阅读说明：本技术 一种基于图像处理的智能问诊方法、系统及存储介质 (Intelligent inquiry method, system and storage medium based on image processing ) 是由 李耀明 吴宗盛 彭威 于 2020-05-25 设计创作，主要内容包括：本发明公开了一种基于图像处理的智能问诊方法、系统及存储介质,方法包括：获取个人医疗图像、个人历史信息库、标准文本结构、程度评估模型及医疗信息数据库；对个人医疗图像进行OCR识别生成第一医疗文本；对第一医疗文本进行结构化处理及数据映射生成第二医疗文本；对第二医疗文本进行区域划分得到区域划分图像；对个人医疗图像进行疑似关联得到关联图像；显示区域划分图像和关联图像。本发明通过对个人医疗图像的一系列处理,实现了对于个人医疗图像中文本的区域划分,同时可以与个人历史信息进行关联,从而辅助医生快速识别有效信息,提高了医生在线问诊的工作效率。(The invention discloses an intelligent inquiry method, a system and a storage medium based on image processing, wherein the method comprises the following steps: acquiring a personal medical image, a personal historical information base, a standard text structure, a degree evaluation model and a medical information database; performing OCR recognition on the personal medical image to generate a first medical text; performing structural processing and data mapping on the first medical text to generate a second medical text; carrying out regional division on the second medical text to obtain a regional division image; performing suspected association on the personal medical image to obtain an associated image; the display area divides the image and the associated image. According to the invention, through a series of processing on the personal medical image, the region division of the text in the personal medical image is realized, and meanwhile, the text can be associated with personal historical information, so that a doctor is assisted to quickly identify effective information, and the working efficiency of on-line inquiry of the doctor is improved.)

1. An intelligent inquiry method based on image processing is characterized by comprising the following steps:

after the image is uploaded through the intelligent terminal, acquiring a personal medical image, a personal historical information base, a standard text structure, a degree evaluation model and a medical information database;

performing OCR recognition on the personal medical image to generate a first medical text;

performing structural processing and data mapping on the first medical text by using the medical information database and the standard text structure to generate a second medical text;

performing regional division on the second medical text by using the medical information database and the degree evaluation model to obtain a regional division image;

performing suspected correlation on the personal medical image by using the personal historical information base to obtain a correlated image;

and displaying the area division image and the associated image on the intelligent terminal.

2. The intelligent image-processing-based interrogation method of claim 1, wherein said step of performing OCR recognition on said personal medical image to generate a first medical text comprises:

performing OCR recognition on the personal medical image to obtain an initial text;

traversing the initial text to obtain basic information of the text; the basic information comprises word size information, text information corresponding to different word sizes and spacing information;

and merging the initial texts according to the basic information to generate the first medical text.

3. The method of claim 2, wherein the step of combining the initial text based on the basic information to generate the first medical text comprises:

acquiring the distance information; the distance information comprises row distance information and column distance information;

performing line merging on the initial text according to the line spacing information to obtain a first text;

column combination is carried out on the first text according to the column spacing information to obtain a second text;

and generating the first medical text according to the second text.

4. The personal medical information processing method according to claim 3, wherein the execution direction of the row merge is from bottom to top; the column merge is performed from right to left.

5. The intelligent image-processing-based inquiry method according to claim 1, wherein the step of generating a second medical text by performing a structuring process and a data mapping process on the first medical text by using the medical information database and the standard text structure comprises:

identifying a separator in the first medical text using the medical information database;

segmenting the first medical text according to the separators to obtain segmented texts;

performing data mapping on the segmented text by using the standard text structure to obtain personal medical data;

and mining the associated information of the personal medical data by using the medical information database to generate the second medical text.

6. The intelligent image-processing-based inquiry method according to claim 1, wherein said step of performing region segmentation on said second medical text using said medical information database and said degree evaluation model to obtain a region segmentation image comprises:

inputting the second medical text into the degree evaluation model;

the degree evaluation model acquires medical information provided in the medical information database to evaluate the second medical text to obtain an evaluation score of a text region in the second medical text;

and respectively carrying out level division on the text regions in the second medical text according to the evaluation scores, and marking by using different background colors to obtain the region division images.

7. The image-processing-based intelligent inquiry method of claim 6, wherein the levels of the text region comprise four levels of red, yellow, green and blue.

8. The intelligent image-processing-based interrogation method of claim 1, wherein the step of performing a suspected correlation on the personal medical image using the personal history information base to obtain a correlated image comprises:

acquiring a personal historical medical image from the personal historical information base;

performing similarity matching on the personal historical medical image and the personal medical image;

and obtaining the associated image according to the matching result and listing the image in a queue to be checked.

9. An intelligent inquiry system based on image processing is characterized by comprising the following modules:

the resource acquisition module is used for acquiring a personal medical image, a personal historical information base, a standard text structure, a degree evaluation model and a medical information database after the image is uploaded through the intelligent terminal;

the first medical text generation module is used for performing OCR recognition on the personal medical image to generate a first medical text;

the second medical text generation module is used for performing structural processing and data mapping on the first medical text by using the medical information database and the standard text structure to generate a second medical text;

the region division module is used for carrying out region division on the second medical text by utilizing the medical information database and the degree evaluation model to obtain a region division image;

the suspected correlation module is used for performing suspected correlation on the personal medical image by utilizing the personal historical information base to obtain a correlated image;

and the interactive display module is used for displaying the area division image and the associated image on the intelligent terminal.

10. A computer-readable storage medium, in which a program executable by a processor is stored, characterized in that the program executable by the processor is adapted to implement the method according to any one of claims 1-8 when executed by the processor.

Technical Field

The invention relates to the field of medical online inquiry, in particular to an intelligent inquiry method and system based on image processing and a storage medium.

Background

With the further development of society, people can enjoy better medical services while having rich lives; however, in view of the fact that most of high-quality medical resources in China are mostly concentrated in cities at present, patients are difficult to meet the requirements of themselves when seeking medical services, such as the sailing and the driving, the facing to the problems of the strange urban environment, the uncertainty of hospital systems and the like.

Therefore, remote inquiry through network becomes a new information path; when seeking medical help through a network approach, because of different culture levels of patients, the condition of an illness is difficult to express intuitively through typing or voice, the patients often need to use personal medical images as auxiliary data, the images can clearly display the previous information, but the text types displayed by the images are too many, and the text formats displayed by different hospitals are different, so that doctors are difficult to acquire effective information quickly, and the working efficiency of on-line inquiry of the doctors and the medical experience of the patients in the inquiry process are seriously influenced.

Disclosure of Invention

In order to solve at least one of the technical problems in the prior art, an object of the present invention is to provide an intelligent inquiry method, system and storage medium based on image processing.

According to a first aspect of the embodiments of the present invention, an intelligent inquiry method based on image processing includes the following steps:

after the image is uploaded through the intelligent terminal, acquiring a personal medical image, a personal historical information base, a standard text structure, a degree evaluation model and a medical information database;

performing OCR recognition on the personal medical image to generate a first medical text;

performing structural processing and data mapping on the first medical text by using the medical information database and the standard text structure to generate a second medical text;

performing regional division on the second medical text by using the medical information database and the degree evaluation model to obtain a regional division image;

performing suspected correlation on the personal medical image by using the personal historical information base to obtain a correlated image;

and displaying the area division image and the associated image on the intelligent terminal.

Further, the step of performing OCR recognition on the personal medical image to generate a first medical text includes:

performing OCR recognition on the personal medical image to obtain an initial text;

traversing the initial text to obtain basic information of the text; the basic information comprises word size information, text information corresponding to different word sizes and spacing information;

and merging the initial texts according to the basic information to generate the first medical text.

Further, the step of merging the initial texts according to the basic information to generate the first medical text includes:

acquiring the distance information; the distance information comprises row distance information and column distance information;

performing line merging on the initial text according to the line spacing information to obtain a first text;

column combination is carried out on the first text according to the column spacing information to obtain a second text;

and generating the first medical text according to the second text.

Further, the execution direction of the row merging is from bottom to top; the column merge is performed from right to left.

Further, the step of performing structuring processing and data mapping on the first medical text by using the medical information database and the standard text structure to generate a second medical text includes:

identifying a separator in the first medical text using the medical information database;

segmenting the first medical text according to the separators to obtain segmented texts;

performing data mapping on the segmented text by using the standard text structure to obtain personal medical data;

and mining the associated information of the personal medical data by using the medical information database to generate the second medical text.

Further, the step of performing regional division on the second medical text by using the medical information database and the degree evaluation model to obtain a regional division image includes:

inputting the second medical text into the degree evaluation model;

the degree evaluation model acquires medical information provided in the medical information database to evaluate the second medical text to obtain an evaluation score of a text region in the second medical text;

and respectively carrying out level division on the text regions in the second medical text according to the evaluation scores, and marking by using different background colors to obtain the region division images.

Further, the levels of the text area include four levels of red, yellow, green, and blue.

Further, the step of performing pseudo-correlation on the personal medical image by using the personal history information base to obtain a correlated image includes:

acquiring a personal historical medical image from the personal historical information base;

performing similarity matching on the personal historical medical image and the personal medical image;

and obtaining the associated image according to the matching result and listing the image in a queue to be checked.

According to a second aspect of the embodiments of the present invention, an intelligent inquiry system based on image processing comprises the following modules:

the resource acquisition module is used for acquiring a personal medical image, a personal historical information base, a standard text structure, a degree evaluation model and a medical information database after the image is uploaded through the intelligent terminal;

the first medical text generation module is used for performing OCR recognition on the personal medical image to generate a first medical text;

the second medical text generation module is used for performing structural processing and data mapping on the first medical text by using the medical information database and the standard text structure to generate a second medical text;

the region division module is used for carrying out region division on the second medical text by utilizing the medical information database and the degree evaluation model to obtain a region division image;

the suspected correlation module is used for performing suspected correlation on the personal medical image by utilizing the personal historical information base to obtain a correlated image;

and the interactive display module is used for displaying the area division image and the associated image on the intelligent terminal.

When executed by the at least one processor, cause the at least one processor to implement a method as described in the first aspect.

The invention has the beneficial effects that: through the processing of the personal medical image, the region division of the text in the personal medical image is realized, and meanwhile, the text can be associated with personal historical information, so that a doctor is assisted to quickly identify effective information, and the working efficiency of the doctor on-line inquiry is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description is made on the drawings of the embodiments of the present invention or the related technical solutions in the prior art, and it should be understood that the drawings in the following description are only for convenience and clarity of describing some embodiments in the technical solutions of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.

FIG. 1 is a diagram of method steps provided by an embodiment of the present invention;

FIG. 2 is a general flow chart provided by an embodiment of the present invention;

FIG. 3 is a diagram illustrating an interface display provided by an embodiment of the present invention;

fig. 4 is a block diagram of a module connection provided by an embodiment of the invention.

Detailed Description

The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention.

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.