Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

Xunchao Song

Pengcheng Yuan

Xinwei Feng

Miao Yu

Huanyu Zhou

Yang Wang

Yong Zhu

Xiaobo Liu

Songtai Dai

Xi Chen

Ying Li

Wenbin Jiang

Haiping Zhang

Yifei Wang

Meng Tian

Yang Zhang

Yabing Shi

Ye Jiang

Yajuan Lyu

Shuangjie Li

Yilin Zhang

Renkai Yang

Shaoshun Kang

Xuefeng Hao

Hongjian Shi

Xueqian Wu

The present disclosure discloses a question analysis method, a device, a knowledge base question answering system and an electronic equipment. The method includes: analyzing a question to obtain N linearized sequences, N being an integer greater than 1; converting the N linearized sequences into N network topology maps; separately calculating a semantic matching degree of each of the N network topology maps to the question; and selecting a network topology map having a highest semantic matching degree to the question as a query graph of the question from the N network topology maps. According to the technology of the present disclosure, the query graph of the question can be obtained more accurately, and the accuracy of the question to the query graph is improved, thereby improving the accuracy of question analysis.

Question analysis method, device, knowledge base question answering system and electronic equipment

A method of processing an information, an electronic device, and a storage medium are provided, which relate to a field of an artificial intelligence technology, in particular to a field of a knowledge graph technology. An implementation includes: determining a first information, in response to receiving a first query request; querying an information associated with the first information from a current graph database, so as to obtain a first query result; determining at least one federation node, according to at least one of the first query result and the first information; and sending a second query request to the at least one federation node, so that the at least one federation node queries an information associated with a second information in the second query request from a graph database corresponding to the at least one federation node, so as to obtain at least one second query result.

Method of processing information, electronic device, and storage medium

The present disclosure discloses a method, apparatus, device, and storage medium for training a model, relates to the technical fields of knowledge graph, natural language processing, and deep learning. The method may include: acquiring a first annotation data set, the first annotation data set including sample data and a annotation classification result corresponding to the sample data; training a preset initial classification model based on the first annotation data set to obtain an intermediate model; performing prediction on the sample data in the first annotation data set using the intermediate model to obtain a prediction classification result corresponding to the sample data; generating a second annotation data set based on the sample data, the corresponding annotation classification result, and the corresponding prediction classification result; and training the intermediate model based on the second annotation data set to obtain a classification model.

Method, apparatus, device and storage medium for training model

The present disclosure provides a method for graph computing, an electronic device and a non-transitory computer-readable storage medium. An execution engine for managing execution of the graph computing is configured in a CPU. One or more interface functions running in a GPU for processing parameters of the graph computing are configured. During the execution of the graph computing, the one or more interface functions are called by the execution engine through a graph computing interface. The interface functions are executed in the GPU in parallel through multiple parallel threads. The interface functions are configured to process a plurality of graph vertexes in parallel. The multiple parallel threads are configured to feedback respective execution results of the interface functions to the execution engine. The graph computing is completed by the execution engine according to the execution results.

Method and apparatus for graph computing, electronic device and storage medium

A method and an apparatus for processing information are provided. The method can include: acquiring a word sequence obtained by performing word segmentation on two paragraphs in a text; inputting the word sequence into a to-be-trained natural language processing model to generate a word vector corresponding to a word in the word sequence; inputting the word vector into a preset processing layer of the to-be-trained natural language processing model; predicting whether the two paragraphs are adjacent, and a replaced word in the two paragraphs; and acquiring reference information of the two paragraphs, and training the to-be-trained natural language processing model to obtain a trained natural language processing model, based on the prediction result and the reference information.

Method and apparatus for processing information

A method for processing a sematic description of a text entity is proposed. The method includes: acquiring a plurality of target texts containing a main entity, and extracting related entities describing the main entity from each target text; acquiring a sub-relation vector of a pair of the main entity and each related entity in each target text; calculating a similarity distance of the main entity between different target texts based on the sub-relation vector; and determining a semantic similarity of the main entity descripted in different target texts based on the similarity distance.

Method and apparatus for processing sematic description of text entity, and storage medium

Embodiments of the present disclosure provide a method, apparatus, computer device, and storage medium for verifying community question answer data. The method may include: acquiring a community question answer data set, and generating a plurality of question answer pairs based on the community question answer data set, a question answer pair including: a question, and a to-be-verified answer corresponding to the question; generating an authoritative data set based on data stored in at least one confidence source site; and performing an authority verification on the to-be-verified answer, based on a score of a similarity between the to-be-verified answer and authoritative data in the authoritative data set in at least one dimension.

Method, apparatus, computer device and storage medium for verifying community question answer data

A method for obtaining an answer to a question is provided. The method may include: acquiring a question; determining at least a part of articles in a preset article database as candidate articles, and determining first scores of the candidate articles respectively, the first score of any of the candidate articles representing a matching degree between the candidate article and the question; determining at least a part of texts in each of the candidate articles as candidate texts, and determining second scores of the candidate texts respectively, the second score of any of the candidate texts representing a matching degree between the candidate text and the question; and determining at least a part of the candidate texts as the answer based on a score set of each of the candidate texts, the score set of any of the candidate texts including the second score and the first score.

Method, apparatus, electronic device and computer readable medium for obtaining answer to question

A method for storing a determinant text, an electronic device, and a computer-readable storage medium is disclosed. The method includes: obtaining a determinant text that is to be stored, the determinant text including a plurality of fields; obtaining valid fields from the plurality of fields; querying a field type table according to the valid fields to generate a data description field of the determinant text; determining a value storage field of the determinant text according to contents of the plurality of fields and the field type table; and storing the data description field and the value storage field to store the determinant text.

Method, device, and storage medium for storing determinant text

The present disclosure provides a search method and device based on artificial intelligence and an electronic device. The search method based on artificial intelligence includes: obtaining a query; performing a word segmentation on the query to obtain a term sequence containing a plurality of terms; performing a structured analysis on the term sequence to generate a semantic pattern; performing a knowledge-based analysis on the term sequence based on the semantic pattern to generate a semantic analysis result; determining an understanding result corresponding to the query based on the semantic pattern and the semantic analysis result; and performing a search based on the understanding result corresponding to the query.

Search method and device based on artificial intelligence

Embodiments of the present disclosure provide a query processing method and an apparatus, a server and a storage medium. The method includes: determining a word vector representation of a query sequence and an entity vector representation of the query sequence respectively based on respective words and respective entities included in the query sequence; determining a word vector representation of a paragraph and an entity vector representation of the paragraph respectively based on respective words and respective entities included in the paragraph; and determining a similarity between the query sequence and the paragraph according to the word vector representation of the query sequence, the entity vector representation of the query sequence, the word vector representation of the paragraph, and the entity vector representation of the paragraph.

Query processing method, apparatus, server and storage medium

Embodiments of the disclosure disclose a method and apparatus for generating information. A specific embodiment of the method comprises: acquiring a historical click log, the historical click log comprising a historical search term and a clicked historical search result corresponding to the historical search term; determining whether matching clicked historical search results exist in the historical click log; establishing a synonymous relationship between historical search terms corresponding to the matching clicked historical search results, in response to determining the matching clicked historical search results existing in the historical click log; and generating a relational word list based on the established synonymous relationship. The embodiment helps to enrich the content of the relational word list, and improve the coverage of the relational word list.

Method and apparatus for generating information

The present disclosure provides a method for updating a relational index, a storage medium and an electronic device. The method includes: reading out relational data of an entity to be operated from a disk to a memory; performing an updating operation on the relational data in the memory; storing the updated relational data into a memory relational index; writing content data of the entity to be operated into the disk; and synchronizing periodically the memory relational index to a disk relational index.

Method for updating relational index, storage medium and electronic device

A method and an apparatus for storing data are provided. The method includes: acquiring target data, the target data including first key-value pair data, object data or array data, the key-value pair data including key data and value data, the object data including second key-value pair data, and the array data including object data; determining an object data number of the object data included in the target data, an array data number of the array data included in the target data, a first key-value pair data number of the first key-value pair data included in the target data, and a second key-value pair data number of the second key-value pair data included in the target data; determining a storage space based on the determined numbers; and storing the target data into the storage space.

Growing community of inventors

Beijing, China

Xunchao Song