Abstract: A track restoration method, a track restoration device and a non-transitory computer-readable storage medium are provided, related to the field of intelligent transportation. The track restoration method includes: acquiring vehicle-passing data in a target area, where the vehicle-passing data is generated based on shooting data, and the shooting data is obtained by shooting a vehicle in the target area by a shooting device in the target area; restoring a driving track of the vehicle shot by the shooting device, based on the vehicle-passing data.

Abstract: The embodiments of the present disclosure provide a private data processing method, a device and a medium, and relate to data security technologies. The method includes: initiating a user request to an intermediate server according to an input of a user to request the intermediate server to perform intermediate business processing according to the user request and to initiate a target business processing request to a business server; obtaining business result data encrypted with an account key of the user and fed back by the business server based on the target business processing request from the intermediate server; and using the account key of the user to decrypt the encrypted business result data.

Abstract: The present application disclosures a voice skill starting method, an apparatus, a device, and a storage medium, and relates to the field of artificial intelligence. An implementation scheme is that: the method is applied to an electronic device including at least one third-party voice skill and a built-in voice skill, and the electronic device is currently in the built-in voice skill. The method includes: receiving a current demand instruction of a user; judging whether the current demand instruction belongs to an entry demand instruction corresponding to the third-party voice skill according to a mapping relationship in response to the current demand instruction; and switching from the built-in voice skill to the third-party voice skill if it is determined that the current demand instruction belongs to the entry demand instruction corresponding to the third-party voice skill.

Abstract: Provided are a sampling object determination method and apparatus, an electronic device, and a computer-readable storage medium. The sampling object determination method includes: determining a sampling number through a sampling proportion and a total number of users of an application; determining at least one version in order of versions of the application from high to low, where a sum of a number of users of the at least one version is greater than or equal to the sampling number; and determining the sampling number of users in the users of the at least one version as sampling objects.

Abstract: A method includes obtaining a current query of a user, the search history information of the user in a first time period, the search history information of the user in a second time period and candidate search results for the current query, and inputting the current query of the user, the search history information of the user in the first time period, the search history information of the user in the second time period and the candidate search results for the current query into a search result ranking model, and determining search results corresponding to the current query according to scores of the candidate search results, the second time period being greater than the first time period.

Abstract: The present disclosure discloses a speech chip and an electronic device. The speech chip includes a first processing module, a second processing module and a third processing module. The first processing module is configured to run an operating system, and to perform data scheduling on modules other than the first processing module in the chip. The second processing module is configured to perform a mutual conversion between speech and text based on a speech model. The third processing module is configured to perform digital signal processing on inputted speech.

Abstract: The present disclosure provides an apparatus for controlling battery module, power supply device and power supply system. The apparatus includes a switch circuit and a first power controller. The first power controller is coupled with the switch circuit, a first busbar, a second busbar, and a battery module, and is configured to: control the switch circuit to conduct in a first direction, in a case of the voltage between the first busbar and the second busbar being greater than the voltage of the battery module and the power of the battery module being smaller than a first preset power; and control the switch circuit to conduct in a second direction, in a case of the voltage between the first busbar and the second busbar being smaller than the voltage of the battery module and the power of the battery module being greater than a second preset power.

Abstract: A shooting method includes: obtaining a preview image collected by an image collection device; detecting a first relative distance and a first relative angle between a foreground of the preview image and the image collection device, and detecting a second relative distance and a second relative angle between a background of the preview image and the image collection device; determining a target shooting position of the image collection device based on the first relative distance, the first relative angle, the second relative distance and the second relative angle, wherein a picture obtained by shooting the foreground and the background at the target shooting position has a composition that matches with a set composition strategy; and displaying a prompt message about the target shooting position for prompting the image collection device to move to the target shooting position.

Abstract: The present disclosure provides a method and apparatus of pre-rending a page, an electronic device, and a storage medium. The method of pre-rendering the page may include: acquiring a static resource of a page to be processed; acquiring a hypertext markup language structure information compiled of the page; and generating a static hypertext markup language file of the page by using a native server-side rendering function of a web frame according to the static resource and the hypertext markup language structure information.

Abstract: Embodiments of the present disclosure disclose a view-based voice interaction method, an apparatus, a server, a terminal and a medium. The method includes: obtaining voice information of a user and voice-action description information of a voice-operable element in a currently displayed view on a terminal; obtaining operational intention of the user by performing semantic recognition on the voice information of the user according to view description information of the voice-operable element; locating a sequence of actions matched with the operational intention of the user in the voice-action list according to the voice-action description information; and delivering the sequence of actions to the terminal for performing.

Abstract: The disclosure provides a special effect processing method for live broadcasting. A video stream is acquired. Positions of key points of a human body contained in each frame of the video stream are obtained. For each frame, positions of target key points contained in a virtual object template are adjusted based on the positions of the key points of the human body in the frame to obtain a target virtual object corresponding to the frame. The target virtual object corresponding to the frame and the frame of the video stream are fused to generate a target video stream. The target video stream is sent to the live broadcasting client and a user client.

Abstract: A resource processing method and apparatus are proposed in the embodiment of the present disclosure. The method includes: obtaining a resource allocation scenario; querying a corresponding strategy combination configuration according to the resource allocation scenario; executing each allocation strategy to determine a target resource pool allocated with the allocation strategy; obtaining resources corresponding to each allocation strategy from the target resource pool allocated with the allocation strategy; executing the combination operation on the resources corresponding to the allocation strategy to obtain target resources.

Abstract: The present application discloses a method and apparatus for acquiring point-of-interest (POI) state information, a device and a computer storage medium, and relates to the field of big data. An implementation includes acquiring a text containing POI information in a preset time period from the Internet; and identifying the text using a pre-trained POI-state identifying model to obtain a binary group in the text, the binary group including a POI name and the POI state information corresponding to the POI name; wherein the POI-state identifying model performs label prediction of the POI name and a POI state on a word sequence corresponding to the text, and label prediction results of the POI name and the POI state are aligned to obtain the binary group. With the present application, a human cost may be saved, and timeliness and accuracy may be improved.

Abstract: A monocular vision tracking method, apparatus, and a non-volatile computer-readable storage medium are provided. The method includes: acquiring a first camera pose by using a wireless tracker; capturing calibration board images by using a camera, and selecting a set of images from the captured calibration board images according to image sharpness and camera pose difference; calculating a second camera pose in the camera calibration algorithm according to the selected set of images; obtaining a conversion parameter between the first camera pose and the second camera pose; and converting a first capturing pose into a second capturing pose by means of the conversion parameter when a scenario is captured, wherein the first capturing pose is acquired by the wireless tracker and the second capturing pose corresponds to a pose of the camera.

Abstract: A visual search method, a visual search device, and an electrical device are provided. The method includes determining a first object in a visual search process. A power consumption of the first object in the visual search process is greater than a power consumption of a second object in the visual search process. The first object includes at least one of a program and an algorithm and the second object includes at least one of a program and an algorithm. The method further includes performing a visual search through an optimized object of the first object. At least one of a calculating speed of the optimized object is greater than a calculating speed of the first object and a total calculating time of the optimized object within a unit time is less than a total calculating time of the first object within the unit time.

Abstract: Disclosed in the embodiments of the present disclose are a method and device for sending information. A particular embodiment of the method comprises: acquiring user input information input to a user terminal; determining, from a target expression image set, at least one expression image to be sent to the user terminal and matching the user input information, and a presentation order of the at least one expression image; and sending presentation information to the user terminal in response to determining that, during a historical time period, the user terminal presents the at least one expression image according to the presentation order less than or equal to a target number of times, wherein the presentation information is for instructing the user terminal to present the at least one expression image according to the presentation order.

Abstract: A data processing method and device are provided. The method includes: performing a forward calculation of a neural network on global data to obtain intermediate data for a reverse calculation of the neural network; storing the intermediate data in a buffer unit; reading the intermediate data from the buffer unit; and performing the reverse calculation of the neural network on the intermediate data to obtain a result of the reverse calculation. According to embodiments, in the reverse calculation of the neural network, the number of accessing the global memory is reduced, thereby reducing the computational time cost and increasing the data processing speed.

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: Disclosed are a model parameter adjusting method and device, a storage medium and a program product. The method includes: performing classification processing on input data by using a classification model obtained through training based on secure multi-party computing, to obtain classification prediction values of the classification model (S201); performing reduction processing on the classification prediction values (S202); performing normalization processing on the classification prediction values subjected to the reduction processing, to obtain a normalization result of the classification prediction values (S203); and updating a parameter of the classification model according to the normalization result of the classification prediction values (S204).

Abstract: Disclosed are a method and apparatus for processing an account of a blockchain network. The method includes: obtaining an account transaction request associated with a chain account, wherein, the chain account belongs to the blockchain; obtaining an account smart contract from the account transaction request, and writing the account smart contract into a block, wherein, the account smart contract is configured to perform operation on a chain element in the chain account when executed.