Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

Qiaoqiao She

Hao Tian

Daren Li

Bo Huang

Yingchao Shi

Jianqing Cui

Kai Liu

Haifeng Wang

Jing Liu

Yu Sun

Hua Wu

Shiqi Zhao

Chao Qiao

Wei He

Wei Xu

Yuan Gao

Yan Chen

Tian Wu

Xinyan Xiao

Kun Liu

Yajuan Lyu

Jiachen Liu

Dai Dai

Jian Gong

Xiangyang Zhou

Junqiang Zheng

Moye Chen

A method is provided. The method includes converting a search request of a user into a first request semantic vector. The method further includes searching a search resource database for at least one first data semantic vector matched with the first request semantic vector, wherein the search resource database is constructed as a semantic vector space in which different types of data are converted into corresponding data semantic vectors, and the different types of data include at least texts, pictures and videos. The method further includes generating, based on the at least one first data semantic vector, a search result.

Search method, computing device and storage medium

A model training method, a model training platform, an electronic device and a storage medium are provided, which can be used in the field of artificial intelligence, particularly the fields of natural language processing and deep learning. The model training method includes: receiving an input; determining, based on the input, a user-oriented prefabricated function; determining, based on the input, a model training function; determining, based on the input, a pre-trained model; determining, based on the input, a network structure associated with the pre-trained model so as to support use of the pre-trained model; training, based on the input, the model by using the prefabricated function, the model training function, and the pre-trained model; and providing an output associated with a trained model.

Model training

The present disclosure provides a search method, an electronic device and a storage medium, and belongs to a technical field of the Internet. The method includes: determining a first set of features corresponding to an original search statement by parsing the original search statement; obtaining each initial search result corresponding to the original search statement; determining a second set of features corresponding to an initial search result by parsing a title of the initial search result; determining a rewritten search statement corresponding to the original search statement and the initial search result by codecing the first set of features and the second set of features; and obtaining a supplementary search result corresponding to the rewritten search statement.

Search method, electronic device and storage medium

Embodiments of the application disclose a summary generation method and apparatus. A specific embodiment of the method comprises: acquiring a target article including a headline and a body of the article; determining whether a question is included in the headline; determining, in the body of the article, an information-satisfied-paragraph including an answer to the question, in response to determining that the question is included in the headline; and generating a summary of the target article based on the determined information-satisfied-paragraph. The above embodiment may generate a summary that directly satisfies the users' demand for information.

Summary generation method and apparatus

A method and apparatus for recognizing a low-quality article based on artificial intelligence, a device and a medium. The method comprises: obtaining a user feedback behavior feature of a to-be-recognized article in a news-recommending system; according to the user feedback behavior feature of the to-be-recognized article and a predetermined low-quality article recognition model, recognizing whether the to-be-recognized article is a low-quality article. Automatically recognizing whether the to-be-recognized article is a low-quality article according to the user feedback behavior feature of the to-be-recognized article and the predetermined low-quality article recognition model, thereby overcoming the technical problem about consumption of time and effects and low recognition efficiency in manually checking whether the to-be-recognized article is a low-quality article in the prior art, not only substantially saving the time spent in recognizing whether the to-be-recognized article is the low-quality article, saving manpower consumed in recognition, improving the recognition efficiency of the low-quality article.

Method and apparatus for recognizing a low-quality article based on artificial intelligence, device and medium

There is provided a method and apparatus for generating a competition commentary based on artificial intelligence, and a storage medium. The method comprises: obtaining commentator's words commentaries and structured data of historical competitions; generating a commentating model according to obtained information; during live broadcast of a competition, determining a corresponding words commentary according to the commentating model with respect to the structured data obtained each time.

Method and apparatus for generating a competition commentary based on artificial intelligence, and storage medium

The present disclosure provides a method and apparatus for evaluating article value based on artificial intelligence, and a storage medium. The solution of present disclosure may be employed to pre-mine high-quality articles and low-quality articles as training data, and train according to the training data to obtain a value-scoring model. As such, value evaluation needs to be performed for the to-be-evaluated article, it is feasible to first perform feature extraction for the to-be-evaluated article, determine a score of the to-be-evaluated article based on the extracted features and the value-scoring model, and thereby implement effective evaluation of the article value.

Method and apparatus for evaluating article value based on artificial intelligence, and storage medium

Embodiments of the present disclosure provide a method and an apparatus for training a machine reading comprehension model, and a storage medium. The method includes: training an initial model to generate an intermediate model based on sample data; extracting samples to be processed from the sample data according to a first preset rule; generating a noise text according to a preset noise generation method; adding the noise text to each of the samples to be processed respectively to generate noise samples; and performing correction training on the intermediate model based on the noise samples to generate the machine reading comprehension model.

Method and apparatus for training machine reading comprehension model, and storage medium

Embodiments of the disclosure disclose a method and apparatus for pushing information based on artificial intelligence. A specific embodiment of the method includes: mining, in response to a new match occurring, real-time match data of the match and real-time associated data of the match; generating structured data using the real-time match data; generating a to-be-recommended item using the real-time associated data and an offline item; determining whether a current time point is a recommendation node based on the structured data and real-time match state information acquired from a state manager; generating a to-be-pushed message based on the to-be-recommended item, the real-time match state information, and basic match information acquired from the state manager, and updating a to-be-pushed message record in the state manager, if the current time point is the recommendation node; and pushing the to-be-pushed message. The embodiment has improved the quality and timeliness of pushing a to-be-pushed message.

Method and apparatus for pushing information based on artificial intelligence

The present disclosure provides a method and apparatus for recognizing a low-quality news resource, a computer device and a readable medium. The method comprises: obtaining information of a to-be-recognized news resource; determining whether the to-be-recognized new resource is a low-quality news resource, according to a pre-built low-quality news information repository and the information of the to-be-recognized news resource. The technical solutions of the present disclosure may be employed to automatically recognize whether the to-be-recognized news resource is the low-quality resource through the information of the to-be-recognized news resource such as the text information and/or pictures, and can overcome technical problems in the prior art such as time-consuming and arduous manual-check manner and a low recognition efficiency due to leakage in checking. Through the above technical solutions, present embodiments may achieve automatic check of the to-be-recognized news resource and thereby substantially shorten the time spent in recognizing the low-quality news resource.

Method and apparatus for recognizing a low-quality news resource, computer device and readable medium

Embodiments of the present disclosure provide a method and a device for determining a comment, a server and a storage medium. The method includes: obtaining text content of an event; determining an event tag of the event according to the text content; comparing the event tag with comment tags in a comment graph, to determine candidate comments, the comment graph being generated according to other events and corresponding comments, and the comment graph including comments and corresponding comment tags; and screening the candidate comments, to determine a candidate comment satisfying a preset condition as the comment of the event.

Method and device for determining comment, server and storage medium

Embodiments of the present disclosure provide a method and a device for managing a dialogue based on artificial intelligence. The method includes the followings. An optimum system action is determined from at least one candidate system action according to a current dialogue status feature, a candidate system action feature and surrounding feedback information of the at least one candidate system action and based on a decision model. Since the current dialogue status corresponding to the current dialogue status feature includes uncertain results of natural language understanding, the at least one candidate system action acquired according to the current dialogue status also includes the uncertain results of natural language understanding.

Growing community of inventors

Beijing, China

Qiaoqiao She