Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

57 results about "Word type" patented technology

Prompt word generation method of large language model and question answering method of large language model

The invention relates to a cue word generation method of a large language model and a question answering method of the large language model, and relates to the technical field of natural languages. The cue word generation method of the large language model comprises the following steps: obtaining an initial cue word, and carrying out semantic classification processing on the initial cue word to obtain classification information of the initial cue word; judging that the dialogue intention of the initial cue word is a preset dialogue intention needing cue word generation; obtaining a cue word template bound with the dialogue intention needing to generate the cue word in advance; initial entity words in the initial cue words are extracted, and target entity words are determined in the initial entity words according to a first entity word type in the cue word template; and replacing the vacant cue word in the cue word template with the target entity word, and taking the replaced cue word template as the target cue word. According to the method and the device, knowledge enhancement can be performed on the initial cue word related to the preset dialogue intention needing to generate the cue word, so that the use of computing resources is reduced.
Owner:HUBEI QIGUANG TECHNOLOGY CO LTD

Differential privacy-based text desensitization method, program product and computing device

Embodiments of the present specification relate to a differential privacy-based text desensitization method, program product and computing device, the method comprising: obtaining a cluster set, any target word in any cluster having a preset replacement probability distribution, the replacement probability distribution being determined based on an exponential mechanism, the probability description module is used for describing the probability of replacing the target word with each word in the cluster; named entity recognition is carried out on an input text to be desensitized, and entity types to which all words belong are determined and comprise entity types preset as sensitive word types; for any target sensitive word belonging to the sensitive word type, judging whether the target sensitive word exists in any cluster of a cluster set, and when the target sensitive word exists in a first target cluster, sampling according to replacement probability distribution of the target sensitive word in the first target cluster to obtain a target replacement word; and replacing the target sensitive word in the to-be-desensitized text with the target replacement word to obtain a desensitized text.
Owner:ANT BLOCKCHAIN TECHNOLOGY (SHANGHAI) CO LTD

Systems and methods for training a model to determine whether a query with multiple segments comprises multiple distinct commands or a combined command

Systems and methods are disclosed herein for training a model to accurately determine whether two phrases are conversationally connected. A media guidance application may detect a first phrase and a second phrase, translate each phrase to a string of word types, append each string to the back of a prior string to create a combined string, determine a degree to which any of the individual strings matches any singleton template, and determine a degree to which the combined string matches any conversational template. Based on the degrees to which the individual and combination strings match the singleton and conversational templates, respectively, strengths of association are correspondingly updated.
Owner:ADEIA GUIDES INC

Content processing method and apparatus, content recommendation method, electronic device, and storage medium

A content processing method and apparatus, a content recommendation method, an electronic device, and a storage medium, relating to the technical field of information processing. The content processing method comprises: obtaining a plurality of pieces of historical content data which have been subjected to social interaction positive feedback in a first virtual interaction scene by a target user, wherein the historical content data comprises words or characters representing content and the semantics of the content; generating a word vector used for representing the words or the characters in the plurality of pieces of historical content data, and a word position vector used for representing the position of the words or the characters; generating a word type vector used for representing the meaning of the words or the characters, and a content position vector used for representing the position of each piece of historical content data among the plurality of pieces of historical content data; generating a user sequence representation on the basis of the vectors; and obtaining a plurality of content sequence representations, and determining a candidate content sequence representation on the basis of the similarity between the user sequence representation and each content sequence representation, content corresponding to the candidate content sequence representation being used to be recommended to the target user.
Owner:NETEASE (HANGZHOU) NETWORK CO LTD

Recommendation method and system based on reinforcement learning driven large model adaptive prompt

The application discloses a recommendation method and system based on reinforcement learning driving large model adaptive prompt, the method comprises the following steps: obtaining user portrait text and performing semantic similarity matching to determine the corresponding prompt word type of the user; through a deep Q network (DQN) and a confidence upper bound algorithm (UCB), a preset multiple prompt optimization strategy is selected to recommend a prompt optimization strategy and obtain the prompt optimization strategy S; based on the prompt optimization strategy S and the corresponding prompt word type of the user, a large model is used to generate an optimized prompt word, a recommendation system is used for verification and performance index evaluation; continue iteration until the preset end condition is met to obtain the optimized prompt word for application in a target recommendation system. The application aims to introduce fine-grained user portraits and reinforcement learning driving large models to optimize personalized prompts for different user groups, solve the problem of rigid soft prompt templates and insufficient personalization in existing recommendation technologies, and improve recommendation accuracy.
Owner:HUNAN NORMAL UNIVERSITY

Semantic recognition method, semantic recognition device, storage medium and electronic device

The present disclosure provides a semantic recognition method, a semantic recognition device, a computer-readable storage medium and an electronic device, and relates to the technical field of natural language processing. The semantic recognition method comprises: obtaining a sentence to be recognized, performing word segmentation processing on the sentence to be recognized according to a semantic template, obtaining a set of words to be recognized and a first template word set corresponding to the set of words to be recognized; determining the evaluation index value corresponding to each word based on each word in the set of words to be recognized and the word type of each word, and calculating the first similarity between the sentence to be recognized and the semantic template using the evaluation index value corresponding to each word; calculating the second similarity between the sentence to be recognized and the semantic template based on the sum of the lengths of each word in the set of words to be recognized and the sum of the lengths of each word in the first template word set; and outputting the first recognition sentence corresponding to the sentence to be recognized based on the first similarity and the second similarity. The present disclosure can improve the recognition rate of semantics and expand the recognition range of semantics.
Owner:BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1

AI generation code identification method based on multi-modal feature fusion model

The invention relates to the technical field of crossing of artificial intelligence and software engineering, and discloses an AI generation code recognition method based on a multi-modal feature fusion model, which comprises the following steps of: obtaining global features of a method source code sample to be recognized, and performing word processing on the whole source code by adopting a sub-word level word processing strategy; distinguishing the sub-words based on the sub-word types to realize sub-word level separation modeling of the code stream and the annotation stream; carrying out fusion through bidirectional cross attention to obtain window-level local semantic representation; splicing the window-level text local representation and the method-level global feature to obtain a window-level fusion vector; inputting the window-level fusion vector into a classifier to obtain a window-level probability set; when the maximum probability in the window-level probability set is larger than a threshold value during prediction, the method is judged to be AI code generation, and otherwise, the method is judged to be human compiled code. According to the method, the generalization ability of the model can be improved, and the detection ability of local AI generated fragments and the engineering application feasibility are improved.
Owner:HANGZHOU DIANZI UNIV

Linear grabbing and transplanting mechanism for graphite boat

The linear grabbing and transplanting mechanism comprises a sealing plate and a profile frame which are fixedly connected, the outer surface wall of the profile frame is connected with a housing in a sliding mode, and the outer surface wall of the housing is fixedly connected with a lower plate through a connecting frame. A longitudinal moving assembly used for grabbing the transplanting mechanism to move longitudinally and a lifting assembly used for vertically moving the housing are integrated on the top of the sealing plate. According to the graphite boat cover plate, the two sets of side edge cylinder bodies are in linkage with the corresponding grippers, the two sets of side edge cylinder bodies are combined to the two opposite sides of the two sets of connecting parts at the top of the graphite boat cover plate correspondingly, then the two sets of middle cylinder bodies drive the corresponding grippers, and the two sets of grippers are combined to the two adjacent sides of the two sets of connecting parts; and the guide wheels, the guide blocks, the centering limiting plates and the boat cushion blocks on the multiple sets of grippers are all arranged in a manner of being attached to the outer contour of the connecting part, so that stable grabbing and transplanting of the graphite boat are realized.
Owner:CHANGZHOU QUANSHENG AUTOMATION CO LTD

Conversation preference data construction method and device, computer equipment and storage medium

The invention relates to a dialogue preference data construction method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring original dialogue data and a corresponding original dialogue reply; respectively constructing dialogue data generation requests for the original dialogue data, the original dialogue reply and a plurality of pre-constructed cue words corresponding to different cue word types, inputting each dialogue data generation request into a plurality of pre-constructed dialogue generation large models corresponding to different architectures, and generating candidate dialogue replies; inputting each candidate dialogue reply and the original dialogue reply as a to-be-evaluated dialogue reply into a plurality of pre-constructed dialogue evaluation large models corresponding to different architectures, and outputting dialogue preference evaluation results for each to-be-evaluated dialogue reply through each dialogue evaluation large model; and generating dialogue preference data based on the dialogue preference evaluation result. By adopting the method, the efficiency of constructing the dialogue preference data can be improved.
Owner:GUANGZHOU QUWAN NETWORK TECH CO LTD

Systems and methods for training a model to determine whether a query with multiple segments comprises multiple distinct commands or a combined command

Systems and methods are disclosed herein for training a model to accurately determine whether two phrases are conversationally connected. A media guidance application may detect a first phrase and a second phrase, translate each phrase to a string of word types, append each string to the back of a prior string to create a combined string, determine a degree to which any of the individual strings matches any singleton template, and determine a degree to which the combined string matches any conversational template. Based on the degrees to which the individual and combination strings match the singleton and conversational templates, respectively, strengths of association are correspondingly updated.
Owner:ADEIA GUIDES INC

Sensitive word type determination method and device

Embodiments of the invention provide a sensitive word type determination method and apparatus. The method comprises the steps of obtaining a to-be-recognized text vector; inputting the to-be-recognized text vector into a three-branch attention model to obtain a sensitive word recognition result and an entity word recognition result, and obtaining a weighted vector of each branch; determining a first sensitive word type corresponding to a sensitive word vector from preset sensitive word types according to the similarity between the sensitive word vector in the sensitive word recognition result and feature vectors of the preset sensitive word types; and according to an entity word vector in the entity word recognition result, the feature vector of the preset sensitive word type and the weighted vector of each branch, performing sensitive word type recognition on the entity word vector to obtain a second sensitive word type corresponding to the entity word vector.
Owner:CHINA TELECOM CORP LTD

GUI (Graphical User Interface) positioning method and system based on routing prediction framework

The invention belongs to the technical field of computers, and discloses a GUI (Graphical User Interface) positioning method and system based on a routing prediction framework. According to the method, a route prediction mechanism based on lexical item type judgment is introduced in the autoregression decoding process of the multi-modal large language model, and an interface semantic generation task and a spatial positioning task are dynamically shunted, so that a user instruction with a target element can jump out of a discrete text generation path; continuous space coordinate regression is directly carried out based on a hidden state and structure enhanced interface image features, and a null positioning result is returned through a special refusal response lexical item when a target element does not exist, so that the coordinate quantization error and illusion positioning problems are effectively avoided under an end-to-end unified framework, the positioning reasoning delay is remarkably reduced, and the positioning accuracy is improved. Precision, real-time performance and robustness of graphical user interface element positioning are improved, and the overall understanding ability of the model for interface structure semantics and spatial layout relation is enhanced.
Owner:ZHEJIANG UNIV

BLS-based intelligent decision support method for navtex message context

ActiveCN116756311BSemantic analysisBiological modelsContext classificationEngineering
The application discloses a BLS-based NAVTEX message context intelligent decision support method, applies data cleaning, word type reduction and reference stop word operations to NAVTEX message data, and proposes a message context label to mark the categories of the message, which specifically shows that the message content contained in the navigation warning is analyzed, and six categories of message context labels are summarized.Through the application, effective information in the original message data can be accurately extracted, and strong support is provided for subsequent message context classification tasks and navigation decision support, so that the trained message features are more concise and representative.The application is based on BLS and is improved, the accuracy of the NAVTEX message context classification is improved, intelligent navigation decision support services are provided for the mariners, the working strength can be effectively reduced and the working efficiency can be improved, meanwhile, the safety navigation performance of the ship is further enhanced, and the function of the navigation aid equipment is enriched.
Owner:DALIAN MARITIME UNIVERSITY

Text de-sensitization method, program product, and computing device based on differential privacy

Embodiments of the present specification relate to a text desensitization method based on differential privacy, a program product and a computing device. The method comprises: obtaining a cluster set, any target word in any cluster has a preset replacement probability distribution, the replacement probability distribution is determined based on an exponential mechanism, and is used to describe the probability of replacing the target word with each word in the cluster; performing named entity recognition on the input text to be desensitized to determine the entity type to which each word belongs, which includes an entity type preset as a sensitive word type; for any target sensitive word belonging to the sensitive word type, it is judged whether it exists in any cluster of the cluster set, when the target sensitive word exists in a first target cluster, a target replacement word is obtained by sampling according to the replacement probability distribution of the target sensitive word in the first target cluster; and the target sensitive word in the text to be desensitized is replaced with the target replacement word to obtain a desensitized text.
Owner:ANT BLOCKCHAIN TECHNOLOGY (SHANGHAI) CO LTD

Method for realizing automatic transcription of hot word extraction specification based on NLP

The invention discloses an NLP-based method for realizing automatic transcription of hot word extraction specifications, which comprises the following steps of: presetting different scenes, defining hot word types in the scenes and constructing a common hot word library, and preprocessing and cleaning a document; automatically analyzing the cleaned context data, and automatically extracting hot words in the corresponding file content; the extracted hot words are intelligently classified, and a dynamic hot word library is constructed; meanwhile, a voice transfer result is transferred into a hot word verification module in real time; carrying out semantic analysis according to the context of the voice recognition result, judging the most coincident hot word, and carrying out replacement display on the extracted hot word result; according to the method, a normalized result of hot word replacement is displayed, a text result of speech recognition is automatically adjusted, weights of hot words in a dynamic hot word library are updated in real time, representative hot words are extracted from preprocessed texts based on a trained NLP semantic model by applying technologies such as a clustering algorithm and topic analysis, and the accuracy of transcription is improved.
Owner:JIANGSU ZHONGWEI TECH SOFTWARE SYST

Traffic network security event extraction method and system based on machine reading understanding

The invention relates to a traffic network security event extraction method based on machine reading understanding, which performs joint training and optimization on a trigger word prediction module and an argument extraction module by sharing a coding layer of a pre-training language model, so that two tasks promote each other in a shared semantic space. Accurate context constraints are provided for argument role judgment through trigger word recognition, disambiguation of trigger word types is facilitated through argument information, and the deep interactive optimization mechanism enables the model to learn collaborative representation sensitive to the whole event structure. Therefore, the overall accuracy of event extraction and the generalization ability of the model are remarkably improved, and the inherent error propagation problem in a traditional assembly line method is solved.
Owner:TSINGHUA SHENZHEN INTERNATIONAL GRADUATE SCHOOL

planing tool (straight)

1. Name of the designed product: planer blade (one word type). 2. Use of the designed product: for peeling. 3. Design points of the designed product: in shape. 4. Picture or photo best showing the design points: perspective view 1.
Owner:张木清

Word-award kitchen garbage classification box with recognition function

The invention discloses a prize word type kitchen garbage classification box with a recognition function, and relates to the field of garbage disposal, the prize word type kitchen garbage classification box comprises a classification box body, an internal processor and a kitchen garbage barrel, the kitchen garbage barrel is made of an easy-to-clean and corrosion-resistant material, and a chip is arranged in the side wall of the kitchen garbage barrel; a recognition cavity and a cleaning cavity are formed in the two sides of the face, close to the human body, of the classification box body correspondingly, a detection assembly is arranged on the inner wall of the recognition cavity and used for recognizing and detecting the kitchen waste barrels, a cleaning assembly is arranged in the cleaning cavity, an interaction screen is installed on the portion, located above the recognition cavity, of the outer wall of the classification box body, and a processor is arranged at the portion, located on the interaction screen, in the classification box body. The processor is provided with a resident data management module, a database, an image recognition module, an accounting module, a voice playing module and a software intercommunication module. According to the garbage can, the trouble of bag breaking can be solved, meanwhile, the inner wall of the can does not need to be manually cleaned after garbage is thrown, pollutant residues are avoided, and kitchen garbage is thrown for digital treatment.
Owner:ZHONGKE GIANT ARTIFICIAL INTELLIGENCE TECH (GUANGZHOU) CO LTD

Information model generation method and device, controller, medium and product

ActiveCN118821764BAlgorithmEngineering
The application discloses a method and device for generating an information model, a controller, a medium and a product. The method comprises: obtaining description information corresponding to a device measuring point; performing word segmentation processing on the description information to obtain word segmentation results corresponding to N preset professional word types, N being an integer greater than 1; performing mapping processing on the corresponding word segmentation results according to the preset professional word types to obtain information identifiers corresponding to the word segmentation results; and generating an information model corresponding to the device measuring point based on the N information identifiers. The method can avoid the understanding of the description information corresponding to the device measuring point by different people from being biased, the information model from being greatly different, the use effect of the information model from being affected, and the generation efficiency of the information model from being improved.
Owner:BEIJING JINFENG HUINENG TECH CO LTD

Template bridge-based machine reading comprehension event extraction method and device, and medium

The application discloses a machine reading comprehension event extraction method and device based on template bridging, and medium, the method steps comprise: step S01. Input text and trigger word question template are obtained and combined to form an input instance with a trigger word question prompt template; step S02. Syntax analysis is performed on the input instance to form an adjacency graph, the input text and the trigger word question prompt template are connected according to the adjacency graph to obtain a link graph, and global features are extracted according to the link graph; the global features and semantic features are fused to identify the trigger word and the trigger word type; step S03. A argument question prompt template is generated, the prompt template is combined with the input text to form an input instance with a question prompt template; step S04. Argument extraction is performed to obtain argument and argument type output. The application has the advantages of simple implementation method, high event extraction efficiency and precision, good portability and the like.
Owner:NAT UNIV OF DEFENSE TECH

DATA STORAGE AND LANGUAGE TRANSLATING METHODS

This invention proposes a method for storing and converting data in a language. Its purpose is to improve the efficiency of machine translation, text storage, and processing. The method includes the following steps: + Creating a data structure; the invention stores data object-based rather than the current character-based method. Synonyms can be represented by a common value. + Converting ordinary text into the data format of the invention. Identifying and storing characteristic values ​​such as input language, word type, grammar, vocabulary, etc. + Converting the data of the invention into text or other formats such as audio, images, and symbols. Identifying factors to select appropriate data.
Owner:NGUYEN DUY THANG

Recommendation method and system based on reinforcement learning driving large model adaptive prompt

The invention discloses a recommendation method and system based on reinforcement learning driving large model self-adaptive prompt. The method comprises the steps of obtaining a user portrait text and performing semantic similarity matching to determine a prompt word type corresponding to a user; selecting a recommended prompt optimization strategy from a plurality of preset prompt optimization strategies through a deep Q network DQN and a confidence upper limit algorithm UCB, and obtaining a prompt optimization strategy S; based on a prompt optimization strategy S and a prompt word type corresponding to the user, utilizing a large model to generate an optimized prompt word, and utilizing a recommendation system to perform verification and performance index evaluation; and continuing iteration until a preset end condition is met to obtain an optimized prompt word to be applied to a target recommendation system. According to the method, a mechanism for carrying out personalized prompt optimization on different user groups by introducing a fine-grained user portrait and a reinforcement learning driven large model is adopted, so that the problems of stiffness and insufficient personalization of a soft prompt template in the existing recommendation technology are solved, and the recommendation accuracy is improved.
Owner:HUNAN NORMAL UNIVERSITY

Content processing method and device, content recommendation method and device, electronic equipment and storage medium

The invention provides a content processing method and device, a content recommendation method and device, electronic equipment and a storage medium, and relates to the technical field of information processing. The content processing method comprises the following steps: acquiring a plurality of pieces of historical content data subjected to social interaction positive feedback in a first virtual interaction scene by a target user, wherein the historical content data comprises words or characters representing contents and semantics of the contents; generating word vectors for representing words or characters in the historical content data and word position vectors for representing word or character positions; generating a word type vector used for representing word or character meanings and a content position vector used for representing the position of each piece of historical content data in the multiple pieces of historical content data; generating a user sequence representation according to the vector; obtaining a plurality of content sequence representations, and determining candidate content sequence representations according to the similarity between the user sequence representation and each content sequence representation; the content corresponding to the candidate content sequence characterization is recommended to the target user.
Owner:NETEASE (HANGZHOU) NETWORK CO LTD

Biomedical event assembly methods, apparatuses, devices, and media

This application discloses a biomedical event assembly method, apparatus, device, and medium, relating to the field of natural language processing technology. The method includes: combining trigger words and arguments of the text to be assembled based on their trigger word types to obtain candidate events; tagging the trigger words and arguments of the candidate events using a nested tagging method to obtain candidate instances; encoding the candidate instances using a preset deep learning model to obtain an output representation of the semantic information of the candidate instances; acquiring a first probability result for a preset legal category and a second probability result for a preset illegal category of the output representation; and then determining a target biomedical event from the candidate events based on the first and second probability results. This method can improve the performance of biomedical event assembly.
Owner:SUZHOU UNIV

A controllable concurrent data desensitization method and device based on Chinese-English sensitive dictionary

The present invention proposes a controllable concurrent data desensitization method and device based on a Chinese-English sensitive dictionary. The method comprises the following steps: obtaining the data to be desensitized from the metadata library, and synchronizing the table structure of the data to be desensitized to the metadata table in the parameter library; configuring the Chinese-English sensitive dictionary table; associating the metadata table with the Chinese-English sensitive dictionary table, obtaining the table name of the metadata table with sensitive fields and storing it in file A; looping through the table names in file A, creating an isomorphic table corresponding to file A, obtaining the table structure of the isomorphic table and storing it in file B; obtaining the fields in file B and comparing them with the Chinese-English sensitive dictionary table, performing desensitization conversion according to the sensitive word type, and generating a desensitization script; inputting concurrent parameters, and executing the desensitization script concurrently to complete data desensitization. The present invention changes the value of the data while preserving its original characteristics, so that the data can still be used normally by the business while avoiding the risk of data leakage.
Owner:JIANGSU SUNING BANK CO LTD

Audio playing control method and device, and electronic device

This invention provides an audio playback control method, apparatus, and electronic device, relating to the field of voice processing technology. The audio playback control method includes: acquiring a sampled signal and inputting it into a voice wake-up model to obtain the confidence level of the sampled signal containing a wake-up word, the voice wake-up model being used for wake-up word detection; if the confidence level is greater than a preset confidence level, extracting a signal segment containing the wake-up word from the sampled signal and inputting this segment into a type recognition model to obtain the category of the wake-up word output by the type recognition model, the type recognition model being used for wake-up word type recognition; if the category is a call intro wake-up word and the electronic device is detected to be playing audio, adjusting the current audio playback state of the electronic device. The technical solution of this invention can automatically adjust the audio playback state of an electronic device when a user connects to a callable device.
Owner:SOUNDAI TECH CO LTD

A DGA Domain Name Detection Method for IoT Botnets

The present invention belongs to the field of Internet of Things security technology, and discloses a DGA domain name detection method for the Internet of Things botnet, including: obtaining the domain name string in the DNS domain name resolution request sent by the Internet of Things device; inputting the domain name string into the trained domain name detection model to obtain the binary classification and multi-classification results of the domain name; wherein, the domain name detection model is obtained by training based on the fusion network of the Small BERT pre-trained model and CNN. By combining the two feature extraction capabilities of the SmallBERT model at the sub-word granularity for domain names and CNN at the character granularity for domain names, the present invention improves the learning ability of the algorithm for the comprehensive features of domain name semantics, morphology, pronunciation, character randomness, etc., enhances the detection performance for random word type DGA domain names, improves the problem of performance imbalance in the domain name multi-classification task, meets the requirements of limited computing resources and high inference speed in the Internet of Things environment, and has the advantages of high detection performance, simple process, easy deployment, and wide available range.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Construction method of code word type EP code based on finite field resource and finite field multiple access method thereof

The application discloses a construction method of a code word type EP code based on a finite field resource and a finite field multiple access method thereof, and belongs to the technical field of 6G communication. j The application discloses a construction method of a code word type EP code based on a finite field resource and a finite field multiple access method thereof, and belongs to the technical field of 6G communication. The application discloses a construction method of a code word type EP code based on a finite field resource and a finite field multiple access method thereof, and belongs to the technical field of 6G communication. The application discloses a construction method of a code word type EP code based on a finite field resource and a finite field multiple access method thereof, and belongs to the technical field of 6G communication. The application discloses a construction method of a code word type EP code based on a finite field resource and a finite field multiple access method thereof, and belongs to the technical field of 6G communication.
Owner:HARBIN INST OF TECH

Methods and apparatus for determining sensitive word types

The embodiment of the application provides a sensitive word type determination method and device, the method comprises: obtaining a to-be-recognized text vector; inputting the to-be-recognized text vector into a three-branch attention model to obtain a sensitive word recognition result and an entity word recognition result, and obtain a weighting vector of each branch; determining a first sensitive word type corresponding to a sensitive word vector in the sensitive word recognition result from a preset sensitive word type according to the similarity between the sensitive word vector and a feature vector of the preset sensitive word type; and performing sensitive word type recognition on an entity word vector in the entity word recognition result according to the entity word vector, the feature vector of the preset sensitive word type and the weighting vector of each branch, to obtain a second sensitive word type corresponding to the entity word vector.
Owner:CHINA TELECOM CORP LTD

Text processing method and apparatus, device, medium

ActiveCN114996458BImprove the efficiency of obtaining informationWeb data indexingSemantic analysisPattern recognitionWord group
The embodiment of the application provides a kind of text processing method and device, equipment, storage medium, belong to artificial intelligence technical field.The method comprises: by text extraction processing to original corpus, extract the preliminary abstract text that can express the meaning of original corpus most, again according to the preset segmented text length, preliminary abstract text is divided, and target segmented text is obtained.Target segmented text is filtered to determine target candidate word group, and target candidate word group semantic analysis processing is handled, the importance of word segmentation can be determined by the word type of word segmentation, and according to the word type of word segmentation, word segmentation is linked to the preset upper and lower cognitive graph, and target upper and lower cognitive graph is obtained.Because the upper and lower information of each word segmentation and the connection between each word segmentation can be easily obtained through target upper and lower knowledge graph, therefore, the efficiency of obtaining information can be improved by the text processing method of the embodiment of the application.
Owner:CHINA PING AN LIFE INSURANCE CO LTD