49 results about "Orientation analysis" patented technology

The invention discloses a text orientation analysis method which comprises the following steps of: preprocessing a review text; identifying a dependency relation structure of the Chinese syntax; calculating content polarity values of sentiment words; completing two-tuples extraction of evaluated objects and evaluation words and determining a slave relation between the evaluated objects; weighting and summing orientation values of the sentiment words to obtain an orientation value of a sentence so as to implement discrimination on orientation of a sentence level; discriminating appraising orientation of sentiment in the review by positive and negative polarity values of the sentence level; and according to the size of a polarity absolute value, discriminating intensity of appraising sentiment in the review. A product review orientation discriminator comprises an acquisition module, a preprocessing module, a syntactic analysis module, a sentiment calculating engine, a two-tuples mining engine, a content controller and a sentiment discriminator. According to the invention, a combined sentiment dictionary is combined and a domain ontology is added into text orientation analysis; accuracy of polarity calculation of the sentiment words and (the evaluated objects and the evaluation words) two-tuples extraction is improved; and orientation analysis on product reviews in a forum is implemented.

The invention discloses a text emotion analysis system based on deep learning. The system comprises an information collection module, an information pre-processing module, an emotion analysis module and an information display module, wherein the information collection module is used to collect comment information in each Internet resource website; the information pre-processing module is used to conduct classification, word segmentation, part-of-speech tagging, emotion information tagging processing and storage of the collected comment information; the emotion analysis module transforms the processed comment information into a phrase vector by a word representation model, a sentence module and a section and chapter model, and also inputs the phrase vector into the emotion classification model for emotion analysis; and the information display module is used to present emotion analysis results in a visualized manner. The system has the advantages that emotion orientation analysis can be conducted on the comment information; the analysis results can be presented to users in a visualized manner; and further public opinion analysis results or early warning can be provided to related departments such as enterprises or governments.

A system for analyzing vertical public opinions based on an industry comprises an acquisition and pre-treatment module for acquiring and pre-treating Internet information relevant to the consumer electronics industry and obtaining the formative information of the consumer electronics industry based on documents; a word segmentation module for matching words by means of a character string matching algorithm, and obtaining work segmentation results by amending the matching results in a word segmentation method based on understanding and statistics; an analysis module for performing document clustering and classification on the word segmentation results according to the frequency and similarity of keywords in the word segmentation results of the documents, and for obtaining analyzed and processed information after hotspot / sensitive topic analysis, orientation analysis and trend analysis to the clustered and classified results; and a display module for pushing the analyzed and processed information to users. The invention further provides a method for analyzing vertical public opinions based on an industry.

The invention relates to a text filtering method based on emotional orientation analysis against malicious information, which belongs to the technical field of computer applications and is applicableto content filtering firewalls, content filtering gateways and the like. The method is based on text content analysis, adds the text emotional analysis method and judges whether a text is the malicious information text or not according to a theme and emotional orientation of the text, thereby improving the accuracy of filtering the malicious information text.

The invention discloses a CRFs (conditional random fields) and SVM (support vector machine) based method for extracting fine-granularity sentiment elements in product reviews. The method comprises the steps as follows: a, a CRFs model is adopted, review language characteristics are taken as sequences, then position labelling is performed on review languages according to the sequences, corresponding rules are adopted to perform stratified filtering on error labels, and extraction for sentiment subjects and sentiment words is finished; and b, an SVM model is adopted to perform sentiment orientation analysis on word pairs according to the extracted sentiment subjects and sentiment words as well as introduced sentence structure features. According to the invention, the sentiment subjects and the sentiment words in review sentences are extracted together, further, sentiment classification accuracy in the sentiment orientation analysis is improved, so that the sentiment element extraction and sentiment judgment are improved, and F value is up to 76.3%; due to introduction of word meaning codes, the generalization ability and the robustness of a system are improved by virtue of the word meaning codes, and the accurate rate and recall rate of review result analysis are greatly improved.

The invention discloses a method for establishing a large-scale cross-field text emotion orientation analysis framework. The method comprises the steps that precise word segmentation is carried out on sample documents in a source field and sample documents in a target field to form two word vector tables; word vectors are clustered, and the fields are aligned; primary sentence modeling is carried out on calibration samples in the source field through the word vectors and serves as input of DCELM, and interlayer abstraction features of text vectors are extracted through convolution operation; convolution layer parameters obtained when the classification effect of a verification set is best are recorded and serve as parameters of a DCELM network convolution layer; finally, interlayer abstraction features of calibration samples, extracted through DCNN, of a small number of target fields are used for training implicit layer parameters of a classifier ELM to establish the large-scale cross-field text emotion orientation analysis framework. By means of the technical scheme, the difference of words for expressing emotion polarities among the fields is eliminated on the sample layer, the defects that on a full-connection layer, local optimization is easily caused and the generalization ability is weak are effectively solved, and the anti-interference performance of a model is improved.

The present invention provides an acquisition system and a method of an advertising orientation data in a telecommunication network. The system mainly comprises a data extraction module, which is used to perform a communication with a network element inside the telecommunication network through a network interface, to extract at least two user message datum from the network element, and to take the extracted datum as user original orientation datum to transmit to a data analysis module; the data analysis module, which is used to perform a analysis to the user original orientation data transmitted by the data extraction module according to an orientation analysis approach set up in advance, to get user orientation result data, and to transmit the user orientation result data to a data send module; the data send module, which is used to extract a corresponding targeted advertising and to send to the user according to the user orientation result data transmitted by the data analysis module. The utilization of the present invention can get the user orientation result data correlated with the behavior of the user in the telecommunication network, thereby to ensure a telecom operator to provide a targeted advertising matched with a mobile user height for the mobile user.

The invention provides a code static analysis based multithread deadlock detection method and system. The method comprises the following steps: analyzing morphology, grammar and semanteme of a software source program to be detected to generate an abstract syntax tree and a control flow graph; generating an orientation analysis graph of the program by traversing the abstract syntax tree, analyzing the thread in the program to generate a thread class concurrence set; performing reachability analysis on the program by traversing the control flow graph, generating and analyzing a thread concurrence set, generating and analyzing a possession request feature set and a lock graph, detecting a potential deadlock to find a door lock set of a lock object, deleting the deadlock in which the lock objects with different threads have the same door lock, and updating the potential deadlock set; deleting impossible deadlock conditions by concurrence and escape analysis to obtain a final deadlock set. By applying the method and system, the condition that two or more threads generate deadlocks can be effectively detected, and the testing accuracy and automation degree are improved.

The invention relates to network information processing technology, and discloses a public opinion vertical search analysis system. The system for text-based network public opinion search analysis comprises a vertical search engine crawler module, a template-based information extraction module, a text orientation analysis module based on phrase extraction, a text orientation analysis module based on vocabulary statistical model. In comparison with the prior art, the accuracy of the information emotion orientation algorithm based on phrase model and the vocabulary statistical model is improved by about 5%, and the algorithm has remarkable improvement effect. Meanwhile, the execution efficiency of processing is improved by designing a multi-threading method, thereby realizing quicker and more accurate public opinion search analysis effect.

The embodiment of the invention provides a method and a device for identifying text orientation. The method comprises the following steps of: based on pre-built industry characteristic word dictionary, by taking the sentence as unit, searching and obtaining the sentence which includes at least one industry characteristic word from the text to be analyzed; determining the corresponding orientation of the sentence which includes at least one industry characteristic word according to a text categorization model pre-trained in advance; based on the determining strategy of the pre-set text orientation, determining the orientation of the test to be analyzed according to the corresponding orientation of the sentence which includes at least one industry characteristic word. According to the method and device, by the industry characteristic words in the industry characteristic word dictionary, the texts which describe the evaluation objects and / or elevate the feelings can be screened and obtained; because the interferences of the texts which describe the objects irrelevant to evaluation objects and / or elevate the feelings are eliminated, the accuracy of text orientation analysis of objects elevated in the text to be analyzed is improved.

The invention provides an X-ray diagnostic system and an X-ray image shooting method. The X-ray image shooting method comprises the steps that firstly, orientation parameters including height data of a basis point part of a certain specific part of a diagnosis object is taken as the reference to acquire orientation parameters including position height data of the to-be-detected part, and a shooting position from the X-ray image shooting device to the to-be-detected part is adjusted based on the orientation parameters. The X-ray diagnostic system comprises an X-ray image shooting unit for shooting the X-ray image on the to-be-detected part of the diagnosis object, a basis point part height measurement unit for acquiring the basis point part height data of the diagnosis object, a to-be-detected part orientation analysis unit for acquiring the orientation parameters of the to-be-detected part based on the basis point part height data, and an X-ray image shooting position shooting control unit controlling an X-ray generator and / or detector to move to the to-be-detected part. According to the X-ray diagnostic system and the X-ray image shooting method, positioning of the X-ray generator and / or detector is automatically controlled through the shooting control unit so as to replace detector positioning adjustment through artificial visual estimation, the X-ray image shooting process is simplified, and the shooting efficiency is improved.

The invention discloses a method and device for analyzing the semantic orientation of a Chinese network topic comment text. The method comprises the following steps: performing word segmentation and sentence segmentation on the Chinese network topic comment text to obtain a result sequence; performing syntactic analysis and grammatical analysis on the result sequence to obtain an evaluation object; performing sentence pattern analysis on the result sequence to determine simple sentences and complex sentences in the comment text, judging the relations among all the simple sentences forming a complex sentence, and determining a first emotion orientation value of sentence pattern analysis; extracting emotion phrases in each sentence in the result sequence according to the evaluation object and a preset phrase matching mode, and calculating a second emotion orientation value of each emotion phrase; calculating a third emotion orientation value of each sentence in the comment text according to the first emotion orientation value and the second emotion orientation values; determining a text emotion orientation value of the comment text according to the third emotion orientation values. According to the method, the accuracy and the recall rate of the semantic orientation analysis of the network topic comment text are improved.

The invention provides a digital stand-alone internal-projection whole-spherical-screen projection system, which comprises a digital projector, a fish-eye lens with a super viewing angle used for the digital projector and a spherical screen covering 4 / 5 to 9 / 10 area of a whole sphere, which is used for a combined projection of the digital projector and the fish-eye lens with the super viewing angle. The invention can conduct full-frame internal projection on a nearly whole-spherical transmission-type spherical screen only with one fish-eye lens and one common digital projector, and can guarantee a certain level of brightness and picture definition; the invention can be applied in the fields of city beautification project, advertising campaign on a plaza, corporation image display and product display, military training and command simulation, dimensional orientation analysis and panoramic analysis, synchronous playing of frames in a gymnasium, etc.

The invention relates to a method for realizing super-resolution dipole orientation analysis. The method comprises the following steps: a microscopic imaging system is arranged, wherein the system comprises a laser light source, a half-wave plate, a collimating lens, a dichroscope, an object lens, a reflector, a convergent lens, and an EMCCD imaging device; light splitting difference correction for different polarized light due to diffraction, background noise, and the dichroscope as well as Poisson sampling property factors of EMCCD acquisition signals are considered, a fluorescent polarization modulation microscopic imaging process is modeled, and a super-resolution intensity signal is obtained; after counter-demodulation, polarization modulation properties of singles in a single pixel are used, least square fitting is carried out for the super-resolution intensity signal, average dipole orientation in a single pixel is extracted, and signals with super-diffraction limiting resolution are realized; a direction consistency factor OUF is defined for evaluating validity of average dipole direction after reconstruction; and two visualization methods of super-resolution signals are used, dimensions for distinguishing different molecules are added from the aspect of an angle resolution, and fine understanding of protein compositions is realized.

The invention discloses a pearlite steel wire rod austenitic grain size measuring method. The method comprises the following steps that 1, a small block is cut out from a pearlite steel wire rod to serve as a sample, and the sample is ground, mechanically polished and electrochemically polished; 2, one face of the sample is used as an observation area, and an EBSD system is used for carrying out face scanning on the sample to obtain an orientation imaging figure; 3, a certain deflection angle difference is set, orientation analysis software of the EBSD system is used for carrying out statistics on the grain size, an average grain diameter is obtained, and the pearlite steel wire rod austenitic grain size is calculated according to the average grain diameter. According to the method, the pearlite steel wire rod austenitic grain size is rapidly and accurately measured through the EBSD technology, sample preparation is easy, the result can be quantitative, and the reproducibility is good.

The invention belongs to the technical field of computers, and provides a network information semantic orientation analysis method and system. The method comprises the steps that a name of an enterprise is obtained; information related with the enterprises is searched on the internet by using a web crawler, and the information is stored in a database in the form of a text; the text is decomposed into logical word sequences by using a tokenizer, and the word sequences are stored in a word decomposition base; the word sequences are taken out from the word decomposition base and inputted into a corpus analyzer, and the word sequences with part-of-speech tagging are obtained; the word sequences with part-of-speech tagging are inputted into an emotion tendency classifier, the emotion tendency values of the text are obtained, and accordingly the emotion tendency of the text is obtained. According to the method and system, mass information of the internet is used as an information source, the positive and negative tendency of the enterprise information is rapidly calculated and judged, so that public users can rapidly and comprehensively acquire the business and public opinion information of the enterprise, and the device can also provide information retrieval technical service for industries, institutions and enterprise users.

The invention provides a screening and valuing method of a technical similarity patent, comprising an establishing procedure of docking of stereotactic orientation analysis technology and citation networks TSU-CN microstructure, a procedure of establishing a related subnet, and a procedure of collecting monitoring data of internal and external technical flow based on target patent-similar technology-main technology environment, and a procedure of extracting technological spectrum parameters basic data and a procedure of establishing technological spectrum parameters based on a dynamic TSU-CN microstructure. By macroscopic and microcosmic docking of target patent technical flow in similar technology and main technology environment and stereotactic and quantitative control, relative objectivity and accuracy of valuing and screening results are guaranteed. Thus, enterprises are capable of positioning the 'technology value of target patent under the realistic background' reasonably and accurately in the introduction of technology and the development of foreign invalid patents so as to avoid the competitive failure caused by blind technology introduction and patent development. Meantime, the method helps enterprises make competitiveness evaluation on the technical patent in the international similar technology, as well as the option of stock investment.

The ivnention relates to an array logging tool in the side direction with various layering capabilities. It includes a multi-signal source, multiple groups of shielded electrodes, a monitoring device, a main electrode group, voltage measuring and processing set, and main electrode current detecting and processing set. The multi-signal source produces multiple working signals with different frequencies. Each group of shielded electrodes sends working signal to different layer of earth, meanwhile forms focusing electric field. The monitoring device receives and magnifies first working signal transmitted by multiple groups of shielded electrodes. The main electrode group includes a central electrode and multiple pairs of electrodes arranged outwards for signal refocusing. One measurement in the invention can obtain 12 apparent resistivity curves that describes the geology in detail, explains layers of earth in the orientation analysis, gives quantitative explanations to the problems of layers and alternate laminar layers.

The invention relates to application technology of an intelligent device, and discloses a method for providing an application service for a user based on the intelligent device. The method solves the problems that related application services are not provided for traditional technology, the user needs to inquire corresponding information, and time and labor are wasted. The method can include the steps: acquiring basic information of an application through an application service platform and displaying the basic information in an interface in a function bar form in a classified manner when running the application by the user; transmitting classified information to a server; conducting a search according to the classified information and performing orientation analysis for obtained data by the server; and finally, pushing the service data the most matched with the application to the intelligent device and displaying the service data in corresponding function bars. In addition, the invention further discloses a corresponding system for providing the application service for the user, wherein the system is applicable to the intelligent device.

The invention discloses an emotion analysis and prediction system based on automatic data collection. The system comprises a user interaction module, a data management module, an emotion analysis module, and an emotion prediction module, wherein the user interaction module receives an emotion analysis instruction input by a user, and provides a visible interface for the user to check information;the data management module collects and manages data to undergo emotion analysis, crawls and stores historical text information or real-time text streams under preset conditions through three crawlerslike a webpage, an API and a URL; the emotion analysis module performs emotion analysis on the data to undergo emotion analysis, and delivers a comprehensive emotion analysis result by combining different emotion analysis processes, wherein emotion analysis comprises word property marking, syntactic structure analysis and emotion orientation analysis; and the emotion prediction module predicts emotion orientation corresponding to the data to undergo emotion analysis according to a comprehensive emotion analysis result in a time period. The system can collect data automatically and deliver emotion prediction results based on historical data in the process.

The invention relates to the field of metal material solidification control and preparation, in particular to a preparation method of an anisotropic biomedical directional solidification magnesium-zinc alloy material. The method comprises the steps that a magnesium-zinc alloy is molten in a resistance furnace firstly, a bar is prepared in a direct pouring mode or by cutting a cast ingot, then a magnesium-zinc alloy with specific growth orientation and a microstructure is prepared on a directional solidification device, and the magnesium-zinc alloy material is cut in different orientations according to required performance of biomedical application. By combination of a directional solidification technology and an orientation analysis technology, the anisotropic biomedical directional solidification magnesium-zinc alloy material can be prepared, the directional solidification magnesium alloy with the different orientations and the microstructure is obtained, the problems that an existingmagnesium alloy material is low in mechanical property and too high in degrading speed during biomedical application are solved, and the method is suitable for preparing various biomedical magnesium-zinc alloy materials.

A human motion description method based on an inertial sensor comprises the following steps: collecting motion data through the inertial sensor, defining a skeleton hierarchical structure, and storingthe skeleton hierarchical structure in a motion capture data BVH format; carrying out coordinate conversion on BVH Euler angle data, each frame of action of each limb is represented in the form of relative world coordinates, a data frame sequence is formed, and subsequent action space orientation analysis is facilitated; after a human body posture frame sequence is obtained, extracting a key frame by adopting a key frame extraction technology; and finally, analyzing the spatial orientation of the human motion, calculating other motion characteristic parameters of the action key frame, establishing mapping between limb coordinates and the spatial orientation of the human body, and determining a description language to describe the subject content of the human motion. Three theme contents of time, space and force effect of a human body action process are described in detail through an action description language, so that non-computer related personnel can be applied to the fields of action analysis and recognition, and help is provided for human body action analysis and human body movement biomechanics.

The invention discloses a back reflection structure digital X-ray crystal orientation device and an X-ray detector thereof. The X-ray detector comprises a scintillation screen, a fiber optic taper, a photosensitive element, a digital circuit board, a heat conduction element and a ray collimator, wherein a center through hole extending to the back side of the scintillation screen from the front side of the scintillation screen is formed in the scintillation screen, the fiber optic taper is connected to the back side of the scintillation screen, the photosensitive element is connected to the back side of the fiber optic taper, the rear end of the photosensitive element is connected to the front surface of the digital circuit board, the heat conduction element is connected to the rear surface of the digital circuit board and conduct heat conduction on the photosensitive element, the rear end of the ray collimator is connected to the emission end of an X-ray machine, and the front end of the ray collimator extends to the front side of the scintillation screen from the center through hole. By the adoption of the back reflection structure digital X-ray crystal orientation device and the X-ray detector thereof, orientation analysis precision and efficiency can be improved remarkably.

The invention provides an orientation analysis-based classification model building and content identification method and device. On one hand, according to the embodiment of the invention, first content features are obtained according to a filtered second training data, and further, according to the mutual information of the first content features appearing in a first content category to the first content features appearing in a second content category, the first content features are filtered so as to obtain second content features, so that a classification model can be trained by utilizing the second content features; and as the first content features are filtered according to the mutual information of the first content features appearing in a first content category to the first content features appearing in a second content category, the second content features with higher distinguishing ability can be obtained, and thus, the classification model trained by utilizing the second content features with the higher distinguishing ability is capable of more accurately identifying content with negative orientation, and therefore, the reliability of content identification is improved.

An imaging-guided docking system can separate the tilt and location of an imaged ophthalmic target and present them in an intuitive manner for an ophthalmic surgeon. The docking system can include an ophthalmic imaging system to image a portion of an eye of a patient, an image processor to determine a location and an orientation of the imaged portion of the eye, and a guidance system, coupled to the ophthalmic imaging system, to guide an ophthalmic docking based on the determined location and orientation. In some implementations, the imaging system images an internal eye-structure to determine its orientation and a video-imaging system video-images a frontal eye-structure to determine a location of the frontal eye-structure. The determined orientation and location can be displayed for the surgeon. The alignment of ophthalmic procedures can also be assisted with this imaging capability, e.g. the placement and centration of IOLs into the lens capsule.

The invention discloses a training method of film review emotional orientation analysis based on machine learning, belonging to the field of natural language processing. The purpose of the invention is to solve the problem of improving the accuracy of the film review emotional analysis of the emotional dictionaries in the prior art. The technical points of the training method of the film review emotional orientation analysis based on machine learning are as follows: downloading film reviews; selecting feature words; using a feature word set to represent each film review as a feature vector; dividing a feature vector text into training sets randomly, and adding positive or negative labels to each feature vector of the training set; and training a classifier built with the naive Bayesian thought. The effect of the training method of the film review emotional orientation analysis based on machine learning is that the whole tendentiousness of the words with equal amount of positive and negative orientations in the film reviews can be more accurately judged.

The invention discloses a real-time monitoring method for a three-dimensional structure of a disk type mirror surface. The method is used for solving the defect that the existing technology is slow orinconvenient to install a measurement hardware in the process of obtaining the mirror surface structure, and meanwhile the measurement process is also effective in the operation process of the photothermal system. The method comprises the steps of camera array construction, camera calibration, camera array placement, shooting and picture transmission, picture preprocessing, feature point selection and matching, reference point selection, camera relative position solving, three-dimensional position reconstruction, three-dimensional point correction, orientation analysis, and light spot analysis. The whole process is quick and effective, and the method is high in precision. The hardware facility is convenient to install, the robustness of the installation and use process is strong, a certain offset is allowed, and this offset does not affect the reconstruction result.

The invention firstly provides an interest region judgment system and method based on an elevator scene. The interest region judgment system comprises an image acquisition unit, a human body feature point detection unit, a three-dimensional feature matching unit, a sight orientation analysis unit and an attention time obtaining unit; and the image acquisition unit establishes data connection with the human body feature point detection unit, the human body feature point detection unit establishes data connection with the three-dimensional feature matching unit, the three-dimensional feature matching unit establishes data connection with the sight orientation analysis unit, and the sight orientation analysis unit establishes data connection with the attention time obtaining unit. The invention furthermore provides an interest region judgment method applying the interest region judgment system. By means of the interest region judgment system and method, advertisements can be delivered in a targeted manner, and efficiency of advertisement delivery is improved.

The invention discloses a video linkage system based on large-scale scene video monitoring, and the system comprises the steps: carrying out the orientation analysis of all cameras of a controlled scene through a visual direction analysis unit, obtaining the orientation positions of all cameras, determining a coverage area according to the orientation positions, and forming a standard building model of the controlled scene; carrying out primary splicing on the controlled video group by utilizing a cutting and splicing unit in combination with the building model, primarily fusing all the controlled videos to obtain a primarily fused video, and processing a crossing region in a primary mode; and then the cutting and splicing unit is used for transmitting the building model and the initial fusion video to the image direction analysis unit through the processor, and the image direction analysis unit is used for carrying out two-direction analysis on the real-time initial fusion video in combination with the image direction splicing unit, displaying a display image of a crossed area according to the mode provided by the invention, and monitoring an abnormal condition in real time. A reasonable and efficient combined monitoring system is provided; the method is simple, effective and easy to use.

The invention provides a code static analysis based multithread deadlock detection method and system. The method comprises the following steps: analyzing morphology, grammar and semanteme of a software source program to be detected to generate an abstract syntax tree and a control flow graph; generating an orientation analysis graph of the program by traversing the abstract syntax tree, analyzing the thread in the program to generate a thread class concurrence set; performing reachability analysis on the program by traversing the control flow graph, generating and analyzing a thread concurrence set, generating and analyzing a possession request feature set and a lock graph, detecting a potential deadlock to find a door lock set of a lock object, deleting the deadlock in which the lock objects with different threads have the same door lock, and updating the potential deadlock set; deleting impossible deadlock conditions by concurrence and escape analysis to obtain a final deadlock set. By applying the method and system, the condition that two or more threads generate deadlocks can be effectively detected, and the testing accuracy and automation degree are improved.