Abstract: The present invention discloses an artificial-intelligence (AI)-assisted method for providing an urban design form and layout with an improved wind environment. The method includes data acquisition, construction of a wind field interactive sand table, wind field simulation and evaluation of an urban design plan, AI-assisted adjustment of an urban design form and layout, determination of conformity to urban design standard specifications, wind field simulation and evaluation of an adjusted plan, and holographic display of the plan with an improved wind environment. The present invention can achieve the improvement of the wind environment in the field of urban planning design, and adjust the urban form and layout by performing random dotting on a building based on the random algorithm. Therefore, the wind environment in the urban design is improved more efficiently by means of accurate quantification, and the quality of the urban design plan is more desirable.

Abstract: An automatic urban land identification system integrating business big data with building forms, including a data acquiring and inputting module, a database construction module, a machine learning training module, an automatic identification module, and a data outputting module. The system automatically identifies an urban land by extracting a data distribution feature of an urban business site and a multi-dimensional form feature of an urban spatial three-dimensional entity. The system can be used for the determining of land usage of an urban plot in the field of urban planning and design, to achieve efficient and automatic refined identification of land usages of cities of different scales based on an artificial intelligence system, providing an efficient and convenient surveying and mapping approach and reference for surveying and mapping of the current urban construction land, and effectively saving time costs of manual surveying and mapping.

Abstract: The present disclosure relates to a method and device for video processing, an electronic device, and a storage medium. The method comprises: determining, on the basis of paragraph information of a query text paragraph and video information of multiple videos in a video library, preselected videos associated with the query text paragraph in the multiple videos; and determining a target video in the preselected videos on the basis of video frame information of the preselected videos and of sentence information of the query text paragraph. The method for video processing of the embodiments of the present disclosure indexes videos by means of the relevance between the videos and the query text paragraph, allows the pinpointing of the target video, avoids search result redundancy, allows the processing of the query text paragraph in a natural language form, and is not limited by the inherent contents of content labels.

Abstract: An automatic urban land identification system integrating business big data with building forms, including a data acquiring and inputting module, a database construction module, a machine learning training module, an automatic identification module, and a data outputting module. The system automatically identifies an urban land by extracting a data distribution feature of an urban business site and a multi-dimensional form feature of an urban spatial three-dimensional entity. The system can be used for the determining of land usage of an urban plot in the field of urban planning and design, to achieve efficient and automatic refined identification of land usages of cities of different scales based on an artificial intelligence system, providing an efficient and convenient surveying and mapping approach and reference for surveying and mapping of the current urban construction land, and effectively saving time costs of manual surveying and mapping.

Abstract: The present disclosure relates to a method and device for video processing, an electronic device, and a storage medium. The method comprises: determining, on the basis of paragraph information of a query text paragraph and video information of multiple videos in a video library, preselected videos associated with the query text paragraph in the multiple videos; and determining a target video in the preselected videos on the basis of video frame information of the preselected videos and of sentence information of the query text paragraph. The method for video processing of the embodiments of the present disclosure indexes videos by means of the relevance between the videos and the query text paragraph, allows the pinpointing of the target video, avoids search result redundancy, allows the processing of the query text paragraph in a natural language form, and is not limited by the inherent contents of content labels.