157results about How to "Improve interpretation accuracy" patented technology

A multiattribute frequency division imaging method based on wavelet transformation comprises the following steps: 1) preprocessing the seismic data; 2) executing fine frequency spectrum analysis to the seismic data for confirming the effective frequency spectrum range of seismic data; 3) executing horizon interpretation to the seismic data, and executing processions of interpolation, smoothing, etc.; 4) using seismic data and interpreted seismic horizon as input, adopting a wavelet analyzing technique executing wavelet transformation to the seismic data for obtaining a wavelet transformation frequency division result; 5) computing the instantaneous amplitude, instantaneous frequency or instantaneous phase of wavelet field under the meaning of frequency division (ai-1, ai) according to interpretation requirement; 6) reconstructing the instantaneous amplitude, instantaneous frequency or instantaneous phase data of wavelet field according to interpretation requirement; 7) repeating the steps of 4) to 6) to each seismic channel for obtaining the computing results of all seismic channels; and 8) drafting the computed instantaneous wavelet frequency division data. The method of the invention can increase the recognition capability and detection capability of lithologic trap, stratigraphic trap and small discontinuous object for further increasing the fine prediction precision of container horizon.

The invention relates to a quantitative analogical evaluation method for multiple parameters of a shale gas reservoir. The method comprises the following steps of acquiring the porosity, organic carbon content, methane content, total gas content, gas saturation, brittleness index, thickness and other shale gas reservoir evaluation key parameters of a target layer to be explained and key evaluation parameters of a reference layer with regional representation through logging data, drawing a multi-parameter analogical plate, and observing and comparing by using visual observation to intuitively qualitatively evaluate the gas bearing characteristic of the layer to be explained; according to a fact that an analogical evaluation value=a parameter value of the target layer / a parameter value of the reference layer, calculating the analogical evaluation value of each parameter, calculating a multi-parameter quantitative analogical evaluation index Ia, drawing a multi-parameter quantitative analogical relevance judgment plate, drawing multi-parameter analogical related strength R2, drawing an Ia-R2 evaluation crossplot, and putting the analogical evaluation index Ia-analogical related strength R2 data points of the to-be-explained target layer in the Ia-R2 evaluation crossplot; outputting a result.

The present invention provides a downhole micro-seismic event real-time inversion location method based on grid search. The method comprises: establishing a speed model in a space including a micro-seismic source under the well; performing P-wave and S-wave first arrival time pickup of the micro-seismic event; calculating the degree of polarization and the polarization direction of each channel recorded P-wave first arrival of the micro-seismic event; establishing a inversion target function, and performing the theory first arrival travel time from wave field forward modeling calculation grid points to an observation system; calculating a target function value, and determining the position of the seismic source; and calculating the three-dimensional spatial position coordinates of the seismic source. The method is fast in operation speed and high in efficiency; and moreover, the noise immunity is high, the micro-seismic event with low signal to noise ratio can be subjected to accurate micro-seismic source location to allow the micro-seismic source location result to be more accurate and reliable so as to improve the interpreting precision of the micro-seismic monitoring result.

The invention provides an intelligent method for fusing X-ray dual-energy transmission with Compton backscatter images, and relates to an intelligent technique for fusing X-ray dual-energy transmission with Compton backscatter images in the technical field of radiation detection. The method mainly solves the technical problem that the prior detection image display lacks a method of fusing various types of information in one image for simultaneous display. The method mainly takes an image registration technique as a basis, utilizes an information fusion technique to combine X-ray dual-energy transmission images with Compton backscatter images to give full play to respective advantages, and simultaneously expresses information in various aspects from detected luggage on one fusion image so as to form a more simple and practical platform for displaying and analyzing fusion images. The method is suitable for security inspection display equipment needing to quickly and accurately acquire the information of detected luggage, particularly for equipment sensitively detecting high-density substances with small atomic number.

A computer-aided image interpretation method and a device thereof to easily obtain an accurate image interpretation result are provided. An automatic classification means of the image interpretation device performs automatic classification by one of spectral characteristics, radiometric characteristics, diffuse characteristics, textures and shapes, or combinations thereof and accumulates data to an interpretation result database, for plural features of the same kind obtained by interpreting a remote sensing image obtained with an observation sensor. A means for extracting candidate of modification of interpretation result extracts the candidate of modification of interpretation result by comparing likelihoods that are the automatic classification results. A reinterpretation is performed for the candidate of modification of interpretation, and an interpretation result database is updated by an interpretation result update means. As a result, modification of the interpretation work can be efficiently performed.

The present disclosures relates to a method of detecting, classifying, and counting dots in an image of a tissue specimen comprising detecting dots in an image of the tissue sample that meet criteria for absorbance strength, black unmixed image channel strength, red unmixed image channel strength, and a difference of Gaussian threshold, wherein the detected dots correspond to in situ hybridization signals in the tissue samples; classifying the detected dots as belonging to a black in situ hybridization signal or to a red in situ hybridization signal; and calculating a ratio of those dots belonging to the black in situ hybridization signal and those belonging to the red in situ hybridization signal.

The invention relates to a numerical analysis method for dense gas multi-section volume fracturing horizontal well, comprising the following steps: step 1, establishing a geological structure model ofthe network fracture of the multi-section volume fracturing horizontal well; 2, establishing a heterogeneous geological body of fractured horizontal well network fracture; 3, establish a well test mathematical model of a compact gas multi-stage fracturing horizontal well base on that fracture network form; 4, carrying out numerical solution on a network fractured horizontal well test model by using a mixed element finite element method; 5, generating a multi-section volume fracturing horizontal well actual t well curve according to that well test data, and fitting the theoretical curve solvedby the model in the step 4 with the actual measurement curve to obtain the well test interpretation parameters. This method is of great significance to improve the interpretation accuracy of volume fracturing horizontal wells, to obtain the parameters of volume fracturing network and to evaluate the effect of volume fracturing. The invention has the characteristics of good well test curve fitting, accurate interpretation result, strong practicability and the like.

The invention discloses a remote-sensing image multi-scale object-oriented classification method based on joint sparsity representation. The method includes the steps of firstly, mining a spatial characteristic of a remote-sensing image and constructing an augmentation characteristic through the combination of the spatial characteristic and a spectral characteristic, secondly, constructing a redundant dictionary by means of a training pixel sample and the augmentation characteristic, carrying out joint sparsity representation on initially segmented patches by the adoption of the redundant dictionary, thirdly, carrying out homogeneity analysis and reconstruction effect analysis on the patches on the basis of the joint sparsity representation, and finally, judging whether patch segmentation is reasonable according to analysis results of the homogeneity analysis and the reconstruction effect analysis, and carrying out classification identification on the patches meeting the requirements of the homogeneity level and the reconstruction effect. The method achieves organic combination of the segmentation process and the classification process so as to obtain proper ground object patches for classification, achieves classification identification of the remote-sensing image on the object level, can obtain a classification result meeting the requirement of visual interpretation, greatly improves interpretation precision of the remote-sensing image, and has great application value.

A car side video assist system activated by light signals is revealed. The system includes at least two cameras respectively disposed on the left, right or rear side of a car for capturing images at corresponding sides and forming image signal sources. By using different light signals including left / right turn, warning or reversing signals as the activation signal sources, at least one camera is selected and activated and the images capture form at least one image / picture on a screen. The video signal source switch processor further includes a light signal interpretation processor that starts interpretation after a preset critical time such as 8 milliseconds when a light signal is activated and input. The interpretation continues for a preset period of time such as 300 milliseconds to output the result for preventing misinterpretation and interpreting the light signal is a single left / right turn signal or a warning signal accurately.

The invention relates to the field of microbiological detection, in particular to a method and a device for microbiological analysis of a host sample. The method comprises the following steps: (1) performing first filtering processing on a sequencing data set from a host sample by adopting a host genome database so as to remove sequencing data which can be compared with the host genome database from the sequencing data set; (2) performing second filtering processing on the sequencing data set by adopting a homologous database so as to remove the sequencing data which can be compared with the homologous database from the sequencing data set; and (3) comparing the sequencing data set subjected to the first filtering treatment and the second filtering treatment with a microbial genome database so as to determine microbial sequencing data from the microorganisms in the sequencing data set. By applying the method and the device provided by the invention, rapid and accurate analysis and detection of microorganisms in a host can be realized.

The invention relates to a suppression method and a suppression device for surface wave interference for a seismic record. The suppression method comprises the steps of acquiring a seismic record xi(t), acquiring a surface wave interference high cut-off frequency fg according to the seismic record xi(t), confirming a changing curve q(t) according to the surface wave interference high cut-off frequency fg, acquiring a seismic record yi(t) of a surface wave interference frequency band by conducting low-pass filtering with a high cut-off frequency of fg on the seismic record xi(t), acquiring a seismic record zi(t) of non-surface wave interference frequency range by conducting band-pass filtering with a low cut-off frequency of fg and a high cut-off frequency of 2fg on the seismic record xi(t), acquiring an amplitude variation curve py(t) according to the seismic record yi(t) of the surface wave interference frequency band, acquiring an amplitude variation curve pz(t) according to the seismic record zi(t) of the non-surface wave interference frequency range, acquiring an interference frequency band seismic record by modulating an surface wave interference frequency range yi(t) according to the changing curve q(t), the amplitude variation curve py(t) and the amplitude variation curve pz(t), and acquiring a seismic record after surface wave interference suppression according to the surface wave interference frequency range yi(t) and the seismic record xi(t) of the interference frequency band seismic record.

The invention discloses a data processing method. The method comprises: acquiring first lead monitoring data including at least one kind of lead data from a lead sleeping apparatus in real time; for each kind of lead data among the first lead monitoring data, determining invalid data in the corresponding lead data by using a clustering algorithm to obtain second lead detection data; and on the basis of an association relationship of all kinds of lead data, determining invalid data with conflicts among all kinds of lead data in the second lead monitoring data so as to obtain third lead monitoring data; and outputting the third lead monitoring data as valid data. Meanwhile, the invention also discloses a data processing apparatus.

The invention discloses a heavy oil-based quantitative identification chart interpretation method with gas logging. An oil-water layer is quantitatively identified by comprehensively applying gas logging parameters, the concept that the oil-water layer is identified by use of a concentric circle chart of parameters of a methane-ethane logarithmic ratio and a light-heavy hydrocarbon logarithmic ratio is provided for the first time. The method is characterized by comprising the steps of: a step of parameter acquisition, selecting various parameters including a heavy hydrocarbon component in gas logging; a step of parameter preprocessing, carrying out parameter evaluation by use of the ratio of the sum of hydrocarbon components to total hydrocarbon, and excluding an oil layer with the thickness of less than 1m in consideration of the limitation of the gas logging technology; a step of parameter calculation, calculating two derivative parameters of the methane-ethane logarithmic ratio and the light-heavy hydrocarbon logarithmic ratio; and a step of establishment of an oil-layer quantitative identification chart, respectively drawing a graphic bar by use of gas logging hydrocarbon component derivative parameters of the methane-ethane logarithmic ratio and the light-heavy hydrocarbon logarithmic ratio according to a drilled measured result. According to the method, the oil-water layer in a reservoir stratum is qualitatively and semi-quantitatively identified by use of a comprehensive logging technology, the first-hand logging information can be fully discovered, and the oil-water layer can be evaluated rapidly and reliably.

The invention belongs to the field of photoelectricity testing and relates to a large-diameter parallel light pipe wavefront and image surface position calibration device and method. The device comprises a fiber laser, a two-dimension precision long guiding track, a CCD camera and a control unit. The method comprises the steps that (1) the CCD camera is arranged on the two-dimension precision long guiding track; (2) fiber laser power is adjusted until the CCD camera can receive fiber laser light intensity; (3) the CCD camera obtains center-of-mass coordinates of image points emitted by the fiber laser at different positions of the two-dimension precision long guiding track; (4) the CCD camera obtains center-of-mass coordinates of image points emitted by a parallel light pipe to be calibrated at different positions of the two-dimension precision long guiding track; (5) the wavefront position of the parallel light pipe to be calibrated is determined; and (6) the image surface position of the parallel light pipe to be calibrated is determined. Accurate testing of large-diameter parallel light pipe wavefront and focal plane positions can be achieved.

The invention discloses an X-ray film hand bone maturity interpretation method based on a deep neural network, and the method comprises the steps: carrying out the unified preprocessing of an originalhand bone image, and improving an X-ray film with a poor color to obtain Output1; sampling and training the model M1 to obtain an Output2; training Faster-RCNN model, and segmenting 13 key bone blocks to obtain Output 3 in accordance with RUS- CHN standard; taking Output3 as an input data format standard, sampling and training a model M3, and providing a local feature map F1; taking Output2 as aninput data format standard, sampling and training a model M4, and providing a global feature map F2; combining the M3 model and the M4 model in a manner of connecting F1 and F2 in parallel; and training the model M5 to enable the model M5 to output an optimal bone maturity interpretation result by learning the two characteristic patterns F1 and F2. The maturity score of each key bone block of thehand bone X-ray film can be automatically obtained.

The invention provides a method for accurately settling agricultural disaster claim based on remote sensing data and digital field, involving remote sensing technology, GPS technology, GIS technology,Using high-definition remote sensing image data (remote sensing satellite data or aerial photograph data of unmanned aerial vehicle) and ground survey data to interpret the disaster situation of crops, digital field data is combined to accurately locate the scale of farmers and fields, so as to realize online inquiry of agricultural disaster degree and disaster area according to the information of the fields and the right holders. The invention provides a method for accurately settling agricultural disaster claim based on remote sensing data and digital field, which only needs to sample the disaster areas with different degrees and a small number of people to carry out on-the-spot investigation to realize fast, Accurate identification and inquiry of the disaster situation of each farmer and field, not only improving the work efficiency, but also saving a lot of manpower and material resources in agricultural insurance claim settlement.

The invention discloses a shale oil horizontal well track design and on-site tracking adjustment research method. The method comprises shale oil sweet spot identification and evaluation, horizontal well optimization and track design and shale oil horizontal well on-site tracking adjustment. A 'four-optimal-two-precision' method formed by the shale oil horizontal well track design and on-site tracking adjustment research method lays a foundation for realizing integration of high and stable yield of shale oil in a blocked lake basin and production and storage increase. A set of technical methodis provided for carrying out horizontal well position optimization design research and drilling well dynamic tracking analysis in a shale oil development area, and the method has great reference and popularization significance.

The invention discloses a method for logging well by saturation of a carbon hydrogen ratio to a stratum fluid. The method comprises the following steps of (1) recording on-site data; (2) and analyzing the data, including (a) correcting the depth and dividing a lithologic profile, (b) establishing a "carbon hydrogen ratio interpretation model" having an oil layer water logging degree standard interpretation chart and selecting carbon hydrogen ratio interpretation parameters CHRw and the maximum value CHRmax, (c) establishing a carbon hydrogen ratio interpretation parameter card, (d) solving water saturation, oil saturation, water content and oil displacement efficiency, (e) evaluating oil or remaining oil saturation, movable oil saturation and oil layer water logging degree of a reservoir stratum, and (f) making out a result map and interpreting an analysis report. According to the method, abundance of carbon and hydrogen elements in the stratum fluid is detected, double unification connection is carried out based on the ratio of the carbon element to the hydrogen element, and the oil saturation, the oil layer water logging degree and the water content of the reservoir stratum are subjected to full quantitative evaluation, so that accuracy of the data is improved, the application effect is improved remarkably, and the application range is expanded.

The invention relates to a mixed stratigraphic absorption compensation method in seismic data processing in the geophysical exploration technology. The method comprises the following steps: transforming a seismic wave field signal which is received by a current channel from a time domain to a frequency domain, mapping from a frequency grid in which the seismic wave field signal is located to a new frequency grid, performing frequency-dependent proportional zoom, transforming to the time domain for getting the wave field signal with the seismic wave frequency dispersion effect caused by corrected formation absorption and adopting a time domain gain limit wave filter to perform cyclic convolution for getting the new wave field signal. In the method, the fast frequency dispersion correction is performed in the frequency domain, the stable amplitude compensation is performed in the time domain, the stability and the high efficiency during the absorption compensation process are ensured and the resolution of seismic data and the accuracy of interpretation of a fine bed are improved.

The embodiment of the invention discloses a seismic-data-based thin layer automatic interpretation and thickness prediction method and a seismic-data-based thin layer automatic interpretation and thickness prediction device. The method comprises the following steps of: acquiring seismic data, processing the seismic data to acquire superposed seismic data, determining a target layer which corresponds to the thin layer, and extracting seismic wavelets; preliminarily interpreting the top or the bottom of the thin layer, and determining an automatic tracking time window [t-T1, t+T2] of the thin layer; for each channel of the seismic data of the superposed seismic data, intercepting the current seismic channel data according to the automatic tracking time window of the thin layer in the current seismic channel, and recording the intercepted seismic channel data to be f; setting N reflection coefficient position modes, and uniquely determining each reflection coefficient position mode according to a matrix Hi=[hi1, hi2, ..., and hiMi], wherein i is equal to 1,2, ..., and N; acquiring the optimized reflection coefficient amplitude combination ai and the optimized synthesized seismic record fi which correspond to each reflection coefficient position mode; acquiring the optimized reflection coefficient position mode Hi; acquiring the automatic interpretation time tup and tdown on the top or at the bottom of the thin layer; and acquiring the time thickness delta t of the thin layer according to the tup and tdown. By the method, the top and bottom of the thin layer can be interpreted, and the interpretation precision is high.

The invention belongs to the field of mineral exploration, and aims at solving the problems that the physical heterogeneity of sand bodies in sandstone-type uranium ore stratums in a research area ishigh, and conventional hole-permeability fitting formula accounts for low permeability. The method for calculating the permeability of the sandstone-type uranium ore sand body based on the flow unit classification is provided, and the stratum permeability explanation precision is improved. The method comprises the following steps: 1, calculating a flow unit index of a sample point according to actually measured physical property data of a core of a coring well section; Step 2, realizing reservoir classification by applying a probability graph method; Step 3, establishing a quantitative relation between the flow unit index and the logging response based on five logging curve data of quantitative gamma, natural gamma, density, apparent resistivity and sonic time difference; Step 4, on the basis of flow unit index classification, respectively establishing holes according to different types of reservoirs; a seepage relational expression; Step 5, performing reservoir classification; 6, obtaining a stratum interpretation permeability value; and step 7, drawing a permeability spatial distribution diagram, and establishing an ore searching model.

The invention discloses a carbonate rock reservoir logging identification method based on empirical mode decomposition and energy entropy discrimination. According to outcrop and rock core information, carbonate rock reservoirs are divided into three types, i.e., karst type reservoirs, karst fracture-cave composite type reservoirs and micro-pore type reservoirs, therefore making clear microscopic and macroscopic characteristics of different reservoirs. Single-well reservoirs are calibrated by means of rock core information, imaging logging and array acoustic logging information, and typical logging response characteristics of different reservoirs are qualitatively described. An automatic reservoir identification method based on logging information empirical mode decomposition and energy entropy discriminant analysis is proposed, thereby effectively improving the reservoir identification accuracy rate. The method gets rid of uncertainty of traditional mono-stratum evaluation, relatively meticulously extracts the change law of inter-stratum logging response, and effectively solving the problem that it is difficult to identify the reservoir type during carbonate rock petroleum reservoir exploitation.

The invention discloses a third-generation coherence cube algorithm fast realization method based on recursion and a power method. The recursion and the powder method for selecting an initial vector are used for quickly realizing a third-generation coherence cube algorithm. By utilizing the time / space recursion, the computation for establishing a covariance matrix can be greatly reduced; and when the covariance matrix is characteristically decomposed to get a main characteristic value, the initial vector of the power method is reasonably selected, so that the iteration times for calculating the main characteristic value of the covariance matrix by utilizing the power method can be reduced; and therefore, the computation of the third-generation coherence cube algorithm is greatly reduced, the computation time is reduced, and the error is small.

The invention provides a method for chart interpretation of the water content of oil well. The method comprises the steps that 1, multiple experiments are carried out through an oil well simulation experiment device and the standard water holding rate inside the oil well is measured; 2, according to experiment results of the step 1, a form and an array for chart interpretation of the water holding rate-the water content and a general interpretation chart are made; 3, a total flow numerical value of fluid inside the oil well is obtained according to flow logging information; 4, according to the logging information or drilling data, a well deviation numerical value of a well section to be treated is obtained; 5, according to the characteristics of a water holding rate instrument and a log response, the water holding rate inside the oil well is calculated; 6, chart interpretation is conducted on the water holding rate and the oil-water yield is calculated. The method for chart interpretation of the water content of the oil well is suitable for interpretation of the water content of any non-flow-collecting water holding rate instrument, the water content is no longer obtained according to manual qualitative judgments, the water content is obtained in a quantitative mode according to the interpretation chart, and the interpretation accuracy is improved.

The invention provides a method and device for interpreting an oil field water logging layer by using a state space model, and relates to the technical field of logging data interpretation. The method includes: performing basic interpretation unit division on an oil field whole well segment, and determining basic interpretation unit layer sections; performing initial condition water logging condition determination on the basic interpretation unit layer sections, and forming an initial condition water logging condition determination result; performing target reservoir water logging condition determination on various basic interpretation unit layer sections by using a state space interpretation model according to the initial condition water logging condition determination result, and forming target reservoir water logging condition determination results corresponding to various basic interpretation unit layer sections; and acquiring target reservoir parameters of the basic interpretation unit layer sections by using a dual formation water specific resistance model. The method and device can achieve accurate description of the reservoir water logging condition, can greatly improve the precision of well logging interpretation of a water logging layer, and can meet the demand of oil field development for water logging layer interpretation.

An apparatus for indicating a health-related condition of a subject has an input interface (20), a predictor (30), and an output interface (25), the input interface (20) for receiving a sequence of samples of a first biological quantity derived by a first measurement method, the first measurement method being an invasive measurement and having a first impact on the subject, and for receiving a sequence of samples of a second biological quantity derived by a second measurement method, the second measurement method being a non-invasive measurement and having a second impact on the subject, wherein the first biological quantity gives a more accurate indication of the health-related condition of the subject than the second biological quantity, wherein the first biological quantity and the second biological quantity have a correlation to the health-related condition of the subject, and wherein the second impact is smaller than the first impact, a predictor (30) for providing, for a certain time, for which no sample for the first biological quantity exists, an estimated value of the first biological quantity using samples for the first biological quantity and, as far as available, samples for the second quantity; and an output interface (25) for outputting the estimated value or data derived from the estimated value so that an indication for the health-related condition of the subject is obtained.

The invention provides a method for accurately verifying and protecting agricultural insurance based on remote sensing data and digital field, crop species and crop areas are identified using high-resolution remote sensing image data (remote sensing satellite data or aerial photographs of unmanned aerial vehicles) and ground survey results, by Combining digital field data, the farmer scale and field scale are accurately located, so as to realize the online inquiry of crop species and area and agricultural insurance online protection function according to the field information and the ascertained right holder information. The on-line verifying and protection method for agricultural insurance based on the agricultural remote sensing technology can realize the on-line verifying and protectionof the farmer household and the farmland only by a small amount of field sampling investigation, which not only improves the work efficiency, but also saves a large amount of manpower and material resources in the verifying and protection work of the agricultural insurance.

The invention relates to a calibration method for improving the seismic interpretation precision of fault terrace structures, and belongs to the field of oil and gas rolling development. Single wells in fault terrace structures are selected for well synthesis recording. The seismic time-depth relationship in each of the fault terraces where the selected single wells are located is determined. The corresponding relationship between the drilled formations of all the wells in each fault terrace and earthquake is established based on the time-depth relationship between the drilled formation of the selected well in the fault terrace and the seismic phase of the corresponding fault terrace. For drilling of single wells in different fault terraces, the discordogenic fault depth of a fault terrace in which a single well is drilled is used as a boundary, corresponding time-depth relationship data is extracted and spliced according to the fault terrace position where each section of a well body is located, and the seismic time-depth relationship of more than two drilled fault terrace single wells is established. The seismic interpretation precision of fault terrace structures is improved.

The invention relates to a metagenome or macrotranscriptome sequencing data automatic analysis method and system and belongs to the technical field of data gene detection. According to the method, a CRP (clinically reported pathogen) database and a background library are compared with differences of negative control samples to remove redundant information; a report strain is selected through ranking of strains in the genus; and finally, based on a CCRP database, the strains are screened and filtered again to prevent leakage, the report strain is obtained, and a report is automatically generated. According to the method and system, the manual interpretation process is automated, the interpretation speed and accuracy are improved, and meanwhile, backtracking of historical information is brought into the interpretation process, so that the interpretation accuracy and reliability are improved.

The present application provides a method and system for interpreting the shale reservoir fractureability based on statistical petrophysics. The method comprises subjecting the acquired logging data of each facies to kernel function non-parametric probability density estimation so as to generate two-dimensional probability density functions corresponding to preset seismic attribute combinations; by using a Bayesian classification criterion, performing self-classification screening on each of the seismic attribute combinations according to each of the two-dimensional probability density functions to generate an optimal seismic attribute combination; and performing seismic inversion on the acquired seismic data to generate an inversion profile corresponding to the optimal seismic attribute combination; and by using the Bayesian classification criterion, performing fractureability interpretation on the inversion profile corresponding to the optimal seismic attribute combination accordingto the two-dimensional probability density function corresponding to the optimal seismic attribute combination. The method has the beneficial effects of taking account of the respective advantages ofa mineral brittleness index and an elastic brittleness index, optimizing the evaluation criterion of shale fractureability and improving the accuracy of seismic fractureability quantitative seismic interpretation.