249results about How to "Objective" patented technology

The invention discloses a method for evaluating compressibility of a shale gas reservoir. The method sequentially comprises the following steps of (1) calculating a shale brittleness index Brit, (2), calculating a shale fracture toughness index Kn, (3), calculating a natural weak plane opening facility index Pn, (4), calculating a natural weak plane penetrated index Cn, (5), introducing a complex seam net probability index Fcf and a transforming volume probability index Fsrv, and determining a reservoir compressibility index FI, (6), according to the size of the reservoir compressibility index FI, evaluating the compressibility of a block shale reservoir. According to the method, various compressibility influence factors are considered, and particularly on the basis of a seam net forming mechanism, the influence of the natural weak plane is fully considered; the shortcomings of an existing evaluation method are overcome, and logging data are utilized for calculating brittleness and breaking toughness of the shale gas reservoir; and the dependency on experimental data is reduced. The method is used for evaluating the reservoir quality of a fractured well, has feasibility and accuracy and provides a new decision making method for facture well selecting and layer selecting of the shale gas reservoir.

The invention relates to the technical field of underground road bituminous pavement service performance evaluation. In order to make the evaluation result objective, the effective scientific decision can be provided for the road maintenance and repair department. In order to fulfill the aim, the adopted technical scheme is as follows: the entropy weight-based underground road bituminous pavement service performance evaluation method comprises the following steps of: 1. determining a composite underground road pavement performance integrated evaluation index system, namely 1.1. determining evaluation indexes and evaluation standards, 1.1.1. determining underground road bituminous pavement damage condition evaluation indexes and standards, 1.1.2. determining composite underground road pavement driving quality evaluation indexes and standards, and 1.1.3. determining composite underground road pavement safety performance evaluation index and standards; 1.2, establishing a comprehensive evaluation model; and 2. performing a composite underground road pavement service performance evaluation method. The method is mainly applied to the underground road bituminous pavement service performance evaluation.

The invention discloses a time sequence and CNN-based unsafe behavior identification method and system. The method comprises the steps of inputting original data of a training set video of unsafe behaviors to a CNN for performing training and learning, and outputting a spatial eigenvector from the last pooling layer of the CNN; taking the spatial eigenvector as an input of a time recurrent neuralnetwork, learning a time sequence dependency relationship contained in the spatial eigenvector by using the time recurrent neural network to learn a time sequence representation of spatial behaviors,and obtaining an average pooling eigenvector; inputting the average pooling eigenvector to a softmax layer, thereby obtaining a deep mixed learning model of the CNN and the time recurrent neural network, namely, a softmax classifier; and performing online identification on a monitoring video of a construction site by utilizing the softmax classifier to obtain the unsafe behaviors of the construction site. The support can be provided for real-time investigation and correction of the unsafe behaviors in a whole building engineering construction process.

The present invention relates to a personalized travel route recommendation method based on tourist trust. Firstly, photo information with a geographical label and historical tourist information in a network are gathered, a large number of photo information is subjected to preprocessing, reliable interest point information is obtained, then a body database is constructed by using body-based modeling thought, interest point probability is predicted by using the mixed model of Markov and an subject, the travel route generation algorithm based on interest point heat is generated, and finally combined with a user trust weighted tourist route, a final route is recommended to a user. According to the method, the real travel information of users in a social network is fully utilized, a personalized travel route recommendation service can be effectively provided to the user, and the method has a good reference value for transportation service departments and travel agencies.

The invention discloses a device for detecting a storage battery, comprising a CPU, an operational amplifier, a multi-way switch, a digital/analog (D/A) converter, a high-power MOS tube, a coupling capacitor, a programmable bandpass filter and an analog/digital (A/D) converter. The high-power MOS tube is connected on a storage battery discharge detection circuit in series. The CPU is used for controlling discharge of the storage battery so as to generate excitation current. The detected current signals and voltage signals are amplified by the operational amplifier after the coupling capacitorsubtracts the direct current component, and the signals are transmitted to the A/D converter to be changed into digital signals after the programmable bandpass filter gets rid of the interference signals, then the digital signals are transmitted to the CPU to be processed and complex impedance of the storage battery under the corresponding frequency can be obtained after arithmetical operation. The CPU can control the MOS tube via the D/A converter to change the waveform and frequency of the discharge current of the storage battery so as to realize measuring a plurality of frequencies of the storage battery. A detecting method using the device can be used for detecting the storage battery by an AC discharge method in multiple frequency points.

The invention discloses a cluster interval optimizing method for segmental multi-cluster fracturing of a horizontal well of a low-permeability oil and gas reservoir. The cluster interval optimizing method for segmental multi-cluster fracturing of the horizontal well of the low-permeability oil and gas reservoir sequentially comprises the following steps that (1) the induced stress generated by hydraulic fractures in a stratum is calculated; (2) the formation pore pressure after fracturing liquid is leaked off is calculated; (3) formation pore elastic stress after the fracturing liquid is leaked off is calculated; (4) the three induced stress fields and the original ground stress field are superposed, so that a new ground stress field is obtained; (5) facture network waves and the region area are calculated; and (6) a relation curve chart of the fracture cluster interval, the fracture network waves and the region area is drawn with the cluster interval being used as x-coordinates and the fracture network waves and region areas being used as y-coordinates, and the optimal cluster interval is determined. According to the cluster interval optimizing method for segmental multi-cluster fracturing of the horizontal well of the low-permeability oil and gas reservoir, the interference effect of the hydraulic fractures on the original ground stress field is considered, the expanding and shear fracturing behaviors of natural fractures under a complex ground stress field condition are also considered, and the novel cluster interval optimizing method is formed with the optimization goal of obtaining the maximum fracture network wave and the maximum region area; and the novel cluster interval optimizing method is more objective, accurate and practical.

The invention discloses a method for evaluating a reservoir of a fractured well. The method comprises the following steps: S1, establishing an evaluation database M of the reservoir, wherein M is composed of a parameter set X, a sample set U and an index set Y; S2, dividing all the parameters into three kinds, and establishing a three-stage evaluation system including an index layer, an element layer and a target layer; S3, calculating the correlation between each parameter and open-flow capacity in the sample set U, and establishing a single-factor evaluation criterion set V; S4, calculating the influence weight W of each parameter to fracture improvement effect and the influence weight K of each kind of parameters to the fracture improvement effect in the sample set U by using a grey correlation method; S5, calculating and evaluating the membership degree R of each parameter in the object X in four different stages in the single-factor evaluation criterion set V by using normal-distribution membership functions; and S6, carrying out blurring operation on the weight W and the membership degree R, and grading quantifiably and comprehensively. The method for evaluating the reservoir of the fractured well, which is disclosed by the invention, has high objectivity and accuracy; a novel decision method is provided for selecting a fractured improvement well.

The invention discloses an LSTM and SAE-based telephone voice emotion analysis and recognition method; according to the method, voice information is subjected to a series of preprocessing of sampling,quantifying, pre-emphasis, framing, windowing and the like, and then fast fourier transformation is carried out on the voice information to obtain frequency domain characteristics of the voice information, and next, the voice characteristic parameters MFCC are extracted. By adoption of the method, an LSTM+ SAE neural network model is established to train the extracted MFCC characteristic parameters to obtain depth characteristic information of voice signals; the classification accuracy is obtained by combining a full-connection layer and a softmax regression algorithm, and model training is completed; and finally, the MFCC characteristic parameters to be tested are input into a trained model, emotion analysis is carried out on the telephone voice, and the emotion of a speaker is judged.

The invention provides an application evaluation method, a terminal, and a server. The application evaluation method includes the steps: the terminal acquires a test file of a specified application; the terminal executes the test file to test the specified application so as to obtain test data; the terminal reports the test data of the specified application to the server so that the server acquires evaluation results for the specified application according to the test data. Automatic testing execution and data collection for the specified application can be achieved via a third-party evaluation system composed of the terminal and the server, so that uniform testing execution scheduling, data aggregation and evaluation analysis are achieved. The third-party evaluation system is used for evaluation, so that the method is independent and objective as compared with the prior method in which evaluation is completely based on logs recorded by the application itself; the test data obtained, such as response time, are more accurate and comprehensive; accordingly, evaluation results based on the test data are higher in accuracy.

The invention discloses a topic model-fused scene image classification method, and relates to the field of deep learning and image classification. The method comprises the following steps of: preprocessing data sets, and expanding the quantity of obtained data sets so as to obtain an image data format according with deep learning model processing; constructing a convolutional neural network modelaccording with scene image classification, and pre-training the processed image data sets by using a convolutional neural network; and carrying out end-to-end iterative training on the constructed convolutional neural network by using training sets, adjusting parameters in the network, verifying the trained model by using verification sets, modeling extracted scene image features with discrimination ability, extracting hidden topic variables between the features and images so as to obtain image topic distribution represented by a k-dimensional vector, wherein k represents a topic quantity, each image can be considered as a probability distribution diagram formed by a plurality of topics, and scene image classification is realized by utilizing a classifier.

The invention discloses a risk assessment based intelligent navigation method and device, equipment and a storage medium. The risk assessment based intelligent navigation method includes acquiring a route and navigation request sent from a client side, acquiring multiple original navigation routes according to starting location and target location of the route navigation, further acquiring to-be-assessed traffic data corresponding to each navigation route, performing rick assessment on the to-be-assessed traffic data corresponding to each navigation route through a road rick identification model trained in advance to acquire section risk probability of the corresponding road sections, acquiring the total risk probability corresponding to the original navigation routes according to the section risk probability of at least one corresponding navigation road section of each original navigation route, and finally determining the original navigation route with the lowest total risk probability as a recommended navigation route and sending the recommended navigation route to the client side. The risk assessment based intelligent navigation method can realize route planning based on safetyfactors, thereby guaranteeing safety in driving.

The invention discloses a water supplement and algae control method for a large-scale shallow lake water bloom agglomeration water area. The method utilizes a water environment simulation technology, a soft enclosure technology and a dynamic monitoring and scheduling technology and comprises building a lake water environment analogy model, constructing soft enclosure engineering to form a desired water area, carrying out on-line monitoring on the desired water area, building a space-time high precision water environment analogy model of the desired water area, constructing a water quality neural network model and building a flow scheduling system of a water supplement river. The method is a systematic and quantitative technical system which utilizes a river flowing into lake to supply water for a large-scale shallow lake water bloom agglomeration water area so that algal density is controlled. The method builds a defined quantification relationship between supplement water amount and quality and water quality response of a desired water area so that quantitative water environment in the water resource scheduling system is realized, and the problem that the existing water diversion-based alga control engineering measures cannot form a quantitative technical solution so that alga control effects are uncertain or unconspicuous is solved.

The invention provides a wave-front sensor and corrector aligning device in a self-adaptive optical system, which consists of a wave-front sensor, a wave-front recorder, a wave-front corrector, an electric control transverse moving table, a position mismatching evaluating device, a transverse moving table controller and a computer, wherein the electric control transverse moving table can transversely move and rotate, the position of the wave-front corrector is marked in a mode of exerting the voltage to an independent unit of the wave-front corrector through the computer, and the position mismatching between the wave-front sensor and the wave-front corrector is measured through the self wave-front detection capability of the wave-front sensor. Light beams enter the wave-front sensor through being reflected by the wave-front corrector, the face shape information of the wave-front corrector detected by the wave-front sensor is recorded by the wave-front recorder, the position mismatching evaluating device carries out the calculation according to the recorded information of the wave-front recorder and outputs the position mismatching data into the transverse moving table controller, and finally, the transverse moving table controller is used for controlling the electric control transverse moving table for completing the position regulation of the wave-front sensor. The invention can accurately align the positions of the wave-front sensor and the wave-front corrector, can greatly improve the aligning precision and the aligning efficiency of the wave-front sensor and the wave-front corrector, and can ensure the wave-front control capability of the self-adaptive system.

The invention discloses a method and system for forecasting traffic flow data based on exponential smoothing. The method comprises the steps of conducting pre-processing, wherein collected traffic data are pre-processed; correcting errors, wherein filtering is conducted on the pre-processed traffic data according to the exponential smoothing method, reverse recursion is conducted on a filtering result, and therefore the errors in the filtering result are eliminated; conducting forecasting, wherein forecasting is conducted on the traffic data without errors through a cubic exponential smoothing forecasting model, and therefore traffic flow forecasting information is obtained. According to the method and system for forecasting the traffic flow data based on exponential smoothing, the traffic data which are collected in real time are pre-processed, so that abnormity in measured data is eliminated; accumulative errors are eliminated through forward and reverse filtering on the pre-processed data, and the accuracy of the filtering result is guaranteed; the traffic data flow is accurately forecasted through the single-step forecasting method, and a forecasting result has certain objectivity.

The invention discloses a talent ability depicting method based on scientific research accomplishment data and belongs to the data mining field. The method comprises steps that paper ability of all the talents is acquired through calculation based on quality, the publication time, the author order and the reference information of papers published by the talents; based on acceptance states, the application time and the inventor ordering information of application patents, patent ability of all the patents is acquired through calculation; based on the class, the grade, project fund, the accomplishment time and the project personnel ordering information of accomplished projects, project ability of all the talents is acquired through calculation; based on achievements in recent years, the active degree of all the talents is acquired through calculation; based on projection and patent enforcement situations, the practice degree of all the talents is acquired through calculation; and normalization is carried out according to the calculation results of the five aspects, and radar map visual expression is further realized. The method is advantaged in that talent scientific research ability figure construction and visualization are realized according to the scientific research accomplishment database, and the general scientific research ability situations of the talents can be rapidly and visually mastered.

The invention discloses an image fusion quality evaluation method. The image fusion quality evaluation method comprises the steps of obtaining source images, carrying out image preprocessing, carrying out image fusion and carrying out fusion quality evaluation. According to the step of obtaining the source images, the source images need to be synchronous in time and cover the same area in space. According to the step of carrying out image preprocessing, the quadratic polynomial registration method is adopted and the nearest neighbor interpolation method is adopted for resampling. According to the step of carrying out image fusion, the fusion method combining the multiscale analysis method and the component substitution method is adopted for the source image to obtain fusion images through different fusion methods. According to the step of carrying out fusion quality evaluation, cross entropy and structural similarity of the fusion images and the source images are calculated, a weighting function model of the cross entropy and the structural similarity is built, and then a total fusion quality evaluation value under a preset weight is calculated. According to the image fusion quality evaluation method, the problems that evaluation indexes are multiple and related and subjective evaluation varies from person to person in a traditional fusion quality evaluation method are solved. The image fusion quality evaluation method is simple and universal.

The invention discloses a user sag economic loss assessment method based on multi-quality loss function synthesis. The method comprises the steps of counting user sensitive equipment compositions in apower system, and calculating a synthetic voltage tolerance curve of any node; calculating an equipment failure rate, an energy index and voltage sag severity of the node under each voltage sag eventaccording to historical data, and calculating quality losses caused by the equipment failure rate, the energy index and the voltage sag severity ; according to calculation results, weighting the quality losses of four parts including the equipment fault rate, a voltage sag amplitude, the energy index and the voltage sag severity based on an entropy weight method; performing parameter estimation of a quality loss function according to the economic loss generated by voltage sag in a historical record; and performing voltage sag economic loss assessment of a user according to the sag amplitude and duration of current voltage sag to obtain the economic loss of the current voltage sag. The method has the advantages that the objectivity is higher and an assessment result is more accurate.

The invention belongs to the technical field of metal corrosion morphology grade judgment, and discloses a corrosion grade information processing method and system based on image recognition, and themethod comprises the steps: obtaining a labeled laboratory metal morphology picture as a data set; carrying out the de-duplication on the obtained training data set, randomly selecting a half of images of each category as a test set, and taking other images as training set images; expanding the training data set, namely carrying out the data enhancement; building a convolutional neural network model by using a Keras framework, carrying out model training, and storing optimal model parameters; and analyzing the grade of the corrosion morphology of the metal surface by utilizing the trained optimal model. According to the method, the judgment of the metal corrosion morphology grade is realized by using a computer vision technology, so the judgment efficiency is greatly improved and the judgment uniformity and objectivity are ensured under the condition of ensuring the judgment accuracy. The method can assist engineers engaged in material research in judging the metal corrosion grade, andvarious difficulties of a previous judgment method are solved.

The invention relates to a motion identification method based on a human bone joint point distance. The method comprises the following steps of (1) projecting each frame of a bone sequence on three planes of a Cartesian orthogonal system and generating a human bone distribution map; (2) extracting bone joint points in the human bone distribution map; (3) calculating a euclidean distance among the bone joints of each frame of the bone sequence and making the distances of all the joint points form frame distance vectors; (4) making all the frame distance vectors of the bone sequence form a sequence distance matrix according to a time sequence; (5) using a pseudo-color coding method to carry out color coding on a distance two-dimensional matrix and acquiring a color texture map; and (6) using a depth learning method to carry out picture classification so as to complete a human motion detection identification task. The motion identification method based on the bone joint point distance is not influenced by an environment and interaction motion and is suitable for interactive motion identification under a complex scene so that the method possesses a wide application value.

The present invention discloses a rumor recognition method. The method comprises: grabbing marked text content, cleaning and sorting the text, dividing the text into sentences, and storing the text content in sentences into a database; according to the Chinese word segmentation vocabulary, performing word segmentation on the text content which is segmented into sentences, sorting the word segmented content into a model readable and standardized form, and taking the model readable and standardized form as the input content of the model; performing high latitude vectorization association mappingon the word segmented content through the model, performing the weighted combination on word vectors to obtain a sentence vector, a paragraph vector or an article vector, and outputting the vectors from the model; inputting the processed training corpus information to a classifier model for training, and outputting a determination result; and constructing a to-be-detected text function, and performing an effect test on a rumor determination model. According to the method disclosed by the present invention, while reducing the labor cost, the reliability of rumor determination is improved.

The invention discloses a thyroid ultrasound image nodule automatic positioning and identifying method based on USFaster R-CNN, and belongs to the field of artificial intelligence and deep learning. The method comprises the steps of preprocessing a thyroid ultrasound image, building a deep neural network model, and training and optimizing the network model, wherein the deep neural network model comprises a bottom convolution feature extraction network, a candidate box generation network, a feature map pooling layer and a classification and candidate box regression network. A deep learning method is used to realize thyroid ultrasound image feature automatic extraction, candidate box automatic generation, screening and position correction. An automatic positioning and identification functionof thyroid nodules is realized. The method can effectively assist doctors in thyroid ultrasound image diagnosis, improve the objectivity and accuracy of diagnosis, and effectively reduce the workloadof doctors and the omission ratio of small target nodules.

The invention relates to a method for evaluating damage conditions of an asphalt pavement. The method includes the following steps that firstly, pavement damage data is acquired; secondly, the transverse crack evaluation index (TCEI) of the pavement is calculated; thirdly, the pavement patching condition index (PPCI) is calculated; fourthly, the pavement surface damage condition index (PSCI) is calculated; fifthly, attribute weights of the three indexes are calculated by adopting an analytic hierarchy process; sixthly, grade weights of the three indexes are calculated by adopting an entropy method; seventhly, the comprehensive weight is obtained according to the attribute weights and the grade weights of the three indexes; eighthly, an evaluation model of the pavement damage condition index (PDCI) is established, and an evaluation result of the pavement damage condition is obtained according to the calculated the value of the PDCI. The method for evaluating the damage conditions of theasphalt pavement through a variable-weight comprehensive evaluation method is established, the dynamic weight of each evaluation index is calculated by combining the analytic hierarchy process and anentropy weight coefficient method, and the evaluation result is more accurate.

The invention discloses an automatic test analysis processing method and device, a computer device and a storage medium. The method comprises the steps of obtaining a test analysis request, wherein the test analysis request comprises a target system identifier and a target test period; querying a corresponding interface document library based on the target system identifier, and obtaining a totalinterface number corresponding to standard interface data in the interface document library; querying a corresponding test database based on the target system identifier, and obtaining the number of tested interfaces corresponding to the test interface data in the target test period; calculating the total interface number and the tested interface number by adopting a coverage rate formula to obtain an interface coverage rate; and if the interface coverage rate is smaller than a coverage rate threshold value, acquiring missed test interface data based on the test interface data and standard interface data in the interface document library. According to the method, the objectivity of the determined missed test interface can be verified, so that the objectivity and the test quality of testingbased on the missed test interface are ensured.

The invention discloses a method for staining a digital image, comprising the following steps: selecting a color image with the content similar to a black and white image as a color source; respectively extracting characteristic vector space models of the two images; judging the similarity of a target image and the color source image; converting an RGB expression mode of the image to an L alpha beta mode; transmitting color information; and converting an L alpha beta expression mode of the image to an RGB mode so as to form the strained target image. The method has the color source from a color image with similar content, is automatically completed by utilizing brightness information according to an optimal matching algorithm, has objectivity and retains original information of the stainedimage with adding information, i.e. the color of the color source and the like, thereby enhancing the visual effect, the reality sense and the staining success rate; and in addition, the whole colorobtaining and providing process has completely automatic processing, thereby being convenient and fast and only needing normal visual perception capability without needing any professional skills, i.e. drawing, coloring and the like.

The invention discloses a children concentration evaluation system and a method thereof. The method comprises the steps that forehead electroencephalogram of a child is collected, and primitive concentration data is obtained, processed and analyzed to establish a concentration evaluation model based on the electroencephalogram and obtain each item of objective indicators. According to the system,concentration is divided by the concentration evaluation model into six types of a relaxing state, a concentration transferring state, a task state, a focusing state, an absent-minded state and a concentration disappearing state; a plurality of indicators of concentration is computed: relaxing state average concentration, focusing state average concentration, maximum concentration, concentration intensity, concentration endurance, concentration stability and concentration state transferring stat. The system and the method have the advantages that the system and the method help parents to knowthe concentration situation of the child to improve the concentration level of the child, and therefore the improvement of the score of the child is promoted.

The invention provides an infrared spectrum detection method of ginseng and astragalus injection liquid, which comprises the following steps: a. processing injection liquid samples; b. drawing maps; c. carrying out standard control; d. comparing the maps; and e. obtaining the conclusion: observing whether the ginseng and astragalus injection liquid to be detected conforms to the specification of the standard or not through the comparison and whether the maps conform to the standard maps obtained from the standard ginseng and astragalus injection liquid samples or not, and further obtaining the conclusion. The ginseng and astragalus injection liquid with the feature peak near 779, 818, 867 and 1056 and the similarity between 0.98 and 1.00 is selected as qualified products. The invention uses the macroscopical fingerprint performance of the infrared spectrum, the variation features of the infrared spectrogram is directly used on the quality control, or can be directly used on the quality control after digital processing, and the infrared spectrum technology is sufficiently utilized for fast monitoring the quality of the ginseng and astragalus injection liquid, including the stability, the ingredient variation, the adulteration, the impurities, unpredictable quality problems and the like of the ginseng and astragalus injection liquid.