.
Therefore, there is felt a need to provide an omni-channel chat platform that alleviates the aforementioned drawbacks.
OBJECTS
Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:
An object of the present disclosure is to provide an omni-channel chat platform.
Another object of the present disclosure is to provide a system that enables transition of conversation when customer switches from one channel to other.
Yet another object of the present disclosure is to provide a system that enables retention of customer conversation when customer switches between channels.
Still another object of the present disclosure is to provide a system that keeps track of a customer’s conversation, and refers to live agents to optimize performance.
Another object of the present disclosure is to provide a system which eliminates the need of initiating the chat from beginning.
Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
SUMMARY
The present disclosure envisages a platform that facilitates seamless conversation between a user and a bot when the user switches from a first chat session on a first channel to a second chat session on a second channel during the conversation.
The platform comprises a Natural Language Processing (NLP) engine, a data logger, an omni-channel engine and a response builder.
The NLP engine is configured to receive the conversation associated with the first chat session in order to interpret context of the conversation.
In an embodiment, the NLP engine comprises a context identifier, an intent identifier, an entity identifier and a sentiment analyser. The context identifier is configured to interpret the context of the conversation. The intent identifier is configured to interpret intent of the conversation. The entity identifier is configured to interpret identity of the conversation. The sentiment analyser is configured to analyse sentiments of the conversation.
The data logger is configured to cooperate with the NLP engine to store a log of the conversation associated with the first chat session in a database.
In an embodiment, the database is configured to store a look up table having a list of IDs associated with a plurality of the users, a session ID generated for each chat session of each of the users, a channel ID associated with the channel used by each of the users corresponding to each of the session IDs, and the conversation corresponding to each of the channel ID.
The omni-channel engine is configured to cooperate with the NLP engine and the data logger to retain and display the context and the conversation of the first channel when the user switches from the first channel to the second channel.
In an embodiment, the omni-channel engine includes a notification unit and a retaining module. The notification unit is configured to cooperate with the NLP engine to generate and transmit at least one notification to the second channel for facilitating the user to affirm whether to retain and display the context and the conversation of the first channel or to start a new conversation. The retaining module is configured to cooperate with the notification unit and the data logger to display the context and the conversation of the first channel, when the user decides to retain the context and the conversation.
The response builder is configured to cooperate with the NLP engine to build responses to complete the retained conversation on the second channel and transmit the built responses to the second chat session, thereby facilitating seamless communication between the user and the bot.
In an embodiment, the response builder includes a memory, a response preparing module, a switch unit and an archive module.
The memory is configured to store a pre-determined set of response templates.
The response preparing module is configured to cooperate with the omni-channel engine and the memory to:
• receive the identified intent, context, entity and sentiment of the conversation; and
• build the response using at least one of the templates based on the identified intent, context, and entity of the conversation, when the analysed sentiment is positive.
The switch unit is configured to cooperate with the response preparing module to generate and transmit a switch alert, when the analysed sentiment is negative, to an agent pool, wherein the agent pool is configured to receive the switch alert and select the live agent from a list of available live agents.
The archive module is configured to cooperate with the switch unit and the database to provide the stored log of conversation along with the context, intent, identity and sentiment analysed input to the live agent to continue further chat with the user.
The the NLP engine, the omni-channel engine and the response builder are implemented using one or more processor(s).
The present disclosure envisages a method for facilitating an omni-channel chat platform. The method includes the following steps:
• receiving, by a Natural Language Processing (NLP) engine, conversation associated with a first chat session in order to interpret context of the conversation;
• storing, by a data logger, a log of the conversation associated with the first chat session in a database;
• retaining and displaying, by an omni-channel engine, the context and the conversation of the first channel when the user switches from the first channel to the second channel; and
• building, by a response builder, responses to complete the retained conversation on the second channel and transmit the response to the second chat session, thereby facilitating seamless communication between the user and the bot.

The step of receiving, by a Natural Language Processing (NLP) engine, conversation associated with a first chat session in order to interpret a context of the conversation includes the following sub-steps:
• interpreting, by a context identifier, the context of the conversation;
• interpreting, by an intent identifier, intent of the conversation;
• interpreting, by an entity identifier, identity of the conversation; and
• analysing, by a sentiment analyser, sentiments of the conversation.

The step of retaining and displaying, by an omni-channel engine, the context and the conversation of the first channel when the user switches from the first channel to the second channel includes the following sub-steps:
• generating and transmitting, by a notification unit, at least one notification to the second channel for facilitating the user to affirm whether to retain and display the context and the conversation of the first channel or to start a new conversation; and
• displaying, by a retaining module, the context and the conversation of the first channel and second channels, when the user decides to retain.
BRIEF DESCRIPTION OF ACCOMPANYING DRAWING
An omni-channel chat platform, of the present disclosure will now be described with the help of the accompanying drawing, in which:
Figure 1 illustrates a block diagram of the omni-channel chat platform; and
Figure 2 illustrates a flow chart of a method of executing the omni-channel chat platform.
LIST OF REFERENCE NUMERALS USED IN DETAILED DESCRIPTION AND DRAWING
100 System
102 NLP engine
104 data logger
106 database
108 omni-channel engine
110 response builder
112 context identifier
114 intent identifier
116 entity identifier
118 sentiment analyser
120 notification unit
122 retaining module
124 memory
126 response preparing module
128 switch unit
130 agent pool
132 archive module

DETAILED DESCRIPTION
Embodiments, of the present disclosure, will now be described with reference to the accompanying drawing.
Embodiments are provided so as to thoroughly and fully convey the scope of the present disclosure to the person skilled in the art. Numerous details, are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well-known processes, well-known apparatus structures, and well-known techniques are not described in detail.
The terminology used, in the present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a,” "an," and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms "comprises," "comprising," “including,” and “having,” are open ended transitional phrases and therefore specify the presence of stated features, integers, steps, operations, elements, modules, units and/or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The particular order of steps disclosed in the method and process of the present disclosure is not to be construed as necessarily requiring their performance as described or illustrated. It is also to be understood that additional or alternative steps is be employed.
An omni-channel chat platform (hereinafter referred as “platform”) (100) of the present disclosure is now being described with reference to Figure 1 through Figure 2.
The platform (100) facilitates seamless conversation between a user and a bot when the user switches from a first chat session on a first channel to a second chat session on a second channel during the conversation. The user is associated with a user device to converse with the bot. The user device is selected from the group consisting of a smart phone, an iPad, a laptop, a computer, a palmtop, and a tablet.
Referring to Figure 1, the platform (100) comprises a Natural Language Processing (NLP) engine (102), a data logger (104), an omni-channel engine (108) and a response builder (110).
In an embodiment, the channels are selected from the group consisting of social media platforms, a web application, a mobile application, and a messenger.
The NLP engine (102) is configured to receive the conversation associated with the first chat session in order to interpret context of the conversation.
In an embodiment, the NLP engine (102) is configured to generate a session alert, once the user logs in the channel. The server (not shown in the figure) is configured to receive the session alert and is configured to initiate a session. A unique session ID is assigned by the server for the currently accessed channel. The NLP engine (102) is configured to receive a flag signal generated by the server when a session is initiated.
The NLP engine (102) comprises a context identifier (112), an intent identifier (114), an entity identifier (116) and a sentiment analyser (118).
The context identifier (112) is configured to interpret the context of the conversation. For example, interpreting the context of the conversation may involve determining what is the product.
The intent identifier (114) is configured to interpret intent of the conversation. For example, interpreting intent of the conversation may involve determining whether the user wants to buy or sell the product.
The entity identifier (116) is configured to interpret identity of the conversation. For example, interpreting identity of the conversation may involve determining what is the color, style, size or type of the product.
The sentiment analyser (118) is configured to analyse sentiments of the conversation. For example: if the user is using negative symbols, emojis, words and expressions, the sentiment is analysed as negative. On the contrary, if the user is using positive symbols, emojis, words and expressions, the sentiment is analysed as positive.
In an operative embodiment, the user and the bot have a seamless conversation. The NLP engine (102) identified the product which the user wants to sell, buy or return. Moreover, the NLP engine (102) determines what the type of the product is and whether the user’s emotions and sentiments are negative or positive.
The data logger (104) is configured to cooperate with the NLP engine (102) to store a log of the conversation associated with the first chat session in a database (106).
In an embodiment, the database (106) is configured to store a look up table having a list of IDs associated with a plurality of the users, a session ID generated for each chat session of each of the users, a channel ID associated with the channel used by each of the users corresponding to the session IDs, and the conversation corresponding to each of the channel ID.
The omni-channel engine (108) is configured to cooperate with the NLP engine (102) and the data logger (104) to retain and display the context and the conversation of the first channel when the user switches from the first channel to the second channel.
In an embodiment, the omni-channel engine (108) includes a notification unit (120) and a retaining module (122). The notification unit (120) is configured to cooperate with the (NLP) engine (102) to generate and transmit at least one notification to the second channel for facilitating the user to affirm whether to retain and display the context and the conversation of the first channel or to start a new conversation. The retaining module (122) is configured to cooperate with the notification unit (120) and the data logger (104) to display the context and the conversation of the first channel, when the user decides to retain the context and the conversation.
The response builder (110) is configured to cooperate with the NLP engine (102) to build responses to complete the retained conversation on the second channel and transmit the built responses to the second chat session, thereby facilitating seamless communication between the user and the bot.
The response builder (110) includes a memory (124), a response preparing module (126), a switch unit (128) and an archive module (132).
The memory (124) is configured to store a pre-determined set of response templates.
The response preparing module (126) is configured to cooperate with the omni-channel engine (108) and the memory (124) to:
• receive the identified intent, context, entity and sentiment of the conversation; and
• build the response using at least one of the templates based on the identified intent, context, and entity of the conversation, when the analysed sentiment is positive.
The switch unit (128) is configured to cooperate with the response preparing module (126) to generate and transmit a switch alert, when the analysed sentiment is negative, to an agent pool (130), wherein the agent pool (130) is configured to receive the switch alert and select the live agent from a list of available live agents.
The archive module (132) is configured to cooperate with the switch unit (128) and the database (106) to provide the stored log of conversation along with the context, intent, identity and sentiment analysed input to the live agent to continue further chat with the user.
The the NLP engine (102), the omni-channel engine (108) and the response builder (110) are implemented using one or more processor(s).
The processor may be a general-purpose processor, a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), and/or the like. The processor may be configured to retrieve data from and/or write data to the memory. The memory can be for example, a random access memory (RAM), a memory buffer, a hard drive, a database, an erasable programmable read only memory (EPROM), an electrically erasable programmable read only memory (EEPROM), a read only memory (ROM), a flash memory, a hard disk, a floppy disk, cloud storage, and/or so forth.
Figure 2 illustrates a flow diagram of a method for facilitating an omni-channel chat platform. The method comprises the following steps:
• Step 202: receiving, by a Natural Language Processing (NLP) engine (102), conversation associated with a first chat session in order to interpret context of the conversation;
• Step 204: storing, by a data logger (104), a log of the conversation associated with the first chat session in a database (106);
• Step 206: retaining and displaying, by an omni-channel engine (108), the context and the conversation of the first channel when the user switches from the first channel to the second channel; and
• Step 208: building, by a response builder (110), responses to complete the retained conversation on the second channel and transmit the response to the second chat session, thereby facilitating seamless communication between the user and the bot.

The step of receiving (202), by a Natural Language Processing (NLP) engine (102), conversation associated with a first chat session in order to interpret a context of the conversation includes the following sub-steps:
• interpreting, by a context identifier (112), the context of the conversation;
• interpreting, by an intent identifier (114), intent of the conversation;
• interpreting, by an entity identifier (116), identity of the conversation; and
• analysing, by a sentiment analyser (118), sentiments of the conversation.

The step of retaining and displaying (206), by an omni-channel engine (108), the context and the conversation of the first channel when the user switches from the first channel to the second channel includes the following sub-steps:
• generating and transmitting, by a notification unit (120), at least one notification to the second channel for facilitating the user to affirm whether to retain and display the context and the conversation of the first channel or to start a new conversation; and
• displaying, by a retaining module (122), the context and the conversation of the first channel and second channels, when the user decides to retain.
The foregoing description of the embodiments has been provided for purposes of illustration and not intended to limit the scope of the present disclosure. Individual components of a particular embodiment are generally not limited to that particular embodiment, but, are interchangeable. Such variations are not to be regarded as a departure from the present disclosure, and all such modifications are considered to be within the scope of the present disclosure.
TECHNICAL ADVANCES AND ECONOMICAL SIGNIFICANCE
The present disclosure described herein above has several technical advantages including, but not limited to, the realization of an omni-channel chat platform that:
• enables transition of conversation when customer switches from one channel to other;
• enables retention of customer conversation when customer switches between channels;
• keeps track of a customer’s conversation, and refers to live agents to optimize performance; and
• eliminates the need of initiating the chat from beginning.
The foregoing description of the specific embodiments so fully reveals the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
Throughout this specification the word “comprise”, or variations such as “comprises” or “comprising”, will be understood to imply the inclusion of a stated element, integer or step, or group of elements, integers or steps, but not the exclusion of any other element, integer or step, or group of elements, integers or steps.
Any discussion of documents, acts, materials, devices, articles or the like that has been included in this specification is solely for the purpose of providing a context for the disclosure. It is not to be taken as an admission that any or all of these matters form a part of the prior art base or were common general knowledge in the field relevant to the disclosure as it existed anywhere before the priority date of this application.
While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment as well as other embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.
,CLAIMS:WE CLAIM:
1. An omni-channel chat platform (100) for facilitating seamless conversation between a user and a bot when the user switches from a first chat session on a first channel to a second chat session on a second channel during said conversation, said omni-channel chat platform (100) comprising:
• a Natural Language Processing (NLP) engine (102) configured to receive said conversation associated with said first chat session in order to interpret context of said conversation;
• a data logger (104) configured to cooperate with said NLP engine (102) to store a log of said conversation associated with said first chat session in a database (106);
• an omni-channel engine (108) configured to cooperate with said NLP engine (102) and said data logger (104) to retain and display said context and said conversation of said first channel when said user switches from said first channel to said second channel; and
• a response builder (110) configured to cooperate with said NLP engine (102) to build responses to complete said retained conversation on said second channel and transmit said build responses to said second chat session, thereby facilitating seamless communication between said user and said bot,
wherein said NLP engine (102), said omni-channel engine (108) and said response builder (110) are implemented using one or more processor(s).
2. The platform (100) as claimed in claim 1, wherein said Natural Language Processing (NLP) engine (102) includes:
• a context identifier (112) configured to interpret said context of said conversation;
• an intent identifier (114) configured to interpret intent of said conversation;
• an entity identifier (116) configured to interpret identity of said conversation; and
• a sentiment analyser (118) configured to analyse sentiments of said conversation.
3. The platform (100) as claimed in claim 1, wherein said database (106) configured to store a look up table having a list of IDs associated with a plurality of said users, a session ID generated for each chat session of each of said users, a channel ID associated with the channel used by each of the users corresponding to each of said session IDs, and said conversation corresponding to each of said channel IDs.
4. The platform (100) as claimed in claim 1, wherein said omni-channel engine (108) includes:
• a notification unit (120) configured to cooperate with said (NLP) engine (102) to generate and transmit at least one notification to said second channel for facilitating said user to affirm whether to retain and display said context and said conversation of said first channel or to start a new conversation; and
• a retaining module (122) configured to cooperate with said notification unit (120) and said data logger (104) to display said context and said conversation of said first channel, when said user decides to retain said context and said conversation.
5. The platform (100) as claimed in claim 2, wherein said response builder (110) includes:
• a memory (124) configured to store a pre-determined set of response templates;
• a response preparing module (126) configured to cooperate with said omni-channel engine (108) and said memory (124) to:
o receive said identified intent, context, entity and sentiment of said conversation; and
o build said response using at least one of said templates based on said identified intent, context, and entity of said conversation, when said analysed sentiment is positive,
• a switch unit (128) configured to cooperate with said response preparing module (126) to generate and transmit a switch alert, when said analysed sentiment is negative, to an agent pool (130), wherein said agent pool (130) is configured to receive said switch alert and select said live agent from a list of available live agents; and
• an archive module (132) configured to cooperate with said switch unit (128) and said database (106) to provide said stored log of conversation along with said context, intent, identity and sentiment analysed input to said live agent to continue further chat with said user.

6. A method for facilitating an omni-channel chat platform, said method comprises the following steps:
• receiving (202), by a Natural Language Processing (NLP) engine (102), conversation associated with a first chat session in order to interpret context of said conversation;
• storing (204), by a data logger (104), a log of said conversation associated with said first chat session in a database (106);
• retaining and displaying (206), by an omni-channel engine (108), said context and said conversation of said first channel when said user switches from said first channel to said second channel; and
• building (208), by a response builder (110), responses to complete said retained conversation on said second channel and transmit said response to said second chat session, thereby facilitating seamless communication between said user and said bot.

7. The method as claimed in claim 6, wherein said step of receiving (202), by a Natural Language Processing (NLP) engine (102), conversation associated with a first chat session in order to interpret a context of said conversation includes the following sub-steps:
• interpreting, by a context identifier (112), said context of said conversation;
• interpreting, by an intent identifier (114), intent of said conversation;
• interpreting, by an entity identifier (116), identity of said conversation; and
• analysing, by a sentiment analyser (118), sentiments of said conversation.
8. The method as claimed in claim 6, wherein said step of retaining and displaying (206), by an omni-channel engine (108), said context and said conversation of said first channel when said user switches from said first channel to said second channel includes the following sub-steps:
• generating and transmitting, by a notification unit (120), at least one notification to said second channel for facilitating said user to affirm whether to retain and display said context and said conversation of said first channel or to start a new conversation; and
• displaying, by a retaining module (122), said context and said

•
• conversation of said first channel and second channels, when said user decides to retain.