Remote drug delivery method based on subject drug delivery real-time monitoring and intelligent drug matching

Abstract

The invention discloses a remote drug delivery method based on subject drug delivery real-time monitoring and intelligent drug matching. The method comprises the following steps: collecting image data information matched with a target detection demand corresponding to a target user; sending the image data information to a management end, so that the management end performs image analysis on the image data information to generate first guidance information; receiving the first guidance information fed back by the management end, and performing data analysis on the image data information based on a data analysis model and the first guidance information to obtain second guidance information; and performing drug dynamic adjustment based on the second guidance information. Through the technical adjustment, real-time distribution of the medicine can be remotely controlled, and the real-time performance and reliability of medicine distribution and monitoring are improved.

Description

Technical Field

[0001] This application relates to the field of digital information transmission technology. More specifically, it relates to a remote drug administration method based on real-time monitoring of drug administration to subjects and intelligent drug matching. Background Art

[0002] With the continuous development of medical technology, telemedicine has gradually become an important medical model. Traditional treatment methods mainly rely on patients going to the hospital for face-to-face consultations, and doctors issue drug prescriptions after observation and diagnosis. However, this method has many limitations: on the one hand, patients need to make frequent trips to the hospital, consuming a lot of time and energy; on the other hand, doctors cannot monitor the changes in patients' conditions and treatment effects in real time, making it difficult to adjust treatment plans in a timely manner.

[0003] Although existing telemedicine technologies can alleviate the problem of inconvenient medical treatment for patients to a certain extent, there are still deficiencies in drug administration monitoring and drug matching. Currently, some telemedicine systems can achieve video calls between patients and doctors, and doctors observe the scalp conditions of patients through the video, but this method cannot provide high-precision image data and is difficult to meet the needs of precision medicine. Moreover, for drug matching, most rely on doctors' experience, lacking intelligent analysis and matching means, and it is difficult to dynamically adjust drug plans according to the specific conditions of patients. Summary of the Invention

[0004] To solve the deficiencies in the prior art, the purpose of this application is to address the above-mentioned defects and further propose a remote drug administration method based on real-time monitoring of drug administration to subjects and intelligent drug matching.

[0005] According to one aspect of this application, a remote drug administration method based on real-time monitoring of drug administration to subjects and intelligent drug matching is disclosed, including: Collecting image data information that matches the target detection requirements corresponding to the target user; Sending the image data information to the management end so that the management end performs image analysis on the image data information to generate the first guidance information; Receiving the first guidance information fed back by the management end, and performing data analysis on the image data information based on the data analysis model and the first guidance information to obtain the second guidance information; Performing dynamic drug adjustment based on the second guidance information.

[0006] In some possible embodiments, receiving the first guidance information fed back by the management end, and performing data analysis on the image data information based on the data analysis model and the first guidance information to obtain the second guidance information includes: Construct a first directed graph corresponding to the data analysis model; wherein, each calculation unit in the data analysis model corresponds to a node in the first directed graph; Split the first directed graph into a first part and a second part; The management end performs data analysis on the first guidance information based on the first part of the data analysis model to obtain third data information; and encrypts and transmits it to the client; The client performs data analysis on the third data information based on the second part of the data analysis model to obtain second guidance information.

[0007] In some possible embodiments, generating second guidance information based on the first guidance information, the node access order, and the data analysis model includes: Determine the target first guidance information from multiple first guidance information sent by the management end based on the node access order; Collect and update the detection image based on the retake parameter information and the retake area information included in the target first guidance information; Based on the data analysis model, perform data analysis on the updated detection image and the remaining detection images to determine the second guidance information; the remaining detection images are the detection images other than the images to be retaken among the multiple detection images.

[0008] In some possible embodiments, performing data analysis on the updated detection image and the remaining detection images based on the data analysis model to determine the second guidance information includes: Generate a multi-channel sequence based on the image parameter information of the updated detection image and the remaining detection images; Extract spatial feature information and temporal feature information corresponding to the target detection requirements based on the multi-channel sequence and the data analysis model; Perform feature fusion based on the spatial feature information and the temporal feature information to obtain feature fusion information; there is a mapping relationship between the feature fusion information and the drug candidate data set; Determine the second guidance information based on the feature fusion information and the drug candidate data set.

[0009] In some possible embodiments, the method further includes: Obtain standard drug allocation information; Modify the data analysis model based on the standard drug allocation information and the second guidance information.

[0010] The second aspect of the present application discloses another remote drug administration method based on real-time monitoring of subject drug administration and intelligent drug matching, including: Receive the image data information collected by the client; Perform image analysis on the image data information to generate first guidance information; Send the first guidance information to the client, so that the client can perform data analysis on the first guidance information based on the data analysis model to obtain the second guidance information, and perform dynamic drug adjustment based on the second guidance information.

[0011] In some possible embodiments, image analysis is performed on the image data information to generate the first guidance information, including: Perform image analysis on the image data information based on the analysis index data to obtain the image analysis result; In the case that the analysis index data corresponding to at least one detected image among the multiple detected images indicated by the image analysis result does not meet the preset analysis condition, determine at least one detected image as the image to be detected; Use the retake parameter information and retake area information corresponding to the image to be detected as the first guidance information.

[0012] The third aspect of this application provides a remote drug administration device based on real-time monitoring of drug administration by subjects and intelligent drug matching, including: A data acquisition module, configured to acquire image data information that matches the target detection requirements corresponding to the target user; A first data sending module, configured to send the image data information to the management end, so that the management end performs image analysis on the image data information to generate the first guidance information; A first data receiving module, configured to receive the first guidance information fed back by the management end, and perform data analysis on the image data information based on the data analysis model and the first guidance information to obtain the second guidance information; A drug selection module, configured to perform dynamic drug adjustment based on the second guidance information.

[0013] The fourth aspect of this application provides another remote drug administration device based on real-time monitoring of drug administration by subjects and intelligent drug matching, including: A second data receiving module, configured to receive the image data information collected by the client; An image analysis module, configured to perform image analysis on the image data information to generate the first guidance information; A second data sending module, configured to send the first guidance information to the client, so that the client performs data analysis on the first guidance information based on the data analysis model to obtain the second guidance information, and performs dynamic drug adjustment based on the second guidance information.

[0014] The fifth aspect of this application discloses an electronic device, which includes a processor and a memory. At least one instruction and at least one program segment are stored in the memory, and at least one instruction and at least one program segment are loaded and executed by the processor to implement the above-mentioned remote drug administration method based on real-time monitoring of drug administration by subjects and intelligent drug matching.

[0015] The sixth aspect of the present application discloses a computer storage medium storing at least one instruction and at least one program segment. The at least one instruction and the at least one program segment are loaded and executed by a processor to implement the remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching as described above.

[0016] Compared with the prior art, the present application has the following advantages: The remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching provided by the present application collects image data information matching the detection requirements of the target user, and through the collaborative analysis of the management end and the local end, realizes the efficient and accurate identification and feedback of the user's drug administration status, and further realizes the remote adjustment of the drug use and dosage adjustment of the target user, and improves the convenience, real-time performance and efficiency of the adjustment. On the basis of the preliminary image analysis at the management end to generate the first guidance information, further combining the data analysis model deployed locally at the client to deeply analyze the image information can avoid the leakage of user privacy during the data transmission process and improve the security of the drug use and dosage adjustment of the target user. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is the system architecture diagram corresponding to the remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching provided by the embodiment of the present application; Figure 2 is the flowchart corresponding to a remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching provided by the embodiment of the present application; Figure 3 is the flowchart corresponding to another remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching provided by the embodiment of the present application; Figure 4 is the structural diagram corresponding to a remote drug administration device based on real-time monitoring of drug administration to a subject and intelligent drug matching provided by the embodiment of the present application; Figure 5 is the structural diagram corresponding to another remote drug administration device based on real-time monitoring of drug administration to a subject and intelligent drug matching provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Next, the technical solutions in the embodiments of the present specification will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present specification. Obviously, the described embodiments are only a part of the embodiments of the present specification, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present specification without creative efforts shall fall within the protection scope of the present application.

[0019] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0020] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the drawings. The same reference numerals in the drawings denote elements having the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings do not have to be drawn to scale unless otherwise specified.

[0021] The special term "exemplary" here means "serving as an example, embodiment or illustrative". Any embodiment described as "exemplary" here does not have to be construed as superior to or better than other embodiments.

[0022] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. These three situations. In addition, the term "at least one" in this article means any one of a plurality or any combination of at least two of a plurality. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0023] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. Those skilled in the art should understand that the present disclosure can also be implemented without certain specific details. In some instances, methods, means, elements and circuits well known to those skilled in the art are not described in detail in order to highlight the gist of the present disclosure.

[0024] Figure 1 It is the system architecture diagram corresponding to the remote drug administration method based on real-time monitoring of drug administration to subjects and intelligent drug matching provided by the embodiments of this application. The remote drug administration method based on real-time monitoring of drug administration to subjects and intelligent drug matching disclosed in this application can be applied to the multi-terminal interaction process. Specifically, such as Figure 1As shown, it can include a management terminal and multiple client terminals. The management terminal is used to record and store image data information, and to track and record the entire onset and medication process of a single patient in real time, so as to facilitate remote guidance and summary of cases and form first guidance information. The first guidance information is used to guide the client terminal to retake pictures of the local monitoring area of the target object using LED light sources of different frequency bands to obtain more accurate original data.

[0025] Among them, the management terminal can adopt a star-like hierarchical structure, that is, coordinated by a central management terminal, and the remaining management terminals participate in data exchange as slave nodes. The specific network topology is determined according to the actual deployment environment. Since the management terminal adopts a star-like hierarchical structure, the disease course tracking chain needs to ensure data consistency in each slave management terminal.

[0026] The client terminal can be an application program installed on a mobile terminal or a multi-spectral light source acquisition terminal. The multi-spectral light source acquisition terminal includes a multi-spectral LED light source array and a communication unit. The multi-spectral LED light source array is used to provide different LED light sources during the image data information acquisition process. The communication unit supports wired or wireless transmission protocols, is used to communicate with the management terminal, process the received data, and feedback second guidance information to the target user.

[0027] Among them, the multi-spectral LED light source array can include: white light LED, red light LED, blue light LED, etc.; the multi-spectral LED light source array is arranged in a matrix. Each LED unit can be independently regulated to ensure optimized imaging details in different bands. The light intensity value of the LED is set according to specific detection requirements. For example: the white light LED uses the D65 standard (daylight standard) to simulate natural light at a color temperature of 6500K, and the brightness is controlled at 500–1500 lm / m²; for the ultraviolet LED (365~405nm), to ensure radiation safety, its output power should be strictly controlled. Currently, the industry standard recommends that the ultraviolet radiation does not exceed 15 µW / cm² to ensure human safety.

[0028] In the embodiment of the present application, the collection area corresponding to the target detection requirement of the target user is taken as the scalp as an example for illustration. Specifically, the white light LED simulates standard sunlight to ensure the overall brightness and color restoration of the image, facilitating subsequent algorithms to distinguish the color boundary between the scalp and the hair; the red light LED (620 - 750nm) is used to contrast the bleeding phenomenon between the scalp and the hair base; the blue light LED (450 - 495nm) can enhance the surface details and is suitable for distinguishing the exposed part of the scalp from the covered hair strands; the green light LED (500 - 570nm) is extremely sensitive to the detection of the fiber structure, color, and diameter of the hair, and is used to achieve precise detection of the boundary between the hair and the scalp and the hair density; the ultraviolet LED (365 - 405nm) is used to enhance the imaging of the hair surface, cutin layer, and fine cracks (such as hair scales) in the low-power state; the near-infrared LED is for monitoring the hair follicles and microcirculation under the scalp. The near-infrared light has strong penetration ability and is sensitive to the spectral response of the internal tissues of the hair.

[0029] In this embodiment, a dual-band near-infrared design can be adopted. The short wavelength band (750 - 850nm) is suitable for detecting the structures under the scalp; the long wavelength band (850 - 950nm) can perform penetration imaging on the inside of the hair fibers to distinguish the connection part between the hair shaft and the hair follicle.

[0030] Figure 2 It is a schematic flow chart corresponding to a remote drug administration method based on real-time monitoring of drug administration to subjects and intelligent drug matching provided by the embodiment of the present application. The execution entity is the client, such as Figure 2 As shown, the remote drug administration method based on real-time monitoring of drug administration to subjects and intelligent drug matching includes: Step S201: Collect image data information that matches the target detection requirement corresponding to the target user.

[0031] Specifically, the target detection requirement can be related to the disease of the target user, and the physiological change indicators that can be detected and the corresponding detection areas. In this embodiment, taking the detection area in the target detection requirement as the scalp area of the target user as an example for illustration, the physiological change indicators that can be detected may include the density of hair follicle openings, the arrangement state of hair scales, the contour of hair follicle entrances, etc.

[0032] The image data information can include multiple detection images collected based on the client, or can also be video images, etc. The multiple detection images can correspond to different detection areas. In this embodiment, the client selects a multi-spectral light source acquisition terminal including white light LEDs, red light LEDs, and blue light LEDs, etc.

[0033] Step S202: Send the image data information to the management end so that the management end performs image analysis on the image data information to generate the first guidance information.

[0034] In some embodiments, the client sends the collected image data information to the management end through the communication unit, so that after receiving the image data information, the management end performs image analysis and generates the first guidance information. The first guidance information is used to characterize that there are images to be retaken in multiple detected images, including the retake parameter information and the retake area information corresponding to the images to be retaken.

[0035] Specifically, for multiple detected images in the image data information, there may be situations such as low acquisition accuracy or deviation in the acquisition area, resulting in the detected images being unable to accurately reflect the true physiological state of the target user. Therefore, image analysis can be performed on multiple detected images respectively to generate the first guidance information, so as to determine which areas in the detected images need to be retaken.

[0036] Step S203: Receive the first guidance information fed back by the management end, and perform data analysis on the image data information based on the data analysis model and the first guidance information to obtain the second guidance information.

[0037] In some embodiments, since there is a certain risk of data leakage during the data interaction between the management end and the client, the first guidance information generated by the management end cannot directly indicate how to dynamically adjust the use of drugs. Instead, at the client, the first guidance information and the image data information are combined, and the data analysis model is used to process them to obtain the second guidance information. The second guidance information is used to dynamically adjust the drugs, and may include, for example, drug selection information and dosage adjustment information.

[0038] In a specific embodiment, since the calculation logics corresponding to the first guidance information and the second guidance information are different, the first guidance information may not correspond to the second guidance information, resulting in errors in the dynamic allocation of drugs. To solve this problem, that is, to improve the accuracy of generating the second guidance information, the following method can be adopted: That is, receive the first guidance information fed back by the management end, and perform data analysis on the image data information based on the data analysis model and the first guidance information to obtain the second guidance information, including: Construct a first directed graph corresponding to the data analysis model; each calculation unit in the data analysis model corresponds to a node in the first directed graph; Split the first directed graph into a first part and a second part; The management end performs data analysis on the first guidance information based on the first part of the data analysis model to obtain the third data information; and encrypts and transmits it to the client; The client performs data analysis on the third data information based on the second part of the data analysis model to obtain the second guidance information.

[0039] Since the data analysis model needs to capture both temporal features and spatial features, in some embodiments, the data analysis model may select a ConvLSTM network. Since the ConvLSTM network is an existing algorithm, the core idea of which will not be elaborated in detail in this invention. In addition, it should be understood that the first directed graph is essentially the data analysis model itself. It can be understood that the data analysis model is essentially a string of code, and the process of drawing its internal computing units (equivalent to nodes) and their connection relationships (equivalent to edges) into the first directed graph is the construction process.

[0040] It can be understood that the third data information is essentially the set of data information of all output nodes in the first part. However, from the perspective of time series, the data information of different output nodes may produce inconsistent incentives for the second part, which may lead to the instability of the finally obtained second guidance information.

[0041] Based on this, in a specific embodiment, after the first directed graph is constructed, the loops in it are uniformly replaced with loop nodes to obtain an acyclic second directed graph. Suppose there are the following edges: {a1->a2; a2->a3; a3->a1; a4->a2; a3->a5}, replace {a1, a2, a3} with the loop node A1, and at the same time inherit its connection relationship with other nodes, and transform it into {a4->A1; A1->a5}.

[0042] Taking the nodes corresponding to the original data as the source points, perform a depth-first search. It can be understood that since the original data is multi-dimensional data (equivalent to multiple source nodes), a virtual total source node can be set to point to these multiple source nodes, and then use this total source node as the source point.

[0043] Suppose the second directed graph contains n nodes in total. Then in the process of depth-first search, each node is visited exactly 2 times, and a corresponding access sequence is generated in order. In the access sequence, the numbers correspond to the node numbers, and their positions determine the access order, that is, the node access order.

[0044] Further, split the access sequence according to the access order of the link nodes to determine the first part and the second part. Specifically, it can be assumed that n = 11, and it is assumed that node 2, node 7, and node 9 are all link nodes, and the access sequence is [1, 2, 3, 3, 2, 1, 4, 5, 5, 4, 6, 7, 7, 8, 8, 6, 9, 10, 10, 11, 11, 9]. Then the nodes involved in the second part can be 3, 10, and 11. Among them, the link nodes can only be in the second part (for example: node 10 and node 11 are wrapped by link node 9; node 3 is wrapped by link node 2); the link nodes and other nodes can only be in the first part. The "wrapped" nodes can also only be in the first part.

[0045] Through the setting of the above technical features, using the third data information as an alternative transmission ensures data privacy.

[0046] Further, based on the first guidance information, the node access order, and the data analysis model, generate the second guidance information, including: Determine the target first guidance information from multiple first guidance information sent from the management end based on the node access order; Based on the retake parameter information and the retake area information included in the target first guidance information, collect and update the detection images; Based on the data analysis model, perform data analysis on the updated detection images and the remaining detection images to determine the second guidance information; the remaining detection images are the detection images other than the images to be retaken among the multiple detection images.

[0047] In a specific embodiment, first determine the target first guidance information according to the node access order to ensure the relevance between the second guidance information generated based on the first target guidance information.

[0048] Specifically, obtain the retake parameter information and the retake area information included in the target first guidance information, and then the client collects updated detection images based on the retake parameter information and the retake area information. In a multi-spectral retake, the system automatically identifies and quantifies the following image features: Hair follicle opening density: on average, less than 20 per cm² in the visible area; Ultraviolet-induced fluorescence: significantly thickened stratum corneum area under UV (365 nm), irregular arrangement of hair scales; Red light blood oozing sign: under red light of 620–750 nm, microvascular blood oozing signals appear in some areas; Blue light surface texture: under blue light of 450–495 nm, the depth of scalp surface fine lines increases, and the outline of hair follicle entrances becomes blurred; Near-infrared transmittance: in the short wavelength band of 750–850 nm, local microcirculation perfusion deficiency around hair follicles is shown.

[0049] When the above image features meet their corresponding requirements respectively, the updated detection image and the remaining detection images are input into the data analysis model to generate the second guidance information.

[0050] Based on the data analysis model, data analysis is performed on the updated detection image and the remaining detection images to determine the second guidance information, including: Generating a multi-channel sequence based on the image parameter information of the updated detection image and the remaining detection images; Based on the multi-channel sequence and the data analysis model, extracting the spatial feature information and temporal feature information corresponding to the target detection requirements; Performing feature fusion based on the spatial feature information and the temporal feature information to obtain the feature fusion information; there is a mapping relationship between the feature fusion information and the drug candidate data set; Determining the second guidance information based on the feature fusion information and the drug candidate data set.

[0051] In a specific embodiment, the image parameter information may include the image acquisition time. According to the acquisition time of each detection image, the detection images in different bands (such as white light, red light, blue light, green light, near-infrared, etc.) are integrated into a multi-channel sequence.

[0052] According to the order in the multi-channel sequence, each frame of the detection image is filtered and downsampled using a convolutional layer to extract the spatial feature information of the hair and the scalp. Among them, the spatial feature information includes spatial texture information and structural feature information. And, the spatial feature information is input into the temporal network unit in the data analysis model to extract its temporal feature information. Among them, the temporal feature information characterizes the dynamic changes of the scalp conditions at different time points.

[0053] Performing feature fusion based on the spatial feature information and the temporal feature information, mapping through a fully connected layer to the drug candidate data set to generate the feature fusion information. And outputting the optimal drug and its dosage recommendation as the second guidance information through a regression layer.

[0054] In a specific embodiment, in the multi-channel sequence, preprocessing can be performed on each detection image. For example, by normalizing the image pixel values to the range of [0, 1] or [-1, 1] through normalization processing to accelerate network training and improve numerical stability, or by data augmentation processing to enhance the generalization ability of the model, and organizing the processed detection images into multi-channel inputs according to different bands, such as white light, red light, blue light, etc. channels.

[0055] Further, each frame of the image is input into a convolutional layer, which contains multiple convolutional kernels. Each convolutional kernel slides on the image for convolutional operations. Among them, convolutional kernels with sizes such as 3×3 and 5×5 can be selected, and the convolutional stride is set to determine the stride of the convolutional kernel sliding on the image. Smaller convolutional kernels can capture finer local features, while larger convolutional kernels can capture more extensive context information.

[0056] The spatial feature information obtained through spatial feature extraction is input into a temporal network unit. The temporal network unit can capture the temporal dependencies in the sequence data and memorize long-term information, so as to capture the detection change states at different time points. The temporal feature information output by the temporal feature unit is fused with the corresponding spatial feature information. Usually, a Concatenate (concatenation) operation is adopted to concatenate the two in the channel dimension to generate a fused feature representation, that is, fused feature information.

[0057] The fused feature information output by the fully connected layer can generate the optimal drug and the corresponding dosage recommendation through a Softmax layer or a regression layer. The Softmax layer can convert the output of the fully connected layer into a probability distribution, indicating the probabilities of different drugs being selected. The drug with the highest selection probability is selected as the recommended drug. The regression layer can directly output the continuous value of the drug dosage, which is applicable to the situation where the drug dosage needs to be precisely controlled.

[0058] Step S204: Perform dynamic drug adjustment based on the second guidance information.

[0059] In some embodiments, after generating the second guidance information, the types of drugs used by the target user, the drug usage amount, etc. can be adjusted according to the second guidance information to improve the timeliness and accuracy of drug adjustment.

[0060] The method further includes: Obtain standard drug allocation information; Based on the standard drug allocation information and the second guidance information, correct the data analysis model.

[0061] In some embodiments, when the drug allocation is adjusted according to the second guidance information, the data analysis model can also be corrected by combining the standard drug allocation information provided by medical staff and the second guidance information, which can adjust the parameters of the data analysis model to improve the accuracy of the data analysis model, thereby improving the accuracy of dynamic drug adjustment.

[0062] Figure 3 It is a schematic flowchart corresponding to another remote drug administration method based on real-time monitoring of subject drug administration and intelligent drug matching provided by an embodiment of the present application. The execution entity is the management end, such as Figure 3As described above, the remote drug administration method based on real-time monitoring of drug administration to subjects and intelligent drug matching includes: Step S301: Receive the image data information collected by the client; Step S302: Perform image analysis on the image data information to generate the first guidance information; Each detection image corresponds to analysis index data matching the target detection requirements; Performing image analysis on the image data information to generate the first guidance information includes: Based on the analysis index data, perform image analysis on the image data information to obtain an image analysis result; In the case that among the multiple detection images indicated by the image analysis result, there is at least one detection image whose corresponding analysis index data does not meet the preset analysis conditions, determine at least one detection image as the image to be detected; Take the retake parameter information and retake area information corresponding to the image to be detected as the first guidance information.

[0063] Step S303: Send the first guidance information to the client so that the client performs data analysis on the first guidance information based on the data analysis model to obtain the second guidance information, and perform dynamic drug adjustment based on the second guidance information.

[0064] In some embodiments, data communication can be achieved between the management end and the client to transmit the image data information and the first guidance information.

[0065] Taking the detection image included in the image data information as a scalp image as an example, perform image index analysis on the detection image to determine whether the detection image meets the accuracy requirements, position requirements, etc. for subsequent data processing. Specifically, different target detection requirements can correspond to different analysis index data. The preset analysis conditions can be set according to different analysis index data. For example, when it is necessary to adjust the detection area, the preset analysis condition can be the position information corresponding to the preset detection area. When it is necessary to adjust the LED light intensity parameter during the detection process, the preset analysis condition can be the light intensity range.

[0066] In some embodiments, the first guidance data can correspond to different parameters in different cases. For example: For alopecia areata cases, it is recommended to locally increase the blue light output (adjust the blue light brightness to about 350 lm / m²) to enhance the local texture of the scalp and hair follicle details. For diffuse alopecia cases, it is recommended to appropriately reduce the ultraviolet LED output and enhance the red LED (adjust the red light output to a medium brightness level) to avoid local high reflection interference. In addition, the specific parameter settings of each LED should also be detailed in the guidance data information. For example: It is recommended to increase the green LED light intensity by 10%-20% for the hair sparse area to more clearly collect hair details.

[0067] In summary, in the present application, the provided remote drug administration method based on real-time monitoring of subject drug administration and intelligent drug matching collects image data information that matches the detection requirements of the target user, and through the collaborative analysis of the management end and the local end, realizes the efficient and accurate identification and feedback of the user's drug administration status, and further realizes the remote adjustment of the drug use and dosage adjustment of the target user, and improves the convenience, real-time performance and efficiency of the adjustment. On the basis of generating the first guidance information through preliminary image analysis on the management end, further combining the data analysis model deployed locally on the client side to deeply analyze the image information can avoid the leakage of user privacy during the data transmission process and improve the security of the drug use and dosage adjustment of the target user.

[0068] The embodiment of the present application also provides a remote drug administration device based on real-time monitoring of subject drug administration and intelligent drug matching, as Figure 4 described, the device includes: A data acquisition module 410, configured to acquire image data information that matches the target detection requirements corresponding to the target user; A first data sending module 420, configured to send the image data information to the management end so that the management end performs image analysis on the image data information to generate the first guidance information; A first data receiving module 430, configured to receive the first guidance information fed back by the management end, and perform data analysis on the image data information based on the data analysis model and the first guidance information to obtain the second guidance information; A drug selection module 440, configured to perform dynamic drug adjustment based on the second guidance information.

[0069] In some possible embodiments, the first data receiving module 430 further includes: A first directed graph construction module, configured to construct a first directed graph corresponding to the data analysis model; wherein, each calculation unit in the data analysis model corresponds to a node in the first directed graph; A second directed graph construction module, configured to perform link node replacement on the first directed graph to obtain a second directed graph; An order determination module, configured to perform a depth search with the node corresponding to the image data information in the second directed graph as the source point to determine the node access order; A first information generation module, configured to generate the second guidance information based on the first guidance information, the node access order, and the data analysis model.

[0070] In some possible embodiments, the first information generation module further includes: An information determination module, configured to determine the target first guidance information from multiple first guidance information sent by the management end based on the node access order; An image update module, configured to collect updated detection images based on the reshooting parameter information and reshooting area information included in the target first guidance information; A second information generation module, configured to perform data analysis on the updated detection images and the remaining detection images based on a data analysis model to determine second guidance information; the remaining detection images are the detection images other than the to-be-reshot images among the multiple detection images.

[0071] In some possible embodiments, the second information generation module further includes: A sequence construction module, configured to generate a multi-channel sequence based on the image parameter information of the updated detection images and the remaining detection images; A feature extraction module, configured to extract spatial feature information and temporal feature information corresponding to the target detection requirements based on the multi-channel sequence and the data analysis model; A feature fusion module, configured to perform feature fusion based on the spatial feature information and the temporal feature information to obtain feature fusion information; there is a mapping relationship between the feature fusion information and the drug candidate data set; A third information generation module, configured to determine the second guidance information based on the feature fusion information and the drug candidate data set.

[0072] In some embodiments, the apparatus further includes: An allocation information acquisition module, configured to acquire standard drug allocation information; A model correction module, configured to correct the data analysis model based on the standard drug allocation information and the second guidance information.

[0073] An embodiment of the present application further provides another remote drug administration device for real-time monitoring of drug administration to a subject and intelligent drug matching, as Figure 5 shown, including: A second data receiving module 510, configured to receive image data information collected by a client; An image analysis module 520, configured to perform image analysis on the image data information to generate first guidance information; A second data sending module 530, configured to send the first guidance information to the client, so that the client performs data analysis on the first guidance information based on a data analysis model to obtain second guidance information, and performs dynamic drug adjustment based on the second guidance information.

[0074] In some embodiments, the image analysis module 520 further includes: An index analysis module, configured to perform image analysis on the image data information based on analysis index data to obtain an image analysis result; An image determination module, configured to determine at least one detected image as an image to be detected when the image analysis result indicates that, among multiple detected images, there is at least one piece of analysis index data corresponding to a detected image that does not meet a preset analysis condition; A fourth information generation module, configured to use the reshooting parameter information and reshooting area information corresponding to the image to be detected as first guidance information.

[0075] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0076] An embodiment of the present application further provides an electronic device, including: a processor and a memory. The memory stores at least one instruction, at least one segment of program, a code set or an instruction set. The at least one instruction, at least one segment of program, the code set or the instruction set is loaded and executed by the processor to implement the method according to any one of the method embodiments.

[0077] An embodiment of the present application further provides a storage medium. A computer-readable storage medium may be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium may be an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: 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), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punched card or raised structures in a groove storing instructions thereon, and any suitable combination of the above. The computer-readable storage medium used herein is not construed as an instantaneous signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0078] The computer-readable program instructions described herein can be downloaded from the computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device through a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. A network adapter or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0079] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or, alternatively, may be connected to an external computer (e.g., via an Internet service provider through the Internet). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0080] Aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer - readable program instructions.

[0081] These computer - readable program instructions can be provided to a processor of a general - purpose computer, a special - purpose computer, or other programmable data - processing apparatus to produce a machine such that the instructions, when executed by the processor of the computer or other programmable data - processing apparatus, result in an apparatus that implements the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, which causes a computer, a programmable data - processing apparatus, and / or other devices to operate in a particular manner, so that the computer - readable medium storing the instructions includes a manufacture, which includes instructions for implementing various aspects of the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0082] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices, causing a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other devices to generate a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other devices implement the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0083] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific implementation manners of the present application, and any modification or equivalent replacement that does not depart from the spirit and scope of the present application should be covered by the protection scope of the claims of the present application.

Claims

1. A remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching, characterized in that, The method includes: Collecting image data information that matches the target detection requirements corresponding to the target user; Sending the image data information to the management end so that the management end performs image analysis on the image data information to generate first guidance information; Receiving the first guidance information fed back by the management end and performing data analysis on the image data information based on the data analysis model and the first guidance information to obtain second guidance information; Performing dynamic drug adjustment based on the second guidance information.

2. The remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching according to claim 1, wherein The step of receiving the first guidance information fed back by the management end and performing data analysis on the image data information based on the data analysis model and the first guidance information to obtain second guidance information includes: Constructing a first directed graph corresponding to the data analysis model; wherein each calculation unit in the data analysis model corresponds to a node in the first directed graph; Splitting the first directed graph into a first part and a second part; The management end performs data analysis on the first guidance information based on the first part of the data analysis model to obtain third data information; and encrypts and transmits it to the client; The client performs data analysis on the third data information based on the second part of the data analysis model to obtain second guidance information.

3. The remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching according to claim 2, wherein The image data information includes multiple detection images corresponding to multiple detection regions respectively, and the first guidance information is used to indicate that there are images to be retaken in the multiple detection images, including retake parameter information and retake region information corresponding to the images to be retaken; The step of generating the second guidance information based on the first guidance information, the node access order, and the data analysis model includes: Determining a target first guidance information from multiple pieces of the first guidance information sent by the management end based on the node access order; Collecting updated detection images based on the retake parameter information and the retake region information included in the target first guidance information; Based on the data analysis model, performing data analysis on the updated detection images and the remaining detection images to determine the second guidance information; the remaining detection images are the detection images other than the images to be retaken in the multiple detection images.

4. The remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching according to claim 3, characterized in that, The step of performing data analysis on the updated detection images and the remaining detection images based on the data analysis model to determine the second guidance information includes: Generating a multi-channel sequence based on the image parameter information of the updated detection images and the remaining detection images; Extracting spatial feature information and temporal feature information corresponding to the target detection requirements based on the multi-channel sequence and the data analysis model; Performing feature fusion based on the spatial feature information and the temporal feature information to obtain feature fusion information; the feature fusion information has a mapping relationship with the drug candidate dataset; Determining the second guidance information based on the feature fusion information and the drug candidate dataset.

5. The remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching according to claim 1, characterized in that, The method further includes: Obtaining standard drug allocation information; Correcting the data analysis model based on the standard drug allocation information and the second guidance information.

6. A remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching, characterized in that, The method includes: Receiving the image data information collected by the client; Perform image analysis on the image data information to generate first guidance information; Send the first guidance information to the client, so that the client performs data analysis on the first guidance information based on a data analysis model to obtain second guidance information, and performs dynamic adjustment of the drug based on the second guidance information.

7. The remote drug administration method based on real-time monitoring of drug administration to a subject and intelligent drug matching according to claim 6, wherein, The image data information is multiple detection images, and each detection image corresponds to analysis index data matching the target detection requirement; The performing image analysis on the image data information to generate first guidance information includes: Perform image analysis on the image data information based on the analysis index data to obtain an image analysis result; When the image analysis result indicates that among the multiple detection images, there is at least one detection image corresponding to the analysis index data that does not meet the preset analysis condition, determine the at least one detection image as the image to be detected; Use the reshooting parameter information and reshooting area information corresponding to the image to be detected as the first guidance information.

8. A remote drug administration device based on real-time monitoring of drug administration to a subject and intelligent drug matching, characterized in that, The device includes: A data acquisition module, configured to acquire image data information matching the target detection requirement corresponding to the target user; A first data sending module, configured to send the image data information to the management end, so that the management end performs image analysis on the image data information to generate first guidance information; A first data receiving module, configured to receive the first guidance information fed back by the management end, and perform data analysis on the image data information based on a data analysis model and the first guidance information to obtain second guidance information; A drug selection module, configured to perform dynamic adjustment of the drug based on the second guidance information.

9. A remote drug administration device based on real-time monitoring of drug administration to a subject and intelligent drug matching, characterized in that, The device includes: A second data receiving module, configured to receive the image data information collected by the client; An image analysis module, configured to perform image analysis on the image data information to generate first guidance information; A second data sending module, configured to send the first guidance information to the client, so that the client performs data analysis on the first guidance information based on a data analysis model to obtain second guidance information, and performs dynamic adjustment of the drug based on the second guidance information.

10. An electronic device, the device includes a processor and a memory, and at least one instruction and at least one program segment are stored in the memory, and the at least one instruction and the at least one program segment are loaded and executed by the processor to implement the remote drug administration method based on real-time monitoring of drug administration to subjects and intelligent drug matching as described in any one of claims 1-7.

Images