Hint enhancement method, device, and equipment for medical application, and storage medium

Abstract

The application relates to computer technology and discloses a medical application prompt enhancement method and device, electronic equipment and a computer readable storage medium, wherein the method comprises the following steps: acquiring a real-time interface picture of a medical interface according to a prompt burying point; uniformly splitting the real-time interface picture into an interface block group according to regions; selecting interface blocks in the interface block group as target interface blocks one by one; extracting color distribution features and standard information entropy of the target interface blocks; screening a prompt interface block from the interface block group according to all the standard information entropy; taking a region position of the prompt interface block as a prompt region position; taking color distribution features of the prompt interface block as prompt color distribution features; and generating an application prompt by using the prompt color distribution features and the prompt region position. The application can be applied to the field of medical application prompts, can configure application prompt parameters in a medical application according to page elements, and can improve the prompt effect when the application is prompted.

Description

Technical Field

[0001] This invention relates to the fields of computer technology and healthcare, and more particularly to a method, apparatus, electronic device, and computer-readable storage medium for enhancing prompts in medical applications. Background Technology

[0002] With the development of internet healthcare, the models, types, and forms of medical applications are becoming increasingly diverse, and the information displayed in these applications is becoming more and more complex. In order to facilitate users to obtain the most important information in real time, it is necessary to use application prompts in medical applications to provide information to users.

[0003] Most existing medical applications use application prompts based on fixed configurations, that is, they are based on the system's default configuration or manual fixed configuration. For example, the default background of Android's Toast is a black background frame, the prompt text is white, and the default position is centered. In actual use, application prompts based on fixed configurations often result in insufficient contrast between the overall color and the page, and the pop-up position has a low presence, which may lead to poor prompting effect. Summary of the Invention

[0004] This invention provides a method, apparatus, and computer-readable storage medium for enhancing prompts in medical applications, with the main objective of solving the problem of poor prompting effectiveness when providing application prompts.

[0005] To achieve the above objectives, the present invention provides a method for enhancing prompts in medical applications, comprising:

[0006] Configure prompt tracking points in medical applications, and obtain real-time interface images of the medical interface based on the prompt tracking points;

[0007] The real-time interface image is evenly divided into interface tile groups according to the region, and the interface tile in the interface tile group is selected one by one as the target interface tile, and the color distribution features of the target interface tile are extracted.

[0008] The target interface tile is denoised and enhanced to obtain the target enhanced tile, and the tile information entropy of the target enhanced tile is calculated.

[0009] Text region detection is performed on the target augmented image patch to obtain the target text image patch. The standard information entropy of the target augmented image patch is calculated based on the target text image patch and the image patch information entropy.

[0010] Based on all standard information entropy, prompt interface tiles are selected from the interface tile group. The regional position of the prompt interface tile is used as the prompt region position, and the color distribution characteristics of the prompt interface tile are used as the prompt color distribution characteristics. Application prompts are generated using the prompt color distribution characteristics and the prompt region position.

[0011] Optionally, extracting the color distribution features of the target interface patch includes:

[0012] The target interface tile is converted to a different color space to obtain a target color tile.

[0013] The target color patch is divided into color intervals to obtain a color interval set;

[0014] The color interval set is counted by traversal to obtain a color pixel array;

[0015] The proportion of each color pixel in the color pixel array is calculated to obtain the color distribution characteristics.

[0016] Optionally, the step of denoising and enhancing the target interface patch to obtain the enhanced target patch includes:

[0017] The target interface patch is subjected to median filtering to obtain a filtered interface patch;

[0018] Perform a grayscale operation on the filtered interface block to obtain a grayscale interface block;

[0019] Edge detection and edge enhancement operations are performed sequentially on the grayscale interface patch to obtain an edge interface patch;

[0020] The edge interface patch is subjected to grayscale enhancement and contrast enhancement operations in sequence to obtain the enhanced interface patch.

[0021] Optionally, calculating the tile information entropy of the target enhanced tile includes:

[0022] Calculate the average pixel grayscale value of the target enhanced patch;

[0023] Each pixel in the target enhancement block is selected as the target pixel, and the gray value of the target pixel is used as the target pixel gray value.

[0024] The grayscale difference between the target pixel grayscale value and the average pixel grayscale value is calculated, and the average value of all grayscale differences is used as the tile information entropy of the target enhanced tile.

[0025] Optionally, the step of performing text region detection on the target enhanced map patch to obtain the target text map patch includes:

[0026] Perform multi-level convolution and multi-level pooling operations on the target enhancement patch to obtain target enhancement features;

[0027] The target enhancement features are divided into convolutional groups to obtain bounding box groups;

[0028] Extract the bounding box coordinate group and the confidence group sequentially from the bounding box group;

[0029] The bounding box group is filtered by confidence threshold based on the confidence level group to obtain the target bounding box group;

[0030] The target bounding box group is merged using the box coordinate group to obtain a target merged text box;

[0031] A target text box mask is generated based on the target merged text box, and the target enhanced image block is masked using the target text box mask to obtain the target text image block.

[0032] Optionally, calculating the standard information entropy of the target enhanced map tile based on the target text map tile and the tile information entropy includes:

[0033] Extract the area of ​​the text tile from the target text tile, and extract the area of ​​the enhanced tile from the target enhanced tile;

[0034] Divide the area of ​​the text tile by the area of ​​the enhanced tile to obtain the text information entropy;

[0035] Multiply the text information entropy by a preset text weight to obtain the standard text entropy, and multiply the tile information entropy by a preset tile weight to obtain the standard tile entropy.

[0036] The sum of the standard text entropy and the standard tile entropy is taken as the standard information entropy.

[0037] Optionally, generating application prompts using the prompt color distribution features and the prompt area location includes:

[0038] The system prompts are initialized, and the principal component colors are extracted from the color distribution characteristics of the prompts.

[0039] Complementary color calculation is performed on the principal component colors to obtain the cue complementary color;

[0040] The system prompt text color is configured according to the principal component color to obtain the text system prompt;

[0041] The background color of the text system prompt is configured according to the complementary color of the prompt to obtain the color system prompt;

[0042] The color scheme system prompts are configured according to the location of the prompt area to obtain application prompts.

[0043] To address the above problems, the present invention also provides a prompting enhancement device for medical applications, the device comprising:

[0044] The application tracking module is used to configure prompt tracking points in medical applications and obtain real-time interface images of the medical interface based on the prompt tracking points.

[0045] The color extraction module is used to evenly divide the real-time interface image into interface tile groups according to the region, select the interface tile in the interface tile group one by one as the target interface tile, and extract the color distribution features of the target interface tile.

[0046] The tile information calculation module is used to denoise and enhance the target interface tile to obtain the target enhanced tile, and calculate the tile information entropy of the target enhanced tile;

[0047] The standard information calculation module is used to perform text region detection on the target enhanced map block to obtain the target text map block, and calculate the standard information entropy of the target enhanced map block based on the target text map block and the map block information entropy.

[0048] The prompt configuration module is used to filter prompt interface tiles from the interface tile group based on all standard information entropy, use the regional position of the prompt interface tile as the prompt region position, use the color distribution characteristics of the prompt interface tile as the prompt color distribution characteristics, and generate application prompts using the prompt color distribution characteristics and the prompt region position.

[0049] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0050] At least one processor; and,

[0051] A memory communicatively connected to the at least one processor; wherein,

[0052] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the above-described prompting enhancement method for medical applications.

[0053] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the aforementioned method for enhancing prompts in medical applications.

[0054] This invention, through configuring prompt tracking points in medical applications, acquires real-time interface images of the medical interface based on these tracking points. This allows for the collection of application interface images before prompt generation, facilitating subsequent region and color analysis of the images and enabling the configuration of region and color for the application prompts. By uniformly dividing the real-time interface image into interface tile groups according to regions, and selecting individual interface tiles from each group as target interface tiles, the color distribution features of the target interface tiles are extracted. This allows for color feature extraction of different regions within the real-time interface image, facilitating the determination of the background color for the application prompts. Denoising and enhancing the target interface tiles results in enhanced target tiles, improving image clarity and detail, and increasing the accuracy of subsequent text region detection. By calculating the tile information entropy of the enhanced target tiles, the page complexity of the corresponding region can be determined.

[0055] By performing text region detection on the target enhanced image block, a target text image block is obtained, which can determine the region containing text within the target enhanced image block. By calculating the standard information entropy of the target enhanced image block based on the target text image block and the image block's information entropy, the overall information complexity of the region where the target enhanced image block is located can be calculated, thus facilitating the subsequent determination of the application prompt's location. By filtering the interface image block group based on all standard information entropies, a prompt interface image block is selected. The region location of the prompt interface image block is used as the prompt region location, and the color distribution characteristics of the prompt interface image block are used as the prompt color distribution characteristics. Using the prompt color distribution characteristics and the prompt region location, an application prompt is generated. This allows the application prompt to pop up in the part of the prompt interface with the least amount of information, thereby increasing the prominence of the application prompt. Furthermore, using the inverse color of the primary color of the corresponding position in the prompt interface as the background color of the application prompt enhances its visibility, thus improving the display effect of the application prompt. Therefore, the medical application prompt enhancement method, device, electronic device, and computer-readable storage medium proposed in this invention can solve the problem of poor prompt effects when providing application prompts. Attached Figure Description

[0056] Figure 1 A flowchart illustrating a method for enhancing prompts in a medical application according to an embodiment of the present invention;

[0057] Figure 2 This is a schematic diagram of a process for extracting color distribution features according to an embodiment of the present invention;

[0058] Figure 3 This is a schematic diagram of the process for calculating standard information entropy according to an embodiment of the present invention;

[0059] Figure 4A functional block diagram of a prompt enhancement device for medical applications provided in an embodiment of the present invention;

[0060] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the prompt enhancement method for the medical application according to an embodiment of the present invention.

[0061] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0062] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0063] This application provides a method for enhancing prompts in a medical application. The execution entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for enhancing prompts in a medical application can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cluster of cloud servers. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0064] Reference Figure 1 The diagram shown is a flowchart illustrating a method for enhancing prompts in a medical application according to an embodiment of the present invention. In this embodiment, the method for enhancing prompts in the medical application includes:

[0065] S1. Configure prompt tracking points in the medical application, and obtain real-time interface images of the medical interface based on the prompt tracking points.

[0066] In this embodiment of the invention, the medical application refers to a health management application, a medical information and query application, a health record or health monitoring application, or a health assessment and health diagnosis application.

[0067] In this embodiment of the invention, tracking events can be created in the prompt area of ​​the medical application using tracking tool libraries such as Firebase Analytics and TalkingData to obtain prompt tracking points. Obtaining a real-time interface image of the medical interface based on the prompt tracking points means that when the tracking event of the prompt tracking point is triggered, a screenshot method is called to take a screenshot of the current medical interface to obtain a real-time interface image. The real-time interface image can be an image of the family doctor interface or an image of the disease management page.

[0068] In this embodiment of the invention, by configuring prompt tracking points in a medical application and obtaining real-time interface images of the medical interface based on these tracking points, the interface images of the application can be collected in advance before the application prompts are generated. This facilitates subsequent region and color analysis of the interface images, and allows for the configuration of region and color for the application prompts.

[0069] S2. Divide the real-time interface image into interface tile groups evenly according to the region, select the interface tile in the interface tile group one by one as the target interface tile, and extract the color distribution features of the target interface tile.

[0070] In this embodiment of the invention, dividing the real-time interface image into interface tile groups according to the region means dividing the real-time interface image into multiple interface tiles in a top-to-bottom order, and then assembling all the interface tiles into an interface tile group.

[0071] In this embodiment of the invention, reference is made to Figure 2 As shown, extracting the color distribution features of the target interface patch includes:

[0072] S21. Perform color space conversion on the target interface block to obtain the target color block;

[0073] S22. Divide the target color patch into color intervals to obtain a color interval set;

[0074] S23. Perform pixel statistics on the color interval set by traversal to obtain a color pixel array;

[0075] S24. Calculate the proportion of each color pixel in the color pixel array to obtain the color distribution characteristics.

[0076] Specifically, the color space can be RGB color space or HSV color space. The target interface tile can be converted to color space using image processing libraries such as OpenCV or PIL to obtain the target color tile. Dividing the target color tile into color intervals to obtain a color interval set means dividing the color space into several discrete color intervals, such as dividing the RGB color space into 16x16x16 small cube units.

[0077] In detail, the step of performing pixel statistics on the color interval set by traversal to obtain a color pixel array refers to traversing each pixel of the target color patch, counting the total number of pixels contained in each color interval, and collecting the total number of pixels into a color pixel array.

[0078] Specifically, the step of calculating the proportion of each color pixel in the color pixel array to obtain the color distribution feature means calculating the ratio of each color pixel in the color pixel array to the total number of pixels in the target color patch, using the ratio as the distribution proportion of the corresponding color interval, and summing all the distribution proportions into the color distribution feature.

[0079] In this embodiment of the invention, by uniformly dividing the real-time interface image into interface tile groups according to the region, selecting each interface tile in the interface tile group as a target interface tile, and extracting the color distribution features of the target interface tile, color feature extraction can be performed on different regions in the real-time interface image, thereby facilitating the subsequent determination of the background color of the application prompt.

[0080] S3. Denoise and enhance the target interface tile to obtain the target enhanced tile, and calculate the tile information entropy of the target enhanced tile.

[0081] In this embodiment of the invention, in order to improve the accuracy of subsequent tile information entropy and text region detection, it is necessary to perform noise reduction and enhancement on the target interface tile.

[0082] In this embodiment of the invention, the step of denoising and enhancing the target interface patch to obtain an enhanced target interface patch includes: performing median filtering on the target interface patch to obtain a filtered interface patch; performing grayscale conversion on the filtered interface patch to obtain a grayscale interface patch; sequentially performing edge detection and edge enhancement operations on the grayscale interface patch to obtain an edge interface patch; and sequentially performing grayscale enhancement and contrast enhancement operations on the edge interface patch to obtain an enhanced interface patch.

[0083] In detail, the filtered interface patch can be grayscaled using the average value method or the weighted average value method to obtain a grayscale interface patch. The Sobel operator or the Canny operator can be used to perform edge detection on the grayscale interface patch, and the least squares method or the Random Sample Consensus (RANSAC) algorithm can be used to enhance the edge of the grayscale interface patch.

[0084] Specifically, grayscale enhancement can be performed on the edge interface patch using linear transformation or histogram equalization algorithm, and contrast enhancement can be performed on the edge interface patch using histogram stretching algorithm or adaptive contrast enhancement method.

[0085] In this embodiment of the invention, calculating the block information entropy of the target enhanced image block includes: calculating the average pixel grayscale value of the target enhanced image block; selecting pixels in the target enhanced image block one by one as target pixels, and using the grayscale value of the target pixels as the target pixel grayscale value; calculating the grayscale difference between the target pixel grayscale value and the average pixel grayscale value, and using the average value of all grayscale differences as the block information entropy of the target enhanced image block.

[0086] Specifically, the average pixel grayscale value refers to the average grayscale value of each pixel in the target enhancement patch. The higher the information entropy of the patch, the more information the target enhancement patch contains.

[0087] In this embodiment of the invention, by denoising and enhancing the target interface tile to obtain the target enhanced tile, the clarity and detail of the image can be improved, and the accuracy of subsequent text region detection can be improved. By calculating the tile information entropy of the target enhanced tile, the page complexity of the corresponding region can be determined.

[0088] S4. Perform text region detection on the target augmented image block to obtain a target text image block, and calculate the standard information entropy of the target augmented image block based on the target text image block and the image block information entropy.

[0089] In this embodiment of the invention, the proportion of text information in an image will visually affect the user's attention. In order to visually enhance the application prompts, it is necessary to calculate the proportion of the text area in each target enhancement tile. The target text tile refers to a tile containing text, which may be text such as "disease management" or "family doctor".

[0090] In this embodiment of the invention, the step of performing text region detection on the target augmented image patch to obtain a target text image patch includes: performing multi-level convolution and multi-level pooling operations on the target augmented image patch to obtain target augmented features; performing a partitioning convolution operation on the target augmented features to obtain a bounding box group; sequentially extracting a box coordinate group and a confidence score group from the bounding box group; filtering the bounding box group based on a confidence threshold according to the confidence score group to obtain a target bounding box group; performing a box merging operation on the target bounding box group using the box coordinate group to obtain a target merged text box; generating a target text box mask based on the target merged text box; and performing a masking operation on the target augmented image patch using the target text box mask to obtain the target text image patch.

[0091] In detail, the target augmentation patch can be subjected to multi-level convolution and multi-level pooling operations using the Darknet-53 network or VGG-16 network to obtain target augmentation features. The step of performing a partitioning convolution operation on the target augmentation features to obtain a bounding box group refers to dividing the target augmentation features according to different sizes and performing a convolution operation on the partitioned target augmentation features to obtain a bounding box group. The bounding box group consists of multiple bounding boxes, and each bounding box contains the coordinates of a rectangle and a confidence score.

[0092] Specifically, the step of filtering the bounding box group based on the confidence threshold according to the confidence level group to obtain the target bounding box group means removing bounding boxes with a confidence level less than a preset confidence threshold from the bounding box group to obtain the target bounding box group.

[0093] In detail, the step of using the box coordinate group to perform a box merging operation on the target bounding box group to obtain a target merged text box refers to calculating the distance between every two bounding boxes in the target bounding box group according to the box coordinate group, connecting and merging bounding boxes whose distance is less than a preset distance threshold to obtain a target merged text box.

[0094] For details, refer to Figure 3 As shown, the step of calculating the standard information entropy of the target enhanced map tile based on the target text map tile and the map tile information entropy includes:

[0095] S31. Extract the area of ​​the text tile from the target text tile, and extract the area of ​​the enhanced tile from the target enhanced tile;

[0096] S32. Divide the area of ​​the text tile by the area of ​​the enhanced tile to obtain the text information entropy;

[0097] S33. Multiply the text information entropy by a preset text weight to obtain the standard text entropy, and multiply the tile information entropy by a preset tile weight to obtain the standard tile entropy.

[0098] S34. The sum of the standard text entropy and the standard tile entropy is taken as the standard information entropy.

[0099] In detail, the text weight is a weight coefficient used to measure the proportion of attention in a text region, and the tile weight is a weight coefficient used to measure the proportion of attention in a tile region. The text weight and the tile weight are configured by the user.

[0100] In this embodiment of the invention, by performing text region detection on the target augmented image patch, a target text image patch is obtained, which can determine the region containing text in the target augmented image patch. By calculating the standard information entropy of the target augmented image patch based on the target text image patch and the image patch information entropy, the overall information complexity of the region where the target augmented image patch is located can be calculated, thereby facilitating the subsequent determination of the application prompt location.

[0101] S5. Based on all standard information entropy, filter out prompt interface tiles from the interface tile group, take the area position of the prompt interface tile as the prompt area position, take the color distribution characteristics of the prompt interface tile as the prompt color distribution characteristics, and generate application prompts using the prompt color distribution characteristics and the prompt area position.

[0102] In this embodiment of the invention, selecting the prompt interface tile from the interface tile group based on all standard information entropy means selecting the interface tile with the smallest standard information entropy in the interface tile group as the prompt interface tile, and the prompt area position refers to the pop-up position of the application prompt.

[0103] In this embodiment of the invention, generating application prompts using the prompt color distribution features and the prompt area position includes: initializing system prompts; extracting principal component colors from the prompt color distribution features; calculating complementary colors of the principal component colors to obtain prompt complementary colors; configuring the prompt text color according to the principal component colors to obtain text system prompts; configuring the background color of the text system prompts according to the prompt complementary colors to obtain color scheme system prompts; and configuring the position of the color scheme system prompts according to the prompt area position to obtain application prompts.

[0104] Specifically, the system prompt can be an Android Toast notification. The principal component color refers to the color corresponding to the color range with the largest distribution proportion in the color distribution characteristics. The complementary color calculation of the principal component color to obtain the complementary color of the prompt is obtained by inverting each channel value of the principal component color. For example, for RGB color, the complementary color is (255-R, 255-G, 255-B). For HSV color space, the hue value of the complementary color can be obtained by adding 180 degrees to the hue value.

[0105] Specifically, the `setBackground()` method of Toast can be used to configure the background color of the text system prompt based on the complementary color of the prompt, thus obtaining a color system prompt. The `setGravity()` method can be used to configure the position of the color system prompt based on the position of the prompt area, thus obtaining an application prompt.

[0106] In this embodiment of the invention, prompt interface tiles are selected from the interface tile group based on all standard information entropy. The regional position of the prompt interface tile is used as the prompt region position, and the color distribution characteristics of the prompt interface tile are used as the prompt color distribution characteristics. Application prompts are generated using the prompt color distribution characteristics and the prompt region position. Application prompts can pop up in the part of the prompt interface with the least amount of information, thereby increasing the prominence of the application prompts. Furthermore, the inverse color of the main color of the corresponding position in the prompt interface is used as the background color of the application prompts to enhance their visibility, thereby improving the display effect of the application prompts.

[0107] This invention, through configuring prompt tracking points in medical applications, acquires real-time interface images of the medical interface based on these tracking points. This allows for the collection of application interface images before prompt generation, facilitating subsequent region and color analysis of the images and enabling the configuration of region and color for the application prompts. By uniformly dividing the real-time interface image into interface tile groups according to regions, and selecting individual interface tiles from each group as target interface tiles, the color distribution features of the target interface tiles are extracted. This allows for color feature extraction of different regions within the real-time interface image, facilitating the determination of the background color for the application prompts. Denoising and enhancing the target interface tiles results in enhanced target tiles, improving image clarity and detail, and increasing the accuracy of subsequent text region detection. By calculating the tile information entropy of the enhanced target tiles, the page complexity of the corresponding region can be determined.

[0108] By performing text region detection on the target enhanced image block, a target text image block is obtained, which can determine the region containing text within the target enhanced image block. By calculating the standard information entropy of the target enhanced image block based on the target text image block and the image block's information entropy, the overall information complexity of the region where the target enhanced image block is located can be calculated, thus facilitating the subsequent determination of the application prompt's location. Prompt interface images are selected from the interface image block group based on all standard information entropies. The location of the prompt interface image block is used as the prompt area location, and the color distribution characteristics of the prompt interface image block are used as the prompt color distribution characteristics. Application prompts are generated using the prompt color distribution characteristics and the prompt area location. These prompts can pop up in the part of the prompt interface with the least amount of information, thereby increasing the prominence of the application prompts. Furthermore, the inverse color of the primary color at the corresponding location in the prompt interface is used as the background color of the application prompt, enhancing its visibility and improving the display effect. Therefore, the medical application prompt enhancement method proposed in this invention can solve the problem of poor prompt effects when providing application prompts.

[0109] like Figure 4 The diagram shown is a functional block diagram of a prompt enhancement device for medical applications provided in an embodiment of the present invention.

[0110] The medical application prompt enhancement device 100 of the present invention can be installed in an electronic device. Depending on the functions implemented, the medical application prompt enhancement device 100 may include an application tracking module 101, a color extraction module 102, a tile information calculation module 103, a standard information calculation module 104, and a prompt configuration module 105. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0111] In this embodiment, the functions of each module / unit are as follows:

[0112] The application tracking module 101 is used to configure prompt tracking points in medical applications and obtain real-time interface images of the medical interface based on the prompt tracking points.

[0113] The color extraction module 102 is used to evenly divide the real-time interface image into interface tile groups according to the region, select the interface tile in the interface tile group one by one as the target interface tile, and extract the color distribution features of the target interface tile.

[0114] The tile information calculation module 103 is used to denoise and enhance the target interface tile to obtain the target enhanced tile, and calculate the tile information entropy of the target enhanced tile;

[0115] The standard information calculation module 104 is used to perform text region detection on the target enhanced map block to obtain a target text map block, and calculate the standard information entropy of the target enhanced map block based on the target text map block and the map block information entropy.

[0116] The prompt configuration module 105 is used to filter out prompt interface tiles from the interface tile group based on all standard information entropy, use the regional position of the prompt interface tile as the prompt region position, use the color distribution characteristics of the prompt interface tile as the prompt color distribution characteristics, and generate application prompts using the prompt color distribution characteristics and the prompt region position.

[0117] In detail, each module in the medical application prompt enhancement device 100 described in this embodiment of the invention employs the same methods as described above during use. Figures 1 to 3 The method used is the same as the method for enhancing prompts in medical applications described above, and it can produce the same technical effect, so it will not be elaborated here.

[0118] like Figure 5 The diagram shown is a schematic representation of an electronic device for implementing a prompt enhancement method for medical applications, according to an embodiment of the present invention.

[0119] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13. It may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a prompt enhancement program for medical applications.

[0120] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing prompt enhancement programs for medical applications) and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0121] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code for a prompt enhancement program in a medical application, but also to temporarily store data that has been output or will be output.

[0122] The communication bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0123] The communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or, optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0124] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0125] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0126] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0127] The medical application prompt enhancement program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions that, when run in the processor 10, can achieve the following:

[0128] Configure prompt tracking points in medical applications, and obtain real-time interface images of the medical interface based on the prompt tracking points;

[0129] The real-time interface image is evenly divided into interface tile groups according to the region, and the interface tile in the interface tile group is selected one by one as the target interface tile, and the color distribution features of the target interface tile are extracted.

[0130] The target interface tile is denoised and enhanced to obtain the target enhanced tile, and the tile information entropy of the target enhanced tile is calculated.

[0131] Text region detection is performed on the target augmented image patch to obtain the target text image patch. The standard information entropy of the target augmented image patch is calculated based on the target text image patch and the image patch information entropy.

[0132] Based on all standard information entropy, prompt interface tiles are selected from the interface tile group. The regional position of the prompt interface tile is used as the prompt region position, and the color distribution characteristics of the prompt interface tile are used as the prompt color distribution characteristics. Application prompts are generated using the prompt color distribution characteristics and the prompt region position.

[0133] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0134] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0135] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0136] Configure prompt tracking points in medical applications, and obtain real-time interface images of the medical interface based on the prompt tracking points;

[0137] The real-time interface image is evenly divided into interface tile groups according to the region, and the interface tile in the interface tile group is selected one by one as the target interface tile, and the color distribution features of the target interface tile are extracted.

[0138] The target interface tile is denoised and enhanced to obtain the target enhanced tile, and the tile information entropy of the target enhanced tile is calculated.

[0139] Text region detection is performed on the target augmented image patch to obtain the target text image patch. The standard information entropy of the target augmented image patch is calculated based on the target text image patch and the image patch information entropy.

[0140] Based on all standard information entropy, prompt interface tiles are selected from the interface tile group. The regional position of the prompt interface tile is used as the prompt region position, and the color distribution characteristics of the prompt interface tile are used as the prompt color distribution characteristics. Application prompts are generated using the prompt color distribution characteristics and the prompt region position.

[0141] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0142] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0143] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0144] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0145] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0146] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0147] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0148] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in the system embodiments may also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0149] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for enhancing prompts in a medical application, characterized in that, The method includes: Configure prompt tracking points in medical applications, and obtain real-time interface images of the medical interface based on the prompt tracking points; The real-time interface image is evenly divided into interface tile groups according to the region, and the interface tile in the interface tile group is selected one by one as the target interface tile, and the color distribution features of the target interface tile are extracted. The target interface tile is denoised and enhanced to obtain the target enhanced tile, and the tile information entropy of the target enhanced tile is calculated. Text region detection is performed on the target augmented image patch to obtain the target text image patch. The standard information entropy of the target augmented image patch is calculated based on the target text image patch and the image patch information entropy. Based on all standard information entropy, prompt interface tiles are selected from the interface tile group. The regional position of the prompt interface tile is used as the prompt region position, and the color distribution characteristics of the prompt interface tile are used as the prompt color distribution characteristics. Application prompts are generated using the prompt color distribution characteristics and the prompt region position.

2. The method for enhancing prompts in medical applications as described in claim 1, characterized in that, The extraction of color distribution features of the target interface tiles includes: The target interface tile is converted to a different color space to obtain a target color tile. The target color patch is divided into color intervals to obtain a color interval set; The color interval set is counted by traversal to obtain a color pixel array; The proportion of each color pixel in the color pixel array is calculated to obtain the color distribution characteristics.

3. The method for enhancing prompts in medical applications as described in claim 1, characterized in that, The step of denoising and enhancing the target interface patch to obtain the enhanced target patch includes: The target interface patch is subjected to median filtering to obtain a filtered interface patch; Perform a grayscale operation on the filtered interface block to obtain a grayscale interface block; Edge detection and edge enhancement operations are performed sequentially on the grayscale interface patch to obtain an edge interface patch; The edge interface patch is subjected to grayscale enhancement and contrast enhancement operations in sequence to obtain the enhanced interface patch.

4. The method for enhancing prompts in medical applications as described in claim 1, characterized in that, The calculation of the tile information entropy of the target enhanced tile includes: Calculate the average pixel grayscale value of the target enhanced patch; Each pixel in the target enhancement block is selected as the target pixel, and the gray value of the target pixel is used as the target pixel gray value. The grayscale difference between the target pixel grayscale value and the average pixel grayscale value is calculated, and the average value of all grayscale differences is used as the tile information entropy of the target enhanced tile.

5. The method for enhancing prompts in medical applications as described in claim 1, characterized in that, The step of performing text region detection on the target enhanced map patch to obtain the target text map patch includes: Perform multi-level convolution and multi-level pooling operations on the target enhancement patch to obtain target enhancement features; The target enhancement features are divided into convolutional groups to obtain bounding box groups; Extract the bounding box coordinate group and the confidence group sequentially from the bounding box group; The bounding box group is filtered by confidence threshold based on the confidence level group to obtain the target bounding box group; The target bounding box group is merged using the box coordinate group to obtain a target merged text box; A target text box mask is generated based on the target merged text box, and the target enhanced image block is masked using the target text box mask to obtain the target text image block.

6. The method for enhancing prompts in medical applications as described in claim 1, characterized in that, The step of calculating the standard information entropy of the target enhanced map tile based on the target text map tile and the map tile information entropy includes: Extract the area of ​​the text tile from the target text tile, and extract the area of ​​the enhanced tile from the target enhanced tile; Divide the area of ​​the text tile by the area of ​​the enhanced tile to obtain the text information entropy; Multiply the text information entropy by a preset text weight to obtain the standard text entropy, and multiply the tile information entropy by a preset tile weight to obtain the standard tile entropy. The sum of the standard text entropy and the standard tile entropy is taken as the standard information entropy.

7. The method for enhancing prompts in a medical application as described in claim 1, characterized in that, The step of generating application prompts using the color distribution features of the prompts and the location of the prompt areas includes: The system prompts are initialized, and the principal component colors are extracted from the color distribution characteristics of the prompts. Complementary color calculation is performed on the principal component colors to obtain the cue complementary color; The system prompt text color is configured according to the principal component color to obtain the text system prompt; The background color of the text system prompt is configured according to the complementary color of the prompt to obtain the color system prompt; The color scheme system prompts are positioned according to the location of the prompt area to obtain application prompts.

8. A prompting enhancement device for medical applications, characterized in that, The device includes: The application tracking module is used to configure prompt tracking points in medical applications and obtain real-time interface images of the medical interface based on the prompt tracking points. The color extraction module is used to evenly divide the real-time interface image into interface tile groups according to the region, select the interface tile in the interface tile group one by one as the target interface tile, and extract the color distribution features of the target interface tile. The tile information calculation module is used to denoise and enhance the target interface tile to obtain the target enhanced tile, and calculate the tile information entropy of the target enhanced tile; The standard information calculation module is used to perform text region detection on the target enhanced map block to obtain the target text map block, and calculate the standard information entropy of the target enhanced map block based on the target text map block and the map block information entropy. The prompt configuration module is used to filter prompt interface tiles from the interface tile group based on all standard information entropy, use the regional position of the prompt interface tile as the prompt region position, use the color distribution characteristics of the prompt interface tile as the prompt color distribution characteristics, and generate application prompts using the prompt color distribution characteristics and the prompt region position.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the prompting enhancement method for a medical application as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the prompting enhancement method for a medical application as described in any one of claims 1 to 7.

Images