Abstract: A system is provided for object localization in image data. The system includes an object localization framework comprising a plurality of object localization processes. The system is configured to receive an image comprising unannotated image data having at least one object in the image, access a first object localization process of the plurality of object localization processes, determine first bounding box information for the image using the first object localization process, wherein the first bounding box information comprises at least one first bounding box annotating at least a first portion of the at least one object in the image, and receive first feedback regarding the first bounding box information determined by the first object localization process. The system is further configured to persist the image with the first bounding box information or access a second object localization process based on the first feedback.

Abstract: Embodiments described herein transforms a complex and usually unstructured table to a relational table based on the header pattern. Specifically, the original complex table is expanded into a single dimensional relational database format, in which each cell corresponds to one or more corresponding categories or subcategories from the original header. The transformed one-dimensional relational table is then populated with the corresponding cell values from the original table. In this way, data from the original complex and unstructured data table can be stored at a relational database.

Abstract: Machine learning based models recognize objects in images. Specific features of the object are extracted from the image using machine learning based models. The specific features extracted from the image assist deep learning based models in identifying subtypes of a type of object. The system recognizes the objects and collections of objects and determines whether the arrangement of objects violates any predetermined policies. For example, a policy may specify relative positions of different types of objects, height above ground at which certain types of objects are placed, or an expected number of certain types of objects in a collection.

Abstract: Embodiments of present disclosure relates to method training data generation system for generating training data for classifying intent in conversational system. The training data generation system receives database schema and creates SQL/NoSQL queries. The training data generation system generates natural language queries for the SQL/NoSQL queries. Further, the training data generation system generates training data for intents associated with the natural language queries and provides to classification models associated with conversational system for classification of intents. Embodiments of present disclosure relates to method and conversational system for providing natural language response for query. The conversational system receives query from user and classifies intent of the query and provides relevant response by mapping the query with the SQL/NoSQL queries generated by the training data generation system.

Abstract: A system is provided for referral object processing for textual annotations. The system comprises a memory storing machine executable code and one or more processors coupled to the memory and configurable to execute the machine executable code to cause the one or more processors to parse a document to identify a reference identifier to an external object, the external object associated with information not contained in the document, retrieve the external object using the reference identifier, extract the information associated with the external object based on at least one data pattern detected in the external object, convert the extracted information into textual annotations associated with the reference identifier in the document, and enter the textual annotations to a corpus of content for the document so that the extracted information is associated with the reference in the document for the system.

Abstract: A system (100) for sales forecasting and optimal path to opportunity closure. The system (100) including an enterprise internal database (110), external database (108), a server computer (104), and a sales-representative device (112). The enterprise internal database (110) further includes a customer relationship management database (102). The external database (108) stores all data related to buyers social profile and buyer professional profile. The server computer (104) includes a system processor (106), and a system server memory (120). The system processor (106) extracts data from the customer relationship management database (102), the external database (108), the enterprise internal database (110), to automatically calculate engagement score, buyer segmentation, and further the system processor (106) uses engagement score, buyer segmentation to recommends the best buyer to contact.

Abstract: A system and method for automated recommendations of competitors for sales opportunities. The system includes a customer relationship management database, a calls log and email database, an enterprise resource planning database, an external public server, a system server, and a sales representative device. The system server includes server processing unit, and a server memory. The server processing unit executes computer-readable instructions to receive direct signal and indirect signal of competitors related to particular sales opportunities from customer relationship management database and the enterprise resource planning database. Further the server processing unit uses the trained machine learning model to receive indirect signals of competitors related to particular deals from the calls log and email database. The server processing unit uses the trained machine learning model to extract data of competitors related to particular deals from the external public server.

Abstract: A system (100) and method for automated discount recommendations. The system (100) includes a customer relationship management database (102), a server computer (104), and a user device (112). A system processing unit (106) extracts data from the customer relationship management database (102), and further uses the trained artificial intelligence based classification model to identify the open deals that are on risk. Then the system processing unit (106) uses the trained machine learning scoring model, to recommends best optimize sales quote to sales representative for winning the deal. A system server memory (120) stores computer-readable instructions, the trained artificial intelligence based. classification model and the trained machine learning scoring model. The user device (112) is connected to the server computer (104). A sales representative receives optimize sales quote, on a user device (116), for winning the deal.

Abstract: A system (100) and method for automated generation of optimum thresholds for post processing of machine learning models in case of imbalanced classification. The system (100) includes a server computer (104) and an user device (112). The server computer (104) includes a system processing unit (106), and an system server memory (120). The system processing unit (106) executes computer-readable instructions to automatically calculate the optimum thresholds for post processing of machine learning models. The machine learning model predicts a probability of class, and that probability is used to decide a crisp class label and for deciding a crisp class label a threshold is set, thus based on amount of variation of probability from threshold the crisp class label is decided. Thus optimum threshold needs to be generated to accurately decide a crisp class label in case of imbalance classification.

Abstract: Embodiments described herein automatically classifies numerical expressions from a textual document and designates a context to understand each numerical expression. Specifically, numerical expressions from a textual context are classified as nominal or cardinal. For cardinal numerical expressions that carry a quantitative meaning, inference terms are determined from the textual context to associate with the cardinal numerical expressions. The numerical expressions are then translated to a format of a numerical value and stored with metadata indicating the unit scale or the meaning of the numerical value.

Abstract: The present invention is related to a system and method for automatic updates of customer relationship management and enterprise resource planning fields with the next best actions using machine learning. A system processing unit (106) of a server computer (104), executes computer-readable instructions to retrieve data from a customer relationship management database (102), a calls log and email database (108), an enterprise resource planning database (110), and data from external sources. The system processing unit (106) executes computer-readable instruction to integrate all data into the datasets and feed the datasets into a machine learning analytical module to train the machine learning analytical module. The trained machine learning analytical module analyses various information that suggests the next best actions to be taken.

Abstract: A conversational system and a method for personalized query and interaction set generation. The conversational system includes a system server, a business database server, a user device. The system server further includes a system processing unit. The data points are extracted by a system processing unit from a business database server. The system processing unit creates improved multiple datasets that include the grammatically correct query, corresponding responses of the grammatically correct query, and corresponding data points related to the grammatically correct query. The multiple datasets are being fed into the conversational module to train the conversational module. The user sends queries to the system server through the user device. The system processing unit sends a query to the conversational module. The conversation module sends the query to a search engine that searches data and sends data to an answer generating module to send the answer to the user.

Abstract: Machine learning based models recognize objects in images. Specific features of the object are extracted from the image using machine learning based models. The specific features extracted from the image assist deep learning based models in identifying subtypes of a type of object. The system recognizes the objects and collections of objects and determines whether the arrangement of objects violates any predetermined policies. For example, a policy may specify relative positions of different types of objects, height above ground at which certain types of objects are placed, or an expected number of certain types of objects in a collection.

Abstract: The present invention relates to a method and system for automated sales forecast on a deal level during the black swan scenario. A list of features is being generated that influence the sales forecast on the deal level. The data related to a list of features are processed and transformed into an appropriate form through feature engineering. The artificial intelligence-based model is being selected and trained by the feeding data. The artificial intelligence-based model is optimized with the help of hyper parameter values. The artificial intelligence-based model uses previous data and generates probability scores, forecast close date postponement, and forecast amount on which sale deal would close. Thus, based on the above forecast, overall sales on the deal level are being forecasted. The artificial intelligence-based model is trained and deployed for the sales forecast on the deal level with the help of a computational unit.

Abstract: The present invention relates to a system (100) and method for automated sales forecast on an aggregate level during the black swan scenario. The present invention includes a computational unit (102), and a display unit (108). In an embodiment, the computational unit (102) including, but limited to, a desktop computer, a laptop, a tablet, a smartphone, a mobile phone. The computational unit (102) includes a database unit (104) and a system processing unit (106). The system processing unit (106) executes computer-readable instructions to collect the company data through the company servers and the system processing unit (106) further executes computer-readable instruction to forecast sales of the company on an aggregate level during the black swan scenario. The system processing unit (106) executes computer-readable instructions to provide a comprehensive analysis of forecasts from the top-down level that serves the basis for the Finance Team/CSO/CFO to set modified targets.

Abstract: Embodiments described herein provide a mechanism that translates a natural language question to a database query format that may be applied to a data table to generate an answer to the natural language question. The system may identify key terms from a natural language question and classify the key terms as variable names or operation names. The natural language question is than translated into a format of question template containing variable names and operation names. In this way, the system may map the template question to a database query which can be applied to operate on a relational database to identify a cell value that represents an answer to the natural language question.

Abstract: Machine learning based models recognize objects in images. Specific features of the object are extracted from the image using machine learning based models. The specific features extracted from the image assist deep learning based models in identifying subtypes of a type of object. The system recognizes the objects and collections of objects and determines whether the arrangement of objects violates any predetermined policies. For example, a policy may specify relative positions of different types of objects, height above ground at which certain types of objects are placed, or an expected number of certain types of objects in a collection.

Abstract: Embodiments described herein transforms a complex and usually unstructured table to a relational table based on the header pattern. Specifically, the original complex table is expanded into a single dimensional relational database format, in which each cell corresponds to one or more corresponding categories or subcategories from the original header. The transformed one-dimensional relational table is then populated with the corresponding cell values from the original table. In this way, data from the original complex and unstructured data table can be stored at a relational database.

Abstract: A system is provided for object localization in image data. The system includes an object localization framework comprising a plurality of object localization processes. The system is configured to receive an image comprising unannotated image data having at least one object in the image, access a first object localization process of the plurality of object localization processes, determine first bounding box information for the image using the first object localization process, wherein the first bounding box information comprises at least one first bounding box annotating at least a first portion of the at least one object in the image, and receive first feedback regarding the first bounding box information determined by the first object localization process. The system is further configured to persist the image with the first bounding box information or access a second object localization process based on the first feedback.

Abstract: Embodiments described herein transforms a complex and usually unstructured table to a relational table based on the header pattern. Specifically, the original complex table is expanded into a single dimensional relational database format, in which each cell corresponds to one or more corresponding categories or subcategories from the original header. The transformed one-dimensional relational table is then populated with the corresponding cell values from the original table. In this way, data from the original complex and unstructured data table can be stored at a relational database.