Abstract: The present disclosure provides methods, devices and systems for route deviation quantification and vehicular route learning based thereon. In some examples, there is provided a method for route deviation quantification of a suggested route. The method comprises: obtaining a ground truth route based on a filtered trajectory, the filtered trajectory including an inferred location of origin and an inferred location of destination; obtaining a suggested route generated based on the inferred location of origin and the inferred location of destination; quantifying a deviation of the suggested route from the ground truth route by calculating an off course ratio based on a combined length of road segments in the suggested route that are matched to corresponding road segments in the ground truth route and a combined length of road segments in the ground truth route.

Abstract: Provided is a system for generation of a customized digital map. The system includes an application server that collects one or more reference transportation routes and regulations associated with a geographical area and one or more current transportation routes and activities being implemented in the geographical area. The application server detects one or more conflicts among a digital map of the geographical area, the one or more reference transportation routes and regulations, and the one or more current transportation routes and activities and executes a conflict resolution routine that resolves the one or more conflicts. The application server further generates conflict resolved data based on an output of the conflict resolution routine and updates the digital map of the geographical area to reflect the conflict resolved data based on presence of at least one difference between the digital map and the conflict resolved data.

Abstract: The present disclosure provides methods, devices and systems for route deviation quantification and vehicular route learning based thereon. In some examples, there is provided a method for route deviation quantification of a suggested route. The method comprises: obtaining a ground truth route based on a filtered trajectory, the filtered trajectory including an inferred location of origin and an inferred location of destination; obtaining a suggested route generated based on the inferred location of origin and the inferred location of destination; quantifying a deviation of the suggested route from the ground truth route by calculating an off course ratio based on a combined length of road segments in the suggested route that are matched to corresponding road segments in the ground truth route and a combined length of road segments in the ground truth route.

Abstract: Techniques involving accessing a resume of a person; automatically parsing the resume at least in part by: identifying, based at least in part on formatting of the resume, a plurality of sections in the resume including a first section; identifying, based at least in part on content in the first section and formatting of the content, a plurality of subsections of the first section; and processing text in the plurality of subsections to identify a plurality of credentials and associated attributes; and updating a profile for the person to reflect the plurality of credentials and the associated attributes.

Abstract: Techniques comprising using at least one computer hardware processor to perform: obtaining first credential information for at least one individual; generating at least one representation of job requirements for a job based, at least in part, on the first credential information; obtaining second credential information for a candidate different from the at least one individual; and calculating a talent score for the candidate at least in part by using the at least one representation of job requirements and the second credential information.

Abstract: Techniques comprising: obtaining natural language input comprising a job description for a job; generating at least one representation of job requirements for the job at least in part by automatically processing the natural language input using at least one natural language processing technique; obtaining credential information for a candidate; and calculating a talent score for the candidate based, at least in part, on the at least one representation of job requirements and the credential information.

Abstract: Techniques comprising: obtaining information about a first job associated with a first recruiter; identifying a second job associated with a second recruiter, the identifying comprising calculating a measure of similarity between the information about the first job and information about the second job; identifying at least one candidate for the first job from among a plurality of users of an online service associated with users, each of the plurality of users being associated with the second employer via the online network; and calculating a talent score for the identified at least one candidate based, at least in part, on the information about the first job and credentials of the identified candidate, the talent score indicating suitability of the identified at least one candidate for the first job.

Abstract: Techniques involving accessing a resume of a person; automatically parsing the resume at least in part by: identifying, based at least in part on formatting of the resume, a plurality of sections in the resume including a first section; identifying, based at least in part on content in the first section and formatting of the content, a plurality of subsections of the first section; and processing text in the plurality of subsections to identify a plurality of credentials and associated attributes; and updating a profile for the person to reflect the plurality of credentials and the associated attributes.

Abstract: Techniques comprising: obtaining information associated with a job; obtaining semi-structured natural language input comprising credentials of a candidate for the job; identifying the candidate's credentials at least in part by automatically processing the semi-structured natural language input; and calculating a talent score for the candidate based, at least in part, on the identified the candidate's credentials and the information associated with the job.

Abstract: Techniques comprising using at least one computer hardware processor to perform: generating a representation of job requirements for a job based, at least in part, on obtained information about the job; generating a search query comprising at least a first keyword in the representation of job requirements and at least a second keyword related to the first keyword, wherein the second keyword is not in the job representation; identifying, using the search query, at least one candidate for the job from among users of an online service associated with a plurality of users; and calculating a talent score for each identified candidate for the job based on the at least one representation of job requirements.

Abstract: Techniques for calculating a talent score for a candidate for a job, the talent score being indicative of the candidate's suitability for the job. The techniques include calculating a first value for a first credential of a candidate for a job and a measure of uncertainty for the first value, the first credential indicative of the candidate's knowledge and/or skill in a first area, the first value indicative of an amount of knowledge and/or skill the candidate has in the first area; obtaining an employer's credential value preferences for the job; and calculating a talent score for the candidate and a corresponding measure of uncertainty based, at least in part, on the first value, the credential value preferences, and the measure of uncertainty for the first value.