Private data processing method and device for online inquiry

Abstract

The invention discloses a privacy data processing method and device for online inquiry, and relates to the technical field of internet medical treatment. The method comprises the following steps: receiving disease site information transmitted by a user side, and determining a first target site capable of applying for privacy relief processing according to the disease site information; transmitting application release prompt information to the doctor terminal; receiving a release application request transmitted by the doctor terminal, and transmitting the release application request to the user terminal for display; and receiving agreement relieving information transmitted by the user side, performing part-based image processing on the real-time user video image transmitted by the user side in a video call process between the user side and the doctor side, and sending the processed real-time user video image to the doctor side. According to the implementation mode, the part capable of applying for relieving the privacy processing is determined according to the diseased part, and the privacy processing of the part is relieved under the condition that a doctor applies for relieving and a patient agrees to relieve, so that the doctor is ensured to obtain necessary information under the condition that the privacy of the patient is protected.

Description

Technical Field

[0001] The present invention relates to the field of Internet medical technology, and in particular to a method and device for processing privacy data in online consultations. Background Art

[0002] With the development of Internet medical care, seeing a doctor and purchasing medicine online have gradually become the mainstream of life. Among them, video consultation has become a new type of remote medical model, enabling doctors to see and hear, so as to diagnose and treat diseases more efficiently. However, some patients are reluctant to use this service due to concerns about privacy leakage. And the existing privacy processing methods are relatively single, such as uniformly obscuring the patient's head, which affects the doctor's view of the patient's part during an online consultation when diagnosing head diseases. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and device for processing privacy data in online consultations, which can at least solve the problem of single privacy processing methods in the prior art.

[0004] To achieve the above object, according to one aspect of the embodiments of the present invention, a method for processing privacy data in online consultations is provided, including:

[0005] Receiving the affected part information transmitted by the user terminal, and determining a first target part for which privacy processing can be applied for release according to the affected part information;

[0006] Transmitting a prompt message for applying for release to the doctor terminal;

[0007] Receiving the application for release request transmitted by the doctor terminal, and transmitting the application for release request to the user terminal for display;

[0008] Receiving the consent for release information transmitted by the user terminal, and performing image processing on the real-time user video image transmitted by the user terminal by part during the video call between the user terminal and the doctor terminal, and sending the processed real-time user video image to the doctor terminal; wherein, the image processing by part includes performing privacy processing on other parts except the first target part, so that the processed real-time user video image displays the first target part.

[0009] To achieve the above object, according to another aspect of the embodiments of the present invention, a device for processing privacy data in online consultations is provided, including:

[0010] A part determination module, configured to receive the affected part information transmitted by the user terminal, and determine a first target part for which privacy processing can be applied for release according to the affected part information;

[0011] A privacy release module, configured to transmit a prompt message for applying for release to the doctor terminal;

[0012] Receive the application cancellation request transmitted by the doctor side and transmit the application cancellation request to the user side for display;

[0013] Receive the consent cancellation information transmitted by the user side;

[0014] A privacy processing module, which is used to perform image processing on the real-time user video image transmitted by the user side by part during the video call between the user side and the doctor side, and send the processed real-time user video image to the doctor side; wherein, the image processing by part includes performing privacy processing on other parts except the first target part, so that the processed real-time user video image displays the first target part.

[0015] To achieve the above object, according to another aspect of the embodiments of the present invention, there is provided a privacy processing electronic device for online medical consultation.

[0016] The electronic device according to the embodiment of the present invention includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned privacy data processing method for online medical consultation.

[0017] To achieve the above object, according to another aspect of the embodiments of the present invention, there is provided a computer-readable medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned privacy data processing method for online medical consultation is implemented.

[0018] To achieve the above object, according to another aspect of the embodiments of the present invention, there is provided a computing program product. A computing program product according to an embodiment of the present invention includes a computer program, and when the program is executed by a processor, the privacy data processing method provided by the embodiment of the present invention is implemented.

[0019] According to the solution provided by the present invention, one embodiment of the above invention has the following advantages or beneficial effects: Dynamically determine the part where privacy processing can be applied for cancellation according to the affected part, and only when the doctor applies for cancellation and the patient agrees to cancel, cancel the privacy processing of this part, so as to ensure that the doctor can obtain the necessary information for diagnosis and treatment while protecting the patient's privacy. This method avoids the problem of information loss caused by default occlusion of the entire avatar, solves the limitation of the single existing privacy processing method, and realizes the balance between privacy protection and diagnosis and treatment needs.

[0020] The further effects of the above non-conventional optional methods will be described in combination with specific embodiments below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings are used to better understand the present invention and do not constitute an improper limitation to the present invention. Among them:

[0022] Figure 1 It is a schematic diagram of the main process of a method for processing privacy data in online medical consultations according to an embodiment of the present invention;

[0023] Figures 2(a), 2(b), 2(c) and 2(d) are example diagrams for privacy processing of private parts;

[0024] Figures 3(a) and 3(b) are schematic diagrams for specifically determining the parts where privacy processing can be applied for cancellation and the parts where privacy processing cannot be applied for cancellation;

[0025] Figure 4 It is a schematic diagram of the process of an optional method for processing privacy data in online medical consultations according to an embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of the process of another optional method for processing privacy data in online medical consultations according to an embodiment of the present invention;

[0027] Figure 6(a) is a schematic diagram for implementing dynamic tracking mosaic for a single human body;

[0028] Figure 6(b) is a schematic diagram for implementing dynamic tracking mosaic for multiple human bodies;

[0029] Figures 7(a), 7(b) and 7(c) are example schematic diagrams for implementing dynamic tracking mosaic for a single human body;

[0030] Figure 7(d) is an example schematic diagram for implementing dynamic tracking eye mosaic for multiple human bodies;

[0031] Figure 8 It is a schematic diagram of the main modules of a device for processing privacy data in online medical consultations according to an embodiment of the present invention;

[0032] Figure 9 It is an exemplary system architecture diagram to which the embodiment of the present invention can be applied;

[0033] Figure 10 It is a schematic diagram of the structure of a computer system of a mobile device or a server suitable for implementing the embodiment of the present invention. Detailed implementation manners

[0034] The following makes an explanation of the exemplary embodiments of the present invention with reference to the accompanying drawings. Various details of the embodiments of the present invention are included to help understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted below.

[0035] It should be noted that in the embodiments of the present application, some existing solutions in the industry such as certain software, components, models, etc. may be mentioned. They should be regarded as exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solutions of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0036] Without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. In the technical solutions of the present invention, the acquisition, transmission, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside these legal uses, etc., and are subject to the supervision and management of the regulatory authorities.

[0037] Regarding user information, necessary measures should be taken for user personal information to prevent illegal access to such personal information data, ensure that the personnel with the right to access personal information data comply with the relevant laws and regulations, and ensure the security of user personal information. Once these user personal information data are no longer needed, the risk should be minimized by restricting or even prohibiting data collection and / or deleting the data. When applicable, including in some relevant application programs, protect user privacy by de-identifying the data, such as by removing specific identifiers (e.g., date of birth, etc.), controlling the amount or specificity of the stored data (e.g., collecting location data at the city level instead of at the specific address level), controlling how the data is stored, and / or other methods of de-identifying.

[0038] Video consultation: It refers to a consultation method in which doctors and patients conduct real-time video calls through Internet technology to achieve remote diagnosis and medical services. Privacy processing: During the video consultation process, the patient's personal information (including the patient's image), condition, diagnosis results, etc. all belong to the category of privacy. The leakage of this information may cause unnecessary troubles and harms to the patient, and may even lead to legal disputes. Therefore, protecting the patient's privacy is an indispensable part of the video consultation service.

[0039] There are limitations in the current video privacy processing technology in the Internet medical industry: on the one hand, some Internet medical enterprises are limited in their own video technology capabilities and cannot perform any privacy processing on video images, which is obviously not conducive to the protection of patients' privacy; on the other hand, the existing privacy processing methods usually uniformly block the patient's head, such as mosaicing the patient's head, but when the patient's diseased part happens to be in the head, this one-size-fits-all processing method will instead affect the doctor's diagnosis effect. To improve this situation, the ideal solution is to provide personalized privacy processing according to the different diseased parts of the patient. This can not only effectively protect the patient's privacy but also not prevent the doctor from accurately diagnosing the condition.

[0040] SeeFigure 1 , shown is the main flowchart of a privacy data processing method for online medical consultations provided by an embodiment of the present invention, including the following steps:

[0041] S101: Receive the affected part information transmitted by the user terminal, and determine the first target part for which privacy processing can be applied for release according to the affected part information;

[0042] S102: Transmit the prompt information for applying for release to the doctor terminal;

[0043] S103: Receive the application for release request transmitted by the doctor terminal, and transmit the application for release request to the user terminal for display;

[0044] S104: Receive the consent for release information transmitted by the user terminal, and during the video call between the user terminal and the doctor terminal, perform image processing on the real-time user video image transmitted by the user terminal by part, and send the processed real-time user video image to the doctor terminal; wherein, the image processing by part includes performing privacy processing on other parts except the first target part, so that the processed real-time user video image shows the first target part.

[0045] In this embodiment, first, the key privacy parts of the human body are determined, and recognition training is carried out for these parts. The key privacy parts preferably mainly include four positions, as shown in Table 1 for details. Subsequently, they are divided into the head part, the eye part, and other preset privacy parts. The other preset privacy parts include the breast part and the genital part.

[0046] Table 1

[0047]

[0048] Among them, an example of eye privacy processing is shown in Figure 2(a), an example of head privacy processing is shown in Figure 2(b), an example of breast privacy processing is shown in Figure 2(c), and an example of genital privacy processing is shown in Figure 2(d). In addition to mosaics, using cartoon images or other preset images to cover, virtualization and other methods can also be used. Among them, in digital image processing, a mosaic is a technique of replacing a part of an image with small pieces of color or patterns to hide or blur certain details of the image.

[0049] After determining the key privacy parts of the human body, the images of these four parts will be collected and stored respectively, and four rich human body part image libraries will be gradually established. It should be noted that for these parts, especially those involving privacy, considering the actual application scenarios and compliance requirements, before using the relevant data, it is necessary to report to a specific institution and obtain permission.

[0050] For step S101, an intermediate layer, such as an Internet medical system, can be set up between the user side and the doctor side in this solution to provide an optimized consultation process. This system supports multiple doctors to join, but functions such as video calls still need to establish a connection with the doctor side.

[0051] Before the consultation, the patient needs to complete the following operations in sequence: enter the Internet medical system on the user side, select the consultation option, input symptom information, specify the person seeking medical treatment (relationships such as children or parents can be bound), and select the affected body part. Compared with the prior art, this solution adds a function of selecting the affected body part, which can infer the specific part (such as the eyes or chest) based on the user's selection, input, or combined with symptoms. In addition, the system also supports the selection function of human body part diagrams and acupoint diagrams. Patients can select specific parts or acupoints without the above input operations, which is applicable to the traditional Chinese medicine consultation scenario and further improves the accuracy.

[0052] In addition, the patient can preset the time or select a reservation time before the consultation, such as reserving 8:10 in the morning. This function is mainly for online phone or video consultation forms and requires payment of corresponding fees to confirm the consultation reservation. It should be noted that only after the patient completes the payment of the consultation fee, the system will lock the selected affected body part to avoid confusion or waste of resources in the subsequent processing logic caused by changes in the part. This design ensures the efficiency and accuracy of the consultation process, and also improves the user experience and privacy protection level.

[0053] After the system determines the affected body part through the user side and the patient completes the payment of the consultation fee, it will determine the specific parts that need to be subject to privacy processing based on the affected body part, and determine the first target part that can apply for lifting the privacy processing from these specific parts. Similarly, the second target part that cannot apply for lifting the privacy processing can also be determined. The specific logic can refer to Figures 3(a) and 3(b), and the process is as follows:

[0054] S1: Determine whether the affected body part is located in the head area. If it is, jump to S2; otherwise, jump to S3;

[0055] S2: If it is located in the head area, further determine whether the affected body part is the eye part.

[0056] S21: If the affected body part is not the eye part, mark the eye part as the second target part that cannot apply for lifting the privacy processing;

[0057] S22: If the affected part is the eye area, then the eye area is taken as the part to be privacy-processed. At the same time, the eye area is marked as the first target part for which privacy processing "can be applied for lifting". This means that the doctor side can apply to the patient for lifting the privacy processing of this part when necessary (it can only be lifted with the patient's consent). For example, some symptoms can be diagnosed without checking the eyes, while some require checking the eyes for diagnosis.

[0058] S3: If the affected part is not in the head area, then the entire head area of the patient is privacy-processed. At the same time, privacy processing is also required for the other two privacy parts (such as breasts and genitals), which is only triggered in the case of nudity. In addition, the system will further determine whether the affected part hits the key privacy parts.

[0059] S31: If the affected part hits one or more of the other two privacy parts, such as the breast part, then the hit privacy part is marked as the first target part for which privacy processing "can be applied for lifting". This means that the doctor side is allowed to apply to lift the privacy processing of this part (also requires the patient's consent);

[0060] S32: If the affected part does not hit the key privacy parts, it means that the head part and the other two privacy parts are all second target parts for which privacy processing cannot be applied for lifting, that is, the doctor side cannot apply to lift the privacy processing.

[0061] For steps S102 - S104, at the appointed time, the doctor and the patient start the online consultation. The determination method of the doctor is flexible: the patient can choose a doctor they are familiar with, such as the doctor they saw last time and continue to choose the same doctor this time; if there is only one doctor on duty on the day, the system will automatically select this doctor for the consultation. In addition, the patient can also not actively choose a doctor. After clicking the video consultation option, the system will automatically match the most suitable doctor to provide consultation services according to the user's symptoms and affected part. This mechanism ensures that the consultation arrangement not only meets the user's preferences but also can efficiently match doctors with the right specialty, improving the consultation experience and efficiency. In addition, the user side collects the user's real-time video image through a camera device. Here, the camera device can be a front camera or a rear camera, and there is no limit here.

[0062] Before the patient conducts a video consultation, the system will guide the patient to select the affected part to ensure that the information about the affected part has been provided before the video consultation. Therefore, before or during the establishment of the video call link, the system can already judge which first target parts the doctor can apply to lift the privacy processing based on the affected part of the patient.

[0063] While ensuring patient privacy, it is also necessary to ensure the effectiveness of doctors' video consultations. Therefore, for the first target area marked with "privacy processing can be applied for lifting", before, during, or after establishing a video call link between the user side and the doctor side, the system will transmit prompt information about the first target area to the doctor side, indicating that the first target area supports the application for lifting privacy processing. Assuming there are multiple first target areas, one prompt information can be generated, or prompt information can be generated for each first target area, without any restrictions here.

[0064] Subsequently, the system receives a request for lifting privacy processing initiated by the doctor side and feeds back the request or the reprocessed request to the user side to obtain the patient's consent. For example, a dialog box or a prompt box will pop up on the user side for display, with options such as "agree" or "disagree" attached in the box for the patient to choose. After receiving the consent information for lifting privacy processing returned by the user side, the system will lift the privacy processing operation for the first target area and restore its normal display. However, if the patient does not agree, the privacy will continue to be maintained. This mechanism ensures privacy security and diagnosis and treatment efficiency during the video consultation process.

[0065] For example, when the patient selects the affected area as the chest and completes the payment, since the affected area is the breast area, the system will mark it as the first target area for which "privacy processing can be applied for lifting". The doctor can apply for lifting the privacy processing of the breast area, but the patient's consent is required. Once the patient agrees, the system will lift the privacy processing of this area and restore the normal display. That is, during the video call between the user side and the doctor side, for the real-time user video image transmitted by the user side, privacy processing will no longer be performed on the first target area, and privacy processing will only be performed on other areas except the first target area. This mechanism effectively avoids negative cases such as a certain mental patient paying multiple times to initiate a video consultation with a doctor and deliberately showing up naked.

[0066] For the other areas except the first target area mentioned above, they can be the second target areas for which privacy processing cannot be applied for lifting. According to the aforementioned Figures 3(a) and 3(b), it can be known that before the patient undergoes a video consultation, the system determines which second target areas need privacy processing and cannot be applied for lifting by guiding the patient to select the affected area. For example, in the above example, it will be determined that the entire head area and the genital area of the patient are the second target areas for which privacy processing cannot be applied for lifting. For these second target areas, the pre-configured privacy processing methods are determined respectively to apply these privacy processing methods to the patient's real-time video image in real time during the call. If the patient's affected area exactly hits the key privacy area, the system will automatically perform privacy processing on this area.

[0067] The method provided by the above embodiments can ensure the security of the user's private parts during video calls, dynamically determine the parts for which privacy processing can be applied based on the affected parts, and only lift the privacy processing for these parts when the doctor applies for lifting and the patient consents to the lifting. This solves the limitation of the single existing privacy processing method, effectively balances the relationship between the medical diagnosis needs and the protection of the patient's personal privacy, and at the same time improves the trust and efficiency of doctor-patient communication.

[0068] Refer to Figure 4 , which shows a schematic flowchart of an optional privacy data processing method for online medical consultations according to an embodiment of the present invention, including the following steps:

[0069] S401: Identify the human body contour from the real-time user video image to parse out the images of each part of the human body;

[0070] S402: Use the human body part image library created in advance for the second target part to perform matching processing on the parsed images of each part of the human body to obtain the area to be subjected to privacy processing;

[0071] S403: Use the privacy processing method configured in advance for the second target part to perform privacy processing on the area to be subjected to privacy processing.

[0072] In the above embodiment, before the system displays the real-time video image transmitted by the user terminal, it needs to perform privacy processing on the second target part. The specific process is as follows: First, through image recognition technology, identify the human body contour from the real-time user video image to parse out the images of each part of the human body; then determine the human body part image library corresponding to the second target part to be subjected to privacy processing; use the human body part image library to perform comparison processing on the parsed images of each part of the human body to obtain a matching result; then locate the area that needs privacy processing according to the matching result; finally, apply the corresponding privacy processing method to process these areas.

[0073] Among them, image recognition technology, as an important branch of computer vision, is responsible for processing, analyzing, and understanding images to identify different targets and objects. For the human body part image library, training and correction can be carried out. For example, it can be trained by a large number of video images with different postures, and the cases of matching errors can be continuously corrected and optimized to ensure higher accuracy and richness.

[0074] For example, the system first uses image recognition technology to identify the human body contour from the video and parse out the images of human body parts such as the head, eyes, hands, and body. Assuming that the eye area of the patient needs to be privacy processed, the system will call the pre-trained "eye area image library", compare the parsed eye area image with this image library, so as to accurately locate the eye area. According to the comparison result, the system confirms the position and range of the eyes in the video image, and finally applies eye privacy processing methods, such as blurring or mosaic and other privacy processing methods, to ensure that the patient's eye information will not be leaked, while retaining the clarity of other non-private areas.

[0075] The method provided by the above embodiment can accurately locate the area to be privacy processed by identifying the human body contour and combining with the pre-created human body part image library, and at the same time uses the privacy processing method configured for the privacy part to process this specific area, avoiding the problems of excessive occlusion or privacy leakage, realizing more accurate and personalized privacy protection, and improving the accuracy of doctor diagnosis and the security of patient privacy.

[0076] See Figure 5 , which shows a schematic flow chart of an optional privacy data processing method for online consultation according to an embodiment of the present invention, including the following steps:

[0077] S501: Identify the human body in the real-time user video image;

[0078] S502: Determine each video frame of the real-time user video image, and calculate the position and movement trajectory of the human body in each video frame;

[0079] S503: According to the calculated position and movement trajectory, adjust the position and size of the privacy processing of the second target part in each video frame.

[0080] In the above implementation manner, during a video call, the user may continuously change positions, such as stepping back, standing up, or turning the head, etc. In this case, the privacy processing area needs to dynamically adjust its position and size to adapt to the user's movement. For this reason, this solution realizes the dynamic tracking mosaic technology by combining a tracking algorithm. When the system recognizes the human body in the video, it will calculate the position of the human body in the video frame and its movement trajectory, and automatically adjust the position and size of the mosaic according to the trajectory. It should be noted that in order to apply the mosaic in real-time video, the algorithm needs to be optimized to improve the processing speed, which can be achieved by using GPU acceleration and optimizing the algorithm.

[0081] The algorithms used in the specific implementation and the overall implementation route are shown in Fig. 6(a). This solution employs a variety of advanced algorithms to support dynamic tracking and privacy protection. Among them, the Convolutional Neural Network (CNN) is a deep learning model specifically designed for processing grid-structured data (such as images) and performs excellently in image recognition and object detection tasks. The Kalman Filter is a recursive algorithm for estimating the state of a dynamic system, especially suitable for dealing with linear systems with noise. The Siamese network is a special type of neural network architecture mainly used to compare the similarity of two inputs and is widely applied in tasks such as face verification and image similarity search.

[0082] Taking eye privacy protection as an example, when the user moves, the mosaic can adjust its position and size in real time along with the movement of the human body to ensure that the private parts of the eyes are always covered. See Figures 7(a) to 7(c) as shown. Fig. 7(a) corresponds to the side view of the patient, Fig. 7(b) corresponds to the side view of the patient with the head up, and Fig. 7(c) corresponds to the patient showing half of the head. The front view of the patient is shown in Fig. 2(a). It can be seen that no matter how the patient's head moves or turns, the system can ensure that the mosaic accurately covers the private parts.

[0083] In addition, considering the particularity of the medical scenario, multiple human bodies may appear simultaneously in the video image, such as a child patient and their accompanying parent, or an elderly person and their accompanying child. To protect the privacy of all, privacy processing will be performed on all human bodies in the video image. Here, the privacy processing method can be the same, that is, the same privacy processing method as that of the patient is adopted. As shown in Fig. 7(d), only the head positions are shown, and the eye mosaic processing method is used for all human bodies. The system identifies multiple human bodies in the video through the built-in tracking algorithm and calculates the position and movement trajectory of each object in the video frame, thereby achieving real-time tracking and performing mosaic processing on their private parts.

[0084] The algorithms used in the specific implementation and the overall implementation route are shown in Fig. 6(b). Among them, Faster R-CNN is a deep learning model for object detection that can quickly identify and locate multiple objects in an image. Faster R-CNN is developed on the basis of R-CNN and Fast R-CNN, further improving the speed and accuracy of object detection. SORT (Simple Online and Realtime Tracking) is an efficient multi-object tracking algorithm that realizes object tracking by combining the object detection results and the Kalman filter. In addition, for special situations in multi-person videos, such as object overlap, partial occlusion, or fast movement, etc., the system designs a special edge algorithm to effectively handle these complex scenarios and ensure the accuracy and reliability of privacy protection.

[0085] The method provided by the above embodiments identifies the human body in the real-time user video image, calculates the position and movement trajectory of the human body in each video frame, and dynamically adjusts the position and size of the privacy processing of the private parts. This method can not only accurately adapt to the changes in human body movements, but also support the privacy processing requirements in multiple-person images, effectively solving the limitations of static privacy processing methods, realizing dynamic image privacy capabilities and multiple-person image privacy capabilities, and greatly improving the flexibility and applicability of privacy protection.

[0086] The present invention aims to solve the contradiction between privacy protection and diagnosis and treatment needs during online video consultations for patients, and specifically makes technological breakthroughs for the following problems:

[0087] 1. High-precision privacy area recognition: Set head privacy parts, eye privacy parts and other privacy parts for the human body, and realize high-precision recognition of privacy areas by training the video image learning, processing and recognition capabilities of the system. Existing solutions default to perform privacy processing on the patient's avatar, while this solution only performs privacy processing on the head when the diseased part is not located on the head; for specific head diseases, more refined privacy processing is performed according to the actual diseased part.

[0088] 2. Special privacy processing technology: Develop special privacy processing technology for video consultations to accurately process the logical relationship between the diseased part and the privacy part. For the part where privacy processing can be applied for cancellation, when the diseased part coincides with this privacy part, it supports the doctor to apply for cancellation of the privacy processing of this part, and the privacy processing can be cancelled after obtaining the patient's consent, ensuring that the doctor can obtain the necessary diagnostic information.

[0089] 3. Dynamic and multiple-person privacy processing: Introduce dynamic privacy capabilities for handling human body movements and privacy processing capabilities for handling the presence of multiple human bodies in the video. When multiple people appear on the user-side screen, privacy processing is defaultly performed on all of them.

[0090] By accurately identifying human body privacy areas, dynamic image privacy processing capabilities and multiple-person image privacy processing capabilities, combined with medical characteristics, accurate judgment of the logical relationship between the diseased part and the privacy part is realized. The overall solution determines the parts where privacy processing can be applied for cancellation and the parts where privacy processing cannot be applied for cancellation through precise algorithm processing of the privacy parts of the patient's video image, which can fully protect the patient's privacy while separately processing according to the doctor's diagnosis and treatment needs, improving the patient's trust in the platform and ensuring the effectiveness of video consultations, enabling patients to feel at ease and confident during online video consultations, and at the same time ensuring the doctor's diagnostic accuracy.

[0091] See Figure 8, showing a schematic diagram of the main modules of a privacy data processing device 800 for online medical consultations provided by an embodiment of the present invention, including:

[0092] A site determination module 801, configured to receive the onset site information transmitted by the user terminal, and determine a first target site for which privacy processing can be applied for release according to the onset site information;

[0093] A privacy release module 802, configured to transmit a privacy release prompt message to the doctor terminal; receive a privacy release request transmitted by the doctor terminal, and transmit the privacy release request to the user terminal for display; receive the consent release information transmitted by the user terminal;

[0094] A privacy processing module 803, configured to perform image processing on the real-time user video image transmitted by the user terminal according to the site during the video call between the user terminal and the doctor terminal, and send the processed real-time user video image to the doctor terminal; wherein, the image processing according to the site includes performing privacy processing on other sites except the first target site, so that the processed real-time user video image shows the first target site.

[0095] In the implementation device of the present invention, the site determination module 801 is configured to:

[0096] In the case where the onset site is the eye site, use the eye site as the first target site for which privacy processing can be applied for release;

[0097] In the case where the onset site hits one or more other preset privacy sites except the head site, use the one or more other preset privacy sites that are hit as the first target site for which privacy processing can be applied for release.

[0098] In the implementation device of the present invention, the site determination module 801 is further configured to: determine a second target site for which privacy processing cannot be applied for release according to the onset site information;

[0099] The privacy processing module 803 is configured to: perform privacy processing on the second target site using the privacy processing method pre-configured for the second target site.

[0100] In the implementation device of the present invention, the site determination module 801 is configured to:

[0101] In response to the onset site being located in the head site and the onset site not being the eye site, use the eye site as the second target site for which privacy processing cannot be applied for release;

[0102] In response to the onset site not being located in the head site and the onset site not hitting any other preset privacy sites except the head site, use all preset privacy sites as the second target sites for which privacy processing cannot be applied for release.

[0103] In the implementation device of the present invention, the privacy processing module 803 is used for:

[0104] Identify the human body contour from the real-time user video image to analyze the images of each part of the human body;

[0105] Use the human body part image library created in advance for the second target part to perform matching processing on the analyzed images of each part of the human body to obtain the area to be processed for privacy;

[0106] Use the privacy processing method configured in advance for the second target part to perform privacy processing on the area to be processed for privacy.

[0107] In the implementation device of the present invention, the privacy processing method includes one or more of mosaic and covering with a preset image.

[0108] The implementation device of the present invention further includes a dynamic video privacy processing module, which is used for:

[0109] Identify the human body in the real-time user video image;

[0110] Determine each video frame of the real-time user video image, and calculate the position and movement trajectory of the human body in each video frame;

[0111] According to the calculated position and movement trajectory, adjust the position and size of the privacy processing of the second target part in each video frame.

[0112] The implementation device of the present invention further includes a multi-person video privacy processing module, which is used for:

[0113] When the number of human bodies in the real-time user video image is multiple, perform privacy processing on each human body.

[0114] In addition, the specific implementation content of the device in the embodiments of the present invention has been described in detail in the above method, so the repeated content will not be described here.

[0115] Figure 9 An exemplary system architecture 900 to which the embodiments of the present invention can be applied is shown, including terminal devices 901, 902, 903, a network 904, and a server 905 (merely an example).

[0116] The terminal devices 901, 902, 903 can be various electronic devices with a display screen and supporting web browsing, installed with various communication client applications. Users can use the terminal devices 901, 902, 903 to interact with the server 905 through the network 904 to receive or send messages, etc.

[0117] The network 904 serves as a medium for providing a communication link between the terminal devices 901, 902, 903 and the server 905. The network 904 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0118] The server 905 can be a server that provides various services. For example, it can be a background management server (only for example) that supports shopping websites browsed by users using the terminal devices 901, 902, 903. The background management server can analyze and process data such as product information query requests received, and feedback the processing results (such as target push information, product information - only for example) to the terminal devices. It should be noted that the methods provided in the embodiments of the present invention are generally executed by the server 905. Correspondingly, the device is generally arranged in the server 905.

[0119] It should be understood that Figure 9 the numbers of terminal devices, networks, and servers in

[0120] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers. Figure 10 is a schematic diagram of the structure of a computer system 1000 of a terminal device suitable for implementing the embodiments of the present invention. Figure 10 The terminal device shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0121] As Figure 10 shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to the programs stored in the read-only memory (ROM) 1002 or the programs loaded from the storage section 1008 into the random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the system 1000 are also stored. The CPU 1001, ROM 1002, and RAM 1003 are connected to each other through a bus 1004. The input / output (I / O) interface 1005 is also connected to the bus 1004.

[0122] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. as well as a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 1010 as needed so that a computer program read therefrom is installed into the storage section 1008 as needed.

[0123] Specifically, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 1009, and / or installed from the removable medium 1011. When the computer program is executed by a central processing unit (CPU) 1001, the above-described functions defined in the system of the present invention are performed.

[0124] It should be noted that the computer-readable medium shown in the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination of the above.

[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0126] The modules involved in the embodiments of the present invention can be implemented in software or in hardware. The described modules can also be provided in a processor. For example, it can be described as: A processor includes a location determination module, a privacy release module, and a privacy processing module. Among them, the names of these modules do not constitute a limitation on the modules themselves in some cases. For example, the privacy release module can also be described as the "application for privacy release module".

[0127] As another aspect, the present invention also provides a computer-readable medium, which can be included in the device described in the above embodiments; or can exist alone without being assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by the device, the device is caused to execute the privacy data processing method for online medical consultations described in any of the above.

[0128] The computer program product of the present invention includes a computer program, and the computer program implements the privacy data processing method for online medical consultations in the embodiments of the present invention when executed by a processor.

[0129] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for processing privacy data in online medical consultations, characterized in that, Including: Receiving the affected part information transmitted by the user terminal, and determining a first target part for which privacy processing can be applied for release according to the affected part information; Transmitting a prompt message for applying for release to the doctor terminal; Receiving the application for release request transmitted by the doctor terminal, and transmitting the application for release request to the user terminal for display; Receiving the consent for release information transmitted by the user terminal, and during the video call between the user terminal and the doctor terminal, performing per-site image processing on the real-time user video image transmitted by the user terminal, and sending the processed real-time user video image to the doctor terminal; wherein, the per-site image processing includes performing privacy processing on other parts except the first target part, so that the processed real-time user video image shows the first target part.

2. The method according to claim 1, wherein The determining the first target part for which privacy processing can be applied for release according to the affected part information includes: In the case where the affected part is the eye part, taking the eye part as the first target part for which privacy processing can be applied for release; In the case where the affected part hits one or more other preset privacy parts except the head part, taking the one or more other preset privacy parts that are hit as the first target part for which privacy processing can be applied for release.

3. The method according to claim 1, characterized in that, The method further includes: Determining a second target part for which privacy processing cannot be applied for release according to the affected part information; The performing privacy processing on other parts except the first target part includes: using the privacy processing method pre-configured for the second target part to perform privacy processing on the second target part.

4. The method according to claim 3, wherein The determining the second target part for which privacy processing cannot be applied for release according to the affected part information includes: In response to the affected part being located in the head part, and in the case where the affected part is not the eye part, taking the eye part as the second target part for which privacy processing cannot be applied for release; In response to the affected part not being located in the head part, and in the case where the affected part does not hit any other preset privacy parts except the head part, taking all the preset privacy parts as the second target part for which privacy processing cannot be applied for release.

5. The method according to claim 3, wherein The using the privacy processing method pre-configured for the second target part to perform privacy processing on the second target part includes: Identifying the human body contour from the real-time user video image to parse out the images of each part of the human body; Using the human body part image library pre-created for the second target part to perform matching processing on the parsed images of each part of the human body to obtain the area to be privacy processed; Using the privacy processing method pre-configured for the second target part to perform privacy processing on the area to be privacy processed.

6. The method according to any one of claims 3 to 5, characterized in that, The privacy processing method includes one or more of mosaic and using a preset image to cover.

7. The method according to any one of claims 3 to 5, characterized in that, The method further includes: Identifying the human body in the real-time user video image; Determining each video frame of the real-time user video image, and calculating the position and movement trajectory of the human body in each video frame; According to the calculated position and movement trajectory, adjusting the position and size of the privacy processing of the second target part in each video frame.

8. The method according to claim 7, wherein The method further includes: In the case where the number of human bodies in the real-time user video image is multiple, performing privacy processing on each human body.

9. A privacy data processing device for online medical consultations, characterized in that, Including: A location determination module, configured to receive the onset location information transmitted by the user terminal, and determine a first target location for which privacy processing can be applied for release according to the onset location information; A privacy release module, configured to transmit a privacy release prompt message to the doctor terminal; Receive the release request transmitted by the doctor terminal, and transmit the release request to the user terminal for display; Receive the consent release information transmitted by the user terminal; A privacy processing module, configured to perform location-based image processing on the real-time user video image transmitted by the user terminal during the video call between the user terminal and the doctor terminal, and send the processed real-time user video image to the doctor terminal; wherein, the location-based image processing includes performing privacy processing on other locations except the first target location, so that the processed real-time user video image displays the first target location.

10. An electronic device, characterized in that, Comprising: One or more processors; A storage device, configured to store one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-8.

11. A computer-readable medium having a computer program stored thereon, characterized in that, The program, when executed by the processor, implements the method according to any one of claims 1-8.

12. A computer program product comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the method according to any one of claims 1-8.

Images