Medical bill image classification method, device, model, equipment, medium and product
By obtaining the text word vectors and image feature vectors of medical bills and using transformer models for multimodal fusion, encoding and classification, the problem of low accuracy of medical bills classification in the existing technology is solved, and more efficient medical bills are achieved Automated classification.
Patent Information
- Application Number
- CN202411121303.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-15
- Publication Date
- 2024-11-26
Smart Images

Figure CN119027731A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of computer technology, and specifically relates to a medical bill image classification method, device, transformer model, electronic device, computer-readable storage medium and computer program product. Background Art
[0002] With the in-depth application of information technology in the medical field, the management and processing of electronic medical bills has become an important part of improving the efficiency of medical services and reducing administrative costs. Traditionally, medical bill processing relies on manual review and classification, which is not only time-consuming and labor-intensive, but also prone to errors. In recent years, with the development of big data and artificial intelligence technologies, especially the maturity of natural language processing and computer vision technology, it has become possible to automatically classify medical bills. However, there are limitations to automated medical bill classification, which are mainly manifested in low classification accuracy, poor results, and difficulty in dealing with complex and changing medical bill formats. Summary of the invention
[0003] In view of this, the purpose of this application is to provide a medical bill image classification method, device, transformer model, electronic device, computer-readable storage medium and computer program product to improve the current problems of low accuracy and poor effect of automated medical bill classification, and difficulty in coping with complex and changeable medical bill formats.
[0004] The embodiment of the present application is implemented as follows:
[0005] In a first aspect, an embodiment of the present application provides a method for classifying medical bill images, including: obtaining a text word vector and an image feature vector corresponding to the medical bill; classifying the medical bill according to the text word vector and the image feature vector to obtain a classification result.
[0006] In the above embodiment, by obtaining the text word vector and image feature vector corresponding to the medical bill, and classifying the medical bill according to the text word vector and image feature vector, the accuracy of medical bill classification is improved by integrating information of different dimensions on the medical bill, so as to cope with the common scene of complex and changeable medical bill formats.
[0007] In combination with the first aspect embodiment, in a possible implementation manner, obtaining the image feature vector corresponding to the medical bill includes: obtaining image information corresponding to the medical bill; dividing the image information into multiple blocks of fixed sizes, performing linear transformation on the multiple blocks respectively, and generating an image feature vector.
[0008] In the above embodiment, the image information corresponding to the medical bill is divided into multiple blocks of fixed size, and then the multiple blocks are further linearly transformed to generate image feature vectors, extract important features in the image information, capture the key content of the image information, and identify the pattern and structure of the image, thereby providing important information for the classification of medical bills and improving the accuracy and comprehensiveness of the classification of medical bills.
[0009] In combination with the first aspect embodiment, in a possible implementation manner, classifying the medical bills according to the text word vectors and the image feature vectors to obtain classification results includes: processing the text word vectors and the image feature vectors based on a transformer model to obtain classification results.
[0010] In the above embodiment, the text word vector and image feature vector of the medical bill are processed simultaneously by using the transformer model, thereby providing a new medical bill image classification method based on the transformer model, which can not only achieve more accurate classification effect and higher classification efficiency, but also fully understand the content of the medical bill and adapt to the complex and changeable medical bill format.
[0011] In combination with the first aspect embodiment, in a possible implementation, the transformer model includes: an intermediate layer, a first encoding layer, and a fully connected layer connected in sequence; the text word vector and the image feature vector are processed based on the transformer model to obtain a classification result, including: using the intermediate layer to perform multimodal fusion on the text word vector and the image feature vector to obtain a multimodal vector sequence; using the first encoding layer to encode the multimodal vector sequence to obtain an encoded multimodal vector sequence; using the fully connected layer to classify the encoded multimodal vector sequence to obtain a classification result.
[0012] In the above embodiment, after obtaining a multimodal vector sequence by using the intermediate layer to perform multimodal fusion on the text word vector and the image feature vector, the multimodal vector sequence is encoded by using the first encoding layer to obtain an encoded multimodal vector sequence, and then the encoded multimodal vector sequence is classified by using the fully connected layer to obtain a classification result; by integrating text information and image information, more dimensional information is captured, which not only improves the accuracy and completeness of the medical bill classification results, but also can effectively deal with situations such as blurred bills and similar formats; in addition, automatic processing and integration of bill information not only greatly improves the speed and efficiency of medical bill processing, but also reduces the administrative burden on medical institutions.
[0013] In combination with the embodiment of the first aspect, in a possible implementation, the intermediate layer includes two second encoding layers and a splicing layer, and the use of the intermediate layer to perform multimodal fusion on the text word vector and the image feature vector to obtain a multimodal vector sequence includes: using the two second encoding layers to encode the text word vector and the image feature vector respectively to obtain the encoded text vector and image vector; using the splicing layer to splice the encoded text vector and the encoded image vector to obtain the multimodal vector sequence.
[0014] In the above embodiment, the text word vector and the image feature vector are respectively encoded by using two second encoding layers to obtain the encoded text vector and image vector, and then the encoded text vector and image vector are spliced by using the splicing layer to obtain a multimodal vector sequence; by encoding the text vector and the image vector first and then splicing them, the two are converted into a unified dimension, key information is extracted, the expressive ability of the data is enhanced, and the information complementarity between the text vector and the image vector is achieved, so as to improve the comprehensiveness of the understanding of the content of the medical bill, and realize efficient automatic classification while improving the classification accuracy. At the same time, after the text vector and the image vector are spliced, a lightweight model can be used for processing, which can reduce the computational burden and improve computational efficiency.
[0015] In the second aspect, an embodiment of the present application provides a device for classifying medical bill images, including: a data acquisition module and a classification module; the data acquisition module is used to obtain text word vectors and image feature vectors corresponding to the medical bills; the classification module is used to classify the medical bills according to the text word vectors and image feature vectors to obtain classification results.
[0016] In the third aspect, an embodiment of the present application provides a transformer model, comprising: an intermediate layer, a first encoding layer and a fully connected layer; the intermediate layer is configured to perform multimodal fusion on the text word vector and the image feature vector corresponding to the medical bill to obtain a multimodal vector sequence; the first encoding layer is configured to encode the multimodal vector sequence to obtain an encoded multimodal vector sequence; the fully connected layer is configured to classify the encoded multimodal vector sequence to obtain a classification result.
[0017] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a memory and a processor, the memory being connected to the processor; the memory being used to store programs; and the processor being used to call the programs stored in the memory to execute the method provided in the above-mentioned first aspect embodiment and / or any possible implementation method in combination with the first aspect embodiment.
[0018] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method provided by the above-mentioned first aspect embodiment and / or any possible implementation method combined with the first aspect embodiment is executed.
[0019] In a sixth aspect, an embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it executes the method provided by the above-mentioned first aspect embodiment and / or any possible implementation method combined with the first aspect embodiment.
[0020] Other features and advantages of the present application will be described in the following description. The purpose and other advantages of the present application can be realized and obtained through the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. The above and other purposes, features and advantages of the present application will be more clear as shown in the drawings.
[0022] Figure 1 A schematic diagram of the structure of a Transformer model provided in an embodiment of the present application is shown.
[0023] Figure 2 A flow chart of a medical bill image classification method provided in an embodiment of the present application is shown.
[0024] Figure 3 A module schematic diagram of a device for classifying medical bill images provided in an embodiment of the present application is shown.
[0025] Figure 4 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0026] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The following embodiments can be used as examples to more clearly illustrate the technical solutions of the present application, and cannot be used to limit the scope of protection of the present application. It will be appreciated by those skilled in the art that, in the absence of conflict, the features in the following embodiments and embodiments can be combined with each other.
[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. Moreover, the terms "comprises," "comprising," or any other variation thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.
[0028] Furthermore, the term "and / or" in this application is merely a term used to describe the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone.
[0029] The embodiment of the present application provides a medical bill image classification method, which obtains the text word vector and image feature vector corresponding to the medical bill, and then classifies the medical bill according to the obtained text word vector and image feature vector, and captures the information of different dimensions on the medical bill to enhance the completeness and accuracy of the obtained information, so as to achieve more accurate and efficient automatic classification of medical bills, so as to cope with complex and changeable medical bill styles. The medical bill referred to in the embodiment of the present application is an electronic medical bill.
[0030] In one implementation, when classifying medical bills based on the acquired text word vectors and image feature vectors, a transformer model (hereinafter referred to as a transformer model) may be used to process the information corresponding to the medical bills and integrate information of different modalities on the medical bills to achieve more efficient and accurate classification of medical bills to cope with complex and changeable medical bill styles. For example, the text word vectors and image feature vectors corresponding to the medical bills are processed based on the transformer model to obtain classification results.
[0031] In one implementation, the text word vectors and image feature vectors corresponding to the medical bills are processed based on the transformer model to obtain the classification result. The process can be: multimodal fusion of the text word vectors and image feature vectors based on the transformer model to obtain a multimodal vector sequence, encoding the multimodal vector sequence to obtain an encoded multimodal vector sequence, and classifying the encoded multimodal vector sequence to obtain a classification result.
[0032] In the above implementation, the structure of the transformer model is as follows: Figure 1 As shown, Figure 1 A schematic diagram of the structure of a Transformer model provided in an embodiment of the present application is shown. The Transformer model includes: an input layer, an intermediate layer, a first encoding layer, and a fully connected layer.
[0033] The input layer is configured to receive input data, such as text word vectors and image feature vectors corresponding to medical bills.
[0034] The middle layer is configured to perform multimodal fusion on the text word vector and image feature vector corresponding to the medical bill to obtain a multimodal vector sequence.
[0035] The first encoding layer is configured to encode the multimodal vector sequence to obtain an encoded multimodal vector sequence.
[0036] The fully connected layer is configured to classify the encoded multimodal vector sequence to obtain a classification result.
[0037] In a possible implementation, the middle layer includes two second coding layers and a splicing layer; the number of layers of the two second coding layers can be 4 layers, and the number of layers of the second coding layers given in this embodiment is only exemplary and is not intended to limit the number of layers of the second coding layers.
[0038] The middle layer is specifically used to: use the two second encoding layers to encode the text word vector and the image feature vector respectively to obtain the encoded text vector and the image vector; use the splicing layer to splice the encoded text vector and the encoded image vector to obtain a multimodal vector sequence.
[0039] In a possible implementation manner, the number of layers of the first coding layer may be 4. The number of layers of the first coding layer given in this embodiment is only exemplary and is not intended to limit the number of layers of the first coding layer.
[0040] The above Transformer model can be trained using a data set containing text word vectors and image feature vectors corresponding to a large number of medical bills to obtain a trained Transformer model.
[0041] The present application also provides a method for classifying medical bill images. Figure 2 The flowchart shown illustrates the medical bill image classification method.
[0042] Step S100: Obtain text word vectors and image feature vectors corresponding to the medical bill.
[0043] In one possible implementation, the text word vector and image feature vector corresponding to the medical bill can be directly obtained from the database. The database stores the text word vector and image feature vector corresponding to the processed medical bill. By directly obtaining the text word vector and image feature vector corresponding to the medical bill from the database for use, the tedious recalculation is avoided, the cost is saved, and the classification efficiency is improved.
[0044] In a possible implementation, the process of obtaining the text word vector corresponding to the medical bill may include: obtaining the text information corresponding to the medical bill; using natural language processing technology to segment the text information and convert it into a text word vector; the text word vector corresponding to the medical bill may also be obtained by other means, such as using a pre-trained model for obtaining text information in the medical bill, which will not be repeated here. Converting the text information corresponding to the medical bill into a text word vector can capture the semantic connection between words or phrases in the text information, understand their meaning in the context, identify keywords and phrases in the text information, provide important information for the classification of medical bills, and improve the accuracy of medical bill classification.
[0045] In one possible implementation, the process of obtaining the image feature vector corresponding to the medical bill may include: obtaining the image information corresponding to the medical bill; dividing the image information into a plurality of fixed-size blocks, performing linear transformation on the plurality of blocks respectively, and generating the image feature vector. In one implementation, the process of dividing the image information into a plurality of fixed-size blocks may include: scaling the image according to the resolution distribution of the medical bill image, and then cutting the image; wherein the size of the image block may be 32*32. Smaller image blocks can obtain more fine-grained features, and the specific size of the image block should be determined according to the actual situation. The image block size given in this embodiment is only exemplary and should not be used as a limitation on the image block size.
[0046] Step S200: Classify the medical bills according to the text word vectors and the image feature vectors to obtain classification results.
[0047] In a possible implementation, the above-mentioned process of classifying the medical bills according to the text word vector and the image feature vector in S200 may include: processing the text word vector and the image feature vector based on the Transformer model to obtain a classification result.
[0048] In another possible implementation, the above-mentioned S200 process of classifying medical bills according to text word vectors and image feature vectors may include: performing multimodal fusion on text word vectors and image feature vectors to obtain a multimodal vector sequence; encoding the multimodal vector sequence to obtain an encoded multimodal vector sequence; and classifying the encoded multimodal vector sequence to obtain a classification result.
[0049] In one implementation, the process of performing multimodal fusion on text word vectors and image feature vectors to obtain a multimodal vector sequence may include: encoding the text word vectors and image feature vectors respectively to obtain encoded text vectors and image vectors; and splicing the encoded text vectors and the encoded image vectors to obtain a multimodal vector sequence.
[0050] In one implementation, the process of processing text word vectors and image feature vectors based on the Transformer model to obtain classification results may include: using the Transformer model to perform multimodal fusion on the text word vectors and image feature vectors to obtain a multimodal vector sequence; encoding the multimodal vector sequence to obtain an encoded multimodal vector sequence; and classifying the encoded multimodal vector sequence to obtain a classification result.
[0051] In one implementation, the Transformer model may include: an intermediate layer, a first encoding layer, and a fully connected layer connected in sequence; at this time, the process of processing the text word vector and the image feature vector based on the Transformer model to obtain the classification result may include: using the intermediate layer to perform multimodal fusion on the text word vector and the image feature vector to obtain a multimodal vector sequence; using the first encoding layer to encode the multimodal vector sequence to obtain an encoded multimodal vector sequence; using the fully connected layer to classify the encoded multimodal vector sequence to obtain a classification result.
[0052] In one embodiment, the process of using an intermediate layer to perform multimodal fusion on text word vectors and image feature vectors to obtain a multimodal vector sequence may include: using two second encoding layers to encode the text word vectors and image feature vectors respectively to obtain encoded text vectors and image vectors; using a splicing layer to splice the encoded text vectors and the encoded image vectors to obtain a multimodal vector sequence.
[0053] There are two ways to splice the encoded text vector and image vector. One splicing method is weighted splicing. For example, an encoded text vector is T = [t1, t2, t3..., tn], an encoded image vector is I = [i1, i2, i3..., in], and hyperparameters α and β (hyperparameters α and β are determined according to the characteristics of the data set of the text vector and image feature vector of the acquired medical bill), then the spliced multimodal vector sequence is αT+βI. Another splicing method is same-dimensional splicing. For example, an encoded text vector is T = [t1, t2, t3..., tn], an encoded image vector is I = [i1, i2, i3..., in], then the spliced multimodal vector sequence is [t1, t2, t3..., tn, i1, i2, i3..., in]. The multimodal fusion method of text vectors and image vectors given in this embodiment is only exemplary and should not be used as a limitation on the multimodal fusion method.
[0054] It can be understood that the above embodiment is only one of many embodiments of the present application, and therefore, it cannot be understood as the only embodiment of the present application.
[0055] like Figure 3 As shown, Figure 3 The module schematic diagram of a device 10 for classifying medical bill images provided in an embodiment of the present application is shown. The device 10 includes: a data acquisition module 11 and a classification module 12.
[0056] The data acquisition module 11 is used to obtain the text word vector and image feature vector corresponding to the medical bill.
[0057] The classification module 12 is used to classify the medical bills according to the text word vectors and the image feature vectors to obtain classification results.
[0058] In one possible implementation, the data acquisition module 11 is specifically used to: obtain text information corresponding to the medical bill; segment the text information using natural language processing technology and convert it into a text word vector; obtain image information corresponding to the medical bill; divide the image information into multiple blocks of fixed size, perform linear transformation on each of the multiple blocks, and generate an image feature vector.
[0059] In a possible implementation, the classification module 12 is specifically configured to process the text word vector and the image feature vector based on the transformer model to obtain a classification result.
[0060] Optionally, the transformer model includes: an intermediate layer, a first encoding layer and a fully connected layer connected in sequence; a classification module 12, which is specifically used to: use the intermediate layer to perform multimodal fusion on the text word vector and the image feature vector to obtain a multimodal vector sequence; use the first encoding layer to encode the multimodal vector sequence to obtain an encoded multimodal vector sequence; use the fully connected layer to classify the encoded multimodal vector sequence to obtain a classification result.
[0061] The middle layer includes two second encoding layers and a splicing layer, and the classification module 12 is specifically used to: use the two second encoding layers to encode the text word vector and the image feature vector respectively to obtain the encoded text vector and the image vector; use the splicing layer to splice the encoded text vector and the encoded image vector to obtain a multimodal vector sequence.
[0062] like Figure 4 As shown, Figure 4 The schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application is shown. The electronic device 20 includes: a processor 21 and a memory 22.
[0063] It should be noted that Figure 4 The components and structures of the electronic device 20 shown are merely exemplary and non-limiting. The electronic device may also have other components and structures as required.
[0064] The processor 21, the memory 22, and other components that may appear in the electronic device 20 are directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, the processor 21, the memory 22, and other components that may appear may be electrically connected to each other via one or more communication buses or signal lines.
[0065] The memory 22 is used to store programs, for example, a program corresponding to the medical bill image classification method mentioned above or a device for classifying medical bill images mentioned above. Optionally, when the device for classifying medical bill images is stored in the memory 22, the device for classifying medical bill images includes at least one software function module that can be stored in the memory 22 in the form of software or firmware.
[0066] The processor 21 is used to execute the executable modules stored in the memory 22, such as the software function modules or computer programs included in the apparatus for executing medical bill image classification, so as to execute the above-mentioned medical bill image classification method.
[0067] Of course, the method disclosed in any embodiment of the present application can be applied to the processor 21, or implemented by the processor 21.
[0068] An embodiment of the present application also provides a non-volatile computer-readable storage medium (hereinafter referred to as storage medium), on which a computer program is stored. When the computer program is run by a computer such as the above-mentioned electronic device 20, the method disclosed in any of the above-mentioned embodiments is executed.
[0069] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is run by a computer such as the electronic device 20 described above, the method disclosed in any of the embodiments shown above is executed.
[0070] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0071] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0072] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0073] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a computer-readable storage medium, including several instructions for enabling a computer device (which can be a personal computer, a laptop, a server, or an electronic device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0074] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A medical bill image classification method, characterized in that: include: Obtain the text word vector and image feature vector corresponding to the medical bill; The medical bills are classified according to the text word vectors and the image feature vectors to obtain classification results.
2. The method according to claim 1, characterized in that The step of obtaining the image feature vector corresponding to the medical bill includes: Obtain image information corresponding to medical bills; The image information is divided into a plurality of blocks of fixed size, and a linear transformation is performed on each of the plurality of blocks to generate an image feature vector.
3. The method according to claim 1, characterized in that The medical bills are classified according to the text word vector and the image feature vector to obtain the classification result, including: The text word vector and the image feature vector are processed based on the transformer model to obtain a classification result.
4. The method according to claim 3, characterized in that The transformer model includes: an intermediate layer, a first encoding layer, and a fully connected layer connected in sequence; the text word vector and the image feature vector are processed based on the transformer model to obtain a classification result, including: Using the intermediate layer to perform multimodal fusion on the text word vector and the image feature vector to obtain a multimodal vector sequence; Encoding the multimodal vector sequence using the first encoding layer to obtain an encoded multimodal vector sequence; The encoded multimodal vector sequence is classified using the fully connected layer to obtain a classification result.
5. The method according to claim 4, characterized in that The intermediate layer includes two second encoding layers and a concatenation layer, and the intermediate layer is used to perform multimodal fusion on the text word vector and the image feature vector to obtain a multimodal vector sequence, including: Encoding the text word vector and the image feature vector respectively using the two second encoding layers to obtain an encoded text vector and an encoded image vector; The encoded text vector and the encoded image vector are concatenated using the concatenation layer to obtain the multimodal vector sequence.
6. A device for classifying medical bill images, characterized in that: include: A data acquisition module, used to obtain text word vectors and image feature vectors corresponding to medical bills; The classification module is used to classify the medical bills according to the text word vectors and the image feature vectors to obtain classification results.
7. A transformer model, characterized in that: include: The middle layer is configured to perform multimodal fusion on the text word vector and the image feature vector corresponding to the medical bill to obtain a multimodal vector sequence; A first encoding layer is configured to encode the multimodal vector sequence to obtain an encoded multimodal vector sequence; The fully connected layer is configured to classify the encoded multimodal vector sequence to obtain a classification result.
8. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is connected to the processor; The memory is used to store programs; The processor is used to call the program stored in the memory to execute the method according to any one of claims 1 to 5.
9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is executed.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is performed.
