Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: The present disclosure discloses a method, apparatus, device, and storage medium for matching semantics, relates to the technical fields of knowledge graph, natural language processing, and deep learning. The method may include: acquiring a first text and a second text; acquiring language knowledge related to the first text and the second text; determining a target embedding vector based on the first text, the second text, and the language knowledge; and determining a semantic matching result of the first text and the second text, based on the target embedding vector.

Abstract: 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.

Abstract: A text prediction method includes: obtaining at least two sentences by segmenting a text to be predicted; obtaining at least one sentence set by grouping the at least two sentences based on a number of Central Processing Unit (CPU) cores in a target device, in which the target device is a device configured to perform a prediction operation; assigning each sentence set to a corresponding CPU core of the target device, and predicting each sentence set sentence by sentence through the corresponding CPU core to obtain a prediction result of each sentence set; and determining a prediction result of the text to be predicted based on the prediction result of each sentence set.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: The disclosure discloses a semantics processing method, a semantics processing apparatus, an electronic device, and a medium, and relates to a field of knowledge graph technologies. The detailed implementation includes: determining a target semantic element rule matching a text to be parsed, and parsing the text to be parsed by employing the target semantic element rule to obtain a semantic element parsing result; generating a semantic tree based on the semantic element parsing result by employing a target structured rule associated with the target semantic element rule; and performing semantic understanding on the text to be parsed based on the semantic tree.

Abstract: 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.

Abstract: The present application discloses a method, an apparatus, a device, and a computer readable storage medium for determining a target content, the method includes: splitting an article paragraph determined according to search information into multiple sentences, and determining a relationship between the sentences according to attributes of the sentences; determining a sentence representation corresponding to each of the sentences according to the relationship between the sentences; and determining a target sentence according to the sentence representation of the sentence and the search information, and determining a target content according to the target sentence, so that the method, the apparatus, the device, and the computer readable storage medium provided by the present disclosure can analyze each of the sentences in combination with the relationship between the sentences, thereby determining a target content that more closely matches the search information.