公开(公告)号：MY177900A

公开(公告)日：2020-09-24

申请号：MYPI2015702232

申请日：2015-07-08

Applicant: MIMOS BERHAD

Inventor： BENJAMIN CHU MIN XIAN ,  LIU QIANG ,  KHALIL BOUZEKRI ,  DICKSON LUKOSE

Abstract: The present invention relates to a system (100) and method 5 for validating website usage. The system (100) comprising a content processor (10) to process a plurality of paragraphs of a website by using natural language processing. The system (100) further comprising a knowledge base aggregator (30) to harvest and index a plurality of knowledge bases from a Linked Data repository (50) to produce and maintain a domain mapping table, wherein the domain mapping table includes a plurality of knowledge base entries assigned with a trustworthiness confidence value (TCV), and a website validator (20) to validate intended usage of the website by utilising the domain mapping table. A method for validating website usage is characterised by the steps of processing contents of a website, harvesting a plurality of knowledge bases to produce and maintain a domain mapping table, and validating intended usage of the website by utilising a domain mapping table. Fig. 1

公开(公告)号：MY172808A

公开(公告)日：2019-12-12

申请号：MYPI2012005404

申请日：2012-12-13

Applicant: MIMOS BERHAD

Inventor： TAN SIEOW YEEK ,  BONG CHIN WEI ,  DICKSON LUKOSE

Abstract: The present invention provides a method for identifying multiple entities in a learned image. The present invention utilizes a visual knowledge-base storing multiple pre-defined visual features of various entities. The learned image is sectioned (204) into a plurality of image sub-sections and visual features information from each of the plurality of sub-section images is thereafter extracted (206). The extracted visual features information of the sub-section images is compared (208) with those stored in the knowledge-base. The visual similarity between the extracted visual features information of the sub-section images and the stored visual features is rated (210). Based on the visual similarity rate, entities of the image can thereby be identified (214). A system for identifying multiple entities is also provided.

公开(公告)号：MY168837A

公开(公告)日：2018-12-04

申请号：MYPI20092121

申请日：2009-05-25

Applicant: MIMOS BERHAD

Inventor： KOW WENG ONN ,  MOHAMMAD REZA BEIK ZADEH ,  DICKSON LUKOSE ,  ARUN ANAND SADANANDAN

IPC: G06F40/00

Abstract: A method (100) and a system (200) for an extendable semantic query interpretation, the system (200) comprises an intelligent word sense (202), a semantic query interpreter (206), a query transformer (208), a query enricher (210) and a natural language generator (218). The intelligent word sense (202) comprises means for receiving a structured natural language user query (102). The semantic query interpreter (206) comprises means for interpreting the structured natural language user query (104). The query transformer (208) comprises means for generating from the structured natural language user query, an internal query representation statement (106). The query enricher (210) comprises means for performing query enrichment (108) to generate at least one enriched internal query representation statement, generating from the at least one enriched internal query representation statement, a knowledge base compliant query (110) to provide for searching at least one query result from an ontology knowledge base (220) and generating at least one internal query result representation statement (112). The natural language generator (218) comprises means for converting the at least one internal query result representation statement to a structures natural language result (114). The most illustrative drawing: FIGs. 1 & 2

公开(公告)号：MY190232A

公开(公告)日：2022-04-06

申请号：MYPI2014703769

申请日：2014-12-12

Applicant: MIMOS BERHAD

Inventor： KHALIL BOUZEKRI ,  SHAZZAT HOSSAIN ,  DICKSON LUKOSE

Abstract: The present invention relates to a system (1000) and method for performing a semantic matching process by pruning search space right at the beginning of the semantic matching process. The system (1000) pre-processes binary conceptual structures to identify the most suitable starting point before it expands the starting point to get the best semantic matching between the two binary conceptual structures. The inputs of the system (1000) are two binary conceptual structures (G1, G2) and an ontology (800), while the final output is a percentage of an optimal semantic similarity between the two binary conceptual structures as well as the semantic matching that is used to compute the optimal semantic similarity. The most illustrative drawing: FIG. 1

公开(公告)号：MY186402A

公开(公告)日：2021-07-22

申请号：MYPI2013004282

申请日：2013-11-27

Applicant: MIMOS BERHAD

Inventor： KHALIL BEN MOHAMED ,  BENJAMIN CHU MIN XIAN ,  DICKSON LUKOSE ,  LIU QIANG ,  KLAUS TOCHTERMANN

IPC: G06F17/00

Abstract: [0051] The present invention provides a system (100) for discovering relations between texts in sentence of a machine-readable document. The system comprises a text preprocessor (101) and a relation discovery module (102). The text preprocessor (101) processes the documents to identify and extract entities, noun phrases and verb from therefrom. The relation discovery module (102) discovers the relation through a generic and semantic relation extraction for unstructured and structured texts to resolves intra-sentential and inter-sentential contexts.

公开(公告)号：MY185830A

公开(公告)日：2021-06-11

申请号：MYPI2013701827

申请日：2013-09-27

Applicant: MIMOS BERHAD

Inventor： KOW WENG ONN ,  DICKSON LUKOSE

Abstract: The present invention relates to a method for reasoning knowledge that is distributed across a plurality of linked knowledge bases. It handles queries in two ways. First, it handles a query by determining whether or not a fact is true. Secondly, it handles a query by returning query results that are not directly explicit within the triples of the queries knowledge bases which are the subjects, predicates and objects. The most illustrative drawing: FIG. 1

公开(公告)号：MY181309A

公开(公告)日：2020-12-21

申请号：MYPI2015704499

申请日：2015-12-10

Applicant: MIMOS BERHAD

Inventor： KOW WENG ONN ,  DICKSON LUKOSE ,  DUC NGHIA PHAM

Abstract: A method (100) of generating knowledge cubes from multiple heterogeneous data sources comprises the steps of analyzing all the data sources to identify potential data cubes and parameters (S202), defining (S208) cubes through the use of natural language description (S201) to obtain query results (S503) using the identified data cubes and parameters (S202), aggregating (S510) the query results upon normalization of the query results with parameters, and populating (S508) the data cubes from the heterogeneous data sources by aggregating (S510) and harmonizing the measurements of the data source. The populated cube is stored (S509) in the harmonized results database (608) for sharing and reusability.

公开(公告)号：MY179116A

公开(公告)日：2020-10-28

申请号：MYPI2013701294

申请日：2013-07-24

Applicant: MIMOS BERHAD

Inventor： ARUN ANAND SADANANDAN ,  DICKSON LUKOSE

Abstract: The present invention relates to a system and method for interpreting logical connectives in natural language query. The system (100) and method identify and interpret logical connectives in a natural language query to produce query syntaxes. The system (100) comprises of a morphological analyser (110), a query structure interpreter (120), logical connective interpreter (130), a query enricher (140), a query processor (150) and an answer generator (160).

公开(公告)号：MY176751A

公开(公告)日：2020-08-21

申请号：MYPI2015701631

申请日：2015-05-20

Applicant: MIMOS BERHAD

Inventor： KHALIL BOUZEKRI ,  SHAZZAT HOSSAIN ,  DICKSON LUKOSE

Abstract: The present invention relates to a system and method for diagnosing plant disease from an image. The system (1000) comprises a disease diagnosis component (100) having an image editor (110) to edit an input image. The system (1000) further comprising a disease management component (200) to select images based on priority ranking, extract image features of a plurality of system selected image (SSIMGs), compare user input image (UIIMG) with the SSIMGs, rank the SSIMGs based on priority ranking, notify the user with the SSIMGs and disease management information, and receive a user selected image (USIMG) and priority ranking and a plant data open repository (PDOR) (300) to store collection of knowledge bases of category of context and rearrange the plant disease images based on priority ranking. The disease diagnosis component (100) further includes a domain arbiter (120) to obtain necessary parameters, and contextualize the input to be processed. Figure 1

公开(公告)号：MY170600A

公开(公告)日：2019-08-20

申请号：MYPI2013702274

申请日：2013-11-27

Applicant: MIMOS BERHAD

Inventor： KHALIL BEN MOHAMED ,  BENJAMIN CHU MIN XIAN ,  FAROUQ H HAMED ,  DICKSON LUKOSE

Abstract: The present invention relates to a method for converting a knowledge base (110) to binary form. The method includes converting ontology and conceptual structure of a knowledge base (110) to binary form. An ontology translator (121) converts the ontology of a knowledge base (110) to conceptual binary array (CBA) and descendant?s binary array (DBA), while a conceptual structure translator (122) converts the conceptual structure of a knowledge base (110) to CBA, relations binary array (RBA) and graph binary array (GBA).