Abstract: There is disclosed a method and system for processing a user spoken utterance, the method comprising: receiving, from a user, an indication of the user spoken utterance; generating, a text representation hypothesis based on the user spoken utterance; processing, using a first trained scenario model and a second trained scenario model, the text representation hypothesis to generate a first scenario hypothesis and a second scenario hypothesis, respectively; the first trained scenario model and the second trained scenario model having been trained using at least partially different corpus of texts; analyzing, using a Machine Learning Algorithm (MLA), the first scenario hypothesis and the second scenario hypothesis to determine a winning scenario having a higher confidence score; based on the winning scenario, determining by an associated one of the first trained scenario model and the second trained scenario model, an action to be executed by the electronic device; executing the action.

Abstract: Methods and systems for generating a training set for training a MLA is disclosed. The method comprises: retrieving a plurality of SERPs, generating a graph mapping the plurality of documents and the plurality of queries, such that: a given node of the graph includes a given search query of the plurality of search queries; the given node is connected to a first subset of nodes, each one of the first subset of nodes having a document of the plurality of documents; a specific node of the first subset of nodes being connected to a second subset of nodes; receiving an indication of a search query to generate a negative training example for; identifying a node in the graph associated with the search query; generating the training set including the search query paired with a given document located in another node located by a pre-determined number of nodes away.

Abstract: There is provided a method and a server for retraining a machine learning algorithm (MLA), the MLA having been trained to classify documents based on features thereof. A resource having a plurality of content items submitted by users is accessed. At least one content item associated with a document having been presented as a search result by a search engine server in response to a search query is identified. The at least one content item is analyzed based on a set of features to determine if the document has been misclassified by the MLA in response to the search query. In response to determining that the document has been misclassified, a training object is generated based on the misclassified document. Other misclassified documents are identified in a similar manner to obtain a set of training objects. The MLA is then retrained based on the set of training objects.

Abstract: A method of and server for ranking documents in response to a query are provided. The method includes determining a target resource hosting a document, and generating a first and a second randomly-selected value for the document. During a first time interval, the method includes acquiring a query and generating a first ranked list of documents to the query based on the first randomly-selected value. The first ranked list includes the document at a promoted-rank position. During the second time interval, the method includes acquiring a query and generating a second ranked list of documents to the query based on the second randomly-selected value. The second ranked list includes the document at a demoted-rank position. The promoted-rank position in the first ranked list is above the demoted-rank position in the second ranked list for increasing a gap in user traffic to the document between the first and second time intervals.

Abstract: A method and system for determining a result for a task executed in a crowd-sourced environment is disclosed. The method comprises receiving, a plurality of results of the task having been submitted by a plurality of human assessors; receiving a quality score for each human assessor of the plurality of human assessors; generating a plurality of vector representations comprising a vector representation for each of the results; mapping, the plurality of vector representations into a vector space; clustering the plurality of vector representations into at least a first cluster and a second cluster; executing a machine learning algorithm configured to generate a first confidence parameter and a second confidence parameter; in response to a given one of the first confidence parameter and the second confidence parameter meeting a predetermined condition, generating, an aggregated vector representation; and selecting the aggregated vector representation as the result of the task.

Abstract: There is disclosed a method and system for receiving a label for a digital task executed within a computer-implemented crowd-sourced environment, the method comprising: receiving, an indication of the digital task to be processed in the computer-implemented crowd-sourced environment; generating, a subset of examples, the subset of examples based on past digital tasks executed in the computer-implemented crowd-sourced environment, each of the subset of examples being similar to the digital task within a pre-determined similarity threshold; the subset of examples having a number of examples selected such that to provide maximum benchmark coverage with a minimum number of samples in the subset of examples; associating, the subset of examples to the digital task to be presented; causing the digital task to be presented on a computing device of at least one crowd-sourced worker in the computer-implemented crowd-sourced environment to solicit the label for the digital task.

Abstract: There is disclosed a method and system for ranking a web resource. The method comprises: receiving a set of features associated with the web resource; generating a raw quality score based on the set of features, comparing the raw quality score to a reference score, the reference score being associated with a similar level of user traffic as the web resource; applying an offset adjustment formula to the raw quality score in response to an offset between the raw quality score and the reference score to obtain an adjusted quality score; in response to receiving a query, generating a search engine result page (SERP) including an indication of the web resource at a ranked position based on the adjusted quality score, the adjusted quality score causing a future raw quality score to be closer to a future reference score associated with a future level of user traffic.

Abstract: A computer-implemented method for identifying, among user electronic devices, customer electronic devices associated with genuine customers of organizations, the method being executed by a server, the method comprising: receiving, from a first user electronic device by the server, a first uniform resource locator (URL) of a first user browsing history; generating a first embedding corresponding to the first URL; comparing the first embedding with a template embedding of a plurality of template embeddings, the plurality of template embeddings having been retrieved from a genuity database; and in response to a difference between the first embedding and the template embedding being lower than an embedding difference threshold, adding the first embedding to the genuity database.

Abstract: A speaker device for reproducing sound within a predetermined audio spectrum is provided. The speaker device comprises: a housing including a top, a bottom, and a side surface; at least one speaker disposed within the housing, the at least one speaker including a speaker flange facing towards the bottom; a waveguide including at least a first surface defining at least one sound channel for conducting a given sound produced by the at least one speaker, and the at least one channel includes a first zone, a second zone, and a third zone sequentially defined along a length thereof to provide for sound reproduction from 100 Hz to 20000 Hz.

Abstract: A method and a system for ranking search results using a machine learning algorithm (MLA), the MLA having been trained to determine query similarity based on textual content thereof, comprising: receiving a new query, retrieving a plurality of search queries, computing a respective similarity parameter between the new query and each query of the plurality of search queries, selecting a given past query associated with a highest respective similarity parameter, retrieving a set of search results associated with the given past query, each of the set of search results being associated with an annotation including respective search queries, and computing for each respective one of the plurality of respective search queries having been used to access the respective search result, a respective second similarity parameter, and using the respective second similarity parameter as a ranking feature for ranking the associated search results as search results for the new query.

Abstract: A method and server for storing documents in a database system is disclosed. The method includes acquiring document data associated with the documents. For each document, a Machine Learning Algorithm is employed to generate respective document vectors based on the respective document data. The method also includes storing the documents as groups of documents in the database system. Each group of documents is associated with a respective group vector. A given group of documents has documents associated with document vectors that are in a spatial proximity to the respective group vector.

Abstract: A method and a system for generating a video of a 3D object are provided. The method comprises: generating a visual reference frame; capturing an image of a surrounding area around the 3D object; in response to detecting within the image at least a portion of the 3D object: generating a bounding box encompassing the at least the portion of the 3D object; determining an overlap parameter between the bounding box and the visual reference frame; comparing the overlap parameter to a plurality of thresholds; in response to the overlap parameter being above a given one of the plurality of thresholds, generating a respective one of a plurality of predetermined indications for adjusting a position of the camera to capture the portion of the 3D object within the visual reference frame, thereby generating an adjusted image thereof used for composing the video of the 3D object.

Abstract: Disclosed are a method and a system for determining a response to a digital task in a computer-implemented crowd-sourced environment. The method comprises determining if a number of the plurality of responses to the digital task received meets a pre-determined minimum answer threshold; in response to the number of the plurality of responses to the digital task meeting the pre-determined minimum answer threshold, executing: for each of the plurality of responses generating, by the server, a confidence parameter representing a probability of an associated one of the plurality of responses being correct; ranking the plurality of responses based on the confidence parameter to determine a top response being associated with a highest confidence parameter; and in response to the highest confidence parameter being above a pre-determined minimum confidence threshold, assigning a value of the top response as a label for the digital task and terminating the digital task execution.

Abstract: There is disclosed a method and system for uploading media objects unto a web platform, the method executable by a server that hosts the web platform, the server being coupled to an electronic device, the method comprising: acquiring a first media object having a first duration time and a second media object having a second duration time for uploading; queuing for upload the first media object; determining a remaining time available for publishing the second media object, the remaining time corresponding to a difference between a predetermined time limit set by the web platform and the first duration time; in response to the remaining time being below the second duration time, shortening the first media object to reduce the first duration time; in response to the second duration time being below the remaining time, publishing the first media object and the second media object as a merged media object.

Abstract: There is disclosed a method and system for translating a source phrase in a first language into a second language. The method being executable by a device configured to access an index comprising a set of source sentences in the first language, and a set of target sentences in the second language, each of the target sentence corresponding to a translation of a given source sentence. The method comprises: acquiring the source phrase; generating by a translation algorithm, one or more target phrases, each of the one or more target phrases having a different semantic meaning within the second language; retrieving, from the index, a respective target sentence for each of the one or more target phrases, the respective target sentence comprising one of the one or more target phrases; and selecting each of the one or more target phrase and the respective target sentences for display.

Abstract: There is disclosed a computer-implemented method and system for generating a set of training objects for training a machine learning algorithm (MLA) to determine query similarity based on textual content thereof, the MLA executable by the system. The method comprises retrieving, from a search log database of the system, a first query and other queries with associated search results. The method then comprises selecting a subset of query pairs such that: a query difference in queries in the pair is minimized and a results difference in respective search results is maximized.

Abstract: A method and server for ranking a plurality of documents are disclosed. The method includes determining, by the server, for each document from the plurality of documents a proximity value between a respective document vector and an other document vector. A given proximity value for a respective document being indicative of a similarity between (i) the respective document and (ii) at least one other one from the plurality of documents. The method also comprises using, by the server, the proximity values of the plurality of documents for ranking the plurality of documents.

Abstract: A computer-implemented method for generating a search query completion suggestion by a search engine by receiving an indication of at least a portion of a search query from an electronic device; generating, based on the indication, a ranked set of search query completion suggestions; analyzing a top one of the ranked set of search query completion suggestions to determine if the top one of the ranked set of search query completion suggestions meets a pre-determined trigger condition; in response to a positive outcome, generating a set of search results that are responsive to an intermediate search query that includes the at least the portion of the search query and the top one of the ranked set of search query completion suggestions; transmitting to the electronic device: the ranked set of search query completion suggestions; and a Search Engine Result Page (SERP) containing the set of search results.

Abstract: A method of determining a conversion rate of a targeted message associated with a point of interest (POI) includes determining a plurality of users using wireless devices that have been exposed to a targeted message associated with the POI within a first pre-determined time period and receiving a plurality of sets of local area communication features of the local area communication modules of the wireless devices. These features are inputted into a Machine Learning Algorithm (MLA) trained using a set of heuristics applied to training sets of local area communication features of training wireless devices. The MLA outputs, based on the set of local area communication features of the local area communication module of the wireless device, a plurality of indications of the conversion rate of the targeted message. A server for executing the method is also provided.