44 results about "Adverb" patented technology

The invention discloses a user semantic sentiment analysis-based response method. A specific implementation manner of the method comprises the following steps: acquiring text information of input information of a user; carrying out word segmentation on the text information on the basis of a pre-determined word segmentation method, extracting at least one keyword, modifying a plurality of sentiment feature words of each keyword and modifying an adverb of each sentiment feature word; analyzing a sentiment tendency metric of each sentiment feature word according to a pre-established commendatory term dictionary, a pre-established derogatory term dictionary and a negative adverb dictionary, and analyzing semantic sentiment classification of the text information according to the sentiment tendency metric of each sentiment feature word; selecting a sentence from a pre-stored sentence set according to the semantic sentiment classification of the text information and the at least one keyword to respond the input information. According to the method, the questions of the users are answered in the aspect of logic, the sentiments of the users are considered at the same time, and the satisfaction of the users is improved.

The invention discloses an SVM based micro-blog emotion classification method fusing various kinds of emotion resources. The method includes the following steps: constructing relevant dictionaries including an emotion dictionary, a negation dictionary, and a degree adverb dictionary; performing pretreatment on different corpora, performing word segmentation and part-of-speech tagging on the corpora, and performing sentence structure analysis; comparing the segmented words and positive and negative dictionaries to acquire initial word polarity, comparing words ahead of emotion words and the word degree grade dictionary and the negation dictionary to acquire modifier weight, and multiplying the initial word polarity by the modifier weight to acquire emotion scores of each micro-blog; extracting features such as nouns, verbs, adjectives, positive and negative emotion words, degree adverb weights, emotion scores, privatives and specific symbols from part-of-speech features, emotion features, sentence pattern features, and semantic features; and inputting the extracted features into an Libsvm to perform model training so as to acquire a training model. The method can achieve emotion 5-grade classification of micro-blogs, and can accurately and roundly acquire emotion tendency of netizens.

The invention discloses a part-of-speech-tagging-based dictionary construction method applied in shopping comment emotion analysis. The method comprises the steps of conducting pre-treatment on text data of a shopping comment, in other words, conducting segmentation and word segmentation on a comment text, filtering out words which are not used any more, and partitioning shopping domains; constructing a basic emotion dictionary and a network buzzword emotion dictionary; taking a shopping comment corpus as a data set, conducting part-of-speech tagging on the data set, extracting words with the part-of-speech as habitually used words, adverbs and adjectives as candidate words, selecting new emotion words as domain emotion words by calculating the PTF-IDF values of the candidate words, and adding the domain emotion words to a domain emotion dictionary. The domain emotion dictionary is combined with the basic emotion dictionary and the network buzzword emotion dictionary, emotional characteristic screening and extraction are conducted on the shopping comment, and the emotion classification of the shopping comment is studied. It is shown through experiments that the method is high in accuracy rate, free of limitation of shopping domains and more suitable for practical application.

The present invention is directed to a system for managing business knowledge expressed as statements, preferably sentences using a vocabulary, where such statements may be automated by the generation of programming language source code or computer program instructions. As such, the present invention also manages software design specifications that define, describe, or constrain the programming code it generates or programs with which it or the code it generates is to integrate. All information managed within the present invention is maintained within a relational database that is encapsulated within an object-oriented model. Each object in this model is subject to version control and administration using permissions. Each user of the system is an object and belongs to one or more groups. Users and groups may be granted privileges. Objects may be created, examined, used, modified, deleted, or otherwise operated upon only if corresponding permission or privilege has been granted. The vocabulary managed by the present invention consists of the function words commonly used in a language, such as the auxiliary verbs, prepositions, articles, conjunctions, and other essentially closed parts of speech in English, as well as open parts of speech, such as nouns, verbs, adjectives, and adverbs.

The invention discloses a robot system based on intelligent sound localization and voice control, and a method. A robot body collects ambient voice information continuously, when a voice command occurs, sound localization is conducted, the robot body is controlled to move to the sound source position, the collected voice information is recognized, when effective sentences are recognized, a corresponding control command is sent to the robot body, and the robot body executes corresponding operation; and meanwhile, the effective sentences are converted into corresponding characters so that Chinese word segmentation can be carried out, an affective dictionary, a degree adverb dictionary, a negative word vocabulary and an associated word vocabulary are loaded, all affective characters in the sentences are identified, and a corresponding facial expression is displayed according to the identification result. Through the robot system based on intelligent sound localization and voice control, and the method, the interactive ability of a service robot with an accompanied person can be improved.

The invention provides a construction method for an Internet product review excavation noumenon lexicon. The method comprises the steps that 1, attribute word noumenon lexicons are constructed: product reviews are acquired, and nouns are extracted using a word classification method and a part-of-speech tagging method according to product categories to form the attribute word noumenon lexicons; 2, an evaluation word noumenon lexicon is constructed; 3, a negative word noumenon lexicon is constructed: negative words are collected to construct the negative word noumenon lexicon; 4, a matched emotional word noumenon lexicon is constructed: matched feature words in the reviews are matched with corresponding matched emotional words according to the different kinds of product reviews based on the categories on the Internet to construct the matched emotional word noumenon lexicon; 5, a degree adverb noumenon lexicon is constructed: degree adverbs are collected for modifying the emotional words, and intensity levels and intensity values are given to the degree adverbs; 6, a stop word noumenon lexicon is constructed. According to the construction method for the Internet product review excavation noumenon lexicon, the query efficiency and the hit rate can be effectively promoted.

The invention provides a video and bullet screen combined emotion analysis and visualization method, and belongs to the field of natural language processing and image processing. The method comprisesthe following steps: crawling videos and bullet screen data by using crawlers; preprocessing the crawled data; training a faster R-CNN model, identifying an object and marking an emotion value, then matching emotion words, degree adverb, emoji and negative words, calculating a bullet screen emotion value, and finally calculates a relation trend graph of an emotion value (S (t))-time (t) by combining the emotion value and the bullet screen emotion value of the video object. The method is suitable for network video bullet screens of various themes, and can be used for analyzing content emotion orientations with different fine granularities integrally or locally to obtain an emotion curve graph of the whole video. For the problems that the network video bullet screen content is diverse in structure, complex in symbol and difficult to process, the invention further provides a network video bullet screen standardized processing method.

A method for automatically analyzing the text of a document to generate verification questions to be administered to a user as a quiz for the purpose of verifying whether the user has read the document. Syntactic analysis is applied to statements (e.g. sentences) in the text to automatically generate various types of verification questions, including fill-in-the-blank, true / false, and multiple-choice questions. Nouns and proper nouns in a statement may be used to generate fill-in-the-blank questions; numerical values may be used to generate fill-in-the-blank, true / false and multiple-choice questions; and verbs, adjectives and adverbs may be used to generate true / false questions. The questions may be generated dynamically for each user, or generated once, stored and used for multiple users.

The invention provides a knowledge base construction method based on short text comments, belongs to the field of natural language processing, and aims at providing related world knowledge for short text analysis so as to overcome the defects of existing short text analysis. High combination of short text analysis statistics and analysis with grammatical rules is achieved. By constructing a knowledge base of the related comments, relevant characteristic words, characteristic word matching, evaluation words and grading, and degree adverbs and grading in the related comment field are obtained. By constructing the knowledge base of the related comments, in short text analysis, the comment knowledge database can be used for conducting public opinion analysis, emotion analysis and information extraction, and accuracy and efficiency of related work are improved.

The invention discloses an electric power customer service work order sentiment quantitative analysis method based on Word2Vec, and relates to an electric power customer service work order analysis method. A traditional sentiment analysis method cannot effectively discriminate the sentiment intensity. The method of the invention comprises the steps of combining the power customer service work order text features; classifying and sorting the historical electric power customer service work orders and the unsatisfied work orders, cleaning data, combing based on the Baidu word bank to form an initialized multivariate emotion word bank; carrying out the work order text word segmentation by adopting a reverse maximum matching algorithm; based on the Word2Vec neural network, constructing the positive words, negative words, degree adverbs and a word vector of a word order fused with customer appeal semantics; performing the machine learning training through the historical customer service workorder to generate a learning model fusing appeal emotion, expanding a part-of-speech corpus based on the part-of-speech affinity-consanguinity relationship in the model, performing emotion quantization calculation by adopting a similarity word sequence matrix quantization algorithm, and completing customer service work order emotion quantization analysis, thereby effectively distinguishing emotion intensity differences, and determining an emergency degree.

The invention provides a Chinese sentiment analysis method and system. The method comprises the following steps that: obtaining all sentiment words in Chinese statement, and obtaining the positive sentiment weight and the negative sentiment weight of each sentiment word; obtaining an adverb corresponding to each sentiment word in the Chinese statement, obtaining the weight of the corresponding adverb, and revising the positive sentiment weight or the negative sentiment weight of the sentiment word according to the weight of the corresponding adverb; obtaining a negative word corresponding to each sentiment word from the Chinese statement, and regulating the revised positive sentiment weight and negative sentiment weight according to the number of the negative words; and according to all sentiment words, through corresponding adverb weight and the positive sentiment weight or the negative sentiment weight of which the number of the negative words is regulated, and obtaining Chinese statement sentiment tendency. By use of the method, the adverb corresponding to the sentiment word is considered when the sentiment tendency of the Chinese statement is analyzed, the method has an abilityof analyzing sentiment exquisiteness, the negative words are considered, and sentiment analysis accuracy is improved.

The invention relates to the field of sentiment classification, in particular to a financial field comment sentiment classification method and system based on a sentiment dictionary. The method specifically comprises the following steps: 1, preprocessing a to-be-analyzed financial field comment text to obtain a word list of the text; 2, inputting the word list obtained in the step 1 into a sentiment dictionary for sentiment positioning, and positioning sentiment words, degree adverbs and negative words in the sentiment dictionary; and 3, calculating a text sentiment value according to the positioned sentiment words, degree adverbs and negative words. The emotion dictionary is applied to the financial field, and timeliness and pertinence of the emotion classification model are improved.

The invention discloses a word sense disambiguation method and system based on a graph model, and belongs to the field of natural language processing technology. The technical problem to be solved bythe present invention is how to combine multiple Chinese and English resources, complement each other's advantages, realize full exploitation of disambiguation knowledge in resources, and improve wordsense disambiguation performance.The technical scheme adopted is as follows: 1, a word sense disambiguation method based on graph model, comprising the following steps: S1, extracting contextual knowledge: carrying out part-of-speech tagging on ambiguous sentences, extracting substantive words as contextual knowledge, wherein the substantive words refer to nouns, verbs, adjectives and adverbs; S2, similarity calculation: performing similarity calculation based on English, similarity calculation based on word vector and similarity calculation based on HowNet; 3, constructing a disambiguation graph; S4, performing the correct choice of word meaning. 2, A word sense disambiguation system based on graph model, which comprises a context knowledge extraction unit, a similarity calculation unit,a disambiguation graph construction unit and a word sense correct selection unit.

The invention discloses a Chinese clause emotion polarity distinguishing method based on a context. The method comprises the following steps of: (1) marking a Chinese word and the work property in a Chinese clause to obtain a respective characteristic value, a privative, an adverb and an emotion word in each Chinese clause; matching the emotion word and the emotion word of the Chinese clause; determining the emotion polarity of the emotion word to obtain the emotion polarity of the Chinese clause; (2) calculating the emotion strength degree of each Chinese clause according to the adverb in the Chinese clause; and (3) extracting a conjunction in the Chinese clause; and with regard to three adjacent Chinese clauses, revising the emotion polarity of the Chinese clause of the step (1) according to the conjunction and the emotion strength degree of the adjacent Chinese clauses. According to the Chinese clause emotion polarity distinguishing method based on the context, the working amount of manual work can be obviously reduced and the accuracy in distinguishing the emotion of the Chinese clauses in the complicated language environment can be effectively improved.

The invention relates to a context similarity calculation-based word sense disambiguation method. The method comprises the steps of processing training corpora, and training a model by using a part-of-speech tagging version of ukWaC; screening parts of speech, and only reserving notional words including nouns, adjectives, adverbs and verbs; training a bidirectional LSTM model by using the corporasubjected to part-of-speech screening; inputting example sentences of to-be-disambiguated words to the bidirectional LSTM model to obtain context vectors; inputting contexts of the to-be-disambiguatedwords to the bidirectional LSTM model to obtain context vectors of the to-be-disambiguated words; and calculating cosine similarity for the context vectors of the to-be-disambiguated words and the context vectors of the example sentences, and further selecting semanteme of the to-be-disambiguated words by utilizing a k-neighbor method according to an obtained similarity result. According to the method, the semanteme is better modeled; the words and the parts of speech are combined by using an underline behind the words directly; obtained word vectors well distinguish different parts of speechof the same word; and the disambiguation accuracy is improved by 0.5% on an experimental basis of baselines.

The invention discloses a sentiment analysis method and device of text information and relates to the technical field of networks, and the sentiment analysis accuracy of the text information can be improved. The method comprises the steps as follows: each sentiment phrase in the text information is extracted, wherein each sentiment phrase comprises a sentiment word and a sentiment modifying adverb; a sentiment orientation intensity value corresponding to each sentiment phrase is calculated according to a sorting combination mode of the sentiment word and the sentiment modifying adverb in the sentiment phrase; and the sentiment orientation intensity value of the text information is determined according to the sentiment orientation intensity value corresponding to each sentiment phrase in the text information and the sentiment orientation of the text information is determined according to the sentiment orientation intensity value of the text information. The sentiment analysis method and device are suitable for sentiment analysis of the text information.

The invention provides an emotion analysis method of automobile review based on automobile ontology and part-of-speech rules, which comprises the following steps: a dictionary of automobile ontology,an emotion dictionary and an emotion adjustment dictionary are constructed; Get user comments on the car; The emotion words, negative words and degree adverbs in the comments are identified accordingto the emotion dictionary and the emotion adjustment dictionary, and the automobile feature words in the comments are identified according to the ontology dictionary of automobile field and mapped tothe corresponding automobile performance dimension. Extracting part-of-speech rules from user comments, constructing an effective set of part-of-speech rules for affective analysis; The correspondingemotion comment sentences are extracted from the comment sentences by the part-of-speech rule set. According to the emotion dictionary, degree dictionary and adjustment dictionary, the comprehensive emotion values corresponding to the vehicle performance dimension in the car review are calculated respectively, and the fine-grained and digital emotion values of the users are obtained.

The present invention provides a method and apparatus for defining verbs and adverbs. The method includes creating at least one of a verb and adverb, wherein the at least one of a verb and adverb are adapted to form sequences and the sequences are adapted to create errors in a system. The method further includes defining attributes of the at least one of a verb and adverb.

The invention discloses a method for intelligently analyzing a Chinese character emotional tendency through a computer. The method is characterized by comprising reading Chinese character paragraph files, segmenting the Chinese character paragraph files and performing word segmentation, part-of-speech tagging and syntactic interdependent relationship marking on segmentations to form extensible markup language (EML) files; reading the EML files, going through sentence extraction syntactic interdependent relationship pairs and assigning extracted words based on a dictionary, wherein a word in a positive word dictionary is assigned with 1, and a word in a negative word dictionary is assigned with -1; degree adverbs are divided into 5 grades according to degrees and assigned with 1.8, 1.5, 1.2, 0.9 and 0.5 respectively; and negative adverbs can be divided into -1 and -1.5 grades according to negative degrees; and going through the dictionary according to a formula: emotional score= negative words* adverb sum* adjectives and obtaining the emotional score of the Chinese character paragraph files; and the emotional tendency of the Chinese character paragraph files is judged according to the emotional score.

The invention relates to a method for embedding and extracting a frequency domain watermark in an English text, belonging to the technical field of computer file protection. The method comprises acquiring an adjective or an adverb w from the English text T; finding a synonym assembly Sw from w as a dimension of a vector vc in the text T; finding an agent word wd from w; performing Hash operation to private key information k of a copywriter of the file to obtain a long integer R; dividing R by a preset grouping number n, (n is a positive integer) to obtain a grouping number i of the current Sw; performing single-direction Hash operation of each word ws in Sw with k, determining the oddity of the obtained remainder, and respectively adding into an assembly Ai and an assembly Bi; using the number of words ci of Ai as the vector vc of the English text T; setting a watermark vector vw corresponding to the text vector vc as the watermark information to be embedded or extracted. The method also comprises embedding and watermark detecting steps. The invention can be used for the original text protection.

The invention discloses a Chinese emotion word polarity intensity quantification method oriented to rank of words, and belongs to the field of processing of natural language of computers. Firstly, an emotional tendency value of each word in an emotion dictionary is obtained, then, according to the emotional tendency values of the words, polarity intensity measurement values of measured basic emotion words are obtained, and finally, according to the polarity intensity measurement values of the basic emotion words, polarity intensity measurement values of compound emotion words are obtained. Compared with the prior art, due to the fact that the Gaussian distribution function is adopted to correct emotional tendency value errors of the words obtained through statistics, the accuracy rate of the polarity intensity measurement of the basic emotion words is substantially improved. The compound emotion words are classified in detail on the basis, the computational formulas obtained through reverse derivation of the Sigmoid function are designed respectively, and the polarity intensity measurement accuracy rate of the compound emotion words is substantially improved. Besides, the Sim(A,B) function is introduced, adverbs are automatically classified through the HowNet, manual labeling workloads are reduced, and working efficiency is improved.

The invention relates to an emotion analysis method for Douban network movie comments, which is mainly used for carrying out emotion analysis on Chinese movie comments on the Douban network, and comprises the following steps of: firstly, carrying out data crawling operation on the movie comments on the Douban network, and then carrying out preprocessing operation on the data, including deleting stop words, segmenting words and tagging part of speech; secondly, constructing four types of dictionaries required for movie comment sentiment analysis, wherein the four types of dictionaries are respectively a basic sentiment dictionary, a negative word dictionary, a degree adverb dictionary and a sentiment dictionary in the movie comment field; carrying out emotion calculation on the movie comments by utilizing a designed emotion calculation method to judge emotion polarity; then performing emotion polarity judgment on the comments by utilizing the weak annotation information of the user scores; wherein if the comment emotion polarity obtained through emotion calculation is consistent with the comment emotion polarity judged by the weak annotation information, the emotion polarity of themovie comment can be obtained, and if the comment emotion polarity obtained through emotion calculation is not consistent with the comment emotion polarity judged by the weak annotation information, the emotion polarity of the movie comment is judged according to emotion calculation.

The invention relates to a machine language information processing technology. For the purpose that the machine imitates logic thinking method of human body to understand language and master grammar function, a presentation can be made from sentence structure of a subject, a predicate, an object, an attribute, an adverbial modifier and a complement to theory and application of a noun, a verb, an adjective, a quantifier, an adverb and a function word, and the analysis process of the function of each part can be demonstrated to be used as language teaching demonstration and provide basic exercise for language learning. The method provides each language with a grammar function of analyzing, judging and understanding language information, the grammar function is established on a commonly used and communicating platform, so that the machine can not only recognize language information, but also apply the language information to inter-translate and exchange between languages.

The invention discloses a fixed topic-based text sentiment orientation classification method and belongs to the field of text sentiment orientation classification. The method comprises the steps of first finding out a topic of a sentence, calculating sentiment orientations before and after the topic by two steps according to the position of the topic in the sentence separately, and finally calculating a sentiment orientation of the topic. Sentiment symbols in the sentence are found out by utilizing characteristic sentiment symbols and a common sentiment dictionary; negative words and degree adverbs are searched for between topic words and the sentiment symbols, and the influence of the negative words and the degree adverbs on the sentiment symbols is calculated; and a connection relationship is searched for between the sentiment symbols, and the sentiment orientation of the topic is calculated. According to the method, a user can be assisted to obtain orientation degrees of other users to important attributes of a product, a service, an event or a character, and subdivide sentiment orientations of related users to the aspects of characteristics of the product, the event or the character.

The present invention provides a commodity performance evaluation method through network evaluation test guiding. The method comprises: a, obtaining all the evaluation tests of the commodity from the network aiming at the commodity requiring performance evaluation; b, performing preprocessing of the obtained commodity evaluation test, comprising works such as removing stop words, performing participle, marking phrase and the like; c, obtaining the evaluation object of the commodity according to the processed evaluation test, namely the commodity features which clients may pay attention to, and calculating the weight of the evaluation object; d, performing preprocessing of each comment of the commodity, constructing the evaluation object vector, and performing normalization processing; e, extracting the emotion words related to the evaluation object, and giving emotion polarity, and extracting the privative words and the adverb of degree related to the emotion word and giving a weight; and f, according to the obtained data, calculating the emotion polarity of each comment so as to obtain the emotion polarity of all the evaluation texts.

The invention relates to the technical field of natural language processing, and specifically relates to a historical classics word segmentation method based on word alignment. The historical classics word segmentation method comprises following steps of firstly, carrying out word segmentation on the modern Chinese language in parallel corpora, splitting ancient Chinese prose word for word, and carrying out word alignment on the ancient Chinese prose and the modern Chinese language by means of an IBM Model 3 model; secondly, processing the alignment result obtained in the last step, and eliminating interference of punctuation marks and adverbs; thirdly, merging ancient words in dependence on the processed alignment result obtained in the last step; and finally, verifying words formed by three or more characters in the word segmentation result. According to the invention, on the premise that ancient Chinese tagged corpora are lacked, word segmentation of historical classics is effectively achieved; compared with a word segmentation method trained by modern Chinese tagged corpora, the historical classics word segmentation method based on word alignment is advantaged in that the word segmentation accuracy is greatly improved.

The invention relates to a text TF-IDF feature reconstruction method combined with emotion intensity. According to the present invention, the expressions and the user names are extracted and segmentedthrough a regular matching method, the word intensity is corrected according to an intensity dictionary and the position relation of the negative words, the degree auxiliary words and the repeated words, and the new words are replaced through a synonym replacement method based on Word2Vec, so that the TF-IDF feature vectors of the text are reconstructed. Compared with the prior art, the TF-IDF features of the words are corrected by considering the conditions of negative words, degree auxiliary words, repeated words and the like, the information, such as the strength, positions, etc., of the words is reserved, the new words on the test set are replaced with the mature words appearing in the training set to enhance the generalization performance, and when the method is used, an original sentence can be directly used as input, and the manual word segmentation is not needed.

A method, system and computer program product for presenting tags of a tag cloud in a more understandable and visually appealing manner. Tags of a tag cloud that are associated with an object (e.g., web page) are retrieved. The retrieved tags are then assigned to parts of speech (e.g., noun, verb, adjective, adverb). Combinations of the tags are then generated based on the parts of speech assigned to the tags. For example, the combinations of the tags may be based on a template, such as <NOUN><VERB><ADJECTIVE>, <PRONOUN><VERB><ADJECTIVE>, <PRONOUN>is <ADVERB><VERB>and so forth. The combinations of the tags are then presented after determining the layout to display the generated combinations of tags. Since the tags of the tag cloud are presented in a combination based on the parts of speech assigned to the tags, the tag cloud is more understandable and visually appealing.

The invention relates to a text processing method and system based on meaning group division, and the method comprises the steps: obtaining an article to be analyzed in semantic tendency, wherein thearticle comprises paragraphs, the paragraphs comprise sentences, the sentences are divided into continuous language segments expressing a single meaning, ethe continuous language segments serve as a semantic meaning group, and the word segmentation of the semantic meaning group is carried out, and candidate words are obtained; obtaining a sentiment word library, allocating a tendency weight to each sentiment word in the word library, constructing a sentiment word list, retrieving candidate words in the sentiment word list, and extracting sentiment words corresponding to the candidate words astendency words of sentences; analyzing degree adverbs and negative words in front of the tendency words respectively; endowing the tendency words with degree weights and negative weights, and multiplying the negative weights, the degree weights and the tendency weights of the tendency words to obtain meaning group tendency components of the semantic meaning groups; and collecting the tendency component of each meaning group in the sentence to serve as a sentence tendency component, and obtaining a semantic tendency component of the article according to the sentence tendency component to serveas a semantic tendency analysis result of the article.