Method and system for monitoring data processing for contraceptive devices

Abstract

This invention provides a data processing method for monitoring contraceptive devices, comprising the following steps: acquiring routine symptom data uploaded by a user, and extracting vocabulary from the routine symptom descriptions included in the routine symptom data to obtain feature words; extracting regions from the routine symptom images included in the routine symptom data based on the feature words, and determining routine diagnostic data corresponding to the obtained routine symptom regions based on routine diagnostics, and uploading the routine symptom data and routine diagnostic data to the routine display area of ​​the contraceptive monitoring platform; responding to the user's interaction to create a private display area of ​​the contraceptive monitoring platform, creating an initial private image in the private display area, and updating the initial private image based on the user's adjustment interaction to obtain the current private image; determining the private diagnostic data corresponding to the current private image based on private diagnostics, and uploading the private diagnostic data to the private display area. This invention at least improves convenience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a monitoring data processing method and system for contraceptive devices. BACKGROUND

[0002] During contraception, the reproductive health management of women has special medical needs. According to the statistics of the World Health Organization, about 44% of married women in the world rely on modern contraceptive methods, of which more than 60% are hormone-based contraceptives (such as oral contraceptives, subcutaneous implants) and intrauterine devices (IUDs). However, abnormal symptoms (such as breakthrough bleeding, skin swelling, etc.) that may occur during contraception often indicate potential health risks, including endometritis, ovarian cysts, hormone imbalance, and other diseases.

[0003] At present, when the user has corresponding abnormal symptoms during contraception, the user usually needs to go to the medical institution for offline examination regularly, and the medical staff obtains the physiological symptom data during the use of the contraceptive device through visual observation and manual recording. This mode not only requires the user to spend a lot of time and transportation costs, and there are significant medical barriers for people in remote areas or with limited mobility; in addition, the mechanism for protecting the privacy of the user may also have corresponding deficiencies. Paper medical records face the risk of information leakage during data storage and transmission, and once sensitive data related to reproductive health are leaked, it may have a serious psychological and social impact on the user. SUMMARY

[0004] Based on the above problems, the present application is proposed in order to provide a monitoring data processing method and system for contraceptive devices which overcomes the above problems or at least partially solves the above problems.

[0005] According to one aspect of the present application, a monitoring data processing method for contraceptive devices is provided, comprising the following steps:

[0006] Obtaining normal symptom data uploaded by a user terminal, and performing vocabulary extraction on normal symptom descriptions included in the normal symptom data to obtain feature vocabulary;

[0007] Performing region extraction on normal symptom images included in the normal symptom data based on the feature vocabulary, and determining normal diagnosis data corresponding to the obtained normal symptom regions based on normalization diagnosis, and uploading the normal symptom data and the normal diagnosis data to a normal display area of a contraceptive monitoring platform;

[0008] In response to a user terminal creating interaction on a private display area of a contraceptive monitoring platform, an initial private graph is created in the private display area, and the initial private graph is updated based on adjustment interaction of the user terminal to obtain a current private graph;

[0009] Based on the privacy diagnosis, the privacy diagnosis data corresponding to the current privacy graph is determined, and the privacy diagnosis data is uploaded to the privacy display area.

[0010] Optionally, in the method according to the present invention, vocabulary extraction is performed on the descriptions of common symptoms included in the common symptom data to obtain feature vocabulary, including:

[0011] Obtain the number of horizontal characters in the horizontal arrangement direction corresponding to the description of common symptoms, and the number of vertical characters in the vertical arrangement direction corresponding to the description of common symptoms, and determine the arrangement direction with the larger number of characters as the character arrangement order;

[0012] The description of normal symptoms contains descriptive characters that indicate the meaning of segmentation. The description is segmented based on the character arrangement order to obtain each descriptive sub-segment.

[0013] Semantic recognition is performed on each descriptive character located in the same descriptive sub-paragraph, and the word attributes of each descriptive word are determined based on the comparison results between the obtained descriptive words and the retrieved preset feature table.

[0014] If any descriptive word has a swelling attribute, then that descriptive word is identified as a feature word of the corresponding descriptive sub-paragraph.

[0015] If any descriptive word has a purplish-color attribute, then that descriptive word is identified as a feature word of the corresponding descriptive sub-paragraph.

[0016] Optionally, in the method according to the present invention, region extraction is performed on the normal symptom images included in the normal symptom data based on feature vocabulary, and normal diagnostic data corresponding to the obtained normal symptom regions is determined based on normalized diagnosis, including:

[0017] The preset region extraction strategy corresponding to the word attributes is invoked to extract regions from the normal symptom images included in the normal symptom data, thus obtaining the normal symptom regions;

[0018] Based on the source information of the contraceptive device for the corresponding user, historical symptom descriptions are retrieved, and all historical symptom descriptions containing characteristic words are compared with the description sub-paragraphs.

[0019] If the similarity of a paragraph describing a historical symptom is greater than the preset similarity, it is identified as routine diagnostic data.

[0020] If the paragraph similarity of multiple historical symptom descriptions is greater than the preset similarity, the historical diagnostic data with the highest similarity to the corresponding paragraph and with a diagnostic relationship will be identified as the normal diagnostic data corresponding to the normal symptom area.

[0021] All paragraph similarities obtained from the response are less than or equal to the preset similarity. Historical symptom images with image-text relationships with historical symptom descriptions are retrieved, and normal diagnostic data are determined based on the similarity comparison between historical symptom images and normal symptom areas.

[0022] Optionally, in the method according to the present invention, a preset region extraction strategy corresponding to the word attributes is invoked to extract regions from the normal symptom images included in the normal symptom data, thereby obtaining normal symptom regions, including:

[0023] The response word attribute is swelling attribute. The mean value of each image pixel located at the edge of the normal symptom image is calculated, and the obtained pixel mean value is used as the center value of the interval to establish the first normal interval.

[0024] Any image pixel located inside the normal symptom image that is outside the first normal range is identified as a swollen pixel.

[0025] Connect all swollen pixels with adjacent points to obtain the first connected region;

[0026] If the size of the responding connected region is larger than the preset swelling size, the connected region is defined as the normal symptom region of the corresponding swelling attribute.

[0027] Optionally, in the method according to the present invention, a preset region extraction strategy corresponding to the word attributes is invoked to extract regions from the normal symptom images included in the normal symptom data, thereby obtaining normal symptom regions, including:

[0028] The response word attribute is the bruise attribute. The mean value of each image pixel located at the edge of the normal symptom image is calculated, and the obtained pixel mean value is used as the center value of the interval to establish a second normal interval.

[0029] Any image pixel located inside the normal symptom image that corresponds to a location outside the second normal range is identified as a bruised pixel.

[0030] Based on the coordinate processing of the normal symptom image, the coordinate points of each bruised pixel are obtained, and vertical region lines extending along the Y-axis and corresponding horizontal region lines extending along the X-axis are generated.

[0031] Based on vertical and horizontal area lines, corresponding bruise-like symptom areas are formed.

[0032] Optionally, in the method according to the invention, determining routine diagnostic data based on a similarity comparison between historical symptom images and routine symptom areas includes:

[0033] Identify historical symptom regions in historical symptom images that have the same word attributes as normal symptom regions, and compare the historical symptom regions with normal symptom regions for similarity.

[0034] The obtained region similarity and paragraph similarity of the corresponding historical symptom images are multiplied by the retrieved region weight value and paragraph weight value, respectively. The obtained first confidence value and second confidence value are then summed to obtain the comprehensive confidence value of the corresponding historical symptom images.

[0035] Historical diagnostic data that has a diagnostic relationship with the historical symptom image with the highest corresponding comprehensive confidence value are identified as normal diagnostic data corresponding to the normal symptom area.

[0036] Optionally, in the method according to the present invention, responding to a user's interaction with the creation of a private display area of ​​the contraceptive monitoring platform, creating an initial private image in the private display area, and updating the initial private image based on the user's adjustment interaction to obtain the current private image, includes:

[0037] In response to user interaction with the creation of a private display area on the contraceptive monitoring platform, an initial private image is created in the private display area, which includes a static blood display area and a dynamic blood display area filled with a human body model.

[0038] In response to user interaction to adjust the static blood display area, the standard blood pixel values ​​of the corresponding static blood display area are changed, and the static blood display area is filled with pixels based on the obtained current blood pixel values;

[0039] In response to user interaction with adjustments to the dynamic blood display area, the system locates the genital area within the human body model and adjusts the shape of the dynamic blood flow elements anchored to the genital area.

[0040] Optionally, in the method according to the present invention, responding to a user's interaction to adjust the static blood display area, changing the standard blood pixel values ​​corresponding to the static blood display area, and filling the static blood display area with pixels based on the obtained current blood pixel values, includes:

[0041] The standard blood pixel values ​​are retrieved to fill the static blood display area with pixels, and the static blood display area is divided into regions based on the regional center line of the corresponding static blood display area to obtain the change display area and the interactive display area.

[0042] In response to user interaction with the interactive display area, determine the vertical movement of the user toward the center line of the area based on the interaction, and determine the percentage of the interactive display area that the vertical movement corresponds to.

[0043] The interactive adjustment value is obtained by multiplying the moving percentage by the retrieved preset adjustment value.

[0044] The obtained interactive adjustment value is summed with the standard pixel value, and the changed display area is filled with pixels based on the obtained current blood pixel value.

[0045] Optionally, in the method according to the present invention, responding to user interaction to adjust the dynamic blood display area, locating the genital area included in the human body model, and morphologically adjusting the dynamic blood flow elements anchored to the genital area, includes:

[0046] A regional coordinate system corresponding to the blood dynamic display area is established with the center point of the human body model as the origin, and the coordinate points of each model that makes up the human body model are determined based on the regional coordinate system.

[0047] The coordinate points of each model that make up the outline of the private parts are determined as the private parts coordinate group, and a horizontal connecting line is established based on the model coordinate points with corresponding horizontal coordinate maxima and horizontal coordinate minima located in the private parts coordinate group.

[0048] Map the vertical and horizontal connecting lines to the area outline of the blood dynamic display area in the direction of the vertical and horizontal connecting lines, and form the element anchoring area based on the obtained mapped connecting lines and horizontal connecting lines;

[0049] The retrieved dynamic blood flow elements with the corresponding standard flow rate and standard quantity are anchored to the element anchoring area, and if the dynamic blood flow element overlaps with any model coordinate point, the model coordinate point is hidden.

[0050] In response to user interaction to adjust dynamic blood flow elements, the system makes numerical adjustments to the standard flow rate and / or standard quantity, and makes morphological adjustments to the dynamic blood flow elements based on the numerical adjustments.

[0051] According to another aspect of the present invention, a monitoring data processing system for contraceptive devices is provided, comprising:

[0052] The vocabulary extraction module is configured to acquire common symptom data uploaded by users and extract vocabulary from the common symptom descriptions included in the common symptom data to obtain feature vocabulary.

[0053] The routine diagnosis module is configured to extract regions from the routine symptom images included in the routine symptom data based on feature words, and determine the routine diagnosis data corresponding to the obtained routine symptom regions based on routine diagnosis, and upload the routine symptom data and routine diagnosis data to the routine display area of ​​the contraceptive monitoring platform.

[0054] The private area display module is configured to respond to user interaction with the private area display area of ​​the contraceptive monitoring platform, create an initial private image in the private area display area, and update the initial private image based on the user's adjustment interaction to obtain the current private image.

[0055] The privacy diagnostic module is configured to determine the privacy diagnostic data corresponding to the current privacy graph based on privacy diagnostics, and upload the privacy diagnostic data to the privacy display area.

[0056] According to the present invention, the intelligent online monitoring and dynamic display function effectively alleviates the burden on users who need to frequently visit medical institutions for offline examinations, greatly saving time and transportation costs. This is especially convenient for users in remote areas or those with mobility difficulties. At the same time, the present invention creates a digital health data recording method based on a contraceptive monitoring platform, replacing traditional paper medical records. This not only improves the efficiency of data storage and transmission but also significantly enhances the security of user privacy protection, effectively avoiding the risk of information leakage and thus reducing the psychological and social pressure that users may suffer due to data leakage.

[0057] Furthermore, this invention provides a corresponding interactive adjustment mechanism, enabling users to adjust the private display area in real time according to their own circumstances, thereby enhancing the accuracy and practicality of monitoring. Through intuitive display, medical personnel can understand the user's health status based on the normal display area and the private display area, promptly identifying and addressing potential health risks, thus improving the overall effectiveness of reproductive health management during contraception. Attached Figure Description

[0058] Figure 1 A flowchart of a monitoring data processing method for contraceptive devices according to an embodiment of the present invention is shown;

[0059] Figure 2 A schematic diagram of the normal display area and the private display area in this embodiment is shown;

[0060] Figure 3 A structural block diagram of a monitoring data processing system for contraceptive devices according to another embodiment of the present invention is shown. Detailed Implementation

[0061] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0062] To address the problems existing in the prior art, the inventors proposed the solution of this invention. One embodiment of this invention provides a method for processing monitoring data for contraceptive devices. This method can be executed in a computing device, wherein the computing device can be understood as a terminal with data processing capabilities, such as a mobile phone or a computer.

[0063] Figure 1 shows a flowchart of the monitoring data processing method for contraceptive devices according to this embodiment. Figure 1 As shown, the method begins with step S101, which includes the following:

[0064] Obtain common symptom data uploaded by users, and extract vocabulary from the common symptom descriptions included in the common symptom data to obtain feature vocabulary.

[0065] For example, in this embodiment, when a user uses a contraceptive device to perform contraceptive procedures, in order to determine whether the contraceptive device has any adverse effects on the user's body, medical personnel can create a corresponding contraceptive monitoring platform to periodically acquire the user's monitoring data based on a preset cycle. Here, the preset cycle can be specifically one day, that is, the user can determine whether their body has been adversely affected by the use of the contraceptive device through their own observation. If so, the user can use the corresponding user terminal to upload the data of the common symptoms of the corresponding adverse effects to the server, so that the server can further upload the data of the common symptoms to the contraceptive monitoring platform, so that medical personnel can make online diagnoses based on the data of the common symptoms.

[0066] Here, routine symptom data can include images of routine symptoms and descriptions of routine symptoms that provide supplementary explanations. After receiving the corresponding routine symptom data, the server can first perform corresponding vocabulary extraction based on the routine symptom description to obtain the feature words present in the routine symptom description, so as to quickly obtain the expression of adverse effects that the user wants to convey. It should be noted that routine symptom images can be obtained based on images of the user's own normal body parts, while routine symptom descriptions are textual descriptions of adverse effects provided by the user to make it easier for medical staff to understand the symptoms; for example, when a user's skin shows swelling or bruising, the user can generate a routine symptom description based on adverse effects such as swelling or bruising, and the corresponding feature words will include swelling or bruising, etc.

[0067] It should be noted that, in this embodiment, the user terminal can be understood as the terminal used by the user, such as a mobile phone or computer with data processing capabilities.

[0068] Furthermore, in this embodiment, the aforementioned "extracting vocabulary from the descriptions of common symptoms included in the common symptom data to obtain feature vocabulary" may further include the following steps:

[0069] Obtain the number of horizontal characters in the horizontal arrangement direction corresponding to the description of common symptoms, and the number of vertical characters in the vertical arrangement direction corresponding to the description of common symptoms, and determine the arrangement direction with the larger number of characters as the character arrangement order;

[0070] The description of normal symptoms contains descriptive characters that indicate the meaning of segmentation. The description is segmented based on the character arrangement order to obtain each descriptive sub-segment.

[0071] Semantic recognition is performed on each descriptive character located in the same descriptive sub-paragraph, and the word attributes of each descriptive word are determined based on the comparison results between the obtained descriptive words and the retrieved preset feature table.

[0072] If any descriptive word has a swelling attribute, then that descriptive word is identified as a feature word of the corresponding descriptive sub-paragraph.

[0073] If any descriptive word has a purplish-color attribute, then that descriptive word is identified as a feature word of the corresponding descriptive sub-paragraph.

[0074] For example, in this embodiment, the extraction of vocabulary for describing common symptoms can be achieved based on the following method steps:

[0075] After obtaining the descriptions of common symptoms uploaded by users, since each user may have different writing habits, it is first necessary to determine the corresponding writing order based on the obtained descriptions of common symptoms. For example, the server will calculate the number of horizontal characters in the horizontal direction and the number of vertical characters in the vertical direction corresponding to the description of common symptoms, and further compare these two numbers, determining the direction with more characters as the character arrangement order. For example, if a description of common symptoms is "persistent lower abdominal distension and pain, accompanied by slight bleeding", when the server recognizes that the number of horizontal characters is greater than the number of vertical characters, it determines that the horizontal arrangement of the description is dominant.

[0076] Next, the server can further respond to descriptive characters in the description of normal symptoms that indicate the meaning of the segmentation, such as periods, semicolons, or newlines, and segment the description based on the determined character arrangement order to obtain each descriptive sub-segment. Continuing with the above description as an example, the server can segment it into two descriptive sub-segments: "persistent lower abdominal distension and pain" and "accompanied by slight bleeding".

[0077] Then, the server can further perform semantic recognition on each descriptive character located in the same descriptive sub-paragraph. This step involves combining the descriptive characters into descriptive words and comparing these descriptive words with the words in the preset feature table to determine the word attributes of each descriptive word. It should be noted that the preset feature table is established based on medical professional knowledge and experience and contains a series of words and their attributes related to abnormal symptoms that may occur during the use of contraceptive devices, such as swelling and bruising. In the example above, the word "swelling pain" will be identified as having the attribute of swelling, while "bleeding" may be judged as a manifestation of the potential attribute of bruising due to the context (although "bleeding" itself is not directly equivalent to bruising, it may be considered as a manifestation or related symptom of bruising in this context).

[0078] Finally, the server can respond to any descriptive word with either a swelling attribute or a bruising attribute, and identify that descriptive word as a feature word of the corresponding descriptive sub-paragraph. In the example, "distending pain" is a feature word of the swelling attribute, and "bleeding" (in this context) is extracted as a feature word that may be related to bruising (or at least a noteworthy abnormal symptom word). These feature words have important reference value for subsequent image extraction and diagnosis of normal symptom areas, and can improve the diagnostic efficiency and accuracy of the corresponding online diagnosis.

[0079] Step S102 includes the following:

[0080] Based on feature words, regions of the routine symptom images included in the routine symptom data are extracted, and routine diagnostic data corresponding to the obtained routine symptom regions are determined based on routine diagnosis. The routine symptom data and routine diagnostic data are then uploaded to the routine display area of ​​the contraceptive monitoring platform.

[0081] For example, in this embodiment, after obtaining the feature words in the description of common symptoms, the server first calls up the corresponding preset region extraction strategy according to the symptom attributes (such as swelling, bruising, etc.) indicated by the feature words, and completes the region extraction of the common symptom image corresponding to the description of common symptoms based on the preset region extraction strategy. For example, continuing the above example, assuming that the feature word in the description of common symptoms is "distending pain", the server recognizes that the word has the swelling attribute, so it will call up the preset region extraction strategy for the swelling attribute.

[0082] Next, the server uses the retrieved region extraction strategy to analyze the normal symptom images, thereby locating the normal symptom regions corresponding to the feature words. This step may involve image processing techniques, such as edge detection and pixel value analysis, to determine which parts of the image match the features of attributes such as swelling or bruising.

[0083] Continuing with the example above, the server may analyze the distribution of pixel values ​​in an image to identify areas with a reddish hue and high brightness as potential bruising areas, and then determine the normal symptom areas corresponding to the feature words "bleeding".

[0084] Then, the server can further perform diagnostic analysis on the extracted normal symptom areas based on normal diagnostic logic;

[0085] Finally, the server uploads routine symptom data (including descriptions and images of routine symptoms) and routine diagnostic data to the routine display area of ​​the contraceptive monitoring platform. This allows users and healthcare professionals to view detailed routine symptom information and diagnostic results on the platform, facilitating subsequent health management and treatment decisions.

[0086] Through the above steps, this embodiment realizes intelligent analysis and diagnosis of routine symptom data, improving the efficiency and accuracy of women's reproductive health management during contraception.

[0087] It should be noted that, in this embodiment, to improve the display effect of corresponding routine diagnostic data and routine symptom data based on the routine display area, a periodic filling area and a data filling area can be generated in the routine display area. The periodic filling area is used to fill the corresponding current period, such as the third day, the fourth day, etc., and the corresponding data filling area can further include a routine symptom sub-area and a routine diagnosis sub-area. The routine symptom sub-area is used to fill routine symptom data, and the routine diagnosis sub-area can be used to fill routine diagnostic data. Here, "routine" can be understood as data with low privacy requirements, such as symptom data corresponding to limbs such as arms, legs, and face, while the subsequent mention of "private" can be understood as data with high privacy requirements, generally referring to symptom data corresponding to reproductive organs.

[0088] For example, Figure 2 A schematic diagram of the normal display area in this embodiment is shown. The normal display area includes six data filling areas, and the corresponding five data filling areas have been filled with data.

[0089] Furthermore, in this embodiment, the aforementioned "region extraction of routine symptom images included in routine symptom data based on feature words, and determination of routine diagnostic data corresponding to the obtained routine symptom regions based on routine diagnosis" may further include the following steps:

[0090] The preset region extraction strategy corresponding to the word attributes is invoked to extract regions from the normal symptom images included in the normal symptom data, thus obtaining the normal symptom regions;

[0091] Based on the source information of the contraceptive device for the corresponding user, historical symptom descriptions are retrieved, and all historical symptom descriptions containing characteristic words are compared with the description sub-paragraphs.

[0092] If the similarity of a paragraph describing a historical symptom is greater than the preset similarity, it is identified as routine diagnostic data.

[0093] If the paragraph similarity of multiple historical symptom descriptions is greater than the preset similarity, the historical diagnostic data with the highest similarity to the corresponding paragraph and with a diagnostic relationship will be identified as the normal diagnostic data corresponding to the normal symptom area.

[0094] All paragraph similarities obtained from the response are less than or equal to the preset similarity. Historical symptom images with image-text relationships with historical symptom descriptions are retrieved, and normal diagnostic data are determined based on the similarity comparison between historical symptom images and normal symptom areas.

[0095] For example, in this embodiment, based on the above, the feature words may include different word attributes, such as swelling and bruising. In order to quickly extract images of normal symptoms, different preset region extraction strategies can be pre-set based on different word attributes. After the extraction of the normal symptom region is completed, the determination of normal diagnostic data can be further achieved based on the following method steps:

[0096] First, the server can process the normal symptom image using a pre-set preset region extraction strategy. This strategy can be customized based on the word attributes (such as swelling attribute, bruising attribute, etc.) indicated by the feature words. Assuming the feature word is "swelling and pain" as mentioned above, the server will call up a preset extraction strategy specifically for identifying swelling areas. This strategy may be based on image processing technologies such as color analysis and shape recognition, and can accurately extract the area corresponding to "swelling and pain" from the normal symptom image, that is, the normal symptom area.

[0097] Next, the server can retrieve historical symptom descriptions related to the user from the database based on the traceability information of the user's contraceptive device (including the type, brand, and duration of use of the contraceptive device). Furthermore, it can compare the similarity of these historical symptom descriptions with the current description sub-paragraphs, paying particular attention to those historical descriptions that contain the characteristic word "swelling pain".

[0098] For example, in this embodiment, different types and brands of contraceptive devices may contain contraceptive drugs with different ingredients to help increase the contraceptive effect. The traceability information of the aforementioned contraceptive devices generally corresponds to the lesions caused by other users using the contraceptive device. In the process of obtaining traceability information, in order to determine whether the corresponding lesions are caused by the use of the contraceptive device, the following determination process can be used for verification:

[0099] The first step is to define the research objective. Researchers need to identify the suspected drug or drug class and the target adverse reaction (ADR) in the current study. When setting the research objective, specific time, location, manufacturer, batch number, and other information can be considered.

[0100] The second step is to select a database and generate an analysis dataset. Based on the research objectives, select variables relevant to those objectives and generate the analysis dataset. If adverse reaction risk factor analysis is required, suspected risk factors must be included. The stability of the signal largely depends on the quantity and quality of reports in the database.

[0101] The third step is to select a standard library. Drug names and adverse event names appearing in adverse event reports should be strictly cleaned and coded according to the generic drug name dictionary and the adverse drug event terminology set. Drug name dictionary databases mainly include the *Pharmacopoeia of the People's Republic of China*, the national *Classification and Code of Chemical Drugs (Raw Materials, Preparations)* drug coding standard, and the *Chinese Generic Drug Names*, or the World Health Organization's drug database (WHO-DRUG). Standardized adverse event names mainly include the WHO Adverse Reaction Terminology (WHO-ART), the International Conference on Harmonization of Technical Requirements for the Registration of Pharmaceuticals for Human Use (ICH)'s Medical Dictionary for Regulatory Activities (MedDRA), the coding symbols for thesaurus of adverse reaction terms (COSTART) adopted by the FDA, and the International Classification of Diseases (ICD).

[0102] The fourth step is data cleaning. This involves removing duplicate, excessively missing, or logically flawed data entries, and thoroughly cleaning the data according to the requirements of the statistical model.

[0103] The fifth step is to select the analysis method. Based on the research objective and data type, an appropriate signal detection method should be chosen. During data mining, the detection algorithm and judgment criteria need to be written into the analysis program, which will automatically calculate and determine whether the signal is valid.

[0104] Step 6: Signal Interpretation and Expert Evaluation. Analysts write an analysis report based on the data mining results, and experts, combining the mining results with the findings of specialized literature studies, decide whether further research is needed to examine whether a causal relationship truly exists between drug use and adverse drug events.

[0105] Here, the comparison process in this embodiment can specifically use text similarity algorithms, such as cosine similarity or Jaccard similarity, to calculate the similarity between the current descriptive sub-paragraph and the historical symptom description. If the paragraph similarity of a certain historical symptom description exceeds the preset similarity, it indicates that the disease corresponding to the historical symptom description may be the same as the disease corresponding to the normal symptom description. At this time, the server will regard it as a historical record that is highly matched with the current symptom and preliminarily determine that its corresponding historical diagnostic data may also be able to make a corresponding disease diagnosis for the normal symptom description. Therefore, it can be determined as the normal diagnostic data corresponding to the normal symptom description.

[0106] However, if multiple historical symptom descriptions have paragraph similarity exceeding the preset similarity, the server will prioritize the historical symptom description with the highest paragraph similarity to the current description sub-paragraph and retrieve the historical diagnostic data corresponding to that description in the database. These historical diagnostic data have been verified and are associated with highly similar historical symptom descriptions, and are therefore regarded as the normal diagnostic data that best matches the normal symptom area.

[0107] If the paragraph similarity of all historical symptom descriptions does not reach the preset threshold, the server retrieves historical symptom images that have a text-image relationship with these historical symptom descriptions and uses image similarity algorithms (such as SIFT, SURF and other feature matching methods) to compare the image similarity between the historical symptom images and the current normal symptom areas.

[0108] Ultimately, based on the results of image comparison, the server can determine the historical diagnostic data that most closely matches the current normal symptom area as the normal diagnostic data.

[0109] Through the above method, the present invention achieves intelligent and efficient diagnosis of common symptoms during the use of contraceptive devices, providing strong support for users' health management.

[0110] It should be noted that, based on the above, since the corresponding word attributes can include swelling and bruising attributes, different preset region extraction strategies can be used to extract the corresponding normal symptom regions for different word attributes. Therefore, in one implementation, when the word attribute is swelling, the aforementioned "calling the preset region extraction strategy corresponding to the word attribute to extract regions from the normal symptom images included in the normal symptom data to obtain the normal symptom region" can include the following steps:

[0111] The response word attribute is swelling attribute. The mean value of each image pixel located at the edge of the normal symptom image is calculated, and the obtained pixel mean value is used as the center value of the interval to establish the first normal interval.

[0112] Any image pixel located inside the normal symptom image that is outside the first normal range is identified as a swollen pixel.

[0113] Connect all swollen pixels with adjacent points to obtain the first connected region;

[0114] If the size of the responding connected region is larger than the preset swelling size, the connected region is defined as the normal symptom region of the corresponding swelling attribute.

[0115] For example, in this embodiment, region extraction is performed based on a preset region extraction strategy for word attributes corresponding to swelling attributes, which can be implemented specifically based on the following method steps:

[0116] First, assuming that the server has identified the feature word "swelling pain" in the previous steps and determined that its corresponding word attribute is swelling, the server can calculate the mean value of each image pixel located at the edge of the normal symptom image. It can be explained that this step aims to determine a baseline value for subsequent differentiation between normal skin areas and potential swollen areas. The calculated pixel mean value can further establish a first normal interval, which covers the possible range of normal skin pixel values ​​centered on the mean value.

[0117] Next, the server can check each image pixel located within the normal symptom image. If the pixel value of a certain pixel exceeds the range of the first normal range, it indicates that the image pixel has a large difference from the pixel value of the corresponding normal skin. At this time, the server will determine it as a swollen pixel, so as to effectively identify potential swollen areas by comparing the difference between the pixel value and the normal range.

[0118] Then, after completing the identification of all the corresponding swollen pixels, the server can connect the adjacent positions of all the identified swollen pixels to integrate the scattered swollen pixels into a continuous swollen region, namely the first connected region, so as to reflect the actual distribution of swollen symptoms in the normal symptom image.

[0119] Finally, the server can evaluate the size of the first connected region. If the size of the connected region exceeds the preset swelling size, the server will identify it as a normal symptom region of the corresponding swelling attribute, thereby improving the accuracy of identification of the region with the corresponding swelling attribute, improving the accuracy and reliability of diagnosis, and reducing the noise impact of other regions with smaller area sizes, such as pores, on the identification of this embodiment.

[0120] In another implementation, when the corresponding word attribute is a purplish-brown attribute, the aforementioned "retrieving the preset region extraction strategy corresponding to the word attribute to extract regions from the normal symptom images included in the normal symptom data, and obtaining the normal symptom region" can include the following steps:

[0121] The response word attribute is the bruise attribute. The mean value of each image pixel located at the edge of the normal symptom image is calculated, and the obtained pixel mean value is used as the center value of the interval to establish a second normal interval.

[0122] Any image pixel located inside the normal symptom image that corresponds to a location outside the second normal range is identified as a bruised pixel.

[0123] Based on the coordinate processing of the normal symptom image, the coordinate points of each bruised pixel are obtained, and vertical region lines extending along the Y-axis and corresponding horizontal region lines extending along the X-axis are generated.

[0124] Based on vertical and horizontal area lines, corresponding bruise-like symptom areas are formed.

[0125] For example, in this embodiment, region extraction is performed based on a preset region extraction strategy for the corresponding purplish-color attribute, which can be implemented using the following method steps:

[0126] First, assuming that the server has identified the feature word "bleeding" in the previous steps and determined that its corresponding word attribute is bruising, the server calculates the mean value of each image pixel located at the edge of the normal symptom image. Based on the obtained pixel mean value, a second normal interval is established. This interval aims to define the range of normal skin pixel values, providing a basis for the subsequent identification of bruising pixels. It should be noted that since the pixel change caused by swelling should be less than the pixel change caused by bruising, the numerical range of the second normal interval should be greater than the numerical range of the aforementioned first normal interval.

[0127] Next, the server checks each image pixel located within the normal symptom image. If the pixel value of a certain pixel exceeds the range of the second normal range, it is identified as a bruised pixel. By comparing the pixel value with the normal range, potential bruised areas can be effectively identified.

[0128] Then, the server needs to perform coordinate processing on the normal symptom image to obtain the coordinate points of each bruised pixel. Based on this, it further generates a vertical region line that corresponds to the extreme value of the horizontal coordinate (i.e., the extreme value point of the bruised region in the X-axis direction) and extends along the Y-axis, and a horizontal region line that corresponds to the extreme value of the vertical coordinate (i.e., the extreme value point of the bruised region in the Y-axis direction) and extends along the X-axis. Based on these two region lines, the boundary framework of the bruised region is formed together.

[0129] Finally, the server can form normal symptom areas corresponding to the bruising attributes based on the vertical and horizontal area lines, so as to reflect the actual distribution range of bruising symptoms in the normal symptom images based on the normal symptom areas, providing an important basis for subsequent diagnosis and treatment.

[0130] Furthermore, in this embodiment, the aforementioned "determining routine diagnostic data based on similarity comparison between historical symptom images and routine symptom areas" may further include the following steps:

[0131] Identify historical symptom regions in historical symptom images that have the same word attributes as normal symptom regions, and compare the historical symptom regions with normal symptom regions for similarity.

[0132] The obtained region similarity and paragraph similarity of the corresponding historical symptom images are multiplied by the retrieved region weight value and paragraph weight value, respectively. The obtained first confidence value and second confidence value are then summed to obtain the comprehensive confidence value of the corresponding historical symptom images.

[0133] Historical diagnostic data that has a diagnostic relationship with the historical symptom image with the highest corresponding comprehensive confidence value are identified as normal diagnostic data corresponding to the normal symptom area.

[0134] For example, in this embodiment, the acquisition of routine diagnostic data can be achieved based on the following method steps:

[0135] First, assuming that the server has identified the common symptom area in the previous steps and determined its corresponding word attributes (such as swelling or bruising), the server can then determine the historical symptom area with the same word attributes as the common symptom area from the historical symptom image data for comparison in subsequent processes.

[0136] Next, the server can compare each obtained historical symptom region with the normal symptom region one by one. For example, it can use image similarity algorithms, such as structural similarity (SSIM) or feature point matching, to quantify the degree of similarity between the two.

[0137] Then, for each historical symptom image, the server can multiply the obtained regional similarity with a preset regional weight value to obtain a first confidence value; at the same time, it can also multiply the paragraph similarity between the historical symptom image with the descriptive sub-paragraph and the preset paragraph weight value to obtain a second confidence value; and further, the obtained first confidence value and second confidence value are summed to obtain the comprehensive confidence value of the corresponding historical symptom image.

[0138] Finally, by comparing the overall confidence values ​​of all historical symptom images, the diagnostic data corresponding to the historical symptom image with the highest overall confidence value was determined as the normal diagnostic data corresponding to the normal symptom area, thus ensuring the accuracy and reliability of the diagnostic data and providing strong support for subsequent treatment.

[0139] Through the above method, the present invention realizes the intelligent diagnostic data determination of areas with normal symptoms, which not only improves the accuracy of diagnosis, but also significantly reduces the complexity and time cost of manual diagnosis. This method provides a more efficient and accurate solution for skin health monitoring and diagnosis during the use of contraceptive devices.

[0140] It should be noted that the routine diagnostic data obtained through this application is determined based on the server's comparison of historical symptom data and routine symptom data. Therefore, the actual diagnosis may differ in accuracy from the predicted routine diagnostic data. To address this, the contraceptive monitoring platform can grant medical personnel the right to modify the data. That is, if medical personnel determine, based on their own medical experience, that the routine diagnostic data filled in the routine display area is inaccurate, they can use the corresponding medical terminal to modify the routine diagnostic data at any time to ensure that users can accurately know their actual status and determine the subsequent diagnosis method.

[0141] It should be noted that, in this embodiment, the medical staff terminal can be understood as the terminal used by medical staff, such as a mobile phone or computer with data processing capabilities.

[0142] Step S103 includes the following:

[0143] The system responds to user interaction requests to create a private display area on the contraceptive monitoring platform. An initial private image is created in the private display area, and the initial private image is updated based on user interaction requests to obtain the current private image.

[0144] For example, in this embodiment, based on the above, for "normal" data, since its privacy requirements are low, it can be directly displayed in the normal display area of ​​the corresponding contraceptive monitoring platform based on the user's upload; while for "private" data, in order to ensure that users have a certain degree of privacy and to help relevant medical staff clearly obtain the relevant symptom descriptions, a corresponding private display area can be created on the contraceptive monitoring platform at the same time. This private display area is configured to create an initial private image based on the user's creation interaction, and then further update the initial private image according to the user's adjustment interaction to obtain the current private image displayed in the private display area.

[0145] Here, since the initial private image needs to be generated based on the user's creation interaction, when the initial private image is created, it can be expressed as the user's belief that their own private parts may have been adversely affected by the use of the corresponding contraceptive device. The user can also update the initial private image according to the specific circumstances of the adverse effects, so that the current private image can reflect the specific circumstances of the corresponding adverse effects as much as possible. This makes it easier for medical staff to make diagnoses based on the displayed private image, thereby improving the efficiency and accuracy of diagnosis.

[0146] It can be noted that, in this embodiment, since the generation of the current private image does not involve the image collection of the corresponding user's private parts, the user's privacy can be well determined, thereby preventing the occurrence of corresponding privacy leaks.

[0147] Furthermore, in this embodiment, the aforementioned "responding to the user's interaction with the creation of the private display area of ​​the contraceptive monitoring platform, creating an initial private image in the private display area, and updating the initial private image based on the user's adjustment interaction to obtain the current private image" may also include the following steps:

[0148] In response to user interaction with the creation of a private display area on the contraceptive monitoring platform, an initial private image is created in the private display area, which includes a static blood display area and a dynamic blood display area filled with a human body model.

[0149] In response to user interaction to adjust the static blood display area, the standard blood pixel values ​​of the corresponding static blood display area are changed, and the static blood display area is filled with pixels based on the obtained current blood pixel values;

[0150] In response to user interaction with adjustments to the dynamic blood display area, the system locates the genital area within the human body model and adjusts the shape of the dynamic blood flow elements anchored to the genital area.

[0151] For example, in this embodiment, the specific implementation of updating the initial private image based on user-side adjustment interactions is based on the following:

[0152] First, the server responds to the user's request to create an interactive private display area for the contraceptive monitoring platform. Within this area, an initial private image is automatically created, comprising two key regions: a static blood display area and a dynamic blood display area filled with a human body model. The static blood display area statically displays the user's standard blood status information, such as the blood color corresponding to the user's genital area. The dynamic blood display area, on the other hand, creates a human body model and dynamically simulates blood flow based on the genital area of ​​this model, helping the user to recreate, as accurately as possible, the blood flow corresponding to their genital area, such as flow rate and volume.

[0153] Next, the server can respond to the user's interaction with the static blood display area, allowing the user to adjust the standard blood pixel values ​​according to their needs, such as increasing or decreasing pixel brightness, contrast, or color saturation, to reflect their current blood condition. At the same time, the server receives these adjustment instructions in real time and fills the static blood display area with pixels based on the obtained current blood pixel values, thereby generating a personalized static display effect to represent the specific blood color of the bleeding situation in the user's private parts through the static blood display area.

[0154] Finally, the server can also synchronously respond to user interactions with adjustments made to the dynamic blood display area to accurately locate the genital area in the human body model, ensuring that the dynamic blood flow elements are accurately anchored to the genital area. Furthermore, users can select and adjust the shape of the dynamic blood flow elements through the interactive interface, such as changing the blood flow speed and density, to simulate different blood flow conditions. When it is determined that the blood flow in the corresponding human body model is roughly the same as the actual flow in the user's genital area, the dynamic blood flow elements anchored to the genital area are adjusted accordingly, thereby generating a dynamic display effect that is both realistic and personalized. This allows for the simultaneous display of different states and dimensions of blood conditions in the user's genital area based on both the static and dynamic blood display areas, enabling medical personnel to quickly obtain relevant information about the user.

[0155] It should be noted that, in this embodiment, the "standard blood pixel value" mentioned above can be understood as the corresponding pixel value of blood flowing out of the private parts in a healthy state, while the "human body model" mentioned above is a human-shaped model pre-created by the server. By creating corresponding dynamic blood flow elements, it can express that the user's private parts are in an abnormal bleeding state.

[0156] Furthermore, in this embodiment, the aforementioned "responding to the user's interaction to adjust the static blood display area, changing the standard blood pixel values ​​of the corresponding static blood display area, and filling the static blood display area with pixels based on the obtained current blood pixel values" may also include the following steps:

[0157] The standard blood pixel values ​​are retrieved to fill the static blood display area with pixels, and the static blood display area is divided into regions based on the regional center line of the corresponding static blood display area to obtain the change display area and the interactive display area.

[0158] In response to user interaction with the interactive display area, determine the vertical movement of the user toward the center line of the area based on the interaction, and determine the percentage of the interactive display area that the vertical movement corresponds to.

[0159] The interactive adjustment value is obtained by multiplying the moving percentage by the retrieved preset adjustment value.

[0160] The obtained interactive adjustment value is summed with the standard pixel value, and the changed display area is filled with pixels based on the obtained current blood pixel value.

[0161] For example, in this embodiment, the adjustment of the standard blood pixel value can be implemented based on the following method steps:

[0162] First, the server can retrieve standard blood pixel values ​​to fill the static blood display area with pixels, so as to present a healthy and standardized blood color status display. Furthermore, the server can divide the display area based on the center line of the corresponding static blood display area, thereby dividing the display area into two main parts: a variable display area and an interactive display area. The variable display area is used to dynamically reflect the changes in the standard blood pixel values, while the interactive display area allows users to make adjustments.

[0163] Next, the server responds to the user's adjustment interaction on the interactive display area to determine the vertical movement of the user toward the center line of the area based on the adjustment interaction. Based on this movement, the server can further calculate the movement percentage, that is, the proportion of the interactive display area moved relative to its original position by the user based on the adjustment interaction.

[0164] Then, the server can multiply the calculated movement ratio with the preset adjustment value to obtain the interactive adjustment value, and further sum the interactive adjustment value with the standard pixel value to obtain the current blood pixel value;

[0165] Finally, the server can fill the change display area with pixels based on this current blood pixel value, thereby updating the blood status of the display area in real time to reflect the user's personalized adjustment results. During the adjustment interaction, only the change display area will change pixels according to the obtained current blood pixel value, while the corresponding interactive display area will always maintain the corresponding color of the standard blood pixel value. This allows a corresponding visual contrast between the current blood pixel value and the standard blood pixel value, enabling users and medical staff to quickly determine the blood condition and improve ease of use.

[0166] Furthermore, after completing the corresponding process of adjusting the static blood display area based on the above content, the relevant introduction of adjusting the dynamic blood display area can be further provided. That is, in this embodiment, the above-mentioned "responding to the user's adjustment interaction of the dynamic blood display area, locating the private parts of the human body model, and adjusting the shape of the dynamic blood flow elements anchored to the private parts" can also include the following steps:

[0167] A regional coordinate system corresponding to the blood dynamic display area is established with the center point of the human body model as the origin, and the coordinate points of each model that makes up the human body model are determined based on the regional coordinate system.

[0168] The coordinate points of each model that make up the outline of the private parts are determined as the private parts coordinate group, and a horizontal connecting line is established based on the model coordinate points with corresponding horizontal coordinate maxima and horizontal coordinate minima located in the private parts coordinate group.

[0169] Map the vertical and horizontal connecting lines to the area outline of the blood dynamic display area in the direction of the vertical and horizontal connecting lines, and form the element anchoring area based on the obtained mapped connecting lines and horizontal connecting lines;

[0170] The retrieved dynamic blood flow elements with the corresponding standard flow rate and standard quantity are anchored to the element anchoring area, and if the dynamic blood flow element overlaps with any model coordinate point, the model coordinate point is hidden.

[0171] In response to user interaction to adjust dynamic blood flow elements, the system makes numerical adjustments to the standard flow rate and / or standard quantity, and makes morphological adjustments to the dynamic blood flow elements based on the numerical adjustments.

[0172] For example, in this embodiment, the adjustment interaction of the blood dynamic display area can be implemented based on the following method:

[0173] First, the server can use the center point of the human body model as the origin to construct a regional coordinate system for the corresponding blood dynamic display area, which provides a benchmark for subsequent spatial positioning and dynamic element adjustment. Furthermore, based on the established regional coordinate system, the server accurately determines the coordinate points of each model that makes up the human body model. Here, it can be explained that the human body model can be displayed in the blood dynamic display area based on a two-dimensional form. Therefore, the coordinate points of each model can also be obtained based on the two-dimensional form of the corresponding human body model.

[0174] Next, the server can filter out the coordinate points that make up the outline of the corresponding private parts from all model coordinate points and define them as the private coordinate group. Then, the corresponding horizontal connecting lines can be constructed based on the model coordinate points corresponding to the maximum and minimum values ​​of the horizontal coordinates in the private coordinate group.

[0175] Subsequently, the server maps this line to the area frame of the dynamic blood flow display area in a direction perpendicular to the horizontal connecting line, forming a mapping connecting line. These two connecting lines together define the element anchoring area, providing precise spatial positioning for the placement of dynamic blood flow elements.

[0176] Then, the server retrieves the corresponding preset standard flow rate and standard number of dynamic blood flow elements, anchors them to the element anchoring area, and automatically performs hiding processing when the dynamic blood flow element overlaps with any model coordinate point, ensuring that the display of dynamic elements is not interfered with by the model frame, thereby maintaining the clarity and intuitiveness of the interface.

[0177] Finally, the server responds to user interactions that adjust dynamic blood flow elements. These interactions may include changing the flow rate, adjusting the quantity, etc. By capturing these adjustment operations in real time and adjusting the standard flow rate and / or standard quantity based on the operation results, the server can synchronously adjust the morphology of dynamic blood flow elements, such as changing the flow rate or the density distribution of elements, to reflect the user's dynamic needs in real time.

[0178] It should be noted that, in this embodiment, the user can adjust the dynamic blood flow elements by inputting the corresponding adjustment parameters into the contraceptive monitoring platform, for example, through voice input or text input, so as to complete the precise adjustment of the dynamic blood flow elements and ensure that the dynamic blood flow elements can display the form desired by the user as accurately as possible, thereby improving the accuracy of subsequent diagnosis.

[0179] For example, Figure 2 The same schematic diagram of the private display area in this embodiment is also shown. It can be seen that the corresponding private display area includes a static blood display area and a dynamic blood display area arranged on the left and right sides.

[0180] Step S104 includes the following:

[0181] Based on the privacy diagnosis, the privacy diagnosis data corresponding to the current privacy graph is determined, and the privacy diagnosis data is uploaded to the privacy display area.

[0182] For example, in this embodiment, after obtaining the corresponding current private image, since the user's private parts should be of higher importance than the normal parts corresponding to normal symptom data, the diagnosis of the private parts can be completed by medical staff based on their professional experience, and the obtained private diagnosis data can be uploaded to the private display area so that the user can know his / her symptoms and implement the corresponding treatment methods according to the symptoms.

[0183] In summary, according to the solution of this embodiment, this embodiment effectively alleviates the burden on users who need to frequently visit medical institutions for offline examinations through intelligent online monitoring and dynamic display functions, greatly saving time and transportation costs, especially for users in remote areas or those with mobility difficulties, providing great convenience; at the same time, this embodiment creates a digital health data recording method based on the contraceptive monitoring platform, replacing traditional paper medical records, which not only improves the efficiency of data storage and transmission, but also significantly enhances the security of user privacy protection, effectively avoiding the risk of information leakage, thereby reducing the psychological and social pressure that users may suffer due to data leakage;

[0184] Furthermore, this embodiment also provides a corresponding interactive adjustment mechanism, allowing users to adjust the private display area in real time according to their own situation, enhancing the accuracy and practicality of monitoring. Through intuitive display, medical staff can understand the user's health status based on the normal display area and the private display area, promptly identify and address potential health risks, thereby improving the overall effectiveness of reproductive health management during contraception.

[0185] Figure 3 A system block diagram of a monitoring data processing system for contraceptive devices according to another embodiment of the present invention is shown, as follows: Figure 3 As shown, the system includes:

[0186] The vocabulary extraction module is configured to acquire common symptom data uploaded by users and extract vocabulary from the common symptom descriptions included in the common symptom data to obtain feature vocabulary.

[0187] The routine diagnosis module is configured to extract regions from the routine symptom images included in the routine symptom data based on feature words, and determine the routine diagnosis data corresponding to the obtained routine symptom regions based on routine diagnosis, and upload the routine symptom data and routine diagnosis data to the routine display area of ​​the contraceptive monitoring platform.

[0188] The private area display module is configured to respond to user interaction with the private area display area of ​​the contraceptive monitoring platform, create an initial private image in the private area display area, and update the initial private image based on the user's adjustment interaction to obtain the current private image.

[0189] The privacy diagnostic module is configured to determine the privacy diagnostic data corresponding to the current privacy graph based on privacy diagnostics, and upload the privacy diagnostic data to the privacy display area.

[0190] In the specification provided herein, the algorithms and displays are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used with the examples of this invention. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing preferred embodiments of the invention.

[0191] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0192] Similarly, it should be understood that, in order to streamline this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof.

[0193] Those skilled in the art will understand that modules, units, or components of the devices disclosed in the examples herein can be arranged in the devices described in this embodiment, or alternatively, can be located in one or more devices different from the devices in this example. The modules in the foregoing examples can be combined into a single module or, in addition, can be divided into multiple sub-modules.

[0194] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components.

[0195] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention and form different embodiments.

[0196] Furthermore, some of the embodiments described herein are methods or combinations of method elements that can be implemented by a processor of a computer system or by other means of performing the functions. Therefore, a processor having the necessary instructions for implementing the methods or method elements forms means for implementing the methods or method elements. Furthermore, the elements described herein in the apparatus embodiments are examples of means for implementing the functions performed by elements for the purposes of carrying out the invention.

[0197] As used herein, unless otherwise specified, the use of ordinal numbers such as “first,” “second,” “third,” etc., to describe ordinary objects merely indicates different instances of similar objects and is not intended to imply that the objects being described must have a given order in time, space, ordering, or any other manner.

[0198] Although the invention has been described with respect to a limited number of embodiments, those skilled in the art will understand from the foregoing description that other embodiments are conceivable within the scope of the invention described herein. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and edibility purposes, and not for the purpose of explaining or limiting the subject matter of the invention.

Claims

1. A method for processing monitoring data of contraceptive devices, characterized in that, Includes the following steps: Obtain common symptom data uploaded by users, and extract vocabulary from the common symptom descriptions included in the common symptom data to obtain feature vocabulary; Based on feature words, regions are extracted from the images of routine symptoms included in the routine symptom data. Based on routine diagnosis, routine diagnosis data corresponding to the obtained routine symptom regions is determined. The routine symptom data and routine diagnosis data are then uploaded to the routine display area of ​​the contraceptive monitoring platform. In response to user interaction with the creation of a private display area on the contraceptive monitoring platform, an initial private image is created in the private display area, which includes a static blood display area and a dynamic blood display area filled with a human body model. The standard blood pixel values ​​are retrieved to fill the static blood display area with pixels, and the static blood display area is divided into regions based on the regional center line of the corresponding static blood display area to obtain the change display area and the interactive display area. In response to user interaction with the interactive display area, determine the vertical movement of the user toward the center line of the area based on the interaction, and determine the percentage of the interactive display area that the vertical movement corresponds to. The interactive adjustment value is obtained by multiplying the moving percentage by the retrieved preset adjustment value. The obtained interactive adjustment value and standard pixel value are summed, and the change display area is filled with pixels based on the obtained current blood pixel value. A regional coordinate system corresponding to the blood dynamic display area is established with the center point of the human body model as the origin, and the coordinate points of each model that makes up the human body model are determined based on the regional coordinate system. The coordinate points of each model that make up the outline of the private parts are determined as the private parts coordinate group, and a horizontal connecting line is established based on the model coordinate points with corresponding horizontal coordinate maxima and horizontal coordinate minima located in the private parts coordinate group. Map the vertical and horizontal connecting lines to the area outline of the blood dynamic display area in the direction of the vertical and horizontal connecting lines, and form the element anchoring area based on the obtained mapped connecting lines and horizontal connecting lines; The retrieved dynamic blood flow elements with the corresponding standard flow rate and standard quantity are anchored to the element anchoring area, and if the dynamic blood flow element overlaps with any model coordinate point, the model coordinate point is hidden. In response to user interaction to adjust dynamic blood flow elements, the system makes numerical adjustments to the standard flow rate and / or standard quantity, and makes morphological adjustments to the dynamic blood flow elements based on the numerical adjustments to obtain the current private image. Based on the privacy diagnosis, the privacy diagnosis data corresponding to the current privacy graph is determined, and the privacy diagnosis data is uploaded to the privacy display area.

2. The monitoring data processing method for contraceptive devices according to claim 1, characterized in that, Lexical extraction was performed on the descriptions of common symptoms included in the common symptom data to obtain feature vocabulary, including: Obtain the number of horizontal characters in the horizontal arrangement direction corresponding to the description of common symptoms, and the number of vertical characters in the vertical arrangement direction corresponding to the description of common symptoms, and determine the arrangement direction with the larger number of characters as the character arrangement order; The description of normal symptoms contains descriptive characters that indicate the meaning of segmentation. The description is segmented based on the character arrangement order to obtain each descriptive sub-segment. Semantic recognition is performed on each descriptive character located in the same descriptive sub-paragraph, and the word attributes of each descriptive word are determined based on the comparison results between the obtained descriptive words and the retrieved preset feature table. If any descriptive word has a swelling attribute, then that descriptive word is identified as a feature word of the corresponding descriptive sub-paragraph. If any descriptive word has a purplish-color attribute, then that descriptive word is identified as a feature word of the corresponding descriptive sub-paragraph.

3. The monitoring data processing method for contraceptive devices according to claim 2, characterized in that, Based on feature vocabulary, regions are extracted from the images of common symptoms included in the common symptom data. Then, based on common symptom diagnosis, corresponding common symptom data is determined, including: The preset region extraction strategy corresponding to the word attributes is invoked to extract regions from the normal symptom images included in the normal symptom data, thus obtaining the normal symptom regions; Based on the source information of the contraceptive device for the corresponding user, historical symptom descriptions are retrieved, and all historical symptom descriptions containing characteristic words are compared with the description sub-paragraphs. If the similarity of a paragraph describing a historical symptom is greater than the preset similarity, it is identified as routine diagnostic data. If the paragraph similarity of multiple historical symptom descriptions is greater than the preset similarity, the historical diagnostic data with the highest similarity to the corresponding paragraph and with a diagnostic relationship will be identified as the normal diagnostic data corresponding to the normal symptom area. All paragraph similarities obtained from the response are less than or equal to the preset similarity. Historical symptom images with image-text relationships with historical symptom descriptions are retrieved, and normal diagnostic data are determined based on the similarity comparison between historical symptom images and normal symptom areas.

4. The monitoring data processing method for contraceptive devices according to claim 3, characterized in that, The preset region extraction strategy corresponding to the word attributes is invoked to extract regions from the common symptom images included in the common symptom data, resulting in common symptom regions, including: The response word attribute is swelling attribute. The mean value of each image pixel located at the edge of the normal symptom image is calculated, and the obtained pixel mean value is used as the center value of the interval to establish the first normal interval. Any image pixel located inside the normal symptom image that is outside the first normal range is identified as a swollen pixel. Connect all swollen pixels with adjacent points to obtain the first connected region; If the size of the responding connected region is larger than the preset swelling size, the connected region is defined as the normal symptom region of the corresponding swelling attribute.

5. The monitoring data processing method for contraceptive devices according to claim 3, characterized in that, The preset region extraction strategy corresponding to the word attributes is invoked to extract regions from the common symptom images included in the common symptom data, resulting in common symptom regions, including: The response word attribute is the bruise attribute. The mean value of each image pixel located at the edge of the normal symptom image is calculated, and the obtained pixel mean value is used as the center value of the interval to establish a second normal interval. Any image pixel located inside the normal symptom image that corresponds to a location outside the second normal range is identified as a bruised pixel. Based on the coordinate processing of the normal symptom image, the coordinate points of each bruised pixel are obtained, and vertical region lines extending along the Y-axis and corresponding horizontal region lines extending along the X-axis are generated. Based on vertical and horizontal area lines, corresponding bruise-like symptom areas are formed.

6. The monitoring data processing method for contraceptive devices according to claim 3, characterized in that, Routine diagnostic data is determined based on the similarity comparison between historical symptom images and routine symptom areas, including: Identify historical symptom regions in historical symptom images that have the same word attributes as normal symptom regions, and compare the historical symptom regions with normal symptom regions for similarity. The obtained region similarity and paragraph similarity of the corresponding historical symptom images are multiplied by the retrieved region weight value and paragraph weight value, respectively. The obtained first confidence value and second confidence value are then summed to obtain the comprehensive confidence value of the corresponding historical symptom images. Historical diagnostic data that has a diagnostic relationship with the historical symptom image with the highest corresponding comprehensive confidence value are identified as normal diagnostic data corresponding to the normal symptom area.

7. A monitoring data processing system for contraceptive devices, characterized in that, include: The vocabulary extraction module is configured to acquire common symptom data uploaded by users and extract vocabulary from the common symptom descriptions included in the common symptom data to obtain feature vocabulary. The routine diagnosis module is configured to extract regions from the routine symptom images included in the routine symptom data based on feature words, and determine the routine diagnosis data corresponding to the obtained routine symptom regions based on routine diagnosis, and upload the routine symptom data and routine diagnosis data to the routine display area of ​​the contraceptive monitoring platform. The private area display module is configured to respond to user interaction with the creation of the private display area of ​​the contraceptive monitoring platform, and to create an initial private image in the private display area, which includes a static blood display area and a dynamic blood display area filled with a human body model. The standard blood pixel values ​​are retrieved to fill the static blood display area with pixels, and the static blood display area is divided into regions based on the regional center line of the corresponding static blood display area to obtain the change display area and the interactive display area. In response to user interaction with the interactive display area, determine the vertical movement of the user toward the center line of the area based on the interaction, and determine the percentage of the interactive display area that the vertical movement corresponds to. The interactive adjustment value is obtained by multiplying the moving percentage by the retrieved preset adjustment value. The obtained interactive adjustment value and standard pixel value are summed, and the change display area is filled with pixels based on the obtained current blood pixel value. A regional coordinate system corresponding to the blood dynamic display area is established with the center point of the human body model as the origin, and the coordinate points of each model that makes up the human body model are determined based on the regional coordinate system. The coordinate points of each model that make up the outline of the private parts are determined as the private parts coordinate group, and a horizontal connecting line is established based on the model coordinate points with corresponding horizontal coordinate maxima and horizontal coordinate minima located in the private parts coordinate group. Map the vertical and horizontal connecting lines to the area outline of the blood dynamic display area in the direction of the vertical and horizontal connecting lines, and form the element anchoring area based on the obtained mapped connecting lines and horizontal connecting lines; The retrieved dynamic blood flow elements with the corresponding standard flow rate and standard quantity are anchored to the element anchoring area, and if the dynamic blood flow element overlaps with any model coordinate point, the model coordinate point is hidden. In response to user interaction to adjust dynamic blood flow elements, the system makes numerical adjustments to the standard flow rate and / or standard quantity, and makes morphological adjustments to the dynamic blood flow elements based on the numerical adjustments to obtain the current private image. The privacy diagnostic module is configured to determine the privacy diagnostic data corresponding to the current privacy graph based on privacy diagnostics, and upload the privacy diagnostic data to the privacy display area.

Images