Part recognition method and device based on time series modeling

Abstract

The embodiment of the present application provides a method and device for part recognition based on time series modeling, which solves the problem of low accuracy of existing part recognition methods based on electronic computer tomography images. The method for part recognition based on time series modeling includes: inputting multiple tomography images obtained by electronic computer tomography into a two-dimensional convolutional neural network model for feature extraction; obtaining a feature graph sequence output by the two-dimensional convolutional neural network model, wherein the feature graph sequence includes multiple feature graphs corresponding to the multiple tomography images, and the multiple feature graphs are arranged in the time sequence of the electronic computer tomography; and inputting the feature graph sequence into a recurrent neural network model to obtain a part recognition result.

Description

Technical Field

[0001] The present application relates to the technical field of image analysis, and in particular to a method, device, electronic device and computer-readable storage medium for part recognition based on time series modeling. Background Art

[0002] Computed Tomography (CT) is a common disease examination method in hospitals, which can perform continuous cross-sectional scans on a certain part of the patient. In actual scenarios, there may be missing or incorrect tags about the parts in CT data, and sometimes these tag information is often broad and vague. Accurate part labels will bring convenience in many applications: 1. Many data are sorted based on the part information of the image, and part identification helps to manage and classify the data; 2. More and more artificial intelligence-assisted systems are emerging, and the premise for the operation of these systems is to accurately identify the parts.

[0003] At present, the most common part recognition algorithm is to recognize each layer of CT images, and finally integrate all the results. This algorithm does not utilize the timing information of CT data and has low accuracy. Specifically: 1. The current algorithm recognition accuracy is low and it is difficult to meet the requirements of clinical use; 2. The current part recognition algorithms are all based on convolutional neural networks. The recognition results of different sequences in the same CT are independent of each other. Therefore, frame skipping occurs due to recognition errors during recognition. The frame skipping phenomenon refers to the fact that when recognizing CT, one or several images in a certain continuous area are often recognized as the wrong part, which is an erroneous recognition result. The reason for this is that some existing algorithms do not take into account the timing information between different sequences, which ultimately leads to the inability to obtain accurate recognition results.

[0004] It can be seen that the existing technology uses convolutional neural networks to identify each sequence in CT, without considering the relationship between different sequences, so the error rate is high, especially in the case of continuous CT scanning, when switching between different parts, it is often impossible to accurately identify. Summary of the invention

[0005] In view of this, an embodiment of the present application provides a method and device for part recognition based on time series modeling, which solves the problem of low accuracy of existing part recognition methods based on electronic computer tomography images.

[0006] According to one aspect of the present application, an embodiment of the present application provides a part recognition method based on time series modeling, including: inputting multiple tomography images obtained by electronic computed tomography into a two-dimensional convolutional neural network model for feature extraction; obtaining a feature graph sequence output by the two-dimensional convolutional neural network model, wherein the feature graph sequence includes multiple feature graphs corresponding to the multiple tomography images, respectively, and the multiple feature graphs are arranged in time sequence of the electronic computed tomography; and inputting the feature graph sequence into a recurrent neural network model to obtain a part recognition result.

[0007] In one embodiment of the present application, the two-dimensional convolutional neural network model includes a fully connected layer, wherein, after a plurality of tomographic images obtained by electronic computed tomography are input into the two-dimensional convolutional neural network model for feature extraction, the method further includes: obtaining preliminary part recognition results output by the fully connected layer and corresponding to the plurality of tomographic images respectively.

[0008] In one embodiment of the present application, the two-dimensional convolutional neural network model is established through the following training process: inputting a tomographic image sample with a first part identification label into the two-dimensional convolutional neural network model; obtaining a first part prediction result output by the two-dimensional convolutional neural network; and adjusting the network parameters of the two-dimensional convolutional neural network model according to the difference between the first part prediction result and the first part identification label.

[0009] In one embodiment of the present application, the recurrent neural network model is established through the following training process: inputting image feature sequence samples with a second part identification label into the recurrent neural network model, wherein the image feature sequence samples are obtained by inputting multiple tomographic image samples into the two-dimensional spacing neural network; obtaining the second part prediction result output by the recurrent neural network model; and adjusting the network parameters of the recurrent neural network model according to the difference between the second part prediction result and the second part identification label.

[0010] According to another aspect of the present application, a part recognition device based on time series modeling provided by an embodiment of the present application includes: a feature extraction module, configured to input multiple tomography images obtained by electronic computed tomography into a two-dimensional convolutional neural network model for feature extraction; a feature graph sequence acquisition module, configured to obtain a feature graph sequence output by the two-dimensional convolutional neural network model, wherein the feature graph sequence includes multiple feature graphs corresponding to the multiple tomography images, respectively, and the multiple feature graphs are arranged in time sequence of the electronic computed tomography; and a part recognition module, configured to input the feature graph sequence into a recurrent neural network model to obtain a part recognition result.

[0011] In one embodiment of the present application, the two-dimensional convolutional neural network model includes a fully connected layer, wherein the device further includes: a preliminary part recognition module, configured to obtain preliminary part recognition results corresponding to the multiple tomography images respectively output by the fully connected layer after inputting the multiple tomography images obtained by electronic computed tomography into the two-dimensional convolutional neural network model for feature extraction.

[0012] In one embodiment of the present application, the device further includes: a first training module, configured to establish the two-dimensional convolutional neural network model through the following training process: inputting a tomography image sample with a first part identification label into the two-dimensional convolutional neural network model; obtaining a first part prediction result output by the two-dimensional convolutional neural network; and adjusting the network parameters of the two-dimensional convolutional neural network model according to the difference between the first part prediction result and the first part identification label.

[0013] In one embodiment of the present application, the device further includes: a second training module, configured to establish the recurrent neural network model through the following training process: inputting image feature sequence samples with a second part identification label into the recurrent neural network model, wherein the image feature sequence samples are obtained by inputting multiple tomographic image samples into the two-dimensional spacing neural network; obtaining a second part prediction result output by the recurrent neural network model; and adjusting the network parameters of the recurrent neural network model according to the difference between the second part prediction result and the second part identification label.

[0014] According to another aspect of the present application, an embodiment of the present application provides an electronic device, comprising: a processor; a memory; and computer program instructions stored in the memory, wherein when the computer program instructions are executed by the processor, the processor executes a part recognition method based on time series modeling as described in any one of the above items.

[0015] According to another aspect of the present application, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes a part recognition method based on time series modeling as described in any of the above.

[0016] According to another aspect of the present application, an embodiment of the present application provides a computer program product, including computer program instructions, which, when executed by a processor, enable the processor to execute any of the above-described method for part recognition based on time series modeling.

[0017] The embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for part recognition based on time series modeling. First, a two-dimensional convolutional neural network model is used to extract features. Then, a feature graph sequence output by the two-dimensional convolutional neural network model is input into a recurrent neural network as image features. The feature graph sequence is subjected to time series modeling using a recurrent neural network. The image features extracted by the two-dimensional convolutional neural network model and the time series features of the CT data itself are combined to obtain a part recognition result. This realizes the combination of the image features of the CT sequence and the time series features between different sequences. Compared with simply using a convolutional neural network for part recognition, a higher recognition accuracy can be obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The figure is a flow chart of a method for part recognition based on time series modeling provided in one embodiment of the present application.

[0019] Figure 2 The figure shows a schematic diagram of the training process of a two-dimensional convolutional neural network model in a part recognition method based on time series modeling provided in an embodiment of the present application.

[0020] Figure 3 The figure is a schematic diagram of the training process of a recurrent neural network model in a part recognition method based on time series modeling provided in one embodiment of the present application.

[0021] Figure 4 Shown is a schematic structural diagram of a part recognition device based on time series modeling provided in one embodiment of the present application.

[0022] Figure 5 Shown is a schematic structural diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] The prior art uses convolutional neural networks to identify each sequence in CT, without considering the relationship between different sequences, so the error rate is high, especially in the case of continuous CT scanning, when different parts are switched, it is often impossible to accurately identify. The inventors of the present invention propose to use a recurrent neural network to obtain the temporal features between different sequences while using a convolutional neural network to extract image features, so as to improve the accuracy of part recognition.

[0025] Figure 1 FIG. 1 is a flow chart of a method for part recognition based on time series modeling provided by an embodiment of the present application. Figure 1 As shown, the part recognition method based on time series modeling includes the following steps:

[0026] Step 101: Input multiple tomography images obtained by electronic computer tomography into a two-dimensional convolutional neural network model for feature extraction.

[0027] Since the tomographic scan images to be detected may contain various parts of the body, it is not necessary to use a specific window width and window position, but to normalize the data in the original CT data to obtain more complete data information. Multiple tomographic scan images after normalization are input into the two-dimensional convolutional neural network model.

[0028] Step 102: Obtain a feature map sequence output by the two-dimensional convolutional neural network model, wherein the feature map sequence includes a plurality of feature maps corresponding to a plurality of tomographic images, respectively, and the plurality of feature maps are arranged in chronological order of the electronic computer tomography scan.

[0029] The two-dimensional convolutional neural network has a relatively good image feature extraction capability and can effectively improve the accuracy of part recognition. In one embodiment of the present application, the two-dimensional convolutional neural network model includes multiple convolutional layers and fully connected layers. The two-dimensional convolutional neural network model can be pre-established through a training process, such as Figure 2 As shown, the training process may include the following steps: inputting a tomographic image sample with a first part identification label into a two-dimensional convolutional neural network model (S21); obtaining a first part prediction result output by the two-dimensional convolutional neural network (S22); and adjusting the network parameters of the two-dimensional convolutional neural network model according to the difference between the first part prediction result and the first part identification label (S23). By using a large number of tomographic image samples and continuously looping the above training process, the two-dimensional convolutional neural network model can be enabled to have the ability to identify parts when the preset regression accuracy is reached. In one embodiment of the present application, preliminary part identification results corresponding to multiple tomographic images output by the fully connected layer can be obtained, which can be provided to doctors for reference together with subsequent part identification results.

[0030] However, since it is necessary to combine the recurrent neural network with the timing features for part recognition in the future, it is not necessary to use the fully connected layer of the two-dimensional convolutional neural network model to output the preliminary part recognition results in step 102, but it is necessary to use the convolutional layer output of the two-dimensional convolutional neural network model. The size of the feature map sequence (s*h*w) is used as the input of the recurrent neural network, where s is the length of the feature map sequence, h and w are the sizes of the tomographic images corresponding to the feature maps, and multiple feature maps are arranged in the time sequence of the electronic computer tomography to form a feature map sequence. The feature map sequence already contains the timing features. The timing features here refer to the features between different layers (feature maps) in the same sequence, that is, the timing features based on the scanning order of the same set of feature maps mentioned above.

[0031] Step 103: Input the feature map sequence into the recurrent neural network model to obtain the part recognition result.

[0032] The recurrent neural network model can include multiple hidden layers. The recurrent neural network is a type of chain-connected neural network that takes sequence data as input. It has memory and is advantageous for solving data analysis that contains sequence input, such as CT. The order in which the recurrent neural network accepts feature map input is consistent with the CT scanning order. At the same time, all feature maps will participate in the calculation in chronological order and affect the final output result. Therefore, the recurrent neural network can combine the characteristics of time series.

[0033] In one embodiment of the present application, the recurrent neural network model can be pre-established through a training process, such as Figure 3 As shown, the training process may include the following steps: inputting an image feature sequence sample with a second part identification label into a recurrent neural network model, wherein the image feature sequence sample is obtained by inputting a plurality of tomographic image samples into a two-dimensional spacing neural network (S31); obtaining a second part prediction result output by the recurrent neural network model (S32); and adjusting the network parameters of the recurrent neural network model according to the difference between the second part prediction result and the second part identification label (S33). By using a large number of image feature sequence samples and continuously looping the above training process, the recurrent neural network model can be made capable of part identification when a preset regression accuracy is reached.

[0034] It can be seen that the method for part recognition based on time series modeling provided in the embodiment of the present application first uses a two-dimensional convolutional neural network model for feature extraction, then inputs the feature graph sequence output by the two-dimensional convolutional neural network model as image features into a recurrent neural network, and uses the recurrent neural network to perform time series modeling on the feature graph sequence, and combines the image features extracted by the two-dimensional convolutional neural network model and the time series features of the CT data itself to obtain the part recognition result, thereby realizing the combination of the image features of the CT sequence and the time series features between different sequences, and compared with simply using a convolutional neural network for part recognition, a higher recognition accuracy can be obtained.

[0035] Figure 4 FIG. 1 is a schematic diagram of the structure of a part recognition device based on time series modeling provided by an embodiment of the present application. Figure 4 As shown, the part recognition method and device 40 based on time series modeling includes:

[0036] A feature extraction module 401 is configured to input a plurality of tomography images obtained by electronic computer tomography into a two-dimensional convolutional neural network model for feature extraction;

[0037] A feature graph sequence acquisition module 402 is configured to acquire a feature graph sequence output by the two-dimensional convolutional neural network model, wherein the feature graph sequence includes a plurality of feature graphs corresponding to a plurality of tomographic images, respectively, and the plurality of feature graphs are arranged in a time sequence of electronic computer tomography; and

[0038] The part recognition module 403 is configured to input the feature map sequence into the recurrent neural network model to obtain a part recognition result.

[0039] In one embodiment of the present application, the two-dimensional convolutional neural network model includes a fully connected layer, wherein the device 40 further includes: a preliminary part recognition module 404, configured to obtain preliminary part recognition results corresponding to the multiple tomography images respectively output by the fully connected layer after inputting the multiple tomography images obtained by electronic computed tomography into the two-dimensional convolutional neural network model for feature extraction.

[0040] In an embodiment of the present application, the device 40 further includes:

[0041] The first training module 405 is configured to establish a two-dimensional convolutional neural network model through the following training process: inputting a tomography image sample with a first part identification label into the two-dimensional convolutional neural network model; obtaining a first part prediction result output by the two-dimensional convolutional neural network; and adjusting the network parameters of the two-dimensional convolutional neural network model according to the difference between the first part prediction result and the first part identification label.

[0042] In an embodiment of the present application, the device 40 further includes:

[0043] The second training module 406 is configured to establish a recurrent neural network model through the following training process: inputting an image feature sequence sample with a second part identification label into the recurrent neural network model, wherein the image feature sequence sample is obtained by inputting a plurality of tomographic image samples into a two-dimensional spacing neural network; obtaining a second part prediction result output by the recurrent neural network model; and adjusting the network parameters of the recurrent neural network model according to the difference between the second part prediction result and the second part identification label.

[0044] The specific functions and operations of each module in the above-mentioned part recognition device 40 based on time series modeling have been referred to above. Figures 1 to 3 The part recognition method based on time series modeling described in detail is described in detail. Therefore, its repeated description will be omitted here.

[0045] It should be noted that the part recognition device 40 based on time series modeling according to the embodiment of the present application can be integrated into the electronic device 50 as a software module and / or a hardware module. In other words, the electronic device 50 can include the part recognition device 40 based on time series modeling. For example, the part recognition device 40 based on time series modeling can be a software module in the operating system of the electronic device 50, or can be an application developed for it; of course, the part recognition device 40 based on time series modeling can also be one of the many hardware modules of the electronic device 50.

[0046] In another embodiment of the present application, the part recognition device 40 based on time series modeling and the electronic device 50 may also be separate devices (for example, servers), and the part recognition device 40 based on time series modeling may be connected to the electronic device 50 via a wired and / or wireless network and transmit interactive information in accordance with an agreed image format.

[0047] Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 5 As shown, the electronic device 50 includes: one or more processors 501 and a memory 502; and computer program instructions stored in the memory 502, which, when executed by the processor 501, enable the processor 501 to execute a part recognition method based on time series modeling as any of the above embodiments.

[0048] The processor 501 may be a central processing unit (CPU) or other forms of processing units having image processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0049] The memory 502 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on a computer-readable storage medium, and the processor 501 may run the program instructions to implement the steps in the method for part recognition based on time series modeling of each embodiment of the present application above and / or other desired functions. Information such as light intensity, compensation light intensity, and the position of the filter may also be stored in the computer-readable storage medium.

[0050] In one example, the electronic device 50 may further include: an input device 503 and an output device 504, which are connected via a bus system and / or other forms of connection mechanisms ( Figure 5 ) interconnected.

[0051] For example, when the electronic device is a robot on an industrial production line, the input device 503 may be a camera for capturing the position of the part to be processed. When the electronic device is a stand-alone device, the input device 503 may be a communication network connector for receiving the collected input signal from an external removable device. In addition, the input device 503 may also include, for example, a keyboard, a mouse, a microphone, and the like.

[0052] The output device 504 can output various information to the outside, and may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0053] Of course, to simplify, Figure 5 Only some of the components related to the present application in the electronic device 50 are shown, and components such as a bus, an input device / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device 50 may also include any other appropriate components.

[0054] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, including computer program instructions, which, when executed by a processor, enable the processor to execute the steps in the method for part recognition based on time series modeling in any of the above embodiments.

[0055] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0056] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method for part recognition based on time series modeling according to various embodiments of the present application described in the above "Exemplary method for part recognition based on time series modeling" section of this specification.

[0057] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0058] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0059] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0060] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0061] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0062] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

[0063] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A part recognition method based on time series modeling, characterized in that: include: Inputting a plurality of tomographic images obtained by electronic computer tomography into a two-dimensional convolutional neural network model including a fully connected layer for feature extraction, and obtaining preliminary part recognition results corresponding to the plurality of tomographic images respectively output by the fully connected layer; Acquire a feature graph sequence output by the two-dimensional convolutional neural network model, wherein the feature graph sequence includes a plurality of feature graphs corresponding to the plurality of tomographic images, respectively, and the plurality of feature graphs are arranged in a time sequence of electronic computer tomography; and Inputting the feature map sequence into a recurrent neural network model to obtain a part recognition result, and providing the part recognition result and the preliminary part recognition result together to a doctor as a reference; The recurrent neural network model includes multiple hidden layers, which are pre-established through the following training process: Inputting image feature sequence samples with second part identification labels into a recurrent neural network model, wherein the image feature sequence samples are obtained by inputting multiple tomographic image samples into a two-dimensional convolutional neural network model; obtaining a second part prediction result output by the recurrent neural network model; and adjusting network parameters of the recurrent neural network model according to the difference between the second part prediction result and the second part identification label.

2. The method according to claim 1, characterized in that: The two-dimensional convolutional neural network model is established through the following training process: Inputting the tomographic image sample with the first part identification label into the two-dimensional convolutional neural network model; Obtaining a first part prediction result output by the two-dimensional convolutional neural network model; as well as Adjust the network parameters of the two-dimensional convolutional neural network model according to the difference between the first part prediction result and the first part identification label.

3. A part recognition device based on time series modeling, characterized in that: include: a feature extraction module configured to input a plurality of tomographic images obtained by electronic computer tomography into a two-dimensional convolutional neural network model including a fully connected layer for feature extraction, and obtain preliminary part recognition results output by the fully connected layer and corresponding to the plurality of tomographic images respectively; a feature graph sequence acquisition module, configured to acquire a feature graph sequence output by the two-dimensional convolutional neural network model, wherein the feature graph sequence includes a plurality of feature graphs corresponding to the plurality of tomographic images, respectively, and the plurality of feature graphs are arranged in a time sequence of electronic computer tomography; and A part recognition module is configured to input the feature map sequence into a recurrent neural network model to obtain a part recognition result, and provide the part recognition result and the preliminary part recognition result together to a doctor as a reference; and further includes: The second training module is configured to establish multiple hidden layers in the recurrent neural network model through the following training process: Inputting an image feature sequence sample with a second part identification label into the recurrent neural network model, wherein the image feature sequence sample is obtained by inputting a plurality of tomography image samples into the two-dimensional convolutional neural network model; Obtaining a second part prediction result output by the recurrent neural network model; and Adjust the network parameters of the recurrent neural network model according to the difference between the second part prediction result and the second part identification label.

4. The device according to claim 3, characterized in that Further including: The first training module is configured to establish the two-dimensional convolutional neural network model through the following training process: Inputting the tomographic image sample with the first part identification label into the two-dimensional convolutional neural network model; Obtaining a first part prediction result output by the two-dimensional convolutional neural network model; as well as Adjust the network parameters of the two-dimensional convolutional neural network model according to the difference between the first part prediction result and the first part identification label.

5. An electronic device comprising: processor; as well as A memory, wherein computer program instructions are stored in the memory, and when the computer program instructions are executed by the processor, the processor is caused to perform the method according to any one of claims 1 to 2.

6. A computer-readable storage medium having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the processor is enabled to perform the method according to any one of claims 1 to 2.

Images