Baidu Online Network Technology (beijing) Co., Ltd.

Huaneng Clean Energy Research Institute

Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

China University of Petroleum

Beijing Didi Infinity Technology and Development Co., Ltd.

Jingdong Technology Holding Co., Ltd.

China Huaneng Group Co., Ltd

Bin Huang

Ping Xiao

Shisen Xu

Shiwang Gao

Shiqing Wang

Minhua Jiang

He Zhao

Jinyi Wang

Hongwei Niu

Lianbo Liu

Xin Li

Lei Jia

Xiangang Li

Jinfeng Bai

Ce Zhang

Yiping Peng

Qixiang Fan

Shaomin Wang

Yong Qiao

Fei Wang

Xu Chen

Rui Ma

Wei Liu

Qi Wang

Yang Song

Zhihua Wang

Lingyu Zhang

Ke Tang

Chao Ye

Wei Zou

Xiangtao Jiang

Leilei Gao

Gaofei Cheng

Jin Chen

Qin Xiong

Wenjie Li

Wenlin Dong

Zhaoji Xu

Zhipeng Wu

Kui Xiao

Dongfang Guo

Zhike Zhang

Xinjie Wang

Jiakun Cai

Lifeng Chen

Shaojun Mo

Xiukun Wang

Xinxuan Qi

Cheng Fu

Kaoping Song

Daigang Wang

Xiangyi Zhong

The present application provides a method and device for data-driven fracture-cavity reservoir development and evaluation and a storage medium. The method includes: obtaining a fracture-cavity spatial topological relationship, a geometric shape and a fracture-cavity physical model of fault-controlled fractures and cavities, and establishing a first fault-controlled fracture-cavity reservoir discrete spatial topological network model corresponding to the fault-controlled fractures and cavities according to the fracture-cavity spatial topological relationship and geometric shape; performing, according to the first fault-controlled fracture-cavity reservoir discrete spatial topological network model, modeling processing on quantitative representation of production performance of a fault-controlled fracture-cavity reservoir using fluid vertical equilibrium mechanism and non-Darcy flow law, to form a quantitative representation model of production performance of fault-controlled fracture-cavity reservoir; performing analyzing processing on the quantitative representation model to obtain a development performance characteristic of the fault-controlled fracture-cavity reservoir, and developing the fault-controlled fracture-cavity reservoir according to the development performance characteristic.

Method and device for data-driven fracture-cavity reservoir development and evaluation, and storage medium

A method for desulfurizing and decarbonizing a flue gas includes: feeding a boiler flue gas after denitrating and dedusting to a water cooler; cooling the boiler flue gas in the water cooler to a temperature near room temperature, and discharging condensed water; feeding a wet flue gas to a washing tower; washing and cooling the wet flue gas with a washing liquid to separate HO, SOand COin a solid form from the flue gas; feeding a solid-liquid mixed slurry from a bottom of the washing tower to a solid-liquid separator to separate solid HO, SOand COfrom the washing liquid; feeding the solid HO, SOand COto a rectification separation column; separating COfrom SOand HO by a reboiler at a bottom of the rectification separation column; and discharging CO, SOand HO.

System and method for desulfurizing and decarbonizing flue gas

The present application discloses a method and apparatus for processing a notification trigger message, which method and apparatus relate to the technical field of computers. One specific implementation of the method comprises: receiving a notification trigger message formed by triggering a notification, wherein the notification trigger message includes an identifier of a current push message corresponding to the notification; determining whether the identifier of the current push message exists in a message cache, and if the identifier of the current push message exists in a message cache, ignoring the notification trigger message, wherein the message cache is used for storing an identifier of a push message corresponding to a notification that has been responded to. The implementation can avoid multiple responses of a client to an identical notification.

Method and apparatus for processing notification trigger message

Disclosed is a flue gas low-temperature adsorption denitration system and process. The system includes a booster fan, a cold energy recoverer, a flue gas cooling system, a flue gas switching valve, and two denitration adsorption towers. An inlet of the booster fan is in communication with an inlet flue gas pipeline. The booster fan, the cold energy recoverer, the flue gas cooling system, the flue gas switching valve, and the denitration adsorption towers are sequentially communicated. An outlet of the flue gas switching valve is in communication with each of the two second denitration adsorption towers. Flue gas outlets of the two denitration adsorption towers are in communication with a flue gas manifold. The flue gas manifold is communicated with the cold quantity recoverer. Two denitration adsorption towers take turns to carry out denitration and regeneration processes, so that continuous denitration operations of the system can be achieved.

Flue gas low-temperature adsorption denitration system and process

The present invention discloses a flue gas low-temperature adsorption denitrification method, including: pressurizing a flue gas that has been subjected to dust removal and desulfurization, precooling the pressurized flue gas, cooling the precooled flue gas to a temperature lower than room temperature by a flue gas cooling system, flowing the flue gas at the temperature lower than room temperature into a low-temperature denitrification system, performing physical adsorption denitrification in the low-temperature denitrification system, precooling the flue gas that has been subjected to dust removal and desulfurization with the denitrificated flue gas, and flowing the heat-absorbed clean flue gas into a chimney to be discharged.

Flue gas low-temperature adsorption denitrification method

A method and an apparatus for recognizing a voice are provided. The method may include: inputting a target voice into a pre-trained voice recognition model to obtain an initial text output by at least one recognition network in the voice recognition model, the recognition network including a plurality of preset types of processing layers, and at least one type of processing layer of the recognition network being obtained by training based on a voice sample in a preset direction interval; and determining a voice recognition result of the target voice, based on the initial text.

Method and apparatus for recognizing voice

The disclosure provides a speech recognition method, a device and a computer-readable storage medium. The method includes obtaining a first voice signal collected from a first microphone in a microphone array and a second voice signal collected from a second microphone in the microphone array, the microphone array including at least two microphones, such as two, three or six microphones. The method further includes extracting enhanced features associated with the first voice signal and the second voice signal through a neural network, and obtaining a speech recognition result based on the enhanced features extracted.

Speech recognition method, device, and computer-readable storage medium

Provided is a method for desulphurizating and denitrating a flue gas in an integrated manner based on low-temperature adsorption. The method includes: decreasing a temperature of the flue gas below a room temperature by using a flue gas cooling system; removing moisture in the flue gas by using a dehumidification system; sending the flue gas to a SOand NOadsorbing column system; and simultaneously adsorbing SOand NOof the flue gas with a material of activated coke, activated carbon, a molecular sieve or diatom mud in the SOand NOadsorbing column system to implement an integration of desulphurization and denitration of the flue gas based on the low-temperature adsorption. With the present method, SOand NOof the flue gas can be adsorbed simultaneously in an environment having a temperature below the room temperature.

Method for desulphurizating and denitrating flue gas in integrated manner based on low-temperature adsorption

A method and an apparatus for controlling a vehicle and a storage medium are disclosed. The method includes: controlling a vehicle to drive into a first parking space, the first parking space being a target parking space determined to be in an idle state; controlling the vehicle to stop driving into the first parking space in response to determining that the vehicle fails to drive into the first parking space while the vehicle is controlled to drive into the first parking space; determining a second parking space as the target parking space automatically; and controlling the vehicle to drive into the second parking space.

Method and apparatus for controlling vehicle, and storage medium

The present disclosure relates to systems and methods for remotely operating an interface of a mobile device. The method may include receiving a request for an LBS sent from the mobile device through the information exchange port, and obtaining a current time point in response to the request for the LBS. The method may also include obtaining historical behavior information related to a user of the mobile device. The method may also include determining, based on the historical behavior information and the current time point, one or more recommended destinations for the user. The method may further include remotely controlling the interface of the mobile device, through the information exchange port, to display the one or more recommended destinations.

Systems and methods for recommending a destination

An artificial intelligence-based cross-language speech transcription method and apparatus, a device and a readable medium. The method includes pre-processing to-be-transcribed speech data to obtain multiple acoustic features, the to-be-transcribed speech data being represented in a first language; predicting a corresponding translation text after transcription of the speech data according to the multiple acoustic features and a pre-trained cross-language transcription model; wherein the translation text is represented in a second language which is different from the first language. According to the technical solution, it is unnecessary, upon cross-language speech transcription, to perform speech recognition first and then perform machine translation, but to directly perform cross-language transcription according to the pre-trained cross-language transcription model. The technical solution can overcome the problem of error accumulation in the two-step cross-language transcription manner in the prior art, and can effectively improve accuracy and efficiency of the cross-language speech transcription as compared with the prior art.

Artificial intelligence-based cross-language speech transcription method and apparatus, device and readable medium using Fbank40 acoustic feature format

The present disclosure provides an artificial intelligence-based acoustic model training method and apparatus, a device and a storage medium, wherein the method comprises: obtaining manually-annotated speech data; training according to the manually-annotated speech data to obtain a first acoustic model; obtaining unannotated speech data; training according to the unannotated speech data and the first acoustic model to obtain a desired second acoustic model. The solution of the present disclosure can be applied to save manpower costs and improve the training efficiency.

Artificial intelligence-based acoustic model training method and apparatus, device and storage medium

Embodiments of the present disclosure provide a method and a device for training an acoustic model, a computer device and a storage medium. The method includes obtaining supervised speech data and unsupervised speech data, in which, the supervised speech data is speech data with manual annotation and the unsupervised speech data is speech data with machine annotation; extracting speech features from the supervised speech data and the unsupervised speech data; and performing a multi-task learning having a supervised learning task and an unsupervised learning task on the speech features of the supervised speech data and the unsupervised speech data by using a deep learning network, to train and obtain the acoustic model.

Method and device for training acoustic model, computer device and storage medium

An information exchanging method, an information exchanging device, and a terminal are provided. The information exchanging method is applied to an audio terminal. The method includes: receiving an input instruction from a user; generating a content request message according to the input instruction and a connection state identifier of the audio terminal, and sending the content request message to a server, wherein the connection state identifier indicates whether the audio terminal is connected to the video display device; and receiving a content request response message returned by the server. Thus, voice instructions input by the user can be more accurately performed according to the connection state of the audio device.

Information exchanging method and device, audio terminal and computer-readable storage medium

Growing community of inventors

Beijing, China

Bin Huang