A method and system for searching medical information based on big data

Abstract

The application provides a kind of method and system for searching medical information based on big data, and relates to the technical field of medical big data search.The method comprises collecting unit storage information of medical images, and performing text labeling to establish medical image browsing text guide information;extracting storage annotation feature information of different unit storage information, and combining with medical image browsing text guide information to form medical image browsing text guide data;obtain search feature information, and perform target analysis according to medical image browsing text guide data to determine the target storage object.The method can efficiently and more conveniently search and find massive medical images, which not only improves the efficiency but also greatly reduces the resources consumed in searching, finding and processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical big data search, in particular to a method and system for searching medical information based on big data. BACKGROUND

[0002] Medical image data is the most intuitive and effective reference information for diagnosis, treatment, learning and many other medical activities in the medical field. Medical image data includes static images, dynamic images, three-dimensional images and videos, etc. With the increasing amount of stored medical image data, efficient management to facilitate medical activities has become inevitable. Traditional management methods include classifying medical images, specifically creating different named image sets and then dividing related medical images into these image sets. The disadvantage is that it is time-consuming and laborious to classify, and if there are thousands of images in a sub-image set, it is still difficult to find the required medical image data. In particular, dynamic images, three-dimensional images and videos cannot be accurately found. Whether for static images or dynamic images, videos or three-dimensional images, searching and finding will process a large amount of data information, resulting in low search and find efficiency and resource consumption.

[0003] Therefore, a method and system for searching medical information based on big data are designed to efficiently and more conveniently search and find massive medical image data, which not only improves efficiency but also greatly reduces the resources consumed by search and find processing, which is a problem that needs to be solved. SUMMARY

[0004] The purpose of the present application is to provide a method for searching medical information based on big data. By establishing a text layer based on stored medical image data, a text layer information specifically used for searching and finding is formed, and independent feature information corresponding to each image is provided in the text layer. These feature information is extracted from the image and can fully reflect its characteristics. In this way, a text layer that is convenient to search and can be accurately positioned is established. On the one hand, by searching and finding the corresponding feature information in the text layer based on the information needed to be searched and found, compared with processing and searching the original image information with a huge amount of data, the efficiency of positioning the target image in the medical image is greatly improved. On the other hand, by positioning the search and find information range to the text layer instead of the original image data with a huge amount of information, the resources consumed for searching and finding are greatly saved. At the same time, since the feature information of the text layer is extracted based on the original image data, it can accurately reflect the characteristics of the album, thereby improving the accuracy of image search and find. In addition, the text layer corresponds to the original image. Even when directly browsing medical images, image recognition can be quickly and intuitively performed based on the feature information of the text layer.

[0005] The application also aims to provide a medical information system based on big data search, which provides a text layer corresponding to original medical images and establishes feature information of corresponding images based on the text layer to provide feature data information with small information quantity and high accuracy for search and finding of medical images, so as to efficiently and accurately realize target image search and finding and provide an important material basis for efficient and accurate search and finding of medical images and effectively ensure efficient search and finding of medical images.

[0006] In the first aspect, the application provides a method for searching medical information based on big data, which comprises collecting unit storage information of medical images, performing text labeling, establishing medical image browsing text guide information, extracting storage labeling feature information of different unit storage information, combining the medical image browsing text guide information to form medical image browsing text guide data, obtaining search feature information, and performing target analysis according to the medical image browsing text guide data to determine a target storage object.

[0007] In the application, the method forms text layer information used for search and finding by establishing a text layer based on stored medical image data, provides independent feature information corresponding to each image in the text layer, and extracts the feature information from the medical images to fully reflect the features, so that the text layer is established for convenient search and accurate positioning. On the one hand, compared with processing and searching the original image information with a large amount of data, the corresponding search and finding of the independent feature information in the text layer based on the information to be searched and found greatly improves the efficiency of positioning the target image in the album. On the other hand, the range of search and finding information is positioned to the text layer instead of the original image data with a large amount of information, which greatly saves the resources consumed for search and finding. At the same time, since the feature information of the text layer is extracted based on the original image data, the feature information can accurately reflect the features of the medical images, thereby improving the accuracy of the search and finding of the medical images. In addition, the text layer corresponds to the original image, so that even when the medical images are directly browsed, the feature information of the text layer can be used for quick image recognition.

[0008] As a possible implementation manner, the method for collecting unit storage information of medical images and performing text labeling to establish medical image browsing text guide information comprises: performing compression processing on each unit storage information and storing and arranging the unit storage information according to a time dimension sequence to form bottom layer storage information data; performing storage index number labeling on each unit storage information in the bottom layer storage information data based on the time dimension sequence to form bottom layer storage information index number data; and establishing medical image browsing text guide information corresponding to the bottom layer storage information data according to the bottom layer storage information index number data.

[0009] In the present application, in order to realize the efficient and fast search and find of the image in the medical image data, firstly, the image in the medical image needs to be established with the corresponding relationship of the text layer information used for searching and finding, and then the corresponding text information in the text layer can be ensured to correspond to the image. Considering that the storage index number of the image is marked based on the time dimension sequence without changing the traditional medical image storage mode. Of course, since the time dimension sequence is unique, different images will produce different numbers, effectively avoiding the repetition of the number. For the specific number form, it can be based on the number or letter in a period of time, or the date information can be added to the sequential numbering, as long as the uniqueness of the number is ensured.

[0010] As a possible implementation manner, the storage index number data of the bottom layer storage information is established, and the medical image browsing text guide information corresponding to the bottom layer storage information data is established, including: for each unit storage information in the bottom layer storage information data, a corresponding text layer is established to form a storage browsing text layer; the storage index number corresponding to each unit storage information in the bottom layer storage information data is given to the corresponding storage browsing text layer; all storage browsing text layers are arranged in time dimension sequence according to the corresponding storage index number to form the medical image browsing text guide information.

[0011] In the present application, after the reasonable storage index number setting of the original image, the text layer corresponding to the original image can be established, and the text layer is taken as the implementation object of subsequent image search and find, thereby improving the efficiency of search and find. Of course, to complete the correspondence from the text layer to the original image, it is necessary to establish a one-to-one correspondence between the text layer and the original image. Here, the storage index number of the original image is given to the text layer, on the one hand, the text layer has unique number information, and on the other hand, the one-to-one correspondence between the text layer and the original image is established.

[0012] As a possible implementation manner, the storage annotation feature information of different unit storage information is extracted, and the medical image browsing text guide data is formed by combining the medical image browsing text guide information, including: the storage annotation feature of different unit storage information in the bottom layer storage information data is extracted to form the corresponding storage annotation feature information; the storage annotation feature information corresponding to different unit storage information is processed based on the standard text content sequence of all storage annotation feature information in the range of the bottom layer storage information data to form the text annotation content information corresponding to each unit storage information; the text annotation content information corresponding to each unit storage information is input to the corresponding storage browsing text layer to form the storage unit browsing text guide information; the storage unit browsing text guide information corresponding to different storage browsing text layers under the medical image browsing text guide information is collected to form the medical image browsing text guide data.

[0013] In the present application, after the text layer associated with the original image and used for search is established, in order to ensure that the corresponding original image can be accurately searched in the text layer, the feature information of the original image needs to be extracted and given to the text layer. Of course, considering that the search has certain regularity, the accuracy of the search object can be fully guaranteed, so the feature information given to the text layer needs to be reasonably processed in terms of content sequence to provide a reasonable range limiting procedure for subsequent search. The text layer combined with the feature information of all original images can realize efficient search, greatly reducing the amount of search data information processing, and further saving resources.

[0014] As a possible implementation manner, the storage mark feature extraction of different unit storage information in the bottom layer storage information data is performed to form corresponding storage mark feature information, including: obtaining input mark information corresponding to the unit storage information, and performing input mark feature extraction to form input mark feature information; performing object-based information recognition analysis on the unit storage information to form a recognition descriptive word; and collecting all input mark feature information and recognition descriptive words corresponding to the unit storage information to form storage mark feature information.

[0015] In the present application, the feature information extraction of the original image considers two aspects of feature information sources. One is the input mark information accompanied by the image storage, which has an important guiding role, so that the feature information can be given to the text layer after feature analysis. The other is the feature information extracted based on the classification data mode of the medical image, which can be based on common medical image recognition modes such as face recognition, geographical position, content object, etc. Of course, after the recognition is completed, it needs to be converted into a descriptive word to facilitate the feature information given to the text layer to form a feature information convenient for search.

[0016] As a possible implementation manner, the input mark information corresponding to the unit storage information is obtained, and input mark feature extraction is performed to form input mark feature information, including: extracting the vocabulary in the input mark information to form input mark vocabulary; extracting the font size information in the input mark information to form input mark font size information; extracting the font color information in the input mark information to form input mark font color information; extracting the font position information in the input mark information to form input mark font position information; and collecting the input mark vocabulary, input mark font size information, input mark font color information, and input mark font position information to form input mark feature information.

[0017] In the present application, for the annotation information accompanied by input when the image is stored, when the feature information extraction is performed, the feature information formed by the text layer is considered, and the main extracted feature information includes vocabulary information, font size information, font color information and font position information. Among them, the font size information, the font color information and the font position information are the display of the text layer display mode, and are non-vocabulary type feature information for search and search, which is beneficial to efficient and fast image positioning search outside the non-vocabulary.

[0018] As a possible implementation, the storage annotation feature information corresponding to the storage information of different units is processed based on the standard text content sequence of all storage annotation feature information in the data range of the bottom layer storage information, and the text annotation content information corresponding to each unit storage information is formed, including: extracting the input annotation vocabulary and the recognized descriptive words corresponding to each unit storage information to form medical image annotation vocabulary big data; according to the medical image annotation vocabulary big data, the input annotation vocabulary and the recognized descriptive words corresponding to each unit storage information are arranged in sequence to form the text ordered annotation vocabulary feature information corresponding to each unit storage information; and the input annotation font size information, the input annotation font color information and the input annotation font position information corresponding to each unit storage information are extracted, and the text ordered annotation vocabulary feature information is combined to form the corresponding text annotation content information.

[0019] In the present application, reasonable sequence processing of the feature information obtained from the text layer is beneficial to the reasonable implementation of the range search process of the search and search. Of course, due to the different types of feature information, the vocabulary feature in the text layer is the most important feature information, so it is necessary to reasonably process the content sequence of the vocabulary. For other types of feature information, considering the information in the text layer, it basically belongs to relatively special feature information, which can realize fast positioning, so the sequence of different types of feature information can be performed after the vocabulary feature information.

[0020] As a possible implementation, according to the medical image annotation vocabulary big data, the input annotation vocabulary and the recognized descriptive words corresponding to each unit storage information are arranged in sequence to form the text ordered annotation vocabulary feature information corresponding to each unit storage information, including: the frequency of use of all words in the medical image annotation vocabulary big data is counted to form the annotation vocabulary frequency; all input annotation vocabulary and recognized descriptive words corresponding to each unit storage information are arranged in sequence according to the annotation vocabulary frequency corresponding to each word from large to small to form the text ordered annotation vocabulary feature information corresponding to the unit storage information.

[0021] In the present application, the order processing of the words can improve the rationality of the search finding range defining process. It can be understood that if the initial feature information is located to the image with few remaining bits, although the search finding can be completed quickly, it is not necessarily accurate. After all, when the words capable of locating a large number of images are combined with the words capable of locating a small number of images, if the small number of words are in the front, it will cause the omission of the images labeled by both kinds of words. Therefore, in order to ensure the rationality and accuracy of the search finding, it is necessary to perform the order labeling of the feature words under the text layer based on the usage frequency of the words.

[0022] As a possible implementation, the search feature information is acquired, and target analysis is performed according to the medical image browsing text guide data to determine a target storage object, including: extracting non-word feature information and word feature information according to the search feature information, and performing the following target analysis: according to the word feature information, and in combination with the annotation word frequency of each word in the medical image annotation word big data, the extracted words are stored in the order of the annotation word frequency from large to small, and the corresponding storage unit browsing text guide information in the browsing text layer is determined to determine a suspected storage browsing text layer; according to the non-word feature information, the corresponding storage unit browsing text guide information is determined in different suspected storage browsing text layers to determine the applicable storage browsing text layer, and the target object storage browsing text layer is marked; according to the storage index number corresponding to the target object storage browsing text layer, the corresponding unit storage information in the bottom layer storage information data is determined, and the target storage object is marked.

[0023] In the present application, after the text layer corresponding to the image is established, the range is limited based on the words when searching and finding, and the range is further limited and verified based on the non-word features, which greatly improves the accuracy of image search and finding.

[0024] In the second aspect, the present application provides a medical information system based on big data search, which is configured to: collect unit storage information of medical images, and perform text labeling to establish medical image browsing text guide information; extract storage annotation feature information of different unit storage information, and combine the medical image browsing text guide information to form medical image browsing text guide data; acquire search feature information, and perform target analysis according to the medical image browsing text guide data to determine a target storage object.

[0025] In the present application, the system is configured to provide a text layer corresponding to the medical image original image, and to establish feature information of the corresponding image based on the text layer to provide small and accurate feature data information for the search of the medical image, so as to achieve efficient and accurate search of the target image, and to provide an important material basis for efficient and accurate search of the medical image, thereby effectively ensuring efficient search of the medical image.

[0026] The method provided by the present application has the following advantages:

[0027] The method forms a text layer information used for search and finding by establishing a text layer based on the stored medical image, and provides independent feature information corresponding to each image in the text layer. The feature information is extracted from the medical image and can fully reflect the characteristics. Thus, the text layer is established for convenient search and accurate positioning. On the one hand, compared with processing and searching the original image information with a large amount of data, the corresponding search and finding of the feature information in the text layer based on the information to be searched and found greatly improves the efficiency of positioning the target image in the medical image. On the other hand, the range of search and finding information is positioned to the text layer instead of the original image data with a large amount of information, thereby greatly saving the resources consumed for search and finding. At the same time, since the feature information of the text layer is extracted based on the original image data, the characteristics of the medical image can be accurately reflected, thereby improving the accuracy of the search and finding of the medical image. In addition, the text layer corresponds to the original image. Even when the medical image is directly browsed, the image can be quickly identified according to the feature information of the text layer.

[0028] The system is configured to provide a text layer corresponding to the medical image original image, and to establish feature information of the corresponding image based on the text layer to provide small and accurate feature data information for the search of the medical image, so as to achieve efficient and accurate search of the target image, and to provide an important material basis for efficient and accurate search of the medical image, thereby effectively ensuring efficient search of the medical image. BRIEF DESCRIPTION OF DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0030] Figure 1A step diagram of a method for searching medical information based on big data is provided. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

[0032] Reference Figure 1 The embodiments of the present application provide a method for searching medical information based on big data. The method forms text layer information used for searching and finding by establishing the stored medical image data based on a text layer, and provides independent feature information corresponding to each image in the text layer. The feature information is extracted from the medical image and can fully reflect the features. Thus, the text layer is established for convenient searching and accurate positioning. On one hand, compared with searching and finding the original image information with a large amount of data, the corresponding search and finding of the feature information in the text layer based on the information to be searched and found greatly improves the efficiency of positioning the target image in the medical image. On the other hand, since the search and finding information is positioned in the text layer instead of the original image data with a large amount of information, the resources consumed for searching and finding are greatly saved. Meanwhile, since the feature information of the text layer is extracted based on the original image data, the feature information can accurately reflect the features of the medical image, thereby improving the accuracy of searching and finding the medical image. In addition, the text layer corresponds to the original image. Even when the medical image is directly browsed, the image can be quickly identified according to the feature information of the text layer more intuitively.

[0033] The method for searching medical information based on big data specifically includes the following steps:

[0034] S1: Collect unit storage information of medical images, and perform text labeling to establish medical image browsing text guide information.

[0035] The unit storage information of the medical images is collected, and text labeling is performed to establish medical image browsing text guide information, including: performing compression processing on each unit storage information, and storing and arranging the unit storage information according to a time dimension sequence to form bottom layer storage information data; performing storage index number labeling on each unit storage information in the bottom layer storage information data based on the time dimension sequence to form bottom layer storage information index number data; and establishing medical image browsing text guide information corresponding to the bottom layer storage information data according to the bottom layer storage information index number data.

[0036] To realize efficient and fast search and find of the image in the medical image data, firstly, the image in the medical image needs to be established corresponding relationship with the text layer information used for search and find, and then the corresponding text information can be corresponded to the image after the text layer is determined. And considering that the storage index number of the image is marked based on the time dimension sequence without changing the traditional medical image storage method. Of course, since the time dimension sequence is unique, different images will produce different numbers, effectively avoiding the case of repeated numbering. For the specific numbering form, it can be based on numbers or letters within a period of time, or date information can be added to the sequential numbering, as long as the uniqueness of the numbering is desirable.

[0037] According to the bottom layer storage information index number data, the medical image browsing text guide information corresponding to the bottom layer storage information data is established, including: for each unit storage information in the bottom layer storage information data, a corresponding text layer is established to form a storage browsing text layer; the storage index number corresponding to each unit storage information in the bottom layer storage information data is given to the corresponding storage browsing text layer; all storage browsing text layers are arranged in time dimension sequence according to the corresponding storage index number to form the medical image browsing text guide information.

[0038] After the original image is reasonably stored and indexed, the text layer corresponding to the original image can be established, and the text layer is taken as the implementation object of subsequent image search and find, thereby improving the efficiency of search and find. Of course, to complete the correspondence from the text layer to the original image, it is necessary to establish a one-to-one correspondence between the text layer and the original image. Here, the storage index number of the original image is given to the text layer, on the one hand, the text layer has unique numbering information, and on the other hand, the one-to-one correspondence between the text layer and the original image is established.

[0039] S2: Extract the storage annotation feature information of different unit storage information, and combine the medical image browsing text guide information to form the medical image browsing text guide data.

[0040] The storage mark feature information of different unit storage information is extracted, and the medical image browsing text guide information is combined to form medical image browsing text guide data, including: extracting the storage mark feature information of different unit storage information in the bottom layer storage information data, forming the corresponding storage mark feature information; processing the storage mark feature information corresponding to different unit storage information based on the standard text content sequence of all storage mark feature information in the bottom layer storage information data range, forming the text mark content information corresponding to each unit storage information; inputting the text mark content information corresponding to each unit storage information into the corresponding storage browsing text layer, forming the storage unit browsing text guide information; collecting the storage unit browsing text guide information corresponding to different storage browsing text layers under the medical image browsing text guide information, forming the medical image browsing text guide data.

[0041] After establishing the text layer associated with the original image and used for searching, in order to ensure that the corresponding original image can be accurately searched and found in the text layer, the feature information of the original image needs to be extracted and given to the text layer. Of course, considering that the search has a certain regularity, the accuracy of the search object can be fully guaranteed, so the feature information given to the text layer needs to be reasonably processed in terms of content sequence to provide reasonable range limitation program for subsequent search. The text layer combined with the feature information of all original images can realize efficient search, greatly reducing the amount of search data information processing, and further saving resources.

[0042] The storage mark feature information of different unit storage information in the bottom layer storage information data is extracted, forming the corresponding storage mark feature information, including: obtaining the input mark information corresponding to the unit storage information, and extracting the input mark feature to form the input mark feature information; performing object-based information recognition analysis on the unit storage information to form the recognition descriptive words; collecting all input mark feature information and recognition descriptive words corresponding to the unit storage information to form the storage mark feature information.

[0043] The feature information extraction of the original image considers two aspects of feature information sources. One is the input mark information during image storage, which has an important guiding role, so the feature information can be extracted and given to the text layer after feature analysis. The other is the feature information extracted based on the classification data of medical images. Here, the extraction of recognition feature information can be based on common medical image recognition methods, such as face recognition, geographic location, content object recognition, etc. Of course, after recognition, it needs to be converted into descriptive words to facilitate the assignment of feature information to the text layer to form convenient search feature information.

[0044] The input label information corresponding to the unit storage information is acquired, and input label feature extraction is performed to form input label feature information, including: extracting the vocabulary in the input label information to form input label vocabulary; extracting the font size information in the input label information to form input label font size information; extracting the font color information in the input label information to form input label font color information; extracting the font position information in the input label information to form input label font position information; and collecting the input label vocabulary, input label font size information, input label font color information, and input label font position information to form input label feature information.

[0045] For the label information accompanied by input when the image is stored, when performing feature information extraction, the characteristics of the feature information formed by the text layer are considered, and the main extracted feature information includes vocabulary information, font size information, font color information, and font position information. Among them, the font size information, font color information, and font position information are the display of the text layer display mode, and are non-vocabulary feature information for search and finding, which is beneficial to efficient and fast image positioning and finding outside the non-vocabulary.

[0046] The storage label feature information corresponding to the different unit storage information is processed based on the standard text content sequence of all storage label feature information in the data range of the bottom layer storage information, to form the text label content information corresponding to each unit storage information, including: extracting the input label vocabulary and the recognized descriptive words corresponding to each unit storage information to form medical image label vocabulary big data; according to the medical image label vocabulary big data, the input label vocabulary and the recognized descriptive words corresponding to each unit storage information are arranged in sequence to form the text ordered label vocabulary feature information corresponding to each unit storage information; and the input label font size information, the input label font color information, and the input label font position information corresponding to each unit storage information are extracted, and combined with the text ordered label vocabulary feature information to form the corresponding text label content information.

[0047] Reasonable sequence processing of the feature information obtained from the text layer is beneficial to the reasonable implementation of the range search process of search and finding. Of course, due to the different types of feature information, the vocabulary feature in the text layer is the most important feature information, so it is necessary to perform reasonable content sequence processing on the vocabulary. For other types of feature information, considering the information in the text layer, it basically belongs to relatively special feature information, which can realize fast positioning, so the sequence of different types of feature information can be performed after the vocabulary feature information.

[0048] According to the medical image annotation vocabulary big data, the input annotation vocabulary and the recognized descriptive words corresponding to each unit storage information are sequentially arranged to form the text ordered annotation vocabulary feature information corresponding to each unit storage information, including: counting the usage frequency of all vocabularies in the medical image annotation vocabulary big data to form the annotation vocabulary frequency; according to the annotation vocabulary frequency corresponding to each vocabulary, the all input annotation vocabularies and the recognized descriptive words corresponding to each unit storage information are sequentially arranged in descending order to form the text ordered annotation vocabulary feature information corresponding to the unit storage information.

[0049] The sequential processing of the vocabulary can improve the rationality of the search and find range definition process. It can be understood that if the initial feature information is located to the image with few remaining bits, although the search and find can be completed quickly, it may not be accurate. After all, when the vocabulary that can locate a large number of images and the vocabulary that can locate a small number of images are combined, if the small number of vocabularies are in front, it will cause the omission of some images that contain both types of vocabularies. Therefore, in order to ensure the rationality and accuracy of the search and find, it may be necessary to sequentially mark the feature vocabulary at the text layer based on the usage frequency of the vocabulary.

[0050] S3: Obtain search feature information, and perform target analysis according to the medical image browsing text guide data to determine a target storage object.

[0051] Obtaining search feature information and performing target analysis according to the medical image browsing text guide data to determine a target storage object, including: extracting non-vocabulary feature information and vocabulary feature information according to the search feature information, and performing the following target analysis: according to the vocabulary feature information, and combining the annotation vocabulary frequency of each vocabulary in the medical image annotation vocabulary big data, the extracted vocabulary is sequentially stored in the corresponding storage unit browsing text guide information in the browsing text layer according to the annotation vocabulary frequency from large to small, to determine a suspected storage browsing text layer; according to the non-vocabulary feature information, the corresponding storage unit browsing text guide information is determined in different suspected storage browsing text layers, to determine the applicable storage browsing text layer, and mark it as the target object storage browsing text layer; according to the storage index number corresponding to the target object storage browsing text layer, the corresponding unit storage information in the bottom layer storage information data is determined, and is marked as the target storage object.

[0052] After establishing the text layer corresponding to the image, when searching and finding, the range is first limited based on the vocabulary, then further limited based on the non-vocabulary features, and verified based on the more specific characteristics of the non-vocabulary features, which greatly improves the accuracy of image search and find.

[0053] The application also provides a medical information system based on big data search, which is configured to collect unit storage information of medical images, and perform text labeling to establish medical image browsing text guide information; extract storage labeling feature information of different unit storage information, and combine the medical image browsing text guide information to form medical image browsing text guide data; acquire search feature information, and perform target analysis according to the medical image browsing text guide data to determine a target storage object.

[0054] The system is configured to provide a text layer corresponding to the original image of the medical image, and establish feature information of the corresponding image based on the text layer to provide feature data information with small information quantity and high accuracy for the search and finding of the medical image, so that the device can efficiently and accurately realize target image search and finding, and provide an important material basis for efficient and accurate search and finding of the medical image, and effectively ensure efficient search and finding of the medical image.

[0055] In summary, the method for searching medical information based on big data provided by the embodiment of the application has the following advantages:

[0056] The method forms text layer information used for search and finding by establishing the stored medical image data based on the text layer, and provides independent feature information corresponding to each image in the text layer, which is extracted from the medical image and can fully reflect the features, so that the text layer for convenient search and accurate positioning is established. On the one hand, compared with processing and searching the original image information with a large amount of data, the corresponding search and finding of the feature information in the text layer based on the information to be searched and found greatly improves the efficiency of positioning the target image in the medical image. On the other hand, since the range of search and finding information is positioned to the text layer instead of the original image data with a large amount of information, the resources consumed for search and finding are greatly saved. At the same time, since the feature information of the text layer is extracted based on the original image data, the features of the album can be accurately reflected, so that the accuracy of the search and finding of the medical image is improved. In addition, the text layer corresponds to the original image, so even when directly browsing the album, the image can be quickly identified according to the feature information of the text layer.

[0057] The system is configured to provide a text layer corresponding to the original image of the medical image, and establish feature information of the corresponding image based on the text layer to provide feature data information with small information quantity and high accuracy for the search and finding of the medical image, so that the device can efficiently and accurately realize target image search and finding, and provide an important material basis for efficient and accurate search and finding of the medical image, and effectively ensure efficient search and finding of the medical image.

[0058] In the embodiments of the present application, the indication can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by certain information is referred to as to-be-indicated information. In the implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of various information agreed in advance (for example, specified by a protocol), thereby reducing the indication overhead to a certain extent. Meanwhile, a common part of various information can be identified and uniformly indicated, so as to reduce the indication overhead caused by separately indicating the same information.

[0059] In addition, the specific indication manner can also be various existing indication manners, for example, but not limited to, the above indication manners and various combinations thereof. The specific details of various indication manners can refer to the prior art, and will not be described herein. As known from the above, for example, when multiple information of the same type needs to be indicated, the indication manners of different information can be different. In the implementation process, the required indication manner can be selected according to the specific needs, and the selected indication manner is not limited in the embodiments of the present application. In this way, the indication manner involved in the embodiments of the present application should be understood as covering various methods that can enable the to-be-indicated party to know the to-be-indicated information.

[0060] It should be understood that the to-be-indicated information can be sent as a whole, or can be divided into multiple sub-information and sent separately, and the sending period and / or sending occasion of the sub-information can be the same or different. The specific sending method is not limited in the embodiments of the present application. The sending period and / or sending occasion of the sub-information can be pre-defined, for example, pre-defined according to a protocol, or configured by the sending end device by sending configuration information to the receiving end device.

[0061] The pre-definition or pre-configuration can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate related information in the device, and the specific implementation manner is not limited in the embodiments of the present application. The saving can mean saving in one or more memories. The one or more memories can be separately set, or integrated in the encoder or decoder, processor or communication device. The one or more memories can be partially separately set and partially integrated in the decoder, processor or communication device. The type of the memory can be any form of storage medium, and the embodiments of the present application do not limit this.

[0062] The "protocol" referred to in the embodiments of the present application can refer to a protocol family in the communication field, a standard protocol similar to the protocol family frame structure, or a related protocol applied to a future communication system, and the embodiments of the present application do not make specific limitations thereon.

[0063] In the embodiments of the present application, "when", "in the case of", "if", and the like all refer to the device making corresponding processing under certain objective conditions, and are not limited to time, and do not require the device to have a judgment action when implemented, nor does it mean that there are other limitations.

[0064] In the description of the embodiments of the present application, unless otherwise specified, " / " represents that the objects before and after the " / " are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the embodiments of the present application is only a description of the association relationship of the associated objects, and represents that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or the like refers to any combination of these items, including any combination of single item or multiple items. For example, at least one of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second", and the like are used to distinguish the same items or similar items with basically the same function and role. Those skilled in the art can understand that "first", "second", and the like do not limit the quantity and execution order, and "first", "second", and the like do not necessarily mean different. At the same time, in the embodiments of the present application, "exemplary" or "for example" is used to represent as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, "exemplary" or "for example" is used to present the relevant concept in a specific manner, and is convenient for understanding.

[0065] It should be appreciated that a processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor.

[0066] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DRRAM).

[0067] The above-described embodiments can be implemented in part or in whole through software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When loaded and executed by a computer, the computer instructions or computer programs can produce the processes or functions described above in accordance with the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, such as from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center through a wired (e.g., infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium or a collection of medium accessible by a computer or a data storage device such as a server, a data center, etc. containing one or more available medium. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0068] It should be understood that the term "and / or" in this document is merely used to describe an associated relationship between associated objects, and can represent three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the front and rear associated objects, but can also represent an "and / or" relationship. The specific meaning can be understood according to the context before and after.

[0069] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0070] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0071] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0072] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0073] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0074] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0075] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0076] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0077] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for searching medical information based on big data, characterized in that, The method comprises the following steps: Collecting unit storage information of medical images, and performing text labeling to establish medical image browsing text guide information; Extracting storage labeling feature information of different unit storage information, and combining the medical image browsing text guide information to form medical image browsing text guide data; Obtaining search feature information, and performing target analysis according to the medical image browsing text guide data to determine the target storage object; Wherein, collecting unit storage information of medical images, and performing text labeling to establish medical image browsing text guide information, comprising: Compressing each unit storage information, and storing and arranging according to the time dimension sequence to form bottom layer storage information data; Performing storage index number labeling on each unit storage information in the bottom layer storage information data based on the time dimension sequence to form bottom layer storage information index number data; According to the bottom layer storage information index number data, the medical image browsing text guide information corresponding to the bottom layer storage information data is established; According to the bottom layer storage information index number data, the medical image browsing text guide information corresponding to the bottom layer storage information data is established, comprising: Establishing a corresponding text layer for each unit storage information in the bottom layer storage information data to form a storage browsing text layer; Assigning the storage index number corresponding to each unit storage information in the bottom layer storage information data to the corresponding storage browsing text layer; Arranging all storage browsing text layers according to the corresponding storage index number in time dimension sequence to form the medical image browsing text guide information; Extracting storage labeling feature information of different unit storage information, and combining the medical image browsing text guide information to form medical image browsing text guide data, comprising: Extracting storage labeling features of different unit storage information in the bottom layer storage information data to form corresponding storage labeling feature information; Performing standard text content sequence processing on the storage labeling feature information corresponding to different unit storage information based on all storage labeling feature information within the range of the bottom layer storage information data to form text labeling content information corresponding to each unit storage information; Inputting the text labeling content information corresponding to each unit storage information into the corresponding storage browsing text layer to form storage unit browsing text guide information; Collecting the storage unit browsing text guide information corresponding to different storage browsing text layers under the medical image browsing text guide information to form the medical image browsing text guide data. 2.The method for searching medical information based on big data according to claim 1, wherein, The method comprises the following steps: Obtaining input labeling information corresponding to the unit storage information, and extracting input labeling features to form input labeling feature information; Performing object-based information recognition analysis on the unit storage information to form recognition descriptive words; Collect all the input annotation feature information and the recognition descriptive words corresponding to the unit storage information to form the storage annotation feature information. 3.The method for searching medical information based on big data according to claim 2, characterized in that, The input annotation information corresponding to the unit storage information is obtained, and input annotation features are extracted to form input annotation feature information, including: Extract the vocabulary in the input annotation information to form input annotation vocabulary; Extract the font size information in the input annotation information to form input annotation font size information; Extract the font color information in the input annotation information to form input annotation font color information; Extract the font position information in the input annotation information to form input annotation font position information; Collect the input annotation vocabulary, input annotation font size information, input annotation font color information, and input annotation font position information to form the input annotation feature information. 4.The method for searching medical information based on big data according to claim 3, characterized in that, The storage annotation feature information corresponding to different unit storage information is processed based on the standard text content sequence of all storage annotation feature information in the bottom layer storage information data range to form text annotation content information corresponding to each unit storage information, including: Extract the input annotation vocabulary and the recognition descriptive words corresponding to each unit storage information to form medical image annotation vocabulary big data; According to the medical image annotation vocabulary big data, the input annotation vocabulary and the recognition descriptive words corresponding to each unit storage information are arranged in annotation sequence to form text ordered annotation vocabulary feature information corresponding to each unit storage information; Extract the input annotation font size information, input annotation font color information, and input annotation font position information corresponding to each unit storage information, and combine the text ordered annotation vocabulary feature information to form the corresponding text annotation content information. 5.The method for searching medical information based on big data according to claim 4, characterized in that, According to the medical image annotation vocabulary big data, the input annotation vocabulary and the recognition descriptive words corresponding to each unit storage information are arranged in annotation sequence to form text ordered annotation vocabulary feature information corresponding to each unit storage information, including: Statistical analysis of the frequency of use of all words in the medical image annotation vocabulary big data to form annotation word frequency; According to the annotation word frequency corresponding to each word, all the input annotation vocabulary and the recognition descriptive words corresponding to each unit storage information are arranged in descending order to form the text ordered annotation vocabulary feature information corresponding to the unit storage information. 6.The method for searching medical information based on big data according to claim 5, wherein, The search feature information is obtained, and target analysis is performed according to the medical image browsing text guide data to determine the target storage object, including: According to the search feature information, non-vocabulary feature information and vocabulary feature information are extracted, and target analysis is performed in the following way: According to the word feature information, and in combination with the annotation word frequency of each word in the medical image annotation word big data, the extracted words are stored in the storage unit browsing text guide information in the storage browsing text layer in the order of the annotation word frequency from large to small, and a suspected storage browsing text layer is determined; According to the non-word feature information, the storage unit browsing text guide information is corresponded in different suspected storage browsing text layers, the applicable storage browsing text layer is determined, and the target object storage browsing text layer is marked; According to the storage index number corresponding to the target object storage browsing text layer, the corresponding unit storage information in the bottom layer storage information data is determined, and the target storage object is marked.

7. A system for searching medical information based on big data, adopting the method for searching medical information based on big data according to any one of claims 1-6. The medical information system based on big data search is configured to: Collect the unit storage information of medical images and perform text labeling to establish medical image browsing text guide information; Extract the storage annotation feature information of different unit storage information, and combine the medical image browsing text guide information to form medical image browsing text guide data; Obtain search feature information and perform target analysis according to the medical image browsing text guide data to determine the target storage object.

Images