18 results about "Sentence processing" patented technology

The application relates to the technical field of news media, and discloses a multi-modal knowledge graph construction method and an information retrieval method based on a media field, aiming to solve the problem that the retrieval effect and user experience of a retrieval engine based on a knowledge graph construction are poor, and the scheme mainly comprises the following steps: acquiring and filtering news data; performing sentence processing on news texts corresponding to the news data, and extracting entity words and domain event triples in each sentence; training a CLIP fine-tuning model, performing matching prediction on corresponding entities and events according to the CLIP fine-tuning model, and expanding a multi-modal attribute set of the entities and events according to the matching prediction result; constructing a knowledge base according to the extracted data, performing anaphora resolution and entity disambiguation processing on the data in the knowledge base, constructing an ontology of domain entities and domain events, and writing the ontology into a graph database to obtain a multi-modal knowledge graph of the media field. The application improves the retrieval effect and user experience of news information.

This invention provides a method for calculating semantic similarity based on adjacent word features, relating to the field of natural language processing. First, in the example word extraction module, example words are extracted from the example sentence and the sentence to be matched using the longest common substring algorithm. Second, in the example sentence processing module, word segmentation is performed on the example sentence excluding the example words, and part-of-speech tagging is applied to the example words. Then, in the feature extraction module, features are extracted from the words surrounding the example words in the example sentence. The correlation between the surrounding words and the example words and option words is calculated using a corpus. The calculated results are weighted and combined with their respective features to form the features of the example words and option words. Finally, in the option processing module, the part-of-speech of the option words is compared with that of the example words, and a similarity score is calculated based on the features of the option words to select the optimal option word. This invention determines the features of the current word by extracting features from surrounding words and calculating correlation; it uses a corpus to calculate the mutual information between two words to achieve the correlation between the two words.

Embodiments of the present application disclose a sentence processing method and related device, which are applied to an artificial intelligence scene or a vehicle-mounted scene. For a target sentence and a plurality of first candidate sentences, a sentence similarity between each first candidate sentence and the target sentence is calculated. When it is determined based on the sentence similarity that the plurality of first candidate sentences do not match the target sentence, the plurality of first candidate sentences are segmented to obtain a plurality of second candidate sentences. A plurality of first to-be-fused sentences are determined from the plurality of second candidate sentences according to an importance parameter value of each second candidate sentence for the target sentence. The plurality of first to-be-fused sentences are fused according to a dependency relationship between words in the plurality of first to-be-fused sentences to obtain a fused sentence matched with the target sentence. The method can meet the actual demand for obtaining a matched sentence of the target sentence even when the plurality of first candidate sentences do not match the target sentence, thereby improving the processing effect of application scenarios such as a question and answer system and a search system.

The application discloses a sentence processing method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: constructing a semantic label tree of a target sentence; wherein the semantic label tree is formed by connecting a plurality of nodes, each node represents an entity semantic label, and the connection relationship between the nodes identifies the relationship between the corresponding entity semantic labels; dividing the semantic label tree into at least one sub-label tree; wherein the nodes included in each sub-label tree correspond to an entity semantic label group, and each label group represents an intent; and splitting the target sentence based on the at least one sub-label tree to obtain at least one target clause corresponding to the at least one sub-label tree. In the foregoing manner, the target sentence can be accurately split into single-intent clauses.

The invention discloses an intelligent tendering and bidding question-answering method based on document segmentation, and relates to the technical field of document segmentation, and the method comprises the steps: carrying out the layout analysis of a tendering and bidding document, so as to extract a structural unit set, construct a structural hierarchical relation, and carrying out the sentence processing of each structural unit; constructing a semantic window for the structural unit and generating a mixed semantic window vector, and performing primary segmentation on the structural unit by calculating a semantic gradient to generate a semantic continuous block set; second-level segmentation is carried out on the basis of the length constraint of the token, a text block set is generated, cross-level semantic coding is carried out on text blocks, and block-level vector codes are generated; outputting a local abstract for each text block according to a cross-level coding result, constructing a local abstract set, performing compression to generate a global abstract, and constructing a bidirectional mapping system of clause numbers and the text blocks; and efficient and traceable bidding and tendering document analysis and intelligent question and answer are provided for the user.

The invention relates to a Chinese ancient city space-time knowledge graph construction method and device and a storage medium. The method comprises the steps of obtaining ancient document data related to a target city based on a city place name set of the target city; performing sentence segmentation processing and knowledge extraction based on the ancient book literature data to obtain a plurality of ancient book text entries and triples corresponding to the plurality of ancient book text entries; semantic disambiguation is carried out on each triad corresponding to each ancient book text entry, and attribute values of entities of time and space types uniquely corresponding to each triad are determined, so that the time-space knowledge graph of the ancient Chinese cities is constructed. According to the embodiment of the invention, the time-space knowledge graph can be constructed by taking the ancient cities as the ontology, and the constructed time-space knowledge graph of the ancient Chinese cities can support deep semantic retrieval and analysis related to the ancient Chinese cities. And efficient knowledge support and decision-making assistance can be provided for the fields of urban historical research, cultural heritage protection, urban planning and construction and the like.

To disclose a technique for improving user's convenience.SOLUTION: The computer program causes the computer to function as a first reception unit that receives an input of a first natural sentence, a first supply unit that supplies first natural sentence data representing the first natural sentence to a natural sentence processing unit when the input of the first natural sentence is received, and a first acquisition unit that acquires first object information based on the first natural sentence data from the natural sentence processing unit. The first object information is caused to function as: a first acquisition unit which includes first identification information for identifying the first object for each of M1 screens among the M screens; and a second display control unit which, when the first object information is acquired from a natural sentence processing unit, causes a display device to sequentially display M screens including the M1 screens according to the first object information, wherein the first object is emphatically displayed on each of the M1 screens.SELECTED DRAWING: Figure 6

This application discloses a statement processing method, apparatus, device cluster, and storage medium, belonging to the field of computer technology. The method includes: adjusting the first description information to obtain second description information, where at least two first SQL operators described in the first description information include the same first UDF, and the function calculation results of the first UDF in the at least two first SQL operators should remain the same. The first operators in the second description information are executed before the second SQL operators. The first operators are used to calculate the first UDF, and the second SQL operators are used to call the function calculation results of the first operators. The second SQL operators are obtained by adjusting first SQL operators that are different from the first operators. The database is then operated based on the second description information. The second SQL operator including the first UDF can directly call the function calculation results of the first operator without repeatedly calculating the first UDF, resulting in high execution efficiency of the SQL statement.

The application is suitable for the technical field of text processing, and provides a PLM research and development material processing method and device fusing semantic understanding, the PLM research and development material processing method fusing semantic understanding comprises the following steps: obtaining research and development material text to be recognized, and performing sentence processing on the research and development material text to obtain a plurality of to-be-recognized sentences; extracting the number of entity words and the number of logical connection words in the to-be-recognized sentences; calculating the topic coherence index, the position influence index and the format influence index of the to-be-recognized sentences; extracting key sentences according to the number of entity words, the number of logical connection words, the topic coherence index, the position influence index and the format influence index, and performing labeling processing on the key sentences. This kind of fusing semantic understanding mode ensures that the system not only pays attention to the surface structure of the sentence when extracting information, but also can understand its internal meaning, thereby improving the accuracy and effectiveness of information extraction.

The present disclosure provides a structured query language sentence processing method and system, device and medium, the structured query language sentence processing method comprises: obtaining table information, inputting the table information into a structured query language sentence processing model, and outputting a structured query language sentence, wherein a first training sample is input into a first teacher model and a first student model respectively for distillation training to obtain a second student model; a second training sample is input into a second teacher model and a second student model respectively for distillation training to obtain a trained second student model; the structured query language sentence processing model is obtained by training based on the trained second student model, table samples and predetermined language labels, so that the accuracy and precision of the structured query language sentence can be ensured, and the defects of insufficient memory and slow inference time during online deployment can be overcome.

The application discloses a sentence processing method and device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: obtaining an input sentence input by a user terminal through a preset acquisition instruction; wherein the input sentence comprises a single syntax rule or a sentence of a syntax rule group; performing syntax analysis on the input sentence by using antlr4 at the front end, and converting the analyzed sentence into a syntax tree structure; rendering the syntax tree structure to obtain a visual operation sentence page; performing data operation processing on the nodes in the syntax tree structure based on the visual operation sentence page, and verifying the target syntax tree structure obtained after the data operation processing, so that the input sentence is updated in real time after the verification of the target syntax tree structure is passed. Through the technical scheme of the application, the efficiency problem caused by the high learning cost of manual input of syntax professionals and the large number of input sentences can be solved from the perspective of the user.

The present disclosure provides a demand evaluation information generation method, a demand evaluation information display method and device, relates to the field of data processing, and particularly to the field of search sentence processing. The specific implementation scheme is as follows: determining a target search sentence to be analyzed; obtaining search volume information of the target search sentence in a first time period; wherein the first time period is a time period before the current time, and the search volume information of any search sentence in a time period includes the search volume of the search sentence in each statistical period in the time period; determining an estimated volume corresponding to the target search sentence based on the obtained search volume information; wherein the estimated volume is used to represent the search demand of the target search sentence in a second time period, and the second time period is a time period after the current time; and generating demand evaluation information of the target search sentence based on the estimated volume corresponding to the target search sentence. Through the present scheme, demand evaluation information that can accurately reflect the actual demand can be generated.

The application relates to the field of information retrieval, in particular to an information consultation intelligent retrieval system and method based on cloud services, which comprises a cross-table index module, a retrieval characteristic module, a sentence processing module, a granularity retrieval module and a resource allocation module; the cross-table index module is used for constructing an index structure; the retrieval characteristic module is used for synthesizing a characteristic vector and outputting a retrieval basis vector; the sentence processing module is used for receiving a consultation text and projecting a granularity text; the granularity retrieval module is used for retrieving resources and outputting a retrieval result; and the resource allocation module is used for constructing a vector tree and allocating retrieval resources; the application can improve retrieval precision in a domain, relieve data expansion pressure of a large-scale database, enhance retrieval generalization capability, improve comprehensiveness of retrieval content, reduce time complexity, facilitate maintenance and expansion, reduce the cost of retrieval semantic calculation, improve retrieval efficiency, and realize more stable retrieval performance.

The application provides a sentence processing method and device, electronic equipment and a readable storage medium. When a server for sentence recognition set by an operator acquires voice data to be processed, a first machine learning model or a second machine learning model with different calculation amounts is selected according to the intelligibility of the voice data to be processed, and the sentences in the voice data to be processed are processed by word segmentation and part-of-speech tagging, so as to ensure the accuracy of processing the sentences while improving the speed and efficiency of processing the sentences.

The invention discloses an energy storage project file standard auditing method and device, equipment and a storage medium. The method comprises the steps of obtaining a target project file to be subjected to standard auditing in an energy storage project, and performing file phrase processing on the target project file to obtain project file phrases; for each project file clause, determining a clause comprehensive confidence score of the project file clause according to the project file clause and each predetermined standard specification term; when the clause comprehensive confidence score is smaller than a preset confidence score threshold value, it is determined that the project file clauses do not meet the specification requirement, and when each project file clause meets the specification requirement, it is determined that the target project file meets the specification requirement, so that cross-standard accurate consistency checking can be achieved, and the checking efficiency is improved. The subjectivity and the uncertainty of manual interpretation are effectively avoided, and the accuracy and the reliability of an audit conclusion are remarkably improved.

The present invention discloses a technology for improving user convenience. This computer program causes a computer to function as: a first reception unit that receives an input of a first natural sentence; a first supply unit that, when the input of the first natural sentence is received, supplies first natural sentence data representing the first natural sentence to a natural sentence processing unit; a first acquisition unit that, from the natural sentence processing unit, acquires first object information that is based on the first natural sentence data and that includes first identification information for identifying a first object for each of M1-number of screens among M-number of screens; and a second display control unit that, when the first object information is acquired from the natural sentence processing unit, causes a display device to sequentially display the M-number of screens including the M1-number of screens according to the first object information, the first object being highlighted in each of the M1-number of screens.

The invention discloses a novel intelligent teaching device for a smart classroom, and the device comprises a first fixed plate, the upper end of the front surface of the first fixed plate is fixedly provided with an LED lamp strip, the lower end of the front surface of the first fixed plate is fixedly provided with a microphone, and the front of the first fixed plate is provided with a multimedia display screen. An electrical box is fixedly installed at the middle end of the back face of the first fixing plate, and an image recognition module, a microprocessor main control module, a word database module, a voice recognition module and a sentence processing verification module are sequentially and fixedly installed in an inner cavity of the electrical box from left to right. The physical operation that a student manually shakes the rotating shaft participates in learning, visual presentation of the letter balls, display of the word list, voice interaction of oral sentence making and color feedback of the LED lamp strip are combined, the touch sense, the visual sense and the hearing sense of the student are fully aroused, the interaction mechanism that physical operation and intelligent feedback are deeply fused is adopted, and the learning efficiency is improved. The interestingness of learning and the sense of participation of students are greatly enhanced.