Abstract: A method and an apparatus for visual positioning based on mobile edge computing are provided. In the method, the mobile edge computing node receives an environment image captured by a to-be-positioned device in an area covered by the mobile edge computing node; the mobile edge computing node determines a target image matching the environment image from multiple candidate images, and calculates the position and pose information of the to-be-positioned device based on the position and pose information of the device for capturing the target image; and the mobile edge computing node sends the position and pose information of the to-be-positioned device to the to-be-positioned device, so that the to-be-positioned device determines the positioning information in an electronic map according to the position and pose information.

Abstract: Embodiments of the present disclosure disclose an Internet text mining-based method and apparatus for judging the validity of a point of interest. An implementation of the method includes: determining a search word set for indicating a to-be-detected point of interest; performing a search by using a determined search word as a search keyword, to obtain a description information set for describing the to-be-detected point of interest; and inputting a name of the to-be-detected point of interest and description information in the description information set into a pre-established validity discriminant model, to obtain a status label for indicating validity of the to-be-detected point of interest. This implementation enables timely discovery of invalid POI information. Thus, more accurate information are provided for users, user needs are met, and user experience is improved.

Abstract: The present disclosure provides methods, computing devices, and storage media for generating a training corpus. The method includes: mining out pieces of data from user behavior logs associated with a target application, each piece of data including a first behavior log and a second behavior log, the first behavior log including a user speech and a corresponding speech recognition result, the second behavior log belonging to the same user as the first behavior log and time-dependent with the first behavior log; and determining the user speech and the corresponding speech recognition result in each piece of data as a positive feedback sample or a negative feedback sample, based on the first behavior log and the second behavior log.

Abstract: A method and apparatus for identifying a traffic accident, a device and a computer storage medium are disclosed, which relates to the technical fields of intelligent traffic and big data. An implementation includes: acquiring road features, environmental features and road traffic stream features; inputting the road features, the environmental features and the road traffic stream features into a pre-trained traffic-accident identifying model to obtain an accident-information identifying result of a road which at least includes an accident identifying result. In the present application, the accident road may be automatically identified according to the road features, the environmental features and the road traffic stream features. Compared with a traditional manual reporting way, timeliness is stronger, and a coverage rate is higher.

Abstract: The present disclosure provides a speech error-correction method, device and storage medium. The method includes: determining at least one language type to which a present query speech belongs according to the present query speech of a user, and user description information, wherein the language types include mandarin and at least one dialect; determining each speech error-correction model corresponding to each language type; performing speech analysis on the present query speech by using the determined speech error-correction models, and performing speech error-correction based on a result of the speech analysis.

Abstract: The present application discloses a method and apparatus for processing voices, a device and a computer storage medium, and relates to the technical field of voices. An implementation includes: recognizing a received voice request by a server of a first voice assistant to obtain a text request; sending the recognized text request to a server of a second voice assistant; receiving token information generated and returned by the server of the second voice assistant for the text request; and sending the text request and the token information to a client of the first voice assistant, such that the client of the first voice assistant calls a client of the second voice assistant to respond to the text request based on the token information. Based on the present application, after a user inputs the voice request with the first voice assistant, the first voice assistant may call the second voice assistant to respond to the voice request when the second voice assistant may better respond to the voice request.

Abstract: The present application discloses a method and apparatus for identifying an updated road, a device and a computer storage medium, and relates to the field of big data technologies. A specific implementation solution is as follows: comparing a road area extracted based on the latest satellite image with a road area extracted based on a historical satellite image, to obtain a candidate updated road; mapping the candidate updated road into road network data according to a coordinate position of the candidate updated road; acquiring a user trajectory set corresponding to the candidate updated road within a recent preset period; and identifying, based on a matching result between the user trajectory set and the road network data, whether the candidate updated road is an actual updated road. Updated roads can be more accurately identified through the method according to the present application.

Abstract: The present application discloses a method and apparatus for extracting a geographic location point spatial relationship, and relates to the field of big data technologies. A specific implementation solution is as follows: determining geographic location point pairs included in real-scene images by performing signboard recognition on the real-scene images collected by terminal devices; acquiring at least two real-scene images collected by the same terminal device and including the same geographic location point pair; and determining a spatial relationship of the same geographic location point pair by using shooting parameters of the at least two real-scene images. The geographic location point spatial relationship extracted through the present application has higher accuracy and a coverage rate.

Abstract: The present application discloses a method and apparatus for determining a route, a device and a computer storage medium, and relates to the field of big data.

Abstract: The present disclosure provides a method and apparatus of estimating a road condition, and a method and apparatus of establishing a road condition estimation model, which relates to a field of big data and intelligent traffic. The method includes: acquiring, for a first preset duration before a first moment, a sequence of user tracks for a road and a sequence of road images for the road; extracting a track-related feature of the road from the sequence of the user tracks, and extracting an image-related feature of the road from the sequence of the road images; and inputting the track-related feature of the road and the image-related feature of the road into a pre-trained road condition estimation model, so as to determine, for a second preset duration after the first moment, a road condition information of the road by using an estimated result of the road condition estimation model.

Abstract: A road information processing method, an electronic device and a storage medium are provided, relates to the field of intelligent transportation, and may be used for the field of cloud computing or cloud. The method includes: acquiring a road image, and identifying a street lamp in the road image to obtain a street lamp identification result; associating the road image with an electronic map to obtain a road corresponding to the road image in the electronic map; and marking a street lamp attribute for the road corresponding to the road image in the electronic map based on the street lamp identification result.

Abstract: The present application discloses a method and apparatus for extracting the name of a POI, a device and a computer storage medium, and relates to the field of big data. An implementation includes: acquiring two or more text fragments identified from image data of the POI; constructing two or more candidate names using the text fragments; and ranking the candidate names using a pre-trained name ranking model, and determining the name of the POI according to the result of the ranking; wherein the name ranking model determines the probability of each candidate name as the name of the POI using at least one of a search web page feature, a document statistical feature and a semantic feature extracted from each candidate name, and ranks the candidate names according to the probabilities. With the present application, the name of the POI is automatically extracted with high accuracy. Compared with the manual review and annotation way in the prior art, a human cost is reduced.

Abstract: A method and an apparatus for predicting an epidemic situation, a device, a storage medium, and a program product are provided. The method may include: estimating a variable parameter of the epidemic situation in a preset area using a Markov Chain Monte Carlo (MCMC) method; acquiring a constant parameter of the epidemic situation in the preset area; constructing a transmission model based on the variable parameter and the constant parameter; and fitting, using the transmission model, to predict epidemic information of the preset area.

Abstract: The present disclosure discloses a method, apparatus and electronic device for early-warning, relates to the field of internet of vehicle and used for an intelligent traffic scenario. The specific implementations are: determining a target object crossing a road at a current moment, the road crossed by the target object being a first road; determining a target area based on a location of the target object; determining a target vehicle on the first road based on locations of vehicles on the first road as well as the target area; and sending an early-warning message to the target vehicle. It is using the locations of vehicles on the first road as well as the location of the target object crossing the road to determine the target vehicle during determination of the target vehicle among the vehicles on the first road, in order to send early-warning message to the target vehicle to achieve early-warning of the target vehicle and increase precision of the early-warning.

Abstract: A method and apparatus for identifying a traffic accident, a device and a computer storage medium are disclosed, which relates to the technical fields of intelligent traffic and big data. An implementation includes: acquiring road features, environmental features and road traffic stream features; inputting the road features, the environmental features and the road traffic stream features into a pre-trained traffic-accident identifying model to obtain an accident-information identifying result of a road which at least includes an accident identifying result. In the present application, the accident road may be automatically identified according to the road features, the environmental features and the road traffic stream features. Compared with a traditional manual reporting way, timeliness is stronger, and a coverage rate is higher.

Abstract: Embodiments of the present disclosure provide a method and apparatus for regulating a user emotion, a device and a readable storage medium. The method may include: acquiring a to-be-regulated emotion of a user during driving; reading adopted data of each regulation mode in a plurality of regulation modes for the to-be-regulated emotion from a database according to the to-be-regulated emotion; selecting a target regulation mode from the plurality of regulation modes according to the adopted data of each regulation mode; and performing an emotion regulation operation on the user according to the target regulation mode.

Abstract: A method and an apparatus for visual positioning based on mobile edge computing are provided. In the method, the mobile edge computing node receives an environment image captured by a to-be-positioned device in an area covered by the mobile edge computing node; the mobile edge computing node determines a target image matching the environment image from multiple candidate images, and calculates the position and pose information of the to-be-positioned device based on the position and pose information of the device for capturing the target image; and the mobile edge computing node sends the position and pose information of the to-be-positioned device to the to-be-positioned device, so that the to-be-positioned device determines the positioning information in an electronic map according to the position and pose information.

Abstract: A method for sorting geographic location points, a method for training a sorting model and corresponding apparatuses are disclosed, which relates to the technical field of big data. A specific implementation solution is: receiving a query request for geographic location points of a vertical class from a user; inputting candidate geographic location point data of the vertical class into a preference model of the user, to obtain a preference score of the user for each candidate geographic location point; inputting the preference score of the user for each candidate geographic location point into a sorting model as one of sorting features of each candidate geographic location point, to obtain a sorting score of each candidate geographic location point; and determining, according to the sorting score of each candidate geographic location point, a query result returned to the user.

Abstract: A method, apparatus, device and computer storage medium for processing voices, which relate to the technical field of voices, are disclosed. An implementation includes: recognizing a voice request received by a first voice assistant to obtain a text request; determining information of a second voice assistant which is able to process the text request; and calling the second voice assistant to respond to the text request. With the technical solution, when the first voice assistant is not specialized in some fields, the second voice assistant which is specialized in the fields may be called to perform a specific response processing operation, thereby meeting user requirements more accurately.

Abstract: Methods for predicting an economic state and establishing an economic state prediction model and corresponding apparatuses, and relates to the technical field of big data are disclosed. A specific implementation solution is: acquiring, from map application data, geographic location point active data in N historical time frames before a to-be-predicted future time frame respectively for a to-be-predicted region, the N being a positive integer; and inputting feature vectors of the geographic location point active data in the N historical time frames before the to-be-predicted time frame into a pre-trained economic state prediction model, to obtain economic indicator data of the to-be-predicted region in the to-be-predicted time frame. An economic state of the to-be-predicted region in the to-be-predicted time frame can be predicted, thus providing a reference for policy making in advance.