阅读说明：本技术 基于人工智能的医学影像处理方法、装置、设备及介质 (Medical image processing method, device, equipment and medium based on artificial intelligence ) 是由 高晗 李彬 于 2021-09-17 设计创作，主要内容包括：本申请涉及人工智能技术领域,提供一种基于人工智能的医学影像处理方法、装置、电子设备及介质,所述方法包括：响应于对目标患者的多个医学影像的处理指令,获取每个医学影像对应的识别任务；确定每个识别任务的影响因素；根据影响因素对应的层级关系,构建影响因素层次结构模型；获取影预设的判断矩阵,并基于判断矩阵和影响因素层次结构模型,计算识别任务对应的组合权重；根据识别任务对应的组合权重,生成多个识别任务的任务调度集；在预设存储空间中依次获取任务调度集中每个识别任务对应的目标医学影像；调用AI边缘计算设备对依次获取的目标医学影像进行处理。本申请提高了医学影像的处理效率。(The application relates to the technical field of artificial intelligence, and provides a medical image processing method, a medical image processing device, an electronic device and a medium based on artificial intelligence, wherein the method comprises the following steps: responding to a processing instruction of a plurality of medical images of a target patient, and acquiring an identification task corresponding to each medical image; determining an influencing factor of each recognition task; constructing an influence factor hierarchical structure model according to the hierarchical relation corresponding to the influence factors; acquiring a judgment matrix preset by the shadow, and calculating the combination weight corresponding to the identification task based on the judgment matrix and the influence factor hierarchical structure model; generating a task scheduling set of a plurality of recognition tasks according to the combination weight corresponding to the recognition tasks; sequentially acquiring a target medical image corresponding to each recognition task in a task scheduling set in a preset storage space; and calling AI edge computing equipment to process the sequentially acquired target medical images. The application improves the processing efficiency of the medical image.)

1. A medical image processing method based on artificial intelligence, which is characterized by comprising the following steps:

responding to a processing instruction of a plurality of medical images of a target patient, and acquiring an identification task corresponding to each medical image;

determining influence factors of each identification task according to task information corresponding to the identification tasks;

determining a hierarchical relationship corresponding to the influence factors according to the influence degrees of the influence factors, and constructing an influence factor hierarchical structure model according to the hierarchical relationship;

acquiring a preset judgment matrix, and calculating the combination weight corresponding to the identification task based on the judgment matrix and the influence factor hierarchical structure model;

determining a scheduling order corresponding to each identification task according to the combined weight corresponding to the identification task, and generating a task scheduling set of a plurality of identification tasks according to the scheduling order;

sequentially acquiring a target medical image corresponding to each recognition task in the task scheduling set in a preset storage space;

and calling AI edge computing equipment to process the sequentially acquired target medical images.

2. The artificial intelligence based medical image processing method according to claim 1, wherein the invoking the AI edge computing device to process the sequentially acquired target medical images comprises:

acquiring image type information corresponding to the image type file in the target medical image;

extracting the characteristic value of the image information by using the trained convolutional neural network model to obtain an image characteristic set;

extracting a non-image file in the target medical image by using a preset feature extraction algorithm to obtain a non-image feature set;

taking the non-image feature set as an input of an XGboost algorithm to perform regression analysis to obtain a first result;

taking the image feature set and the non-image feature set as the input of the XGboost algorithm together to perform regression analysis to obtain a second result;

and obtaining a processing result of the target medical image according to the first result and the second result.

3. The artificial intelligence based medical image processing method according to claim 2, wherein the acquiring image class information corresponding to the image class file in the target medical image includes:

performing feature extraction on the image files in the target medical image based on an OCR algorithm to obtain pixel information corresponding to the image files;

generating a pixel matrix according to the color codes of different positions in the pixel information;

and obtaining image class information corresponding to the image class file in the target medical image based on the pixel matrix.

4. The artificial intelligence based medical image processing method of claim 2, wherein the extracting the non-image class file in the target medical image by using a preset feature extraction algorithm to obtain a non-image class feature set comprises:

extracting images of non-image files in the target medical image to obtain a plurality of target images;

and performing feature extraction on the plurality of target images based on an OCR algorithm to obtain the non-image feature set.

5. The artificial intelligence based medical image processing method of claim 1, wherein prior to responding to the processing instructions for the plurality of medical images of the target patient, the method further comprises:

judging whether the medical image meets the preset identification quality requirement or not;

if the medical image meets the preset identification quality requirement, determining a data identifier corresponding to the medical image;

determining a classification space corresponding to the data identifier in the preset storage space;

storing the medical image to the classification space, and using the data identification as an index of the medical image in the classification space.

6. The artificial intelligence based medical image processing method of claim 5, wherein the method further comprises:

if the medical image does not meet the preset identification quality requirement, determining the importance level of the medical image;

and if the importance level of the medical image is greater than or equal to an importance level threshold, generating a data acquisition request corresponding to the medical image, wherein the data acquisition request is used for acquiring target data.

7. The artificial intelligence based medical image processing method of any one of claims 1-6, wherein the determining a scheduling order corresponding to each recognition task according to the combination weight corresponding to the recognition task, and generating a task scheduling set of a plurality of recognition tasks according to the scheduling order comprises:

based on the combination weight corresponding to each recognition task, carrying out weighted calculation on the influence factors in each recognition task by using a fuzzy comprehensive evaluation method to obtain the priority corresponding to each recognition task;

and generating a task scheduling set corresponding to each identification task according to the priority corresponding to each identification task.

8. An artificial intelligence-based medical image processing apparatus, comprising:

the task acquisition module is used for responding to a processing instruction of a plurality of medical images of a target patient and acquiring an identification task corresponding to each medical image;

the factor determining module is used for determining the influence factors of each recognition task according to the task information corresponding to the recognition task;

the model building module is used for determining the hierarchical relationship corresponding to the influence factors according to the influence degrees of the influence factors and building an influence factor hierarchical structure model according to the hierarchical relationship;

the weight calculation module is used for acquiring a preset judgment matrix and calculating the combination weight corresponding to the identification task based on the judgment matrix and the influence factor hierarchical structure model;

the scheduling and arranging module is used for determining a scheduling order corresponding to each identification task according to the combined weight corresponding to the identification task and generating a plurality of task scheduling sets of the identification tasks according to the scheduling order;

the image acquisition module is used for sequentially acquiring a target medical image corresponding to each recognition task in the task scheduling set in a preset storage space;

and the image processing module is used for calling AI edge computing equipment to process the sequentially acquired target medical images.

9. An electronic device, comprising a processor and a memory, wherein the processor is configured to implement the artificial intelligence based medical image processing method according to any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer-readable storage medium, on which a computer program is stored, the computer program, when being executed by a processor, implementing the artificial intelligence based medical image processing method according to any one of claims 1 to 7.

Technical Field

The application relates to the technical field of artificial intelligence, in particular to a medical image processing method, a medical image processing device, medical image processing equipment and a medical image processing medium based on artificial intelligence.

Background

In recent years, with the advent and development of medical imaging technologies such as magnetic resonance imaging and computed tomography, the medical imaging technologies are widely used in the examination, diagnosis, and treatment of various diseases. However, there are some outstanding problems in the field of medical image diagnosis, for example, the accuracy of identification based on medical images is low.

The inventor finds that in the prior art, the machine learning model is used for identification and processing of medical images, but the running of the machine learning model consumes extremely large computing resources, and the machine learning model is transmitted to the cloud platform for operation, so that a large amount of bandwidth resources are occupied, long waiting time delay is caused, and the processing efficiency of the medical images is low.

Disclosure of Invention

In view of the above, there is a need for a medical image processing method, apparatus, electronic device and medium based on artificial intelligence, which process a medical image based on an AI edge computing device, reduce the amount of computation, and improve the processing efficiency of the medical image.

In a first aspect, the present application provides a medical image processing method based on artificial intelligence, the method including:

responding to a processing instruction of a plurality of medical images of a target patient, and acquiring an identification task corresponding to each medical image;

determining influence factors of each identification task according to task information corresponding to the identification tasks;

determining a hierarchical relationship corresponding to the influence factors according to the influence degrees of the influence factors, and constructing an influence factor hierarchical structure model according to the hierarchical relationship;

acquiring a preset judgment matrix, and calculating the combination weight corresponding to the identification task based on the judgment matrix and the influence factor hierarchical structure model;

determining a scheduling order corresponding to each identification task according to the combined weight corresponding to the identification task, and generating a task scheduling set of a plurality of identification tasks according to the scheduling order;

sequentially acquiring a target medical image corresponding to each recognition task in the task scheduling set in a preset storage space;

and calling AI edge computing equipment to process the sequentially acquired target medical images.

According to an optional embodiment of the present application, the invoking the AI edge computing device to process the sequentially acquired target medical images includes:

acquiring image type information corresponding to the image type file in the target medical image;

extracting the characteristic value of the image information by using the trained convolutional neural network model to obtain an image characteristic set;

extracting a non-image file in the target medical image by using a preset feature extraction algorithm to obtain a non-image feature set;

taking the non-image feature set as an input of an XGboost algorithm to perform regression analysis to obtain a first result;

taking the image feature set and the non-image feature set as the input of the XGboost algorithm together to perform regression analysis to obtain a second result;

and obtaining a processing result of the target medical image according to the first result and the second result.

According to an optional embodiment of the present application, the acquiring image class information corresponding to an image class file in the target medical image includes:

performing feature extraction on the image files in the target medical image based on an OCR algorithm to obtain pixel information corresponding to the image files;

generating a pixel matrix according to the color codes of different positions in the pixel information;

and obtaining image class information corresponding to the image class file in the target medical image based on the pixel matrix.

According to an optional embodiment of the present application, the extracting, by using a preset feature extraction algorithm, a non-image-class file in the target medical image to obtain a non-image-class feature set includes:

extracting images of non-image files in the target medical image to obtain a plurality of target images;

and performing feature extraction on the plurality of target images based on an OCR algorithm to obtain the non-image feature set.

According to an optional embodiment of the present application, before responding to the processing instructions for the plurality of medical images of the target patient, the method further comprises:

judging whether the medical image meets the preset identification quality requirement or not;

if the medical image meets the preset identification quality requirement, determining a data identifier corresponding to the medical image;

determining a classification space corresponding to the data identification in a preset storage space;

storing the medical image to the classification space, and using the data identification as an index of the medical image in the classification space.

According to an optional embodiment of the application, the method further comprises:

if the medical image does not meet the preset identification quality requirement, determining the importance level of the medical image;

and if the importance level of the medical image is greater than or equal to an importance level threshold, generating a data acquisition request corresponding to the medical image, wherein the data acquisition request is used for acquiring target data.

According to an optional embodiment of the present application, the determining, according to the combining weight corresponding to the identification task, a scheduling order corresponding to each identification task, and generating a task scheduling set of a plurality of identification tasks according to the scheduling order includes:

based on the combination weight corresponding to each recognition task, carrying out weighted calculation on the influence factors in each recognition task by using a fuzzy comprehensive evaluation method to obtain the priority corresponding to each recognition task;

and generating a task scheduling set corresponding to each identification task according to the priority corresponding to each identification task.

In a second aspect, the present application provides an artificial intelligence-based medical image processing apparatus, the apparatus comprising:

the task acquisition module is used for responding to a processing instruction of a plurality of medical images of a target patient and acquiring an identification task corresponding to each medical image;

the factor determining module is used for determining the influence factors of each recognition task according to the task information corresponding to the recognition task;

the model building module is used for determining the hierarchical relationship corresponding to the influence factors according to the influence degrees of the influence factors and building an influence factor hierarchical structure model according to the hierarchical relationship;

the weight calculation module is used for acquiring a preset judgment matrix and calculating the combination weight corresponding to the identification task based on the judgment matrix and the influence factor hierarchical structure model;

the scheduling and arranging module is used for determining a scheduling order corresponding to each identification task according to the combined weight corresponding to the identification task and generating a plurality of task scheduling sets of the identification tasks according to the scheduling order;

the image acquisition module is used for sequentially acquiring a target medical image corresponding to each recognition task in the task scheduling set in a preset storage space;

and the image processing module is used for calling AI edge computing equipment to process the sequentially acquired target medical images.

In a third aspect, the present application provides an electronic device comprising a processor and a memory, wherein the processor is configured to implement the artificial intelligence based medical image processing method when executing a computer program stored in the memory.

In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the artificial intelligence based medical image processing method.

To sum up, the medical image processing method, the medical image processing device, the medical image processing electronic device and the medical image processing media based on artificial intelligence analyze image calculation tasks by using an analytic hierarchy process to obtain combination weights corresponding to the image calculation tasks, determine a task scheduling set based on the combination weights, and finally perform task scheduling according to the obtained ordered task scheduling set to obtain target image data corresponding to each image calculation task. The method is more comprehensive than the task scheduling consideration only according to the task type or the task execution frequency, is simple to operate and is beneficial to implementation, meanwhile, an influence factor hierarchical structure model is constructed according to the influence degree corresponding to the influence factor, the combination weight corresponding to each recognition task is calculated based on the influence factor hierarchical structure model, and a task scheduling set is generated according to the combination weight corresponding to each recognition task, so that the scheduling sequence corresponding to the recognition tasks is determined, the problem that the task scheduling efficiency of the collected image calculation task is low, the recognition tasks with large combination weights can be scheduled preferentially, the problem that the complex task scheduling time is long is solved, and the efficiency of medical diagnosis can be improved.

Drawings

Fig. 1 is a flowchart of a medical image processing method based on artificial intelligence according to an embodiment of the present application.

Fig. 2 is a block diagram of a medical image processing apparatus based on artificial intelligence according to a second embodiment of the present application.

Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.

Detailed Description

In order that the above objects, features and advantages of the present application can be more clearly understood, a detailed description of the present application will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing an example in an alternative implementation and is not intended to be limiting of the present application.

The medical image processing method based on artificial intelligence provided by the embodiment of the application is executed by the electronic equipment, and correspondingly, the medical image processing device based on artificial intelligence runs in the electronic equipment. The electronic device may include a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, a wearable device, and the like.

The medical image processing method and the medical image processing device can process the medical image based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

Example one

Fig. 1 is a flowchart of a medical image processing method based on artificial intelligence according to an embodiment of the present application. The medical image processing method based on artificial intelligence specifically comprises the following steps, and the sequence of the steps in the flowchart can be changed and some steps can be omitted according to different requirements.

S11, responding to the processing instruction of the plurality of medical images of the target patient, and acquiring the identification task corresponding to each medical image.

The medical image may include medical image information transmitted by a hospital imaging device, including, but not limited to, a Digital Radiography (DR) image, a Computed Tomography (CT) image, a Magnetic Resonance (MR) image, a Radiographic Testing (RT) image, an Electrocardiogram (ECG), an upper gastrointestinal contrast image, an ultrasound image, a pathology image, and the like.

Different medical images correspond to different recognition tasks. For example, electrocardiograms are used to record the electrical activity of the normal heart of the human body, for diagnosing diseases in the heart; the upper gastrointestinal imaging refers to imaging of the upper part of the duodenum to diagnose lesions in the gastrointestinal tract.

In an optional embodiment, before responding to the processing instructions for the plurality of medical images of the target patient, the method further comprises:

judging whether the medical image meets the preset identification quality requirement or not;

if the medical image meets the preset identification quality requirement, determining a data identifier corresponding to the medical image;

determining a classification space corresponding to the data identification in a preset storage space;

storing the medical image to the classification space, and using the data identification as an index of the medical image in the classification space.

The method comprises the steps of presetting identification quality requirements of medical images, wherein the identification quality requirements can comprise image definition requirements, picture integrity requirements, video definition requirements and the like.

And carrying out space division in a preset storage space, and setting classification spaces corresponding to different types of medical images. Different classification spaces correspond to different data identifications. And generating an index corresponding to the medical image according to the data identification. For example, the data identifier and the address corresponding to the classification space may be used as an index of the medical image in the classification space.

Whether the medical images meet the identification quality requirement or not is judged, the medical images meeting the identification quality requirement are stored, validity of the medical images stored in the preset storage space can be guaranteed, and therefore the medical images stored in the preset storage space can be processed conveniently. Meanwhile, the medical images are classified and stored based on the data identification, when the medical images need to be acquired, the medical images can be acquired only from the classification space, and compared with the whole storage space, the classification space is small in storage capacity, so that the target medical images can be acquired quickly, and the acquisition efficiency of the target medical images is improved.

In an optional embodiment, the method further comprises:

if the medical image does not meet the preset identification quality requirement, determining the importance level of the medical image;

and if the importance level of the medical image is greater than or equal to an importance level threshold, generating a data acquisition request corresponding to the medical image, wherein the data acquisition request is used for acquiring target data.

The data acquisition request is used for acquiring target data corresponding to the medical image which does not meet the preset identification quality requirement. Illustratively, after target data is acquired according to the data acquisition request, the medical image which does not meet the preset identification quality requirement is deleted.

And if the importance level of the medical image is smaller than an importance level threshold, deleting the medical image. For example, after the medical image is deleted, a relevant deletion record may be generated.

By generating the data acquisition request for the unqualified medical image with high importance level, the condition that the required medical image does not exist when the medical image is subsequently calculated can be avoided, and the efficiency of the medical image calculation is improved.

And S12, determining the influence factors of each recognition task according to the task information corresponding to the recognition task.

For example, the task information may include a medical image category to be identified, an identification task type, and an identification task execution frequency, and the influence factor of each identification task is determined according to the task information. Different medical images need to be analyzed by different identification tasks, so that diagnosis results corresponding to the identification tasks are obtained according to analysis results. The more medical images the recognition task corresponds to, the more image factors the recognition task corresponds to.

And S13, determining the hierarchical relationship corresponding to the influence factors according to the influence degrees of the influence factors, and constructing an influence factor hierarchical structure model according to the hierarchical relationship.

And determining the hierarchical relationship corresponding to the influence factors according to the influence hierarchy corresponding to the influence factors, wherein the hierarchical relationship corresponding to the influence factors is used for expressing different influence degrees of the influence factors.

The influence degree and the influence levels are in positive correlation, the larger the influence degree of the influence factors is, the higher the influence level corresponding to the influence factors is, the smaller the influence degree of the influence factors is, the lower the influence level corresponding to the influence factors is, and the level relation corresponding to the influence factors is determined according to the influence level corresponding to each influence factor. And constructing an influence factor hierarchical structure model according to the hierarchical relation corresponding to the influence factors. The hierarchical model of influence factors includes influence factors corresponding to each diagnostic task, for example, the influence levels corresponding to the influence factors stored in each level in the hierarchical model of influence factors are the same.

Illustratively, the mapping relationship between the influence factors and the influence degrees can be preset, a factor influence table is generated, and the influence degrees corresponding to the influence factors can be determined by querying the factor influence table, so as to determine the hierarchical relationship corresponding to the influence factors.

For example, the hierarchical relationship corresponding to the influence factor may be determined based on an Analytic Hierarchy Process (AHP) and the influence degree of the influence factor. The AHP analytic hierarchy process is a systematic and hierarchical analytic method combining qualitative analysis and quantitative analysis. By using the AHP analytic hierarchy process, the thinking process of the decision can be mathematized by using less quantitative information on the basis of deeply researching the essence, the influence factors, the internal relation and the like of the complex decision problem, so that the efficiency of determining the hierarchical relation corresponding to the influence factors is improved.

The influence factor hierarchical structure model comprises influence factors corresponding to each recognition task and can be divided into a plurality of hierarchies, and each hierarchy comprises one or more influence factors.

And S14, acquiring a preset judgment matrix, and calculating the combination weight corresponding to the identification task based on the judgment matrix and the influence factor hierarchical structure model.

In an optional implementation manner, the priority of the obtained influence factors can be analyzed and evaluated based on a fuzzy comprehensive evaluation method to obtain a factor set module; and meanwhile, determining a weight matrix based on medical experience, and finally obtaining a preset judgment matrix based on the factor set module and the weight matrix.

Illustratively, according to the level of a plurality of influence factors corresponding to the identification task in the influence factor hierarchical structure model, the weight corresponding to each influence factor is determined, and the weights corresponding to the plurality of influence factors are substituted into the judgment matrix for calculation to obtain the combined weight corresponding to the identification task. For example, the hierarchy of the influencer in the hierarchical model of influencers can be determined as the weight corresponding to the influencer.

S15, determining the scheduling order corresponding to each recognition task according to the combined weight corresponding to the recognition task, and generating a task scheduling set of a plurality of recognition tasks according to the scheduling order.

Illustratively, the multiple recognition tasks are sorted according to the size of the combination weight corresponding to the multiple recognition tasks, and the scheduling order corresponding to each recognition task is determined according to the sorting, so as to obtain the task scheduling sets corresponding to the multiple recognition tasks. For example, the sorting may be done in order from big to small. An order of executing the plurality of identified tasks may be determined according to a task schedule set.

In an optional embodiment, the determining, according to the combined weight corresponding to the identification task, a scheduling order corresponding to each identification task, and generating a task scheduling set of a plurality of identification tasks according to the scheduling order includes:

based on the combination weight corresponding to each recognition task, carrying out weighted calculation on the influence factors in each recognition task by using a fuzzy comprehensive evaluation method to obtain the priority corresponding to each recognition task;

and generating a task scheduling set corresponding to each identification task according to the priority corresponding to each identification task.

For example, based on the combination weight corresponding to each recognition task, the influence factors in each recognition task are weighted and calculated by using a fuzzy comprehensive evaluation method, and the priority corresponding to each recognition task is determined according to the value corresponding to the weighted influence factors. For example, the weighted values of each influence factor in the identification task are added to obtain a target influence value, and the priority corresponding to each identification task is determined based on the target influence value. The larger the target influence value corresponding to the identification task is, the lower the priority corresponding to the identification task is.

By using the fuzzy comprehensive evaluation method to carry out weighting calculation on the influence factors, scientific, reasonable and practical quantitative evaluation can be carried out on the data with the fuzziness of the stored information, so that the priority corresponding to each recognition task is accurately determined, the accuracy of a task scheduling set generated based on the priority corresponding to the recognition task is higher, and the subsequent task scheduling is facilitated.

And S16, sequentially acquiring the target medical image corresponding to each recognition task in the task scheduling set in a preset storage space.

And sequentially acquiring the target medical image corresponding to each recognition task in a preset storage space according to the sequence of the recognition tasks in the task scheduling set. For example, there are an identification task a and an identification task B, and the order of the identification task a in the task scheduling set is before the identification task B, and first a target medical image corresponding to the identification task a is acquired in a preset storage space, and then a target medical image corresponding to the identification task B is acquired in the preset storage space.

And S17, calling AI edge computing equipment to process the sequentially acquired target medical images.

And calling AI edge computing equipment to identify the sequentially acquired target medical images, and obtaining a diagnosis result corresponding to each identification task based on the identification result for identifying the target medical images. For example, one recognition task includes a plurality of target medical images, and based on recognition results of the plurality of target medical images, diagnosis results corresponding to the recognition task are obtained.

In an optional embodiment, the invoking the AI-edge computing device to process the sequentially acquired target medical images includes:

acquiring image type information corresponding to the image type file in the target medical image;

extracting the characteristic value of the image information by using the trained convolutional neural network model to obtain an image characteristic set;

extracting a non-image file in the target medical image by using a preset feature extraction algorithm to obtain a non-image feature set;

taking the non-image feature set as an input of an XGboost algorithm to perform regression analysis to obtain a first result;

taking the image feature set and the non-image feature set as the input of the XGboost algorithm together to perform regression analysis to obtain a second result;

and obtaining a processing result of the target medical image according to the first result and the second result.

The non-image class files may include video class files.

The lifting tree model XGboost (extreme Gradient boosting) is a model integrating a plurality of tree models, and by adding a regular term in a cost function, the complexity of the model is controlled, over-fitting is prevented, parallel processing can be realized, and the processing speed of files is increased.

For example, the first result and the second result may be summarized to obtain a processing result of the target medical image.

By the technical scheme, the common processing of image data and non-image data can be realized, so that the coverage of the analyzed medical image is wide, and the efficiency of medical diagnosis is improved; meanwhile, the XGboost algorithm is utilized, not only is the first-order derivative used, but also the second-order derivative is used, the loss is more accurate, the loss can be customized, overfitting can be reduced, and the calculation amount of the AI edge calculation equipment is reduced.

In an optional embodiment, the acquiring image class information corresponding to an image class file in the target medical image includes:

performing feature extraction on the image files in the target medical image based on an OCR algorithm to obtain pixel information corresponding to the image files;

generating a pixel matrix according to the color codes of different positions in the pixel information;

and obtaining image class information corresponding to the image class file in the target medical image based on the pixel matrix.

And extracting pixel characteristics in the image file by Optical Character Recognition (OCR) to obtain pixel information. And generating a pixel matrix according to the color codes of different positions in the pixel information, such as generating the pixel matrix according to the hexadecimal color code. The pixel matrix can effectively retain the image information in the image class file. For example, the pixel matrix may be determined as image class information corresponding to an image class file in the target medical image.

By using an OCR algorithm, the features in the image files can be effectively extracted, the image feature set is obtained based on the color codes in the pixel information, more features in the image can be reserved, and therefore the identification accuracy can be improved.

In an optional embodiment, the extracting, by using a preset feature extraction algorithm, a non-image-class file in the target medical image to obtain a non-image-class feature set includes:

extracting images of non-image files in the target medical image to obtain a plurality of target images;

and performing feature extraction on the plurality of target images based on an OCR algorithm to obtain the non-image feature set.

The non-image files comprise video files, and image extraction is carried out on the video files to obtain a plurality of target images. For example, image extraction may be performed on a video file at regular time intervals, such as 0.01S, resulting in a plurality of target images.

And performing feature extraction on the plurality of target images by using an OCR algorithm to obtain a non-image data feature set. For example, feature extraction is performed on the multiple target images based on an OCR algorithm to obtain pixel information corresponding to the multiple target images; generating a pixel matrix according to the color codes of different positions in the pixel information; and obtaining a non-image class characteristic set corresponding to the non-image class file in the target medical image based on the pixel matrix.

According to the medical image processing method based on artificial intelligence, image calculation tasks are analyzed through an analytic hierarchy process, combination weights corresponding to the image calculation tasks are obtained, a task scheduling set is determined based on the combination weights, task scheduling is finally carried out according to the obtained task scheduling set after sequencing, and target image data corresponding to each image calculation task are obtained. The method is more comprehensive than the task scheduling consideration only according to the task type or the task execution frequency, is simple to operate and is beneficial to implementation, meanwhile, an influence factor hierarchical structure model is constructed according to the influence degree corresponding to the influence factor, the combination weight corresponding to each recognition task is calculated based on the influence factor hierarchical structure model, and a task scheduling set is generated according to the combination weight corresponding to each recognition task, so that the scheduling sequence corresponding to the recognition tasks is determined, the problem that the task scheduling efficiency of the collected image calculation task is low, the recognition tasks with large combination weights can be scheduled preferentially, the problem that the complex task scheduling time is long is solved, and the efficiency of medical diagnosis can be improved.

Example two

Fig. 2 is a block diagram of a medical image processing apparatus based on artificial intelligence according to a second embodiment of the present application.

In some embodiments, the artificial intelligence based medical image processing apparatus 20 may include a plurality of functional modules composed of computer program segments. The computer program of each program segment in the artificial intelligence based medical image processing apparatus 20 can be stored in the memory of the electronic device and executed by at least one processor to perform the functions of artificial intelligence based medical image processing (detailed in fig. 1).

In this embodiment, the artificial intelligence based medical image processing apparatus 20 may be divided into a plurality of functional modules according to the functions performed by the apparatus. The functional module may include: the system comprises a task acquisition module 201, a factor determination module 202, a model construction module 203, a weight calculation module 204, a scheduling module 205, an image acquisition module 206 and an image processing module 207. A module as referred to herein is a series of computer program segments capable of being executed by at least one processor and capable of performing a fixed function and is stored in a memory. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.

The task acquiring module 201 is configured to, in response to a processing instruction for a plurality of medical images of a target patient, acquire an identification task corresponding to each of the medical images.

The medical image may include medical image information transmitted by a hospital imaging device, including, but not limited to, a Digital Radiography (DR) image, a Computed Tomography (CT) image, a Magnetic Resonance (MR) image, a Radiographic Testing (RT) image, an Electrocardiogram (ECG), an upper gastrointestinal contrast image, an ultrasound image, a pathology image, and the like.

Different medical images correspond to different recognition tasks. For example, electrocardiograms are used to record the electrical activity of the normal heart of the human body, for diagnosing diseases in the heart; the upper gastrointestinal imaging refers to imaging of the upper part of the duodenum to diagnose lesions in the gastrointestinal tract.

In an alternative embodiment, before responding to the processing instructions for the plurality of medical images of the target patient, the task acquisition module 201 is further configured to:

judging whether the medical image meets the preset identification quality requirement or not;

if the medical image meets the preset identification quality requirement, determining a data identifier corresponding to the medical image;

determining a classification space corresponding to the data identification in a preset storage space;

storing the medical image to the classification space, and using the data identification as an index of the medical image in the classification space.

The method comprises the steps of presetting identification quality requirements of medical images, wherein the identification quality requirements can comprise image definition requirements, picture integrity requirements, video definition requirements and the like.

And carrying out space division in a preset storage space, and setting classification spaces corresponding to different types of medical images. Different classification spaces correspond to different data identifications. And generating an index corresponding to the medical image according to the data identification. For example, the data identifier and the address corresponding to the classification space may be used as an index of the medical image in the classification space.

Whether the medical images meet the identification quality requirement or not is judged, the medical images meeting the identification quality requirement are stored, validity of the medical images stored in the preset storage space can be guaranteed, and therefore the medical images stored in the preset storage space can be processed conveniently. Meanwhile, the medical images are classified and stored based on the data identification, when the medical images need to be acquired, the medical images can be acquired only from the classification space, and compared with the whole storage space, the classification space is small in storage capacity, so that the target medical images can be acquired quickly, and the acquisition efficiency of the target medical images is improved.

In an optional embodiment, the task obtaining module 201 is further configured to:

if the medical image does not meet the preset identification quality requirement, determining the importance level of the medical image;

and if the importance level of the medical image is greater than or equal to an importance level threshold, generating a data acquisition request corresponding to the medical image, wherein the data acquisition request is used for acquiring target data.

The data acquisition request is used for acquiring target data corresponding to the medical image which does not meet the preset identification quality requirement. Illustratively, after target data is acquired according to the data acquisition request, the medical image which does not meet the preset identification quality requirement is deleted.

And if the importance level of the medical image is smaller than an importance level threshold, deleting the medical image. For example, after the medical image is deleted, a relevant deletion record may be generated.

By generating the data acquisition request for the unqualified medical image with high importance level, the condition that the required medical image does not exist when the medical image is subsequently calculated can be avoided, and the efficiency of the medical image calculation is improved.

And the factor determining module 202 is configured to determine an influence factor of each identification task according to task information corresponding to the identification task.

For example, the task information may include a medical image category to be identified, an identification task type, and an identification task execution frequency, and the influence factor of each identification task is determined according to the task information. Different medical images need to be analyzed by different identification tasks, so that diagnosis results corresponding to the identification tasks are obtained according to analysis results. The more medical images the recognition task corresponds to, the more image factors the recognition task corresponds to.

And the model construction module 203 is configured to determine a hierarchical relationship corresponding to the influence factor according to the influence degree of the influence factor, and construct an influence factor hierarchical structure model according to the hierarchical relationship.

And determining the hierarchical relationship corresponding to the influence factors according to the influence hierarchy corresponding to the influence factors, wherein the hierarchical relationship corresponding to the influence factors is used for expressing different influence degrees of the influence factors.

The influence degree and the influence levels are in positive correlation, the larger the influence degree of the influence factors is, the higher the influence level corresponding to the influence factors is, the smaller the influence degree of the influence factors is, the lower the influence level corresponding to the influence factors is, and the level relation corresponding to the influence factors is determined according to the influence level corresponding to each influence factor. And constructing an influence factor hierarchical structure model according to the hierarchical relationship corresponding to the influence factors, wherein, for example, the influence hierarchy corresponding to the influence factors stored in each level in the influence factor hierarchical structure model is the same.

Illustratively, the mapping relationship between the influence factors and the influence degrees can be preset, a factor influence table is generated, and the influence degrees corresponding to the influence factors can be determined by querying the factor influence table, so as to determine the hierarchical relationship corresponding to the influence factors.

For example, the hierarchical relationship corresponding to the influence factor may be determined based on an Analytic Hierarchy Process (AHP) and the influence degree of the influence factor. The AHP analytic hierarchy process is a systematic and hierarchical analytic method combining qualitative analysis and quantitative analysis. By using the AHP analytic hierarchy process, the thinking process of the decision can be mathematized by using less quantitative information on the basis of deeply researching the essence, the influence factors, the internal relation and the like of the complex decision problem, so that the efficiency of determining the hierarchical relation corresponding to the influence factors is improved.

The influence factor hierarchical structure model comprises influence factors corresponding to each recognition task and can be divided into a plurality of hierarchies, and each hierarchy comprises one or more influence factors.

And the weight calculation module 204 is configured to obtain a preset judgment matrix, and calculate a combination weight corresponding to the recognition task based on the judgment matrix and the influence factor hierarchical structure model.

In an optional implementation manner, the priority of the obtained influence factors can be analyzed and evaluated based on a fuzzy comprehensive evaluation method to obtain a factor set module; and meanwhile, determining a weight matrix based on medical experience, and finally obtaining a judgment matrix based on the factor set module and the weight matrix.

Illustratively, according to the level of a plurality of influence factors corresponding to the identification task in the influence factor hierarchical structure model, the weight corresponding to each influence factor is determined, and the weights corresponding to the plurality of influence factors are substituted into the judgment matrix for calculation to obtain the combined weight corresponding to the identification task. For example, the hierarchy of the influencer in the hierarchical model of influencers can be determined as the weight corresponding to the influencer.

And the scheduling arrangement module 205 is configured to determine a scheduling order corresponding to each identified task according to the combined weight corresponding to the identified task, and generate a task scheduling set of a plurality of identified tasks according to the scheduling order.

Illustratively, the multiple recognition tasks are ordered according to the magnitude of the combination weights corresponding to the multiple recognition tasks, so as to obtain task scheduling sets corresponding to the multiple recognition tasks. For example, the sorting may be done in order from small to large. An order of executing the plurality of identified tasks may be determined according to a task schedule set.

In an optional embodiment, the scheduling module 205 determines a scheduling order corresponding to each identified task according to the combined weight corresponding to the identified task, and generates a task scheduling set of a plurality of identified tasks according to the scheduling order, including:

based on the combination weight corresponding to each recognition task, carrying out weighted calculation on the influence factors in each recognition task by using a fuzzy comprehensive evaluation method to obtain the priority corresponding to each recognition task;

and generating a task scheduling set corresponding to each identification task according to the priority corresponding to each identification task.

For example, based on the combination weight corresponding to each recognition task, the influence factors in each recognition task are weighted and calculated by using a fuzzy comprehensive evaluation method, and the priority corresponding to each recognition task is determined according to the value corresponding to the weighted influence factors. For example, the weighted values of each influence factor in the identification task are added to obtain a target influence value, and the priority corresponding to each identification task is determined based on the target influence value. The larger the target influence value corresponding to the identification task is, the lower the priority corresponding to the identification task is.

By using the fuzzy comprehensive evaluation method to carry out weighting calculation on the influence factors, scientific, reasonable and practical quantitative evaluation can be carried out on the data with the fuzziness of the stored information, so that the priority corresponding to each recognition task is accurately determined, the accuracy of a task scheduling set generated based on the priority corresponding to the recognition task is higher, and the subsequent task scheduling is facilitated.

An image obtaining module 206, configured to sequentially obtain, in a preset storage space, a target medical image corresponding to each recognition task in the task scheduling set.

And sequentially acquiring the target medical image corresponding to each recognition task in a preset storage space according to the sequence of the recognition tasks in the task scheduling set. For example, there are an identification task a and an identification task B, and the order of the identification task a in the task scheduling set is before the identification task B, and first a target medical image corresponding to the identification task a is acquired in a preset storage space, and then a target medical image corresponding to the identification task B is acquired in the preset storage space.

And the image processing module 207 is configured to invoke AI edge computing equipment to process the sequentially acquired target medical images.

And calling AI edge computing equipment to identify the sequentially acquired target medical images, and obtaining a diagnosis result corresponding to each identification task based on the identification result for identifying the target medical images. For example, one recognition task includes a plurality of target medical images, and based on recognition results of the plurality of target medical images, diagnosis results corresponding to the recognition task are obtained.

In an optional embodiment, the image processing module 207 invoking the AI edge computing device to process the sequentially acquired target medical images includes:

acquiring image type information corresponding to the image type file in the target medical image;

extracting the characteristic value of the image information by using the trained convolutional neural network model to obtain an image characteristic set;

extracting a non-image file in the target medical image by using a preset feature extraction algorithm to obtain a non-image feature set;

taking the non-image feature set as an input of an XGboost algorithm to perform regression analysis to obtain a first result;

taking the image feature set and the non-image feature set as the input of the XGboost algorithm together to perform regression analysis to obtain a second result;

and obtaining a processing result of the target medical image according to the first result and the second result.

The non-image class files may include video class files.

The lifting tree model XGboost (extreme Gradient boosting) is a model integrating a plurality of tree models, and by adding a regular term in a cost function, the complexity of the model is controlled, over-fitting is prevented, parallel processing can be realized, and the processing speed of files is increased.

For example, the first result and the second result may be summarized to obtain a processing result of the target medical image.

By the technical scheme, the common processing of image data and non-image data can be realized, so that the coverage of the analyzed medical image is wide, and the efficiency of medical diagnosis is improved; meanwhile, the XGboost algorithm is utilized, not only is the first-order derivative used, but also the second-order derivative is used, the loss is more accurate, the loss can be customized, overfitting can be reduced, and the calculation amount of the AI edge calculation equipment is reduced.

In an optional embodiment, the image processing module 207 acquires image class information corresponding to an image class file in the target medical image, and includes:

performing feature extraction on the image files in the target medical image based on an OCR algorithm to obtain pixel information corresponding to the image files;

generating a pixel matrix according to the color codes of different positions in the pixel information;

and obtaining image class information corresponding to the image class file in the target medical image based on the pixel matrix.

And extracting pixel characteristics in the image file by Optical Character Recognition (OCR) to obtain pixel information. And generating a pixel matrix according to the color codes of different positions in the pixel information, such as generating the pixel matrix according to the hexadecimal color code. The pixel matrix can effectively retain the image information in the image class file. For example, the pixel matrix may be determined as image class information corresponding to an image class file in the target medical image.

By using an OCR algorithm, the features in the image files can be effectively extracted, the image feature set is obtained based on the color codes in the pixel information, more features in the image can be reserved, and therefore the identification accuracy can be improved.

In an optional embodiment, the image processing module 207, using a preset feature extraction algorithm to extract a non-image file in the target medical image to obtain a non-image feature set, includes:

extracting images of non-image files in the target medical image to obtain a plurality of target images;

and performing feature extraction on the plurality of target images based on an OCR algorithm to obtain the non-image feature set.

The non-image files comprise video files, and image extraction is carried out on the video files to obtain a plurality of target images. For example, image extraction may be performed on a video file at regular time intervals, such as 0.01S, resulting in a plurality of target images.

And performing feature extraction on the plurality of target images by using an OCR algorithm to obtain a non-image data feature set. For example, feature extraction is performed on the multiple target images based on an OCR algorithm to obtain pixel information corresponding to the multiple target images; generating a pixel matrix according to the color codes of different positions in the pixel information; and obtaining a non-image class characteristic set corresponding to the non-image class file in the target medical image based on the pixel matrix.

The medical image processing device based on artificial intelligence analyzes image calculation tasks by using an analytic hierarchy process to obtain combined weights corresponding to the image calculation tasks, determines a task scheduling set based on the combined weights, and performs task scheduling according to the obtained ordered task scheduling set to obtain target image data corresponding to each image calculation task. The method is more comprehensive than the task scheduling consideration only according to the task type or the task execution frequency, is simple to operate and is beneficial to implementation, meanwhile, an influence factor hierarchical structure model is constructed according to the influence degree corresponding to the influence factor, the combination weight corresponding to each recognition task is calculated based on the influence factor hierarchical structure model, and a task scheduling set is generated according to the combination weight corresponding to each recognition task, so that the scheduling sequence corresponding to the recognition tasks is determined, the problem that the task scheduling efficiency of the collected image calculation task is low, the recognition tasks with large combination weights can be scheduled preferentially, the problem that the complex task scheduling time is long is solved, and the efficiency of medical diagnosis can be improved.

EXAMPLE III

The present embodiment provides a computer-readable storage medium, which stores thereon a computer program, which when executed by a processor implements the steps in the above-mentioned artificial intelligence based medical image processing method embodiment, such as S11-S17 shown in fig. 1:

s11, responding to a processing instruction of a plurality of medical images of a target patient, and acquiring an identification task corresponding to each medical image;

s12, determining the influence factors of each recognition task according to the task information corresponding to the recognition task;

s13, determining the hierarchical relationship corresponding to the influence factors according to the influence degree of the influence factors, and constructing an influence factor hierarchical structure model according to the hierarchical relationship;

s14, acquiring a preset judgment matrix, and calculating the combination weight corresponding to the recognition task based on the judgment matrix and the influence factor hierarchical structure model;

s15, determining a scheduling order corresponding to each recognition task according to the combined weight corresponding to the recognition task, and generating a task scheduling set of a plurality of recognition tasks according to the scheduling order;

s16, sequentially acquiring a target medical image corresponding to each recognition task in the task scheduling set in a preset storage space;

and S17, calling AI edge computing equipment to process the sequentially acquired target medical images.

Alternatively, the computer program, when executed by the processor, implements the functions of the modules/units in the above-mentioned device embodiments, for example, the module 201 and 207 in fig. 2:

the task obtaining module 201 is configured to, in response to a processing instruction for a plurality of medical images of a target patient, obtain an identification task corresponding to each of the medical images;

the factor determining module 202 is configured to determine an influence factor of each identification task according to task information corresponding to the identification task;

the model building module 203 is configured to determine a hierarchical relationship corresponding to the influence factor according to the influence degree of the influence factor, and build an influence factor hierarchical structure model according to the hierarchical relationship;

the weight calculation module 204 is configured to obtain a preset judgment matrix, and calculate a combination weight corresponding to the recognition task based on the judgment matrix and the influence factor hierarchical structure model;

the scheduling arrangement module 205 is configured to determine a scheduling order corresponding to each identification task according to the combination weight corresponding to the identification task, and generate a task scheduling set of a plurality of identification tasks according to the scheduling order;

the image obtaining module 206 is configured to sequentially obtain, in a preset storage space, a target medical image corresponding to each recognition task in the task scheduling set;

the image processing module 207 is configured to invoke AI edge computing equipment to process the sequentially acquired target medical images.

Example four

Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present application. In the preferred embodiment of the present application, the electronic device 3 comprises a memory 31, at least one processor 32, at least one transceiver 33, and a communication bus 34.

It will be appreciated by those skilled in the art that the configuration of the electronic device shown in fig. 3 does not constitute a limitation of the embodiments of the present application, and may be a bus-type configuration or a star-type configuration, and that the electronic device 3 may include more or less hardware or software than those shown, or a different arrangement of components.

In some embodiments, the electronic device 3 is a device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware thereof includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The electronic device 3 may also include a client device, which includes, but is not limited to, any electronic product that can interact with a client through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, and the like.

It should be noted that the electronic device 3 is only an example, and other existing or future electronic products, such as those that can be adapted to the present application, should also be included in the scope of protection of the present application, and are included by reference.

In some embodiments, the memory 31 has stored therein a computer program which, when executed by the at least one processor 32, implements all or part of the steps of the artificial intelligence based medical image processing method as described. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only disk (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

In some embodiments, the at least one processor 32 is a Control Unit (Control Unit) of the electronic device 3, connects various components of the electronic device 3 by various interfaces and lines, and executes various functions and processes data of the electronic device 3 by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31. For example, the at least one processor 32, when executing the computer program stored in the memory, implements all or part of the steps of the artificial intelligence based medical image processing method described in the embodiments of the present application; or realize all or part of the functions of the medical image processing device based on artificial intelligence. The at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips.

In some embodiments, the at least one communication bus 34 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.

Although not shown, the electronic device 3 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, an electronic device, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present application.

In the several 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 modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present application 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 integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the specification may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present application and not for limiting, and although the present application is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present application without departing from the spirit and scope of the technical solutions of the present application.