CN112800589B - Oil-water two-phase flow relative permeation grid coarsening method based on artificial intelligence - Google Patents
Oil-water two-phase flow relative permeation grid coarsening method based on artificial intelligence Download PDFInfo
- Publication number
- CN112800589B CN112800589B CN202110023178.8A CN202110023178A CN112800589B CN 112800589 B CN112800589 B CN 112800589B CN 202110023178 A CN202110023178 A CN 202110023178A CN 112800589 B CN112800589 B CN 112800589B
- Authority
- CN
- China
- Prior art keywords
- coarse
- grid
- permeability
- sample set
- grids
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Abstract
The invention provides an oil-water two-phase flow relative infiltration grid coarsening method based on artificial intelligence, which comprises the following steps of 1) establishing a geological model; 2) determining the size and the number of the coarse grids, and dividing the coarse grids; 3) extracting the coarse grids with the set proportion and recording the coarse grids as a sample set F1, recording the rest coarse grids as a sample set F2, and performing relative permeability coarsening calculation on the sample set F1 to obtain the coarse-scale relative permeability of the coarse grids in the sample set F1; 4) preprocessing data of all coarse grid permeability in the geological model; 5) training a machine learning algorithm by using the distribution characteristics of the permeability of each coarse grid in the sample set F1 and the coarse-scale relative permeability data of the coarse grid, and obtaining a prediction model of the coarse-scale relative permeability of the coarse grid by a cross-folding cross-validation method; 6) predicting the coarse-scale relative permeability of the coarse grid in the sample set F2 by adopting a prediction model; 7) and performing reservoir numerical simulation calculation by using the coarse-scale relative permeability in F1 and the predicted coarse-scale relative permeability in F2.
Description
Technical Field
The invention belongs to the technical field of numerical reservoir simulation, and particularly relates to an oil-water two-phase flow relative infiltration grid coarsening method based on artificial intelligence.
Background
Numerical simulation is an important part in oil and gas field development, can predict oil field yield, oil, gas and water distribution states and the like, is widely applied to development scheme optimization and later oil field fine management, and can help oil companies to achieve the purposes of cost reduction and efficiency improvement. Large field development projects are often subjected to repeated detailed numerical simulation studies in order to arrive at an optimal development solution. Reservoir numerical simulation is based on a static geologic model. In order to describe the heterogeneity of the oil reservoir and the small-scale structure and stratum changes, the meshing of the geological model is usually fine, which results in that the number of meshes can reach millions to tens of millions or even higher. And the numerical reservoir simulation needs to solve a complex dynamic partial differential equation, and the modeling complexity is far higher than that of a static geological model. Due to the limitation of the operational capability of the computer and the numerical simulation software, the number of grids which can be borne by the numerical reservoir simulation is far less than that of the geological model. Too many grids not only make the calculation slow, but also cause poor calculation convergence and large errors, and influence the reliability of the simulation result. Therefore, for a reservoir model in oil and gas field development, calculation needs to be performed after a fine geological model is coarsened.
The grid coarsening is to coarsen the fine-scale model into an equivalent coarse-scale model, not only considering the bearing capacity of the oil reservoir numerical simulation software on the grid quantity, but also keeping the oil reservoir physical property and the seepage characteristic of the original fine-scale model as much as possible. However, the grid coarsening method needs to solve information such as pressure and saturation changing along with time on the fine-scale model, and needs to perform a large amount of 'repetitive' calculation on each coarse-scale grid, so that the time consumption of the grid coarsening calculation process is long. Therefore, how to accelerate the mesh coarsening efficiency is a problem to be further solved in the existing mesh coarsening technology.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provides an oil-water two-phase flow relative penetration grid coarsening method based on artificial intelligence, which can obviously improve the coarsening speed of a grid on the premise of ensuring the calculation precision.
The purpose of the invention can be realized by the following technical scheme: an oil-water two-phase flow relative permeation grid coarsening method based on artificial intelligence comprises the following steps:
1) establishing a geological model according to the existing production data;
2) determining the size and the number of the geological model to be coarsened into the coarse grids, and dividing the coarse grids for the geological model according to the set size and the set number;
3) randomly extracting coarse grids with a set proportion from the geological model and recording the coarse grids as a sample set F1, recording the rest coarse grids as a sample set F2, and performing relative permeability coarsening calculation on the coarse grids in the sample set F1 to obtain the coarse-scale relative permeability of the coarse grids in the sample set F1;
4) preprocessing data of all coarse grid permeability in the geological model;
5) training a machine learning algorithm by using the distribution characteristics of the permeability of each coarse grid in the sample set F1 and the coarse-scale relative permeability data of the coarse grid, and obtaining a prediction model of the coarse-scale relative permeability of the coarse grid by a cross-folding cross-validation method;
6) predicting the coarse grids in the sample set F2 by using the prediction model generated in the step 5), and obtaining the predicted coarse-scale relative permeability of each coarse grid in the sample set F2;
7) and performing reservoir numerical simulation calculation by using the coarse-scale relative permeability data of the coarse grid in the sample set F1 and the predicted coarse-scale relative permeability data of the coarse grid in the sample set F2.
In the oil-water two-phase flow relative permeability grid coarsening method based on artificial intelligence, the calculation and acquisition processes of permeability and relative permeability are the prior art. The machine learning algorithm is an existing algorithm. The ten-fold cross-validation method is the prior art.
In the above method for coarsening the oil-water two-phase flow relative penetration grid based on artificial intelligence, in step 4), the method for preprocessing the coarse grid permeability data in the geological model is as follows: firstly, making ln logarithmic transformation on the permeability of all fine grids in the geological model, and then making characteristic scaling treatment on each coarse grid of the geological model, wherein the characteristic scaling treatment formula is shown as (a):
wherein x is i For each fine grid permeability, x, in the coarse grid mean Is the average of the permeabilities of all the fine meshes in the coarse mesh, x max Is the maximum value of permeability, x, of all the fine meshes in the coarse mesh min Is the minimum value, x ', of the permeabilities of all the fine meshes in the coarse mesh' i And the fine grid permeability after the features in the coarse grid are scaled.
In the above oil-water two-phase flow relative penetration grid coarsening method based on artificial intelligence, in step 5), the distribution characteristic of the permeability of each coarse grid in the sample set F1 is a result obtained by preprocessing the permeability data of each fine grid in the coarse grid.
In the method for coarsening the oil-water two-phase flow relative penetration grid based on the artificial intelligence, in the step 5), the distribution characteristic of the permeability of each coarse grid in the sample set F1 is that the permeability field of the fine grid in the coarse grid is drawn into a picture, and a machine learning algorithm is trained in a picture recognition mode, so that a more visual visualization effect is achieved.
In the above oil-water two-phase flow relative penetration grid coarsening method based on artificial intelligence, in step 5), the dimension reduction processing is performed on the distribution characteristics of the penetration rate of each coarse grid in the sample set F1 to accelerate the training speed of the machine learning algorithm.
In the above oil-water two-phase flow relative penetration grid coarsening method based on artificial intelligence, in step 5), a machine learning algorithm adopts a classification algorithm or a regression algorithm.
Compared with the prior art, the oil-water two-phase flow relative permeation grid coarsening method based on artificial intelligence has the following advantages:
the method takes the permeability characteristics of the coarse grids and the relative permeability of the coarse scales as training samples to train a machine learning algorithm to obtain a prediction model, and predicts the grids which are not subjected to coarsening calculation. The method can avoid the grid coarsening calculation process of repeatability, obviously speed up the grid coarsening, simultaneously guarantee higher precision requirement, and has very high practical value for improving the numerical simulation efficiency of the oil reservoir and accelerating the intellectualization of the numerical simulation of the oil reservoir.
Drawings
FIG. 1 is a block flow diagram of the present invention.
Fig. 2 is a flow chart of an embodiment of the present invention.
Fig. 3 is a comparison graph of the calculation results of the grid coarsening method of the present invention and the conventional grid coarsening method.
Fig. 4 is a comparison graph of computation time of the grid coarsening method of the present invention and a conventional grid coarsening method.
Detailed Description
The following description of the embodiments of the present invention will be made with reference to the accompanying drawings:
as shown in figure 1, the oil-water two-phase flow relative permeation grid coarsening method based on artificial intelligence comprises the following steps:
1) establishing a geological model according to the existing production data;
2) determining the size and the number of the geological model to be coarsely formed into coarse grids, and dividing the coarse grids for the geological model according to the set size and the set number;
3) randomly extracting coarse grids with a set proportion from the geological model and recording the coarse grids as a sample set F1, recording the rest coarse grids as a sample set F2, and performing relative permeability coarsening calculation on the coarse grids in the sample set F1 to obtain the coarse-scale relative permeability of the coarse grids in the sample set F1;
4) preprocessing data of all coarse grid permeability in the geological model;
5) training a machine learning algorithm by using the distribution characteristics of the permeability of each coarse grid in the sample set F1 and the coarse-scale relative permeability data of the coarse grid, and obtaining a prediction model of the coarse-scale relative permeability of the coarse grid by a cross-turn verification method;
6) predicting the coarse grids in the sample set F2 by adopting the prediction model generated in the step 5), and obtaining the predicted coarse-scale relative permeability of each coarse grid in the sample set F2;
7) and performing reservoir numerical simulation calculation by using the coarse-scale relative permeability data of the coarse grid in the sample set F1 and the predicted coarse-scale relative permeability data of the coarse grid in the sample set F2.
In the oil-water two-phase flow relative permeability grid coarsening method based on artificial intelligence, the calculation and acquisition processes of permeability and relative permeability are the prior art. The machine learning algorithm is an existing algorithm. The ten-fold cross-validation method is the prior art.
In the step 4), the data preprocessing mode of the coarse grid permeability data in the geological model is as follows: firstly, making ln logarithmic transformation on the permeability of all fine grids in the geological model, and then making characteristic scaling treatment on each coarse grid of the geological model, wherein the characteristic scaling treatment formula is shown as (a):
wherein x is i For each fine grid permeability, x, in the coarse grid mean Is the average of the permeabilities of all the fine meshes in the coarse mesh, x max Is the maximum value of permeability, x, of all the fine meshes in the coarse mesh min Is the minimum value, x ', of the permeabilities of all the fine meshes in the coarse mesh' i And the fine grid permeability after the features in the coarse grid are scaled.
In step 5), the distribution characteristic data of the permeability of each coarse grid in the sample set F1 is a distribution result of preprocessing the permeability data of each fine grid in the coarse grid.
In the step 5), the distribution characteristic of the permeability of each coarse grid in the sample set F1 is that the permeability field of the fine grid in the coarse grid is drawn into a picture, and a machine learning algorithm is trained in a picture recognition mode to achieve a more visual visualization effect.
In step 5), the distribution characteristics of each coarse grid permeability in the sample set F1 are subjected to dimensionality reduction to accelerate the training speed of the machine learning algorithm.
In step 5), the machine learning algorithm adopts a classification algorithm or a regression algorithm.
Compared with the prior art, the oil-water two-phase flow relative penetration grid coarsening method based on artificial intelligence has the following advantages:
the method takes the permeability characteristics of the coarse grids and the relative permeability of the coarse scales as training samples to train a machine learning algorithm to obtain a prediction model, and predicts the grids which are not subjected to coarsening calculation. The method can avoid the grid coarsening calculation process of repeatability, obviously speed up the grid coarsening, simultaneously ensure higher precision requirement, and has very high practical value for improving the numerical simulation efficiency of the oil reservoir and accelerating the intellectualization of the numerical simulation of the oil reservoir.
As shown in fig. 2, the specific embodiment is as follows:
based on the method, the permeability of the geological model and the relative permeability data of the coarse scale are used for training a random forest algorithm, and the method specifically comprises the following steps:
the first step is as follows: a geological model consisting of 2000 x 2000 fine grids is built with the goal of coarsening it into a coarse scale model consisting of 200 x 200 coarse grid systems. Considering the problem of two-phase seepage of water flooding, setting the boundary conditions as upper and lower boundary closure, the left side is a water injection end, and the right side is an oil extraction end.
The second step is that: 5000 coarse grids (marked as a sample set F1) are randomly selected to carry out relative permeability coarsening calculation to obtain coarse scale relative permeability data of the coarse grids in F1, and the rest 4.5 ten thousand coarse grids which are not subjected to coarsening calculation are marked as a sample set F2.
The third step: in order to better extract the heterogeneity of each coarse grid so as to facilitate the recognition of a machine learning algorithm, the permeability of the coarse grid of the geological model is subjected to data preprocessing, and the processing method comprises the following steps: firstly, ln logarithmic transformation is carried out on the permeability, and characteristic scaling processing is carried out on all the coarse grids, wherein the characteristic scaling processing formula is as follows:
wherein x is i Permeability, x, for each fine mesh in the coarse mesh mean Is the average of the permeabilities of all the fine meshes in the coarse mesh, x max Is the maximum value of permeability, x, of all the fine meshes in the coarse mesh min The minimum value of the permeability of all the fine grids in the coarse grid is obtained; x' i And the fine grid permeability after the coarse grid characteristic is scaled.
The fourth step: and training a random forest algorithm by using the permeability of the coarse grid and the relative permeability data of the coarse scale in F1 to obtain a prediction model of the relative permeability of the coarse scale.
The fifth step: and predicting the coarse-scale relative permeability of the coarse grid in the F2 by using the prediction model obtained in the fourth step.
And a sixth step: and performing reservoir numerical simulation calculation by using the relative permeability data of the coarse scales of the coarse grids in F1 and F2 to obtain data such as oil-water flow and the like, and recording the time required by coarsening and simulation.
The comparative examples are as follows:
and performing traditional grid coarsening and numerical simulation calculation by using a geological model consisting of 2000 multiplied by 2000 fine grids established in the specific embodiment to obtain data such as oil-water flow and the like, and recording time required by coarsening and simulation.
FIG. 3 is a comparison of the calculation results of the grid coarsening numerical simulation and the traditional grid coarsening numerical simulation based on the relative permeability of the oil-water two-phase flow of artificial intelligence, wherein PVI is dimensionless time and represents different water injection stages, and the calculation formula is
Wherein q is t Is the total flow (m) 3 S); t is time(s); v. of p Is the total pore volume (m) 3 )。
FIG. 4 is a comparison of calculation time of grid coarsening numerical simulation and traditional grid coarsening numerical simulation based on artificial intelligence relative permeability of oil-water two-phase flow.
As can be seen from fig. 3 and 4, compared with the conventional grid coarsening numerical simulation result, the grid coarsening numerical simulation precision predicted by machine learning is high, and the efficiency is improved by about 7.3 times.
It is to be understood that the above description is not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art may make various changes, modifications, additions and substitutions within the spirit and scope of the present invention.
Claims (2)
1. An oil-water two-phase flow relative permeation grid coarsening method based on artificial intelligence is characterized by comprising the following steps of:
1) establishing a geological model according to the existing production data;
2) determining the size and the number of the geological model to be coarsely formed into coarse grids, and dividing the coarse grids for the geological model according to the set size and the set number;
3) randomly extracting coarse grids with a set proportion from the geological model and recording the coarse grids as a sample set F1, recording the rest coarse grids as a sample set F2, and performing relative permeability coarsening calculation on the coarse grids in the sample set F1 to obtain the coarse-scale relative permeability of the coarse grids in the sample set F1;
4) preprocessing data of all coarse grid permeability in the geological model;
5) training a machine learning algorithm by using the distribution characteristics of the permeability of each coarse grid in the sample set F1 and the coarse-scale relative permeability data of the coarse grid, and obtaining a prediction model of the coarse-scale relative permeability of the coarse grid by a cross-folding cross-validation method;
the distribution characteristic of the permeability of each coarse grid in the sample set F1 is that the permeability data of each fine grid in the coarse grid is preprocessed to obtain a result;
the distribution characteristic of the permeability of each coarse grid in the sample set F1 is that the permeability field of the fine grid in the coarse grid is drawn into a picture, and a machine learning algorithm is trained in a picture recognition mode to achieve a more visual visualization effect;
carrying out dimensionality reduction on the distribution characteristics of the permeability of each coarse grid in the sample set F1 to accelerate the training speed of a machine learning algorithm;
the machine learning algorithm adopts a classification algorithm or a regression algorithm;
6) predicting the coarse grids in the sample set F2 by adopting the prediction model generated in the step 5), and obtaining the predicted coarse-scale relative permeability of each coarse grid in the sample set F2;
7) and performing reservoir numerical simulation calculation by using the coarse-scale relative permeability data of the coarse grid in the sample set F1 and the coarse-scale relative permeability data predicted by the coarse grid in the sample set F2.
2. The method for coarsening the oil-water two-phase flow relative penetration grid based on artificial intelligence of claim 1, wherein in the step 4), the method for preprocessing the coarse grid permeability data in the geological model comprises the following steps: firstly, making ln logarithmic transformation on the permeability of all fine grids in the geological model, and then making characteristic scaling treatment on each coarse grid of the geological model, wherein the characteristic scaling treatment formula is shown as (a):
wherein x is i For each fine grid permeability, x, in the coarse grid mean Is the average of the permeabilities of all the fine meshes in the coarse mesh, x max Is the maximum value of permeability, x, of all the fine meshes in the coarse mesh min Is the minimum value, x ', of the permeabilities of all the fine meshes in the coarse mesh' i And the fine grid permeability after the features in the coarse grid are scaled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110023178.8A CN112800589B (en) | 2021-01-08 | 2021-01-08 | Oil-water two-phase flow relative permeation grid coarsening method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110023178.8A CN112800589B (en) | 2021-01-08 | 2021-01-08 | Oil-water two-phase flow relative permeation grid coarsening method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112800589A CN112800589A (en) | 2021-05-14 |
| CN112800589B true CN112800589B (en) | 2022-09-09 |
Family
ID=75809214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110023178.8A Active CN112800589B (en) | 2021-01-08 | 2021-01-08 | Oil-water two-phase flow relative permeation grid coarsening method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800589B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108363886A (en) * | 2018-03-08 | 2018-08-03 | 杭州鲁尔物联科技有限公司 | Deformation prediction method and system based on deep learning |
| CN109800521A (en) * | 2019-01-28 | 2019-05-24 | 中国石油大学(华东) | A kind of oil-water relative permeability curve calculation method based on machine learning |
| CN111706318A (en) * | 2020-05-26 | 2020-09-25 | 中国石油天然气集团有限公司 | Method for determining residual oil distribution condition of low-permeability reservoir |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354362A (en) * | 2015-10-08 | 2016-02-24 | 南京大学 | Cubic spline multi-scale finite element method for simulating two-dimension flow movement |
-
2021
- 2021-01-08 CN CN202110023178.8A patent/CN112800589B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108363886A (en) * | 2018-03-08 | 2018-08-03 | 杭州鲁尔物联科技有限公司 | Deformation prediction method and system based on deep learning |
| CN109800521A (en) * | 2019-01-28 | 2019-05-24 | 中国石油大学(华东) | A kind of oil-water relative permeability curve calculation method based on machine learning |
| CN111706318A (en) * | 2020-05-26 | 2020-09-25 | 中国石油天然气集团有限公司 | Method for determining residual oil distribution condition of low-permeability reservoir |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112800589A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210350208A1 (en) | Method and device for predicting production performance of oil reservoir | |
| CN113052371A (en) | Residual oil distribution prediction method and device based on deep convolutional neural network | |
| CN110807544B (en) | Oil field residual oil saturation distribution prediction method based on machine learning | |
| CN114595608B (en) | Fracturing construction parameter and working system parameter optimization method and system | |
| CN112016212B (en) | Reservoir longitudinal heterogeneity evaluation method based on seepage control equation | |
| CN112761628B (en) | Shale gas yield determination method and device based on long-term and short-term memory neural network | |
| CN116699096B (en) | Water quality detection method and system based on deep learning | |
| CN112800590B (en) | Grid coarsening method for machine learning-assisted two-phase flow oil reservoir random modeling | |
| CN105023029B (en) | A kind of on-line handwritten Tibetan language syllable recognition methods and device | |
| CN112861890B (en) | Reservoir evaluation model construction method and reservoir identification method | |
| US10922451B2 (en) | Ensemble-based reservoir characterization method using multiple Kalman gains and dynamic data selection | |
| CN109034192B (en) | Track-vehicle body vibration state prediction method based on deep learning | |
| CN111027249A (en) | Machine learning-based inter-well connectivity evaluation method | |
| CN112800589B (en) | Oil-water two-phase flow relative permeation grid coarsening method based on artificial intelligence | |
| CN115115783B (en) | Digital rock core construction method and system for simulating shale matrix nano-micro pores | |
| CN115758911A (en) | Fusion point cloud residual error network and flow field and pressure field prediction method considering slippage | |
| CN112001055B (en) | Low-amplitude thin oil reservoir water content prediction method based on microstructure | |
| CN112302638B (en) | Streamline field characterization method and device for oil reservoir | |
| CN113569464A (en) | Wind turbine generator oscillation mode prediction method and device based on deep learning network and multi-task learning strategy | |
| CN111625925A (en) | Ternary combination flooding injection-production optimization method based on chromatographic separation | |
| CN104462792A (en) | Log data lithological stratum numerical value reduction method | |
| CN114092489B (en) | Porous medium seepage channel extraction and model training method, device and equipment | |
| CN116226623B (en) | Mark layer division method and device based on SegNet segmentation model and computer equipment | |
| CN117152373B (en) | Core-level pore network model construction method considering cracks | |
| Xiaoyun | Ancient Calligraphy Features Analysis Based on Image Recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |