34 results about "Author name" patented technology

The invention discloses a name duplication disambiguation method of Chinese literature authors. The method comprises the following steps: carrying out normalized preprocessing on a literature data set; carrying out author primary extraction and formalized expression; according to the basic attributes of the author with name duplication ambiguity, calculating a basic attribute similarity score between every two authors for the authors with the name duplication ambiguity; constructing a keyword relationship corresponding table of a name duplication author, and calculating a keyword similarity score; establishing a cooperative relationship network for the name duplication author, and calculating a cooperative relationship similarity score between every two authors; according to relative basic attributes, keywords and the cooperative relationship network, calculating a comprehensive similarity index to judge the name duplication author; and according to a judgment result, updating the relevant information of the author. Through the name duplication disambiguation method, an author name duplication phenomenon in the Chinese literature can be disambiguated, and a method for improving an academic analytics precision degree is provided for applying to aspects including science and technology evaluation, academic research and the like through academic literature analytics.

The invention discloses a scholars name disambiguation method based on heterogeneous network embedding, which comprises the following steps of 1) setting a plurality of authors needing disambiguation,collecting all papers related to the authors needing disambiguation, and generating a paper relation heterogeneous network by utilizing the authors of the collected papers and semantic information ofthe papers; 2) according to the paper relation heterogeneous network, generating paths containing text information of neighbor nodes of paper nodes through a meta-path-based random walk strategy, andstoring the paths as a training corpus; 3) using Skip-gram to train the training corpus, and generating a paper representation vector corresponding to each paper; 4) for an author needing disambiguation in the step 1), obtaining a paper representation vector corresponding to the paper of the author from the obtained paper representation vector, and 5) clustering the paper representation vector obtained in the step 4) to obtain a plurality of clusters to realize disambiguation of the author name.

The invention discloses a literature author name duplication disambiguation method and a literature author name duplication disambiguation construction system. The literature author name duplication disambiguation method comprises the following steps of 1, reading literature data and scholarship data in a database; 2, training and predicting a document vector of each document by using a Word2Vec model; 3, constructing a to-be-disambiguated author partner relationship network graph, and calculating node similarity and clustering; and 4, obtaining document vectors of documents in document clusters clustered by the partner relation graph, and calculating similarity and clustering among the document clusters. The invention can ensure that the disambiguation result has relatively high accuracyand recall rate level, and is suitable for multi-language and multi-literature types of Chinese literature, English literature, patents and the like.

The invention provides a paper author name disambiguation method based on rule matching and machine learning. The method comprises the following steps of preprocessing the paper information to be processed; matching the author names in the preprocessed paper information with a pre-constructed name matching rule to obtain a candidate author set; and determining authors of the to-be-processed paperaccording to the number of the candidate authors in the candidate author set. By applying the method, the paper disambiguation effect can be improved, and the author name disambiguation accuracy can be effectively improved.

The invention discloses an electronic book query method and an electronic book reading device. The method comprises the following steps: acquiring the identification tag of a real book by use of an image acquiring module of the electronic book reading device; extracting the ISBN code from the identification tag; on-line querying the book information, such as the book name or the author name, corresponding to the ISBN code; on-line querying the electronic book information corresponding to the book information; and displaying the electronic book information on the screen of the electronic book reading device. When the electronic book information includes downloading information, a user can directly one-line download the electronic book document from the electronic book reading device.

The invention relates generally to a mesh type apparatus for liquid atomising and filtration, for example, of the atomiser having a concave ultrasonic transducer, which also forms a part of the liquid container (1). This transducer is emitted an ultrasonic energy which created a spout (2) of the liquid (3) to be atomised. The liquid (8) plays a role of the transmission media. The container (9) with liquid (3) is set up on the top of the container (1). The liquid (3) is separated from the transmission media (8) through the bottom of the container (9) by a material that has minimum attenuation of ultrasonic energy. This separation could be temporary of permanent. The focal zone extender (5) is placed in the vicinity of the bottom of container (9). In this case all liquid above the bottom of the focal zone extender will be forced up to the top of the focal zone extender and atomized at the constant intensity of acoustical energy conveyed from the bottom of the focal zone extender. This new technology author named for Dynamic Mesh Technology.

The invention discloses a personalized academic literature recommendation method. The method comprises the following steps: S1, data collection and cleaning, wherein paper data with papers and authorsas cores are collected, the paper data include paper titles, paper abstracts, author names, publication years, publication periodicals and reference literature, and data which have obvious format errors or miss data are cleared; S2, model establishment, wherein a process comprises the following steps: S2.1, constructing a training set, and S2.2, calculating features; S3, model training; and S4, academic literature recommendation, wherein a process includes the following steps: S4.1, establishing a candidate literature set, and requiring that publication time of cited literature selected at each step is earlier than publication time of a paper, and S4.2, carrying out prediction, and taking papers of k' highest probability values as lastly recommended reference literature. The method can more accurately and highly efficiently generate a reference literature list meeting user needs.

The invention provides an academic article processing method and a search processing method and apparatus for academic articles. The academic article processing method comprises: acquiring a plurality of articles with the same author name characteristic; clustering the plurality of articles according to the author subsidiary organ characteristics of the articles to obtain a plurality of first clusters; clustering the plurality of first clusters according to the cooperator characteristics and the first semantic characteristics of the articles to obtain a plurality of second clusters; and clustering the plurality of second clusters according to the author subsidiary organ characteristics and the second semantic characteristics of the articles to obtain a plurality of third clusters, wherein the set of the second semantic characteristics is the subset of the set of the first semantic characteristics. According to the academic article processing method and the search processing method and apparatus for the academic articles, which are provided by the invention, the accuracy rate and recall rate of the articles corresponding one author entity are improved.

The invention belongs to the fields of social data analysis and visualization, relates to the technologies of social network analysis, information analysis, information retrieval and filtering and sorting, and discloses a multi-mode-supported retrieval of leading figures in academic fields and a visualized navigation system. The retrieval of leading figures in the academic fields and the visualized navigation system include 1 data acquisition and processing, 2 multi-mode retrieval and 3 visualized representation of search results and relevance among the search results with an appropriate visualized placement algorithm applied, wherein 1 the data acquisition and processing mainly relate to author correlating validation in a collecting stage and relates to analysis and extraction of data internal relevance; 2 the multi-mode retrieval includes (1) retrieval based on author names, (2) retrieval based on fields and (3) retrieval based on contents, wherein (1) the retrieval based on the author names copes with conditions that a user has certain impression of the name an author but do not remember the name of the author very clearly, (2) the retrieval based on the fields which are divided according to the subject division system of international natural science foundation can retrieve the author with high influence, and (3) the retrieval based on the contents can retrieve relevant papers and authors of the papers by searching the contents and the aim is to collect the relevant authors to meet the needs of learners for knowledge; and 3 the search results and the relevance among the search results are visually presented with the appropriate visualized placement algorithm applied.

The invention discloses a microblog acquisition system and method based on events and belongs to the technical field of information security. The system comprises an URL structure module, a JSSH client module, a browser acquisition module and an HTML analysis module, wherein the URL structure module is connected with the JSSH client module and used for transmitting acquired URL information, the JSSH client module is connected with the browser acquisition module and used for transmitting JSSH instructions, and the browser acquisition module is connected with the HTML analysis module and used for transmitting HTML text messages. By means of the microblog acquisition system and method based on the events, abstract data such as a microblog author name, a microblog author homepage URL, a microblog author head portrait URL, microblog body content, a microblog short link, microblog issue time, a microblog issue client, the number of forwarding times and the number of comments of a microblog message can be acquired through analysis, each piece of unstructured data is changed into structural data, and therefore abstract data can become concrete to be used in follow-up data mining.

The invention provides a disambiguation method and device for scholars with the same name, and belongs to the field of computers, and the method comprises the steps: obtaining a pre-stored data set, wherein the data set comprises at least one piece of literature data and identifiers corresponding to the literature data, and the literature data comprises author names; determining a name set from author names contained in the data set through a preset similarity algorithm, wherein the name set comprises author names meeting a preset similarity condition and identification of literature data to which each author name belongs; for the author names are included in the name set, determining a first knowledge graph corresponding to the author name according to the identifier of the literature data to which the author name belongs and a preset knowledge graph generation rule, the first knowledge graph comprising at least one node, the node being used for representing a set of literature data which comprises the author name and belongs to the same author. By adopting the method, the efficiency of determining scholars with the same name can be improved.

A method and email system for improving efficiency of email discussion within an email client comprising: an email tag filter for filtering a special tag in email contents, extracting original email contents, and identifying tag related information which includes at least an author name corresponding to the email contents; and a content style setting component for receiving and keeping the tag related information fed by the email tag filter, then identifying which part of the email contents is written by which author according to the tag information, and assigning correct style to corresponding contents using a user customization style for each author. The invention differentiates different users mainly by automatically labeling the contents input by the users, and the input contents can be distributed in different positions within a single email, which matches the natural convention of the current users to use the email system.

The invention discloses an author disambiguation method based on a paper key attribute network. The key attribute relationship network is a relationship network which is formed by collecting key attributes in papers and through correlations between the key attributes, a relationship network of the same institution and a relationship network of the same field are respectively formed, and finally, the relationship network of the key attributes of the papers is formed. According to the method, a paper name, an author institution and an author field in a paper are extracted, and a relationship network is established around the author name; when the paper authors are disambiguated, the names of the paper authors are matched, author institutions in the relationship network are combined, and theauthor field can effectively solve the problem that the names of the paper authors are the same but correspond to different actual authors. In addition, by combining the paper name with the coauthor of the current author to be disambiguated and matched again, the situation that the same actual author has different name writing methods can be effectively solved.

The present invention is directed to a method and corresponding system for parsing author name text strings in documents. The method and system may electronically scan a document that contains an author name text string comprising a set of initials, one or more author surnames, and punctuation. The author name text string may be in non-standardized format. The method and system may identify a character sequence in the document as potentially being the author name test string based on (i) a sequence of title-case words, capital letter, and punctuation, and (ii) the character sequence ending with a recognized indicator. The method and system may parse the identified character sequence by converting any punctuation and whitespace between terms in the character sequence to a single space character, identifying a pattern of surname and set of initials comprising each author name contained in the character sequence, and marking up the components of surname and set of initials comprising each author name. The method and system may use the marked up character sequence to identify and correct errors in punctuation and capitalization in the character sequence, and output an updated character sequence in standardized format.

The invention discloses an entity alignment method and system applied to a knowledge graph, and relates to the technical field of computers. The method comprises the steps: carrying out the entity alignment of an author name and a stored author name, and enabling matched second author attribute data to serve as a candidate entity; performing entity alignment scoring on the first author attribute data and the second author attribute data according to a first entity alignment model to obtain a first entity alignment score, wherein the first entity alignment score is smaller than a first entity alignment threshold and the knowledge graph data is a college thesis, and performing entity alignment scoring on the first author attribute data and the second author attribute data according to a second entity alignment model to obtain a second entity alignment score; taking a summation result of the first entity alignment score and the second entity alignment score as a total entity alignment score, and adding knowledge graph data into an author entity library when the total entity alignment score is smaller than a second entity alignment threshold; otherwise performing knowledge fusion. According to the method, the entity alignment accuracy and recall rate are effectively improved.

The invention is suitable for the software field, and provides a method and device for adding underscore, a terminal and a computer-readable storage medium. the method includes displaying a pluralityof music names and an addition function key on that right side of the music name on a network novel read platform; recording and storing a score name to be added in the addition directory; receivinga network novel name and an author name inputted by a user, and receiving a network novel returned by the network novel storage server based on a search request; importing the chapter list of the network novel, displaying the chapter of the chapter list, and obtaining the selected chapter by receiving the click action of the user to the chapter in the chapter list; on the other side of the page, displaying a score name to be added; obtaining the selected score; establishing the corresponding relationship between the selected score and the selected chapter to generate a score addition scheme; playing the selected score when the content of the selected chapter is displayed on the online novel reading platform. The invention is conducive to creating the reading atmosphere of the network novel.

The invention discloses a method for intelligently recommending professional books in a library, relating to the technical field of library resources management. The method comprises the following steps: receiving the book title keywords input by readers in the book title column, obtaining a plurality of recommended books in the library collection according to the book title keywords input, receiving the author names input by readers in the author column, and obtaining a plurality of recommended books in the library collection according to the author names input. The method enables the readerto obtain the detailed information of the book, also enables the reader to obtain the detailed information of the book and find out for the reader the specific position of the book in the library, also helps readers find the books they need when they only know the book keywords, and records the readers' search records and personal expertise and preferences to help readers find books better next time. The method is very suitable for the intelligent recommendation of books in libraries.

The invention relates to a system and method for protecting original data modification right. By adopting the system and the method, original data of a writer can be prevented from being modified. The method comprises the following steps: firstly, logging into a system, and adding a login name as a writer name into a file head of the original data when a file is newly established. By adopting the system, when the file is read, whether the login name is identical to the writer of the file or not can be judged by the system, if the login name is identical to the writer of the file, the original data can be modified, and notes can be also made for the original data; if the login name is not identical to the writer of the file, only notes can be made for the original data.

A personalized academic literature recommendation method, including the following steps: S1 data collection and cleaning: collecting paper data with papers and authors as the core, the paper data including paper titles, paper abstracts, author names, publication years, publications and references, cleaning out data with obvious format errors and missing data; S2 model establishment, the process is as follows: S2.1 Construction of training set; S2.2 Feature calculation; S3 model training; S4 Academic literature recommendation, the process is as follows: S4 .1 To establish a set of candidate documents, it is required that the publication time of the cited paper selected in each step is earlier than the publication time of the paper; S4.2 Forecasting, the paper with the highest k′ in the probability value is taken as the final recommended reference. The invention can more accurately and efficiently generate a list of references meeting user needs.

The invention discloses an entity linking method, device and equipment and a storage medium. The entity linking method comprises the steps: extracting text information of a to-be-stored entity, wherein the text information comprises an author name of the to-be-stored entity, and the to-be-stored entity represents a to-be-stored thesis; searching an entity matched with the author name of the entityto be warehoused from a researcher entity library at least according to the author name of the entity to be warehoused, and obtaining text information of candidate entities; comparing the text information of the candidate entities with the text information of the to-be-stored entity and determining a comparison result; and when the comparison result represents that the to-be-warehoused entity andthe candidate entity are the same author, linking the to-be-warehoused entity with the to-be-warehoused entity. According to the method and the device, the to-be-warehoused entity can be connected with the entity in the entity library.

The Chinese five-element playing card features that each of the card has its front side including edition number area in the upper left corner, collection number area in the lower left corner, theme background describing area in the top, card name area, theme drawing author name area, theme drawing area, element expense area, combat force area, card classification area, card regulation describing area and dashed frame; and the back side with five-element text and figure. The present invention is used in collecting and exchanging game.

The invention discloses a paper author name disambiguation method and device and a storage medium, nodes are judged based on names and organizations, edges are constructed for the nodes with the same names and organizations and the distance smaller than a set threshold value, author information records with the edges are merged through a graph automatic encoder to obtain a related expert data set, and the expert data set is used for disambiguation of the authors. And associating the expert data set with a mailbox, realizing homonymy disambiguation by inevitably different mailbox addresses adopted by authors with different homonymy persons, judging the same authors according to the same or inclusion relationship of the author names and institutions and the distance smaller than a set threshold value, merging to form the expert data set, merging the paper data of the mailbox used by the authors into groups, and carrying out disambiguation. And after all experts associated with the mailbox are recorded, expert data sets in which organizations, author names and research subjects coincide are combined, so that an expert data set associated with the mailbox is realized, and disambiguation of authors is realized.

The invention belongs to the technical field of name disambiguation, and particularly relates to a Chinese and English literature author name disambiguation method. According to the method, Chinese author name disambiguation and English author name disambiguation are carried out based on semantic fingerprints, author cooperation network similarity, author reference network similarity and the like, and disambiguation of Chinese authors and name pinyin in English literatures is completed according to a Chinese disambiguation result and an English disambiguation result. According to the method, whether authors of different literatures are the same person or not can be accurately distinguished, the same author in Chinese and English can be well recognized, the author needing to be found can be quickly positioned, the accuracy rate is high, and retrieval work can be conveniently carried out; the calculation of the similarity of the scientific research duration of the authors is introduced, so that disambiguation of Chinese and English names of the Chinese authors can be well assisted, the age range of the authors can be determined, other authors with the same name not in the range can be filtered out, and the disambiguation accuracy is improved.

The invention provides a disambiguation method for author names of papers based on rule matching and machine learning. The method includes: preprocessing the paper information to be processed; matching the author name in the preprocessed paper information with the pre-built name matching rule to obtain a set of candidate authors; determining according to the number of candidate authors in the set of candidate authors The author of the pending paper. The application of the invention can improve the disambiguation effect of papers and effectively improve the accuracy of author name disambiguation.

The invention is suitable for the technical field of data search, and provides a book popularity value acquisition method and device, terminal equipment and a storage medium, and the method comprisesthe steps: obtaining a target book word list which comprises book names and author names of M books, and M being an integer greater than zero; obtaining a historical search statement of a target bookin the M books, wherein the target book is selected from the M books; obtaining the page view of the historical search statement of the target book; and obtaining a target popularity value of the target book according to the page view of the historical search statement of the target book. According to the invention, when the book popularity value is obtained, influence of the book resource platform on the book popularity value is reduced.

The invention discloses a literature parameter matching method, and the method comprises the steps: obtaining a first parameter set of a first literature and a second parameter set of a second literature, wherein a to-be-matched author name of the first literature is the same as a to-be-matched author name of the second literature; performing extended retrieval based on the first parameter set toobtain a first associated retrieval document set of the first document; performing extended retrieval based on the second parameter set to obtain a second associated retrieval document set of the second document; performing association matching on the first association retrieval document set and the second association retrieval document set to obtain an information overlap ratio data set between the first association retrieval document set and the second association retrieval document set; and judging whether the author to be matched of the first literature and the author to be matched of thesecond literature are the same author according to the information overlap ratio data set. According to the invention, whether the authors with the same name in the two literatures are the same authorcan be accurately judged.

The invention provides a team information determination method and apparatus. The method comprises the steps of creating an institution information library based on at least one piece of institution name information corresponding to obtained text data; based on at least one piece of author name information corresponding to the obtained text data, and in combination with the text data and the institution information, creating a personnel information library; based on topic information contained in any obtained text data and distribution information of author name information corresponding to the topic information, selecting the topic information corresponding to any author for any author to create a topic information library; and based on the institution information library, the personnel information library and the topic information library, determining a team information library for topics. Compared with other methods, team information determined by applying the technical scheme is more detailed, and the team information determination method is more effective and valuable for team information-based scientific research management decisions.