Patents Assigned to BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
  • Publication number: 20210064616
    Abstract: The present disclosure relates to systems and methods for recommending locations. The systems may receive data related to a plurality of historical service requests, generate a plurality of feature matrices based on each of a plurality of candidate points of interest (POIs) associated with the plurality of historical service requests, generate a set of sample POIs from the plurality of candidate POIs based on the plurality of feature matrices, train a preliminary POI recommendation model using the set of sample POIs with associated feature matrixes; and determine at least one target POI based on a trained POI recommendation model.
    Type: Application
    Filed: October 30, 2020
    Publication date: March 4, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Po HU, Ximin WANG, Yonggang XUE
  • Publication number: 20210065548
    Abstract: The present disclosure provides systems and methods for navigation based on intersection coding. A method may include obtaining a current location of a subject and navigation information. The method may also include determining, based on the current location and the navigation information, one or more road features associated with an upcoming intersection with respect to a current road segment. The method may also include determining, based on the one or more road features and a coding system, one or more navigation codes corresponding to the upcoming intersection. The method may further include determining, based on the one or more navigation codes, a prompt for navigation associated with the upcoming intersection.
    Type: Application
    Filed: November 16, 2020
    Publication date: March 4, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventor: Yan LI
  • Publication number: 20210064669
    Abstract: The present disclosure relates to systems and methods for determining points of interest. The methods may include obtaining a target address query associated with a service request from a user terminal; determining a plurality of initial terms based on the target address query; determining a plurality of term weights based on the plurality of initial terms, respectively; determining one or more candidate points of interest (POIs) based on the plurality of term weights according to an iterative process; determining one or more target POIs based on the one or more candidate POIs; and transmitting the one or more target POIs to the user terminal.
    Type: Application
    Filed: November 13, 2020
    Publication date: March 4, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Juan HU, Huan CHEN, Qi SONG, Li MA
  • Publication number: 20210063180
    Abstract: The present disclosure relates to systems and methods for identifying a closed road section. The systems may obtain a first heat map representing a first density of tracked vehicles in a target area over a first time period and a second heat map representing a second density of tracked vehicles in the target area over a second time period; determine a difference map between the first heat map and the second heat map; determine one or more candidate regions based on the difference map; identify one or more candidate links associated with the one or more candidate regions in a road network map; determine one or more confidence levels associated with the one or more candidate links based on the one or more candidate regions; and identify one or more closed road sections based on the one or more confidence levels.
    Type: Application
    Filed: November 11, 2020
    Publication date: March 4, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Kaiqiang AN, Guoping LIU
  • Publication number: 20210064665
    Abstract: The present disclosure relates to systems and methods for determining at least one recommended search strategy for a user query. The method may include receiving the user query including at least one first segment from a terminal device; obtaining a plurality of search strategies matching the user query, each search strategy including at least one second segment; obtaining a text similarity determination model adapted to incorporate an attention mechanism; for each of the plurality of search strategies, determining a similarity score between a first vector representing the user query and a second vector representing the search strategy based on the text similarity determination model, at least one of the first vector or the second vector being associated with an attention weight of each corresponding segment; and determining the at least one recommended search strategy based on the similarity scores among the plurality of search strategies.
    Type: Application
    Filed: November 10, 2020
    Publication date: March 4, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Ji ZHAO, Huan CHEN, Qi SONG, Li MA
  • Publication number: 20210064478
    Abstract: Systems and methods for data synchronization are provided. The system may include a first Hadoop service cluster, a second Hadoop service cluster and a third service cluster. The first Hadoop service cluster may store the file metadata from a client. The second Hadoop service cluster connects to the first Hadoop service cluster. The third service cluster may back up updated data block of the first Hadoop service cluster to the second Hadoop service cluster.
    Type: Application
    Filed: October 11, 2020
    Publication date: March 4, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventor: Guoquan SHEN
  • Publication number: 20210063186
    Abstract: A method for rendering an object is provided. The method may include obtaining tile information associated with a region of interest (ROI) from a database. The method may include extracting, from the tile information, one or more links along a center line of an overpass in the ROI. The method may include determining at least one intersection of the one or more links. The method may include performing a topology analysis on the one or more links and the at least one intersection to generate a link chain of the one or more links. The method may include constructing a model of the overpass based on the link chain of the one or more links. The method may further include rendering the model of the overpass.
    Type: Application
    Filed: November 11, 2020
    Publication date: March 4, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventor: Zhirui GUO
  • Patent number: 10933884
    Abstract: Systems and methods for operating a vehicle automatically in real time may be provided. The system may receive and process real time sensor data from a sensing system via an arithmetic and control unit (ACU). The system may obtain, via the ACU, one or more tasks during the processing of the real time sensor data. The system may classify, via the ACU, the one or more tasks into real time vehicle controlling (VC) tasks and non real time VC tasks. The system may further send the real time VC tasks to at least one dedicated processing core of the ACU for processing the real time VC tasks and generating one or more real time VC commands accordingly.
    Type: Grant
    Filed: June 17, 2020
    Date of Patent: March 2, 2021
    Assignee: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Fenglei Wang, Jintao Wang
  • Patent number: 10936298
    Abstract: The present disclosure relates to systems and methods for updating and loading an application installed in a terminal device. The system may perform the methods to transmit an update notice of the application to the mobile device; and provide a resource installation package to the mobile device upon a response from the mobile device to the update notice. The application includes a shell and a pre-update plugin, and the shell includes a plugin engine. The resource installation package is configured to direct the application to use the plugin engine in the shell to utilize components of the resource installation package to update the pre-update plugin without attaining approval from an application store platform.
    Type: Grant
    Filed: December 27, 2019
    Date of Patent: March 2, 2021
    Assignee: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Yugang Ren, Hai Wang, Tao Zheng
  • Patent number: 10937231
    Abstract: Embodiments of the disclosure provide systems and methods for updating a high-resolution map. The system may include a communication interface configured to receive a plurality of image frames captured by a binocular camera equipped on a vehicle, as the vehicle travels along a trajectory. The system may further include a storage configured to store the high-resolution map and the plurality of image frames. The system may also include at least one processor. The at least one processor may be configured to generate point cloud frames based on the respective image frames. The at least one processor may be further configured to position the vehicle using the point cloud frames. The at least one processor may be further configured to merge the point cloud frames based on the vehicle positions. The at least one processor may also be configured to update a portion of the high-resolution map based on the merged point cloud.
    Type: Grant
    Filed: December 11, 2018
    Date of Patent: March 2, 2021
    Assignee: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Sheng Yang, Teng Ma, Xiaozhi Qu
  • Patent number: 10936867
    Abstract: The present disclosure relates to systems and methods for automated identification of presence of a facial action from sequential images. The systems and methods may obtain a plurality of sequential candidate image frames containing a facial object. Each of the plurality of candidate image frames may include a plurality of feature points associated with an eye of the facial object. For each of the plurality of sequential candidate image frames, the systems and methods may determine an area of a polygon based on the plurality of feature points. The systems and methods may determine a distance associated with the eye of the facial object. The systems and methods may determine an action parameter based on the area and the distance. The systems and methods may identify the presence of a blink action in response to that the action parameters satisfy one or more preset conditions.
    Type: Grant
    Filed: June 10, 2020
    Date of Patent: March 2, 2021
    Assignee: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO.. LTD.
    Inventor: Xiubao Zhang
  • Patent number: 10937430
    Abstract: The present disclosure relates to a method, apparatus, and system for speaker verification. The method includes: acquiring an audio recording; extracting speech signals from the audio recording; extracting features of the extracted speech signals; and determining whether the extracted speech signals represent speech by a predetermined speaker based on the extracted features and a speaker model trained with reference voice data of the predetermined speaker.
    Type: Grant
    Filed: March 14, 2019
    Date of Patent: March 2, 2021
    Assignee: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Jie Chen, Dan Su, Tianxiao Fu, Na Hu
  • Patent number: 10936786
    Abstract: The present disclosure relates to a system and a method for displaying a prompt message. The method includes displaying a first prompt message in an entry box on a user interface of an electronic terminal; determining there is an input instruction in the entry box; replacing the first prompt message with a second prompt message; and changing display status of the first prompt message.
    Type: Grant
    Filed: January 19, 2018
    Date of Patent: March 2, 2021
    Assignee: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Baoming Qu, Jing Ou
  • Publication number: 20210055121
    Abstract: A method for determining a recommended location may include identifying a candidate location based on historical order data of a plurality of historical passengers; obtaining a plurality of images showing sights around the candidate location, wherein the plurality of images are captured by at least one vehicle recorder; determining an identification result as to whether a road element is present around the candidate location based on the plurality of images; and determining whether the candidate location is a recommended location based on the identification result.
    Type: Application
    Filed: November 10, 2020
    Publication date: February 25, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Yushu GAO, Pengfei XU
  • Publication number: 20210058682
    Abstract: A system and a method for storing a multimedia resource are provided. The method may include determining a time slice of the multimedia resource having a specified format in real time. The method may further include storing the multimedia resource to a corresponding file based on a corresponding relation between the time slice and a preset time slice.
    Type: Application
    Filed: October 11, 2020
    Publication date: February 25, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventor: Gengxin WU
  • Publication number: 20210055109
    Abstract: The present disclosure is related to systems and methods for indoor positioning. The method includes obtaining a first location of a subject at a first time point. The method also includes determining one or more motion parameters associated with the subject at least based on one or more sensors carried by the subject. The method further includes determining, based on the first location of the subject and the one or more motion parameters associated with the subject, a second location of the subject at a second time point after the first time point. The method still further includes adjusting, at least based on surroundings information associated with the subject at the second time point, the second location of the subject to determine a target location of the subject.
    Type: Application
    Filed: November 10, 2020
    Publication date: February 25, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Xiaoqiang TENG, Rongzhi WANG, Jiankuan LI, Zhiwei RUAN, Zongyue LIU, Jun ZHANG, Pengfei XU, Shenggang BAO, Chao LIU
  • Patent number: 10929984
    Abstract: The present disclosure relates to systems and methods for action recognition. The systems and methods may obtain a plurality of sequential target image frames associated with facial information of an object. Each of the plurality of sequential target image frames may include a plurality of feature points associated with the facial information. The systems and methods may determine a first area and a second area based on the plurality of feature points in each of the plurality of sequential target image frames. The systems and methods may determine an asymmetry parameter in each of the plurality of sequential target image frames based on the first area and the second area. The systems and methods may identify a shaking action in response to that the asymmetry parameter satisfies a preset condition.
    Type: Grant
    Filed: June 10, 2020
    Date of Patent: February 23, 2021
    Assignee: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO.. LTD.
    Inventor: Xiubao Zhang
  • Publication number: 20210049623
    Abstract: Systems and methods for determining a marketing strategy for an online to offline service are provided. A method may include: obtaining a plurality of historical vectors, determining a first value function according to a first reinforcement learning algorithm based on the plurality of historical vectors, determining a first value under a state of a driver to provide the online to offline service based on the first value function and the plurality of historical vectors, and obtaining a first regression model by training an initial model, wherein the plurality of historical vectors are inputs of the initial model, and the first value under the state is a label of the initial model.
    Type: Application
    Filed: November 3, 2020
    Publication date: February 18, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventor: Wenjuan LUO
  • Publication number: 20210049224
    Abstract: The present disclosure relates to systems and methods for determining target search results associated with a target query. The method may include obtaining a transportation service request including a target address query from a user terminal, and determining a plurality of candidate points of interest (POIs) associated with the target address query. The method may also include identifying one or more target POIs based on the candidate POIs by using a trained identification model. The trained identification model may be configured to provide a correlation probability for each of the one or more target POIs with the target address query. The method may further include ranking some or all of the one or more target POIs to produce a ranking result based on the correlation probabilities, and transmitting the ranking result to the user terminal.
    Type: Application
    Filed: November 3, 2020
    Publication date: February 18, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Wanji ZHENG, Huan CHEN, Peng YU, Qi SONG
  • Publication number: 20210048311
    Abstract: A method for online to offline services is provided. The method may include one or more of the following operations. A transportation service request may be received. The transportation service request may include a target address query from a user terminal. Whether the target address query is directed to a target area of interest (AOI) may be determined. At least one target point of interest (POI) and a target semantic description associated with the target AOI may be obtained from an AOI database. The at least one target POI and the target semantic description may be sent to the user terminal.
    Type: Application
    Filed: November 3, 2020
    Publication date: February 18, 2021
    Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
    Inventors: Ji ZHAO, Huan CHEN, Peng YU, Qi SONG