阅读说明：本技术 识别图片中电话号码的方法、系统、终端设备及存储介质 (Method, system, terminal device and storage medium for identifying telephone number in picture ) 是由 杨絮 于 2019-07-19 设计创作，主要内容包括：本发明涉及一种识别图片中电话号码的方法、系统、终端设备及存储介质,该方法包括：获取待处理的图像；对所述待处理的图像进行边缘提取,得到边缘像素点集；根据预先建立的高斯混合模型对所述边缘像素点集进行聚类处理,识别所述图像中的内容。本发明提供的技术方案利用建立的高斯混合模型分割图像,将数字信息分割出来,通过识别得到图片中的电话号码,大大减少了在使用手机过程中因为手机无法自动识别图片中的电话号码给用户带来的不便。(The invention relates to a method, a system, a terminal device and a storage medium for identifying telephone numbers in pictures, wherein the method comprises the following steps: acquiring an image to be processed; performing edge extraction on the image to be processed to obtain an edge pixel point set; and clustering the edge pixel point set according to a pre-established Gaussian mixture model, and identifying the content in the image. The technical scheme provided by the invention utilizes the established Gaussian mixture model to segment the image, segments the digital information, and obtains the telephone number in the image by identification, thereby greatly reducing the inconvenience brought to a user because the mobile phone can not automatically identify the telephone number in the image in the process of using the mobile phone.)

1. A method for identifying a telephone number in a picture, comprising:

acquiring an image containing a telephone number;

performing edge extraction on the image to obtain an edge pixel point set;

clustering the edge pixel point set according to a pre-established Gaussian mixture model, and segmenting the content in the image;

and identifying the divided content to obtain the digital information in the image.

2. The method of claim 1, wherein the establishing of the gaussian mixture model comprises:

establishing a Gaussian mixture target function according to the probability density function of the pixel points;

and calculating target parameters in the Gaussian mixture target function according to an expectation-maximization algorithm.

3. The method of claim 2, wherein the gaussian mixture objective function is expressed by the following formula:

wherein x is_iIs a pixel point, i ═ 1, 2.., N; pi ═ pi₁,π₂,...,π_K}，π_jIs a pixel x_iA priori probability of (a); theta_jA parameter for the jth component distribution; Θ ═ Θ_jJ is a set of all parameters; sigma_jAnd mu_jAre parameters.

4. The method of claim 3, wherein calculating the objective parameters of the Gaussian mixture objective function according to the expectation-maximization algorithm comprises:

step one, initializing the target parameters according to an expectation maximization algorithm;

secondly, calculating the posterior probability value in the Bayes posterior probability according to the target parameter;

calculating an updated target parameter according to a log-likelihood function of the Gaussian mixture model;

step four, judging whether the log-likelihood function is converged;

step five, if the log likelihood function is not converged, returning to the step two; otherwise, carrying out mark classification on the pixel points according to the Bayesian posterior probability.

5. The method as claimed in claim 4, wherein the Bayesian posterior probability is expressed as follows:

wherein the content of the first and second substances,is x_iBayes posterior probability of (d); t is the number of iterations.

6. The method of claim 5, wherein the log-likelihood function of the Gaussian mixture model is represented by the following formula:

7. the method of claim 6, wherein the calculating the updated target parameter according to the log-likelihood function of the Gaussian mixture model comprises:

calculating a time value when the partial derivative is equal to zero for the target parameter in the log-likelihood function to obtain an updated target parameter, wherein the updated target parameter is represented by the following formula:

wherein the content of the first and second substances,the updated target parameter; t +1 is the number of iterations.

8. The method of claim 2, wherein the establishing of the gaussian mixture model further comprises:

and carrying out constraint optimization on the Gaussian mixture objective function through prior probability and edge detection.

9. The method of claim 8, wherein the prior probability is expressed by the following equation:

wherein, pi_ijIs a prior probability distribution function; xi (x)_i) Is a pixel x_iA weighting function of; z_iIs a normalization factor; h (i, q) represents a pixel value difference between the pixel i and the pixel q; sigma_gIs the width parameter of the function; x is the number of_iAnd x_qPixel values for pixel i and pixel q, respectively.

10. The method as claimed in claim 9, wherein the gaussian mixture objective function obtained by constraining the gaussian mixture objective function according to the prior probability is represented by the following formula:

11. a system for identifying a telephone number in a picture, comprising:

the acquisition module is used for acquiring an image to be processed;

the extraction module is used for carrying out edge extraction on the image to be processed to obtain an edge pixel point set;

the segmentation module is used for clustering the edge pixel point set according to a pre-established Gaussian mixture model and segmenting the content in the image;

and the identification module is used for identifying the divided contents to obtain the digital information in the image.

12. A terminal device, characterized in that the terminal device comprises a memory and a processor; the memory stores a management computer program of an application program, and the processor executes the computer program to realize the method for identifying the telephone number in the picture according to any one of claims 1 to 10.

13. A storage medium storing a computer program for managing an application program, the computer program being executable by at least one processor to implement the method for identifying a telephone number in a picture according to any one of claims 1 to 10.

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to a method, a system, a terminal device, and a storage medium for identifying a phone number in a picture.

Background

This is often the case in our lives: when inquiring about the contact way of another person, the opposite party often sends a screenshot to the person directly, and in this case, there are two general solutions, one is to record the telephone number by memory and then input in the dial for dialing, and the other is to write the telephone number on paper and then input in the dial for dialing.

However, both of these methods are inconvenient in situations where memory is poor or current conditions are not allowed.

Therefore, it is desirable to provide a method, a system, a terminal device and a storage medium for identifying a phone number in a picture to solve the deficiencies of the prior art.

Disclosure of Invention

In order to solve the problems in the prior art, the invention provides a method, a system, terminal equipment and a storage medium for identifying a telephone number in a picture.

The application provides a method for identifying a telephone number in a picture, which comprises the following steps:

acquiring an image containing a telephone number;

performing edge extraction on the image to obtain an edge pixel point set;

clustering the edge pixel point set according to a pre-established Gaussian mixture model, and segmenting the content in the image;

and identifying the divided content to obtain the digital information in the image.

Further, the establishing of the gaussian mixture model comprises:

establishing a Gaussian mixture target function according to the probability density function of the pixel points;

and calculating target parameters in the Gaussian mixture target function according to an expectation-maximization algorithm.

Further, the gaussian mixture objective function is expressed by the following formula:

wherein x is_iIs a pixel point, i ═ 1, 2.., N; pi ═ pi₁,π₂,...,π_K}，π_jIs a pixel x_iA priori probability of (a); theta_jA parameter for the jth component distribution; Θ ═ Θ_jJ is a set of all parameters; sigma_jAnd mu_jAre parameters.

Further, calculating target parameters in the gaussian mixture objective function according to an expectation-maximization algorithm, comprising:

step one, initializing the target parameters according to an expectation maximization algorithm;

secondly, calculating the posterior probability value in the Bayes posterior probability according to the target parameter;

calculating an updated target parameter according to a log-likelihood function of the Gaussian mixture model;

step four, judging whether the log-likelihood function is converged;

step five, if the log likelihood function is not converged, returning to the step two; otherwise, carrying out mark classification on the pixel points according to the Bayesian posterior probability.

Further, the bayesian posterior probability is shown as follows:

wherein the content of the first and second substances,is x_iBayes posterior probability of (d); t is the number of iterations.

Further, the log-likelihood function of the gaussian mixture model is shown as follows:

further, the calculating the updated target parameter according to the log-likelihood function of the gaussian mixture model includes:

calculating a time value when the partial derivative is equal to zero for the target parameter in the log-likelihood function to obtain an updated target parameter, wherein the updated target parameter is represented by the following formula:

wherein the content of the first and second substances,the updated target parameter; t +1 is the number of iterations.

Further, the establishing of the gaussian mixture model further includes:

and carrying out constraint optimization on the Gaussian mixture objective function through prior probability and edge detection.

Further, the prior probability is shown as:

wherein, pi_ijIs a prior probability distribution function; xi (x)_i) Is a pixel x_iA weighting function of; z_iIs a normalization factor; h (i, q) represents a pixel value difference between the pixel i and the pixel q; sigma_gIs the width parameter of the function; x is the number of_iAnd x_qPixel values for pixel i and pixel q, respectively.

Further, a gaussian mixture objective function obtained by constraining the gaussian mixture objective function according to the prior probability is shown as follows:

the present application further provides a system for identifying a phone number in a picture, comprising:

the acquisition module is used for acquiring an image to be processed;

the extraction module is used for carrying out edge extraction on the image to be processed to obtain an edge pixel point set;

the segmentation module is used for clustering the edge pixel point set according to a pre-established Gaussian mixture model and segmenting the content in the image;

and the identification module is used for identifying the divided contents to obtain the digital information in the image.

The application also provides a terminal device, which comprises a memory and a processor; the memory stores a management computer program of an application program, and the processor executes the computer program to realize any one of the above methods for identifying the telephone number in the picture.

The present application further provides a storage medium storing a computer program for managing an application program, where the computer program can be executed by at least one processor to implement any one of the above methods for identifying a phone number in a picture.

Compared with the closest prior art, the technical scheme of the invention has the following advantages:

the technical scheme provided by the invention comprises the steps of firstly obtaining an image containing a telephone number, then carrying out edge extraction on the image to obtain an edge pixel point set, carrying out clustering processing on the edge pixel point set according to a pre-established Gaussian mixture model to segment the content in the image, and finally identifying the segmented content to obtain the digital information in the image. The technical scheme provided by the invention utilizes the established Gaussian mixture model to segment the image, segments the digital information, and obtains the telephone number in the image by identification, thereby greatly reducing the inconvenience brought to a user because the mobile phone can not automatically identify the telephone number in the image in the process of using the mobile phone.

Drawings

Fig. 1 is a flowchart of a method for identifying a phone number in a picture according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.

The execution subject of each step in the present invention may be a terminal. The terminal can be a terminal device such as a mobile phone, a tablet computer, a palm computer, a wearable device, a smart band and the like.

As shown in fig. 1, the present invention provides a method for identifying a phone number in a picture, which may include the steps of:

acquiring an image containing a telephone number;

performing edge extraction on the image to obtain an edge pixel point set;

clustering the edge pixel point set according to a pre-established Gaussian mixture model, and segmenting the content in the image;

and identifying the divided content to obtain the digital information in the image.

In the embodiment of the application, an image containing a telephone number is obtained, then edge extraction is carried out on the image to obtain an edge pixel point set, the edge pixel point set is subjected to clustering processing according to a pre-established Gaussian mixture model to segment the content in the image, and finally the segmented content is identified to obtain the digital information in the image. The technical scheme provided by the invention utilizes the established Gaussian mixture model to segment the image, segments the digital information, and obtains the telephone number in the image by identification, thereby greatly reducing the inconvenience brought to a user because the mobile phone can not automatically identify the telephone number in the image in the process of using the mobile phone.

In some embodiments of the present application, performing edge extraction on the image to obtain an edge pixel point set specifically includes:

and detecting the acquired image containing the telephone number, and performing edge extraction on the image to obtain an edge pixel point set corresponding to the picture. The edge extraction may be an edge extraction method known to those skilled in the art, and is not described herein again.

In some embodiments of the present application, the establishing of the gaussian mixture model specifically includes:

establishing a Gaussian mixture target function according to the probability density function of the pixel points;

and calculating target parameters in the Gaussian mixture target function according to an expectation-maximization algorithm.

Namely, an objective function is established first, and then objective parameters in the objective function are optimized to obtain the establishment of a Gaussian mixture model.

The purpose of establishing the model is to segment the image by clustering of pixels, namely labeling each pixel and finding out the pixels corresponding to the interested labels.

Specifically, the process of model building is as follows:

wherein x is_iIs a pixel point, i ═ 1, 2.., N; pi ═ pi₁,π₂,...,π_K}，π_jIs a pixel x_iA priori probability of (a); theta_jA parameter for the jth component distribution; Θ ═ Θ_jJ is a set of all parameters; sigma_jAnd mu_jIs a parameter;is x_iBayes posterior probability of (d); sigma_j、μ_jAnd pi_jIs a target parameter;the updated target parameter; pi_ijIs a prior probability distribution function; xi (x)_i) Is a pixel x_iA weighting function of; z_iIs a normalization factor; h (i, q) represents a pixel value difference between the pixel i and the pixel q; sigma_gIs the width parameter of the function; x is the number of_iAnd x_qPixel values for pixel i and pixel q, respectively; omega₁,Ω₂,...,Ω_KRepresenting K marks, wherein each mark corresponds to one Gaussian model, and the K marks correspond to K Gaussian models; t and t +1 are the number of iterations, respectively.

P(x_i|Θ_j) (j 1, 2.. K) is the probability density function for each marker, which is a function of:

the pixel set obeys the finite mixture distribution, and the model corresponding to the pixel set is the finite mixture model. Where pi is { pi ═ n₁,π₂,...,π_K}，π_jIs a pixel x_iBelonging to the mark omega_jA priori probability of the mixture of the component distributions. Theta_jIs a parameter of the jth component distribution, Θ ═ Θ_jJ is the set of all parameters. For a prior probability pi_ijAs to the requirements, it is necessary to satisfy:

if each component distribution obeys the Gaussian distribution, the corresponding model is the Gaussian mixture model.

Wherein Θ is_j＝{μ_j,σ_j}. The statistical independence between pixel samples is 0-pi_ij≤1，Then for pixel X ═ X₁,x₂,...,x_N) The combined conditional densities of (a):

this is the likelihood function of the parameters { Π, Θ } with respect to X. Since the logarithmic function is monotonous, taking the logarithm of the above equation (3) yields the log-likelihood function of the gaussian mixture model:

wherein Θ ═ Θ_j,j＝1,2,...,K}。

The above log-likelihood function may then be parametrically estimated using an expectation-maximization algorithm (EM algorithm) to achieve a maximized log-likelihood function, resulting in a segmented result.

The EM algorithm is an iterative algorithm for solving maximum likelihood estimates of parameters, and is a relatively simple and practical algorithm that can solve the parameters of the model from incomplete data sets. The method has good effect of processing incomplete data, and is widely applied to processing truncated data, polluted data, missing data and the like. When the EM algorithm fits a limited mixed model through a maximum posterior probability (MAP) or a maximum likelihood estimation (ML) method, the method is greatly simplified into two steps of E step and M step, and parameters are conveniently estimated.

The E step of the EM algorithm is to convert the expectation of the log likelihood function of the complete calculation data into the x calculation_iBayesian posterior probability from the j-th gaussian component:

the above formula represents x_iFrom Ω_jBayes posterior probability of (a).

And M, solving the maximum likelihood estimation of the model parameters, and updating the parameters:

the formula (4) is respectively matched with the parameter mu_j,σ_j,π_jTaking the partial derivative and making it equal to 0 yields:

wherein t and t +1 represent the number of iterations respectively, and the EM algorithm for summarizing the Gaussian mixture model is as follows:

step 1: initialization parameter { Θ, Π } - { μ_j,σ_j,π_j}。

Step 2 (step E): calculating (5) the value of the posterior probability from the initialized parameter values.

Step 3 (step M): updating the parameter mu by the formulas (6), (7) and (8)_j,σ_j,π_j。

And 4, step 4: and (4) calculating a log-likelihood function (4), detecting whether the function or the parameter is converged, and returning to the step 2 if the function or the parameter is not converged.

After the EM algorithm is executed, class label assignment is performed for each pixel in the image using equation (5).

The model is then expanded and optimized. Specifically, two constraints are added. One is a prior probability constraint based on spatial neighborhood relationships and the other is a Canny edge detection constraint. And traversing all pixel points on the image by using the model. The two constraints are specified below:

by considering the neighborhood information of the pixels, the neighborhood information of the pixels is introduced into the prior probability distribution of a Gaussian mixture model, the prior probability is constrained, and then the Gaussian mixture model constrained by the prior probability of the Gaussian kernel function is provided, and if the distances of the pixels in the image are closer, the prior probability distribution of the pixels is more similar or even the same. Based on the prior probability distribution, a Gaussian kernel function and a Gaussian radial basis function are introduced into a Gaussian mixture model as space constraints on the prior probability distribution of the pixels to constrain the prior probability distribution, and a weight function of each pixel belonging to each category is introduced according to the expanded Gaussian mixture model to constrain the prior probability distribution.

In this model, a representative pixel x is first defined_iBelong to omega_jFunction of the weight of the class:

here, i and q belong to neighborhood pixels, and σ takes a value of 10. Introducing a Gaussian kernel function as a spatial constraint on pixel probability distribution into a Gaussian mixture model to constrain prior probability distribution, wherein the prior probability distribution is as follows:

wherein:

is a normalization factor and h (i, q) represents the difference in pixel values between pixel i and pixel q. h is a gaussian function of the difference between the relative pixel values of pixel i to pixel q, i.e. the similarity between two pixels, and the gaussian kernel function is expressed as follows:

wherein σ_gIs a width parameter of the function, controlling the radial range of action, x, between adjacent pixels_iAnd x_qOther are the pixel values of pixel i and pixel q. In this model σ_gThe value is 10, and when the distance | | | x is obtained from the formula 3 to the formula 18_i-x_qThe function h decreases as | increases. If two are providedThe closer the pixel distance between the pixels, the greater the probability that the two pixels belong to the same class; the farther the pixel distance between two pixels is, the smaller the probability that the two pixels belong to the same class.

Then, combining the original Gaussian model, x in the Gaussian mixture model_iThe density function of (a) is:

the following formulae (2), (9), (10), (11) and (12) are combined:

since the target contour extracted by the Gaussian mixture model is not obvious, in order to obtain a clearer edge and avoid the interested target edge from being smoothed, an edge penalty needs to be introduced into the energy function, so that the edge information of the region can be well maintained. The introduction of edge penalties can reduce edge blurring and thus more accurately locate edges.

Since the logarithmic function is a monotonically increasing function, we can consider the negative logarithm of the posterior probability as:

the energy function is minimal when the posterior probability takes a maximum.

Wherein, when the segmentation object is determined,andall are constant values, so only the minimum of the other two terms is required. So in general the energy function can be expressed as:

E＝{E₁(x_i|Ω_j,Θ)+E₂(Ω_j)} (15)

the first term is a data term and the second term is a smoothness constraint term. By omega₁,Ω₂,...,Ω_KRepresenting K labels, Ω is the set of all labels, in the EM algorithm, the total a posteriori energy is to be minimized:

for a given x_iAnd Ω_jThe likelihood energy is:

a priori energy function E₂(Ω_j) In the form of:

wherein V_C(Ω_j) Is the region energy, and C is the set of all possible regions.

In the image domain, we assume that a pixel has a maximum of 4 neighborhood pixels: pixels in their neighborhood. Then the energy of this region is defined over the adjacent pixel pair:

here, s and t are pairs of labels of neighborhood pixels. Wherein the content of the first and second substances,

we solve (15) with an iterative algorithm:

1. first, we have an initial estimate Ω⁰From the previous cycle of the EM algorithm.

2. When i is more than or equal to 1 and less than or equal to N,

3. repeating step 2 until E₁(x_i|Ω_j)+E₂(Ω_j) Converge or reach a maximum value k.

Now it is desirable that the segmentation preserves edges obtained by edge detection algorithms, such as Canny edge detection, Prewitt edge detection or Sobel contour detection. Suppose we have a binary edge map z_iWherein if the ith pixel is on an edge, then z_i1, if not, then z_i0. We then modify (20) to:

and finally, adding a Gaussian kernel function and a weight function of each pixel in the Gaussian mixture model with the edge constraint to constrain the prior probability of the pixel together, and providing the Gaussian mixture model based on the prior probability constraint of the Gaussian kernel function and the edge detection.

The information including the telephone number in the image can be segmented by the model, and then the segmented content is identified to obtain the digital information in the image, namely the telephone number in the image. The content segmented in the image is identified by an identification method known to those skilled in the art, and will not be described herein again.

Based on the same inventive concept, the invention also provides a system for identifying the telephone number in the picture, which comprises:

the acquisition module is used for acquiring an image to be processed;

the extraction module is used for carrying out edge extraction on the image to be processed to obtain an edge pixel point set;

the segmentation module is used for clustering the edge pixel point set according to a pre-established Gaussian mixture model and segmenting the content in the image;

and the identification module is used for identifying the divided contents to obtain the digital information in the image.

The invention also provides a terminal device, which comprises a memory and a processor; the memory stores a management computer program of an application program, and the processor executes the computer program to realize the steps of any one of the methods.

For example, the processor executes the computer program to implement the steps of:

acquiring an image containing a telephone number;

performing edge extraction on the image to obtain an edge pixel point set;

clustering the edge pixel point set according to a pre-established Gaussian mixture model, and segmenting the content in the image;

and identifying the divided content to obtain the digital information in the image.

In the embodiment of the application, an image containing a telephone number is obtained, then edge extraction is carried out on the image to obtain an edge pixel point set, the edge pixel point set is subjected to clustering processing according to a pre-established Gaussian mixture model to segment the content in the image, and finally the segmented content is identified to obtain the digital information in the image. The technical scheme provided by the invention utilizes the established Gaussian mixture model to segment the image, segments the digital information, and obtains the telephone number in the image by identification, thereby greatly reducing the inconvenience brought to a user because the mobile phone can not automatically identify the telephone number in the image in the process of using the mobile phone.

In some embodiments of the present application, performing edge extraction on the image to obtain an edge pixel point set specifically includes:

and detecting the acquired image containing the telephone number, and performing edge extraction on the image to obtain an edge pixel point set corresponding to the picture. The edge extraction may be an edge extraction method known to those skilled in the art, and is not described herein again.

In some embodiments of the present application, the establishing of the gaussian mixture model specifically includes:

establishing a Gaussian mixture target function according to the probability density function of the pixel points;

and calculating target parameters in the Gaussian mixture target function according to an expectation-maximization algorithm.

Namely, an objective function is established first, and then objective parameters in the objective function are optimized to obtain the establishment of a Gaussian mixture model.

The purpose of establishing the model is to segment the image by clustering of pixels, namely labeling each pixel and finding out the pixels corresponding to the interested labels.

The present invention also provides a storage medium storing a computer program for managing an application program, the computer program being executable by at least one processor to perform any of the above method steps for identifying a telephone number in a picture.

When the embodiment of the invention is specifically implemented, the embodiment can be referred to, and the same technical effects are achieved.

It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the Processing units may be implemented within one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units configured to perform the functions described herein, or a combination thereof.

For a software implementation, the techniques described herein may be implemented by means of units performing the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or make a contribution to the prior art, or may be implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

It is to be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.