Monitoring data processing method and system for contraceptive apparatus

Abstract

The invention provides a monitoring data processing method for a contraceptive device, and the method comprises the following steps: obtaining normal symptom data uploaded by a user side, and carrying out the vocabulary extraction of normal symptom description included in the normal symptom data, and obtaining feature vocabularies; performing region extraction on a normal symptom image included in the normal symptom data based on the feature vocabularies, determining normal diagnosis data corresponding to an obtained normal symptom region based on normalized diagnosis, and uploading the normal symptom data and the normal diagnosis data to a normal display region of the contraception monitoring platform; in response to creation interaction of the user side on the private display area of the contraception monitoring platform, creating an initial private graph in the private display area, and updating the initial private graph based on adjustment interaction of the user side to obtain a current private graph; and determining private diagnosis data corresponding to the current private graph based on the private diagnosis, and uploading the private diagnosis data to the private display area. According to the invention, the convenience is at least improved.

Description

Technical Field

[0001] The present invention relates to data processing technologies, and in particular to a method and system for processing monitoring data of contraceptive devices. Background Art

[0002] During contraception, the reproductive health management of women has special medical needs. According to statistics of the World Health Organization, approximately 44% of married women globally rely on modern contraceptive methods, and hormonal contraceptives (such as oral contraceptives, subdermal implants) and intrauterine devices (IUDs) account for more than 60%. However, abnormal symptoms that may occur during contraception (such as breakthrough bleeding, skin swelling, etc.) often indicate potential health risks, including diseases such as endometritis, ovarian cysts, and hormonal imbalances.

[0003] Currently, when users experience corresponding abnormal symptoms during contraception, they usually rely on users to regularly go to medical institutions for offline examinations. Medical staff obtain physiological symptom data during the use of contraceptive devices through visual observation and manual recording. This mode not only requires users to spend a lot of time and transportation costs, but also poses significant barriers to seeking medical treatment for people in remote areas or with limited mobility; in addition, there may also be corresponding deficiencies in the mechanism for protecting user privacy. Paper medical records face the risk of information leakage during data storage and transmission, and once sensitive data related to reproductive health is leaked, it may cause serious psychological and social impacts on users. Summary of the Invention

[0004] Based on the above problems, the present invention is proposed to provide a method and system for processing monitoring data of contraceptive devices that overcome the above problems or at least partially solve the above problems.

[0005] According to one aspect of the present invention, there is provided a method for processing monitoring data of contraceptive devices, including the following steps: Obtain the normal symptom data uploaded by the user terminal, and extract vocabulary from the normal symptom description included in the normal symptom data to obtain characteristic vocabulary; Based on the characteristic vocabulary, extract the region of the normal symptom image included in the normal symptom data, and based on the normal diagnosis, determine the normal diagnosis data corresponding to the obtained normal symptom region, and upload the normal symptom data and the normal diagnosis data to the normal display area of the contraceptive monitoring platform; Respond to the creation interaction of the user terminal with the private display area of the contraceptive monitoring platform, create an initial private image in the private display area, and update the initial private image based on the adjustment interaction of the user terminal to obtain the current private image; Based on the private diagnosis, determine the private diagnosis data corresponding to the current private image, and upload the private diagnosis data to the private display area.

[0006] Optionally, in the method according to the present invention, lexical extraction is performed on the normal symptom descriptions included in the normal symptom data to obtain feature words, including: Obtain the number of horizontal characters in the horizontal arrangement direction corresponding to the normal symptom description and the number of vertical characters in the vertical arrangement direction corresponding thereto, and determine the arrangement direction with the larger corresponding number as the character arrangement order; In response to the description characters indicating the segmentation meaning in the normal symptom description, perform description segmentation based on the character arrangement order to obtain each description sub-paragraph; Perform semantic recognition on each description character located in the same description sub-paragraph, and determine the word attributes of each description word based on the comparison result between the obtained description words and the retrieved preset feature table; In response to the word attribute of any description word being the swelling attribute, determine the description word as the feature word of the corresponding description sub-paragraph; In response to the word attribute of any description word being the bruising attribute, determine the description word as the feature word of the corresponding description sub-paragraph.

[0007] 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 the feature words, and normal diagnosis data corresponding to the obtained normal symptom regions is determined based on the normal diagnosis, including: Retrieve the preset region extraction strategy corresponding to the word attribute to perform region extraction on the normal symptom images included in the normal symptom data to obtain the normal symptom regions; Retrieve the historical symptom descriptions based on the traceability information of the contraceptive device of the corresponding user, and perform similarity comparison between all the historical symptom descriptions containing the feature words and the description sub-paragraphs; In response to the paragraph similarity of a historical symptom description being greater than the preset similarity, determine it as the normal diagnosis data; In response to the paragraph similarities of multiple historical symptom descriptions being greater than the preset similarity, determine the historical diagnosis data having a diagnostic relationship with the historical symptom description with the largest paragraph similarity retrieved as the normal diagnosis data corresponding to the normal symptom region; In response to all the obtained paragraph similarities being less than or equal to the preset similarity, retrieve the historical symptom images having a graphic relationship with the historical symptom descriptions, and determine the normal diagnosis data based on the similarity comparison between the historical symptom images and the normal symptom regions.

[0008] Optionally, in the method according to the present invention, retrieve the preset region extraction strategy corresponding to the word attribute to perform region extraction on the normal symptom images included in the normal symptom data to obtain the normal symptom regions, including: In response to the word attribute being the swelling attribute, calculate the mean value of each image pixel point located at the edge of the normal symptom image, and establish a first normal interval with the obtained pixel mean value as the interval center value; If any image pixel point located inside the normal symptom image corresponds to being outside the first normal interval, determine it as a swelling pixel point; Connect the positions of all swelling pixel points adjacent to each other to obtain a first connected region; If the region size of the connected region is greater than the preset swelling size, determine this connected region as the normal symptom region corresponding to the swelling attribute.

[0009] Optionally, in the method according to the present invention, retrieve the preset region extraction strategy corresponding to the word attribute to perform region extraction on the normal symptom image included in the normal symptom data, and obtain the normal symptom region, including: In response to the word attribute being the bruising attribute, calculate the mean value of each image pixel point located at the edge of the normal symptom image, and establish a second normal interval with the obtained pixel mean value as the interval center value; If any image pixel point located inside the normal symptom image corresponds to being outside the second normal interval, determine it as a bruising pixel point; Based on the coordinate processing performed on the normal symptom image, obtain the respective bruising coordinate points corresponding to all bruising pixel points, and generate a vertical region line passing through the corresponding horizontal coordinate extreme value and extending along the Y-axis, and a horizontal region line passing through the corresponding vertical coordinate extreme value and extending along the X-axis; Based on the vertical region line and the horizontal region line, form the normal symptom region corresponding to the bruising attribute.

[0010] Optionally, in the method according to the present invention, determine the normal diagnosis data based on the similarity comparison between the historical symptom image and the normal symptom region, including: Determine the historical symptom region in the historical symptom image that has the same word attribute as the normal symptom region, and perform a similarity comparison between the historical symptom region and the normal symptom region; Perform a product calculation on the obtained region similarity and paragraph similarity corresponding to the same historical symptom image respectively with the retrieved region weight value and paragraph weight value, and perform a summation calculation on the obtained first confidence value and second confidence value to obtain the comprehensive confidence value corresponding to the historical symptom image; Determine the historical diagnosis data having a diagnostic relationship with the historical symptom image with the largest comprehensive confidence value retrieved as the normal diagnosis data corresponding to the normal symptom region.

[0011] Optionally, in the method according to the present invention, in response to a creation interaction by the client for a private display area of the contraceptive monitoring platform, an initial private image is created in the private display area, and the initial private image is updated based on an adjustment interaction of the client to obtain the current private image, including: In response to a creation interaction by the client for a private display area of the contraceptive monitoring platform, an initial private image is created in the private display area, wherein the initial private image includes a blood static display area and a blood dynamic display area for filling a human model; In response to an adjustment interaction by the client for the blood static display area, pixel values of standard blood pixel values corresponding to the blood static display area are changed, and the blood static display area is pixel-filled based on the obtained current blood pixel values; In response to an adjustment interaction by the client for the blood dynamic display area, the private part included in the human model is positioned, and the morphology of the dynamic blood flow elements anchored to the private part is adjusted.

[0012] Optionally, in the method according to the present invention, in response to an adjustment interaction by the client for the blood static display area, pixel values of standard blood pixel values corresponding to the blood static display area are changed, and the blood static display area is pixel-filled based on the obtained current blood pixel values, including: Retrieve standard blood pixel values to pixel-fill the blood static display area, and divide the blood static display area based on the regional center line of the corresponding blood static display area to obtain a change display area and an interaction display area; In response to an adjustment interaction by the client for the interaction display area, determine the vertical movement amount of the client towards the regional center line based on the adjustment interaction, and determine the movement ratio of the interaction display area corresponding to the vertical movement amount; Multiply the movement ratio by a preset adjustment value retrieved to obtain an interaction adjustment value; Based on the obtained interaction adjustment value and the standard pixel values, perform a summation calculation, and pixel-fill the change display area based on the obtained current blood pixel values.

[0013] Optionally, in the method according to the present invention, in response to an adjustment interaction by the client for the blood dynamic display area, the private part included in the human model is positioned, and the morphology of the dynamic blood flow elements anchored to the private part is adjusted, including: Establish a regional coordinate system corresponding to the blood dynamic display area with the model center point of the human model as the origin, and determine each model coordinate point constituting the human model based on the regional coordinate system; Determine each model coordinate point constituting the private part contour as a private part coordinate group, and establish a horizontal connection line based on the model coordinate points corresponding to the maximum and minimum horizontal coordinates in the private part coordinate group; Map the vertical and horizontal connection lines to the regional bounding lines of the blood dynamics display area in the direction of the vertical and horizontal connection lines, and form an element anchoring area based on the obtained mapped connection lines and the horizontal connection lines; Anchoring the retrieved dynamic blood flow elements corresponding to the standard flow rate and the standard quantity to the element anchoring area, and hiding the model coordinate point when the dynamic blood flow element overlaps with any model coordinate point; Respond to the adjustment interaction of the dynamic blood flow element by the client, adjust the numerical value of the standard flow rate and / or the standard quantity, and adjust the shape of the dynamic blood flow element based on the numerical adjustment.

[0014] According to another aspect of the present invention, there is provided a monitoring data processing system for contraceptive devices, including: A vocabulary extraction module, configured to obtain the normal symptom data uploaded by the client, and extract the vocabulary from the normal symptom description included in the normal symptom data to obtain characteristic vocabulary; A normal diagnosis module, configured to extract the region from the normal symptom image included in the normal symptom data based on the characteristic vocabulary, and determine the normal diagnosis data corresponding to the obtained normal symptom region based on the normal diagnosis, and upload the normal symptom data and the normal diagnosis data to the normal display area of the contraceptive monitoring platform; A private part display module, configured to respond to the creation interaction of the client for the private display area of the contraceptive monitoring platform, create an initial private image in the private display area, and update the initial private image based on the adjustment interaction of the client to obtain the current private image; A private diagnosis module, configured to determine the private diagnosis data corresponding to the current private image based on the private diagnosis, and upload the private diagnosis data to the private display area.

[0015] According to the solution of the present invention, through the intelligent online monitoring and dynamic display functions, the present invention effectively alleviates the burden on users to frequently go to medical institutions for offline examinations, greatly saves time and transportation costs, and especially provides great convenience for users in remote areas or with inconvenient mobility; at the same time, the present invention creates a digital health data recording method based on the contraceptive monitoring platform, replacing the 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; In addition, the present invention also provides a corresponding interaction adjustment mechanism, enabling users to adjust the private display area in real time according to their own situations, 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 discover and address potential health risks, thereby improving the overall effect of reproductive health management during contraception. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 FIG. 1 shows a flowchart of a method for processing monitoring data of a contraceptive device according to an embodiment of the present invention; Figure 2 FIG. 2 shows a schematic diagram of the normal display area and the private display area in this embodiment; Figure 3 FIG. 3 shows a block diagram of the structure of a system for processing monitoring data of a contraceptive device according to another embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be completely conveyed to those skilled in the art.

[0018] To solve the problems existing in the above-mentioned prior art, the inventor proposed the solution of the present invention. An embodiment of the present invention provides a method for processing monitoring data of a contraceptive device, which can be executed in a computing device. Herein, the computing device can be understood as a terminal having data processing functions, such as a mobile phone or a computer.

[0019] FIG. 1 shows a flowchart of the method for processing monitoring data of a contraceptive device in this embodiment. As Figure 1 shown, the method starts from step S101, where S101 includes the following content: Obtain the normal symptom data uploaded by the user terminal, and perform vocabulary extraction on the normal symptom descriptions included in the normal symptom data to obtain characteristic vocabulary.

[0020] For example, in this embodiment, when a user uses a corresponding contraceptive device to perform contraception on themselves, in order to determine whether the contraceptive device has certain adverse effects on the user's body, medical staff can create a corresponding contraceptive monitoring platform to regularly obtain 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 adverse effects due to the use of the contraceptive device through their own observation. If so, the user can use their corresponding user terminal to upload the normal symptom data corresponding to the adverse effects to the server, so that the server can further upload the normal symptom data to the contraceptive monitoring platform for medical staff to conduct online diagnosis based on the normal symptom data.

[0021] Here, the normal symptom data can include normal symptom images and normal symptom descriptions that assist in explaining the normal symptom descriptions. After receiving the corresponding normal symptom data, the server can first perform corresponding vocabulary extraction based on the normal symptom descriptions to obtain the characteristic vocabulary existing in the normal symptom descriptions, so as to quickly obtain the expression of the adverse effects to be expressed by the user. It should be noted that the normal symptom images can be obtained by the user collecting images of their own normal parts, and the normal symptom descriptions are the text descriptions of the adverse effects for medical staff to facilitate understanding of the symptoms. For example, when there is swelling or bruising on the user's skin, the user can generate a normal symptom description based on the adverse effects such as swelling or bruising. At this time, the corresponding characteristic vocabulary includes swelling or bruising, etc. It can be explained that in this embodiment, the user terminal can be understood as the terminal used by the user, such as a mobile phone or a computer with data processing functions.

[0022] Furthermore, in this embodiment, the above-mentioned "performing vocabulary extraction on the normal symptom descriptions included in the normal symptom data to obtain characteristic vocabulary" can further include the following steps: Obtain the number of horizontal characters in the horizontal arrangement direction corresponding to the normal symptom description and the number of vertical characters in the vertical arrangement direction corresponding to it, and determine the character arrangement order as the arrangement direction with the larger corresponding number. Respond to the description characters indicating the meaning of segmentation in the normal symptom description, and perform description segmentation based on the character arrangement order to obtain each description sub-paragraph. Perform semantic recognition on each description character located in the same description sub-paragraph, and determine the word attribute of each description word based on the comparison result between the obtained description words and the retrieved preset feature table. Respond that the word attribute of any description word is the swelling attribute, and determine the description word as the characteristic vocabulary of the corresponding description sub-paragraph. If the word attribute corresponding to any descriptive word is the bruising attribute, then determine this descriptive word as the characteristic word of the corresponding descriptive sub-paragraph.

[0023] For example, in this embodiment, the extraction of the words for the description of normal symptoms can be specifically implemented based on the following method steps: After obtaining the description of normal symptoms uploaded by the client, since the writing habits of each user may be different, therefore, it is first necessary to determine the corresponding writing order based on the obtained description of normal symptoms. For example, the server will calculate the number of horizontal characters in the horizontal arrangement direction corresponding to the description of normal symptoms and the number of vertical characters in the vertical arrangement direction respectively, and further compare these two numbers, and determine the arrangement direction with the larger number as the character arrangement order. For example, if a description of normal symptoms is "Persistent dull pain in the lower abdomen, accompanied by slight bleeding", when the server recognizes that the number of horizontal characters is more than the number of vertical characters, it is determined that the horizontal arrangement of this description is the main one; Next, the server can further respond to the descriptive characters indicating the meaning of paragraph segmentation in the description of normal symptoms, such as full stops, semicolons or line breaks, etc., and perform description segmentation based on the determined character arrangement order, so as to obtain each descriptive sub-paragraph. Continuing with the above example, the server can segment it into two descriptive sub-paragraphs: "Persistent dull pain in the lower abdomen" and "Accompanied by slight bleeding"; Then, the server can further perform semantic recognition on each descriptive character 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 expertise and experience, and contains a series of words and their attributes related to the abnormal symptoms that may occur during the use of contraceptive devices, such as swelling, bruising, etc. In the above example, the word "dull pain" will be recognized as having the swelling attribute, and "bleeding" may be determined as a manifestation of the potential bruising attribute due to the context (although "bleeding" itself is not directly equivalent to bruising, but may be considered as a manifestation form or related symptom of the bruising symptom in this context); Finally, if the word attribute corresponding to any descriptive word is the swelling attribute or the bruising attribute, the server can determine this descriptive word as the characteristic word of the corresponding descriptive sub-paragraph. In the example, "dull pain" is used as the characteristic word of the swelling attribute, and "bleeding" (in this context) is extracted as a characteristic word that may be related to bruising (or at least an abnormal symptom word worthy of attention). These characteristic words have important reference value for the subsequent extraction and diagnosis of the images of the normal symptom area, and can improve the diagnosis efficiency and corresponding diagnostic accuracy of the corresponding online diagnosis.

[0024] In step S102, the following content is included: Region extraction is performed on the normal symptom images included in the normal symptom data based on characteristic vocabulary, and normal diagnosis data corresponding to the obtained normal symptom regions is determined based on normalized diagnosis. The normal symptom data and the normal diagnosis data are uploaded to the normal display area of the contraception monitoring platform.

[0025] For example, in this embodiment, after obtaining the characteristic vocabulary in the normal symptom description, the server first retrieves the corresponding preset region extraction strategy according to the disease attributes indicated by the characteristic vocabulary (such as swelling, bruising, etc.), and completes the region extraction for the normal symptom image corresponding to the normal symptom description based on the preset region extraction strategy. For example, continuing the above example, assuming that the characteristic vocabulary in the normal symptom description is "‌distending pain‌", the server recognizes that this word has a swelling attribute, so it retrieves the preset region extraction strategy for the swelling attribute; Next, the server analyzes the normal symptom image using the retrieved region extraction strategy to locate the normal symptom region corresponding to the characteristic vocabulary. This step may involve image processing techniques such as edge detection and pixel value analysis to determine which parts of the image conform to the characteristics of attributes such as swelling or bruising; Continuing the above example, the server may identify the region with a relatively red color and higher brightness as a potential bruising region by analyzing the distribution of pixel values in the image, and then determine the normal symptom region corresponding to the characteristic vocabulary of "bleeding‌‌"; Then, the server can further perform diagnostic analysis on the extracted normal symptom region based on the normalized diagnosis logic; Finally, the server uploads the normal symptom data (including the normal symptom description and the normal symptom image) and the normal diagnosis data to the normal display area of the contraception monitoring platform. In this way, users and medical staff can view detailed normal symptom information and diagnosis results on the platform, facilitating subsequent health management and treatment decisions.

[0026] Through the above steps, this embodiment realizes the intelligent analysis and diagnosis of normal symptom data, improving the efficiency and accuracy of female reproductive health management during contraception.

[0027] It should be noted that in this embodiment, in order to improve the display effect of the corresponding normal diagnosis data and normal symptom data based on the normal display area, a periodic filling area and a data filling area can be generated in the normal display area. Among them, the periodic filling area is used to fill the corresponding current period, such as the third day, the fourth day, etc. The corresponding data filling area can further include a normal symptom sub-area and a normal diagnosis sub-area. The normal symptom sub-area is used to fill the normal symptom data, and the normal diagnosis sub-area can be used to fill the normal diagnosis data. Here, "normal" can be understood as data with relatively low privacy requirements, such as symptom data of limbs such as the arms, legs, and face, while "private" mentioned later can be understood as data with relatively high privacy requirements, generally referring to symptom data of the reproductive organs.

[0028] For example, Figure 2 FIG. shows a schematic diagram of the normal display area in this embodiment. Among them, the normal display area includes six data filling areas, and five of the corresponding data filling areas have completed the corresponding data filling.

[0029] Furthermore, in this embodiment, the above-mentioned "performing region extraction on the normal symptom images included in the normal symptom data based on the characteristic vocabulary, and determining the normal diagnosis data corresponding to the obtained normal symptom region based on the normalized diagnosis" may further include the following steps: Invoking a preset region extraction strategy corresponding to the word attribute to perform region extraction on the normal symptom images included in the normal symptom data to obtain a normal symptom region; Invoking historical symptom descriptions based on the traceability information of the contraceptive device of the corresponding user, and performing a similarity comparison between all the historical symptom descriptions containing the characteristic vocabulary and the description sub-paragraphs; Responding that the paragraph similarity of a historical symptom description is greater than the preset similarity, and determining it as the normal diagnosis data; Responding that the paragraph similarities of multiple historical symptom descriptions are greater than the preset similarity, and determining the historical diagnosis data having a diagnostic relationship with the historical symptom description with the largest paragraph similarity among the retrieved ones as the normal diagnosis data corresponding to the normal symptom region; Responding that all the obtained paragraph similarities are less than or equal to the preset similarity, retrieving the historical symptom images having a graphic relationship with the historical symptom description, and determining the normal diagnosis data based on the similarity comparison between the historical symptom images and the normal symptom region.

[0030] For example, in this embodiment, based on the above, it can be known that the characteristic vocabulary can include corresponding different word attributes, such as the swelling attribute and the bruising attribute. In order to quickly extract the normal symptom image, different preset region extraction strategies can be preset based on different word attributes. After the extraction of the normal symptom region is completed, the determination of the normal diagnosis data can be further realized based on the following method steps: First, the server can process the normal symptom image by using the preset region extraction strategy set in advance, and this strategy can be customized according to the word attributes indicated by the characteristic vocabulary (such as the swelling attribute, the bruising attribute, etc.); assuming that the characteristic vocabulary is the above-mentioned "distending pain", the server then retrieves the preset extraction strategy specifically used to identify the swelling region. This strategy may be based on image processing technologies such as color analysis and shape recognition, and can accurately extract the region corresponding to "distending pain" from the normal symptom image, that is, the normal symptom region; Next, the server can retrieve the historical symptom descriptions related to the user from the database according to the traceability information of the user's contraceptive device (including the type, brand, usage duration, etc. of the contraceptive device), and further compare the similarity between these historical symptom descriptions and the current description subparagraph, especially paying attention to those historical descriptions containing the characteristic vocabulary "distending pain"; For example, in this embodiment, since there may be contraceptive drugs with corresponding different ingredients in different types and brands of contraceptive devices to assist in increasing the corresponding contraceptive effect, and the above-mentioned traceability information of the corresponding contraceptive device generally corresponds to the corresponding lesion conditions generated by other users using the contraceptive device. In the process of obtaining the traceability information, in order to determine that the corresponding disease condition is caused by using the contraceptive device, the following determination process can be used for verification: The first step is to determine the research objective. The researcher needs to clarify the suspected drug or drug category and the target adverse reaction (ADR) of the current research. When formulating the research objective, information such as specific time, space, specific manufacturer, and batch number can be considered.

[0031] The second step is to select the database and generate the analysis set. According to the research objective, select the variables related to the research objective and generate the analysis data set. If adverse reaction risk factor analysis is required, the suspected risk factors need to be included. The stability of the signal largely depends on the quantity and quality of the reports in the database.

[0032] Step 3: Select the standard library. For the drug names and adverse event names appearing in the adverse event reports, cleaning and coding should be strictly carried out in accordance with the drug general name dictionary and the drug adverse event terminology set. The drug name dictionary databases mainly include Pharmacopoeia of the People's Republic of China, the national drug coding standard of Classification and Codes of Chemical Drugs (Raw Materials, Preparations), Chinese Approved Drug Names, etc. Coding can also be carried out based on the drug database compiled by the World Health Organization (WHO-DRUG). The norms for adverse event names mainly include the WHO Adverse Reaction Terminology (WHO-ART) of the World Health Organization, the Medical Dictionary for Regulatory Activities (MedDRA) of the International Conference on Harmonization of Technical Requirements for the Registration of Pharmaceuticals for Human Use (ICH), the Coding Symbols for Thesaurus of Adverse Reaction Terms (COSTART) adopted by the FDA, the International Classification of Diseases (ICD), etc.

[0033] Step 4: Data collation. Delete the data entries with excessive duplicate, missing information or obvious logical errors, and fully clean the data according to the requirements of the statistical model.

[0034] Step 5: Select the analysis method. Select the corresponding signal detection method according to the research purpose and data type. During the data mining process, the detection algorithm and judgment criteria need to be written into the analysis program, and the program automatically calculates and judges whether the signal is established.

[0035] Step 6: Signal interpretation and expert evaluation. The analyst writes an analysis report based on the data mining results. The expert combines the mining results and the results of the literature special research to decide whether further research is needed to test whether there is indeed a causal relationship between drug use and drug adverse events.

[0036] Here, the comparison process in this embodiment can specifically adopt a text similarity algorithm, such as cosine similarity or Jaccard similarity, to calculate the similarity between the current descriptor 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 this historical symptom description may be the same as the disease corresponding to the normal symptom description. At this time, the server regards it as a historical record highly matching the current symptom and preliminarily determines that the corresponding historical diagnosis data may also be able to diagnose the corresponding disease for the normal symptom description. Therefore, it can be determined as the normal diagnosis data corresponding to the normal symptom description; However, if the paragraph similarities of multiple historical symptom descriptions all exceed the preset similarity, the server will give priority to considering the historical symptom description with the highest paragraph similarity corresponding to the current descriptor paragraph and retrieve the corresponding historical diagnosis data of this description in the database. These historical diagnosis data have been verified and are associated with the highly similar historical symptom descriptions, so they are regarded as the normal diagnosis data most matching the normal symptom area; If the paragraph similarities of all historical symptom descriptions do not reach the preset threshold, the server retrieves the historical symptom images having a graphic relationship with these historical symptom descriptions and uses an image similarity algorithm (such as feature matching methods like SIFT, SURF, etc.) to compare the image similarity between the historical symptom images and the current normal symptom area; Finally, the server can determine the historical diagnosis data closest to the current normal symptom area as the normal diagnosis data based on the result of the image comparison.

[0037] Through the above method, the present invention realizes the intelligent and efficient diagnosis of normal symptoms during the use of contraceptive devices, providing strong support for the health management of users.

[0038] It should be noted that based on the above content, since the corresponding word attributes can include a swelling attribute and a bruise color attribute, therefore, for different word attributes, the extraction of the corresponding normal symptom area can be completed based on different preset area extraction strategies. Based on this, in one implementation, when the word attribute is the swelling attribute, the above "retrieve the preset area extraction strategy corresponding to the word attribute to perform area extraction on the normal symptom image included in the normal symptom data to obtain the normal symptom area" can include the following steps: In response to the word attribute being the swelling attribute, calculate the mean value of each image pixel point located at the edge of the normal symptom image, and establish a first normal interval with the obtained pixel mean value as the interval central value; In response to any image pixel point located inside the normal symptom image corresponding to being outside the first normal interval, determine it as a swelling pixel point; Connect the positions of all swelling pixel points adjacent to each other to obtain a first connection area; If the regional size of the response connection area is greater than the preset swelling size, determine the connection area as the normal symptom area corresponding to the swelling attribute.

[0039] For example, in this embodiment, based on the preset area extraction strategy for the word attribute corresponding to the swelling attribute to perform area extraction, it can be specifically implemented based on the following method steps: First, assume that in the previous step, the server has recognized the feature word "‌swelling pain‌" and determined that its corresponding word attribute is the swelling attribute. The server can calculate the mean value of each image pixel point located at the edge of the normal symptom image. It should be noted that this step aims to determine a reference value for subsequent differentiation between the normal skin area and the potential swelling area. The pixel mean value obtained through calculation can further establish a first normal interval, which is centered on the mean value and covers the possible range of normal skin pixel values; Next, the server can check each image pixel point located inside the normal symptom image one by one. If the pixel value of a certain pixel point exceeds the range of the first normal interval, it indicates that there is a large difference between the pixel value of this image pixel point and the pixel value of the corresponding normal skin. At this time, the server will determine it as a swelling pixel point. By comparing the pixel value with the normal interval, the potential swelling area can be effectively identified; ‌Then, after completing the identification of all corresponding swelling pixel points, the server can connect the positions of all the identified swelling pixel points adjacent to each other, so as to integrate the scattered swelling pixel points into a continuous swelling area, that is, the first connection area, thereby being able to reflect the actual distribution of the swelling disease in the normal symptom image.

[0040] Finally, the server can evaluate the regional size of the first connection area. If the size of the connection area exceeds the preset swelling size, the server will determine it as the normal symptom area corresponding to the swelling attribute, thereby improving the recognition accuracy of the area corresponding to the swelling attribute, improving the accuracy and reliability of the diagnosis, and reducing the noise impact on the recognition of this embodiment caused by other areas with smaller regional sizes such as pores.

[0041] In another implementation manner, when the corresponding word attribute is the bruise color attribute, the above "invoke the preset area extraction strategy for the corresponding word attribute to perform area extraction on the normal symptom image included in the normal symptom data to obtain the normal symptom area" may include the following steps: In response to the word attribute being the bruise color attribute, calculate the mean value of each image pixel point located at the edge of the normal symptom image, and establish a second normal interval with the obtained pixel mean value as the interval central value; In response to any image pixel point located inside the normal symptom image corresponding to being outside the second normal interval, determine it as a bruise color pixel point; Based on the coordinate processing of the normal symptom image, each bruise coordinate point corresponding to all bruise pixel points is obtained, and a vertical area line passing through the corresponding horizontal coordinate extreme value and extending along the Y-axis, and a horizontal area line passing through the corresponding vertical coordinate extreme value and extending along the X-axis are generated; Based on the vertical area line and the horizontal area line, a normal symptom area corresponding to the bruise attribute is formed.

[0042] For example, in this embodiment, based on the preset area extraction strategy of the word attribute corresponding to the bruise attribute for area extraction, it can be specifically implemented based on the following method steps: First, assume that in the previous step, the server has recognized the feature word "bleeding" and determined that its corresponding word attribute is the bruise attribute. The server calculates the average value of each image pixel point located at the edge of the normal symptom image, and based on the obtained pixel average value, a second normal interval is established. This interval is intended to define the range of normal skin pixel values and provide a basis for the subsequent identification of bruise pixel points; 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; Next, the server checks each image pixel point located inside the normal symptom image one by one. If the pixel value of a certain pixel point exceeds the range of the second normal interval, it is determined as a bruise pixel, so as to effectively identify potential bruise areas by comparing the pixel value with the normal interval; Then, the server needs to perform coordinate processing on the normal symptom image to obtain each bruise coordinate point corresponding to all bruise pixel points. On this basis, a vertical area line passing through the corresponding horizontal coordinate extreme value (i.e., the maximum and minimum points of the bruise area in the X-axis direction) and extending along the Y-axis, and a horizontal area line passing through the corresponding vertical coordinate extreme value (i.e., the maximum and minimum points of the bruise area in the Y-axis direction) and extending along the X-axis are further generated, and based on these two area lines, the boundary framework of the bruise area is jointly formed; Finally, the server can form a normal symptom area corresponding to the bruise attribute based on the vertical area line and the horizontal area line, so as to reflect the actual distribution range of the bruise disease in the normal symptom image based on the normal symptom area, providing an important basis for subsequent diagnosis and treatment.

[0043] Furthermore, in this embodiment, the above "determining normal diagnosis data based on the similarity comparison between the historical symptom image and the normal symptom area" may further include the following steps: Determine the historical symptom area in the historical symptom image that has the same word attribute as the normal symptom area, and perform a similarity comparison between the historical symptom area and the normal symptom area; Calculate the product of the obtained regional similarity and paragraph similarity corresponding to the same historical symptom image with the retrieved regional weight value and paragraph weight value respectively, and calculate the sum of the obtained first confidence value and second confidence value to obtain the comprehensive confidence value corresponding to the historical symptom image; Determine the historical diagnosis data having a diagnostic relationship with the historical symptom image with the largest comprehensive confidence value as the normal diagnosis data corresponding to the normal symptom area.

[0044] For example, in this embodiment, for the acquisition of normal diagnosis data, it can be specifically implemented based on the following method steps: First, assume that in the previous step, the server has identified the normal symptom area and determined its corresponding word attribute (such as swelling or bruising). On this basis, the server can correspondingly determine the historical symptom area having the same word attribute as the normal symptom area from the historical symptom image data for corresponding comparison in the subsequent process; Next, the server can perform a similarity comparison between each obtained historical symptom area and the normal symptom area one by one. For example, an image similarity algorithm such as structural similarity (SSIM) or feature point matching can be used to quantify the similarity degree between the two; Then, for each historical symptom image, the server can calculate the product of the obtained regional similarity corresponding to it and the preset regional weight value to obtain the first confidence value; at the same time, it can also calculate the product of the paragraph similarity between the historical symptom image having a graphic-text relationship with the historical symptom image and the descriptor paragraph and the preset paragraph weight value to obtain the second confidence value; and further sum the obtained first confidence value and second confidence value to obtain the comprehensive confidence value corresponding to the historical symptom image.

[0045] Finally, by comparing the comprehensive confidence values of all historical symptom images, determine the diagnosis data corresponding to the historical symptom image with the largest comprehensive confidence value as the normal diagnosis data corresponding to the normal symptom area to ensure the accuracy and reliability of the diagnosis data and provide strong support for subsequent treatment.

[0046] Through the above method, the present invention realizes the determination of intelligent diagnosis data for the normal symptom area, 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.

[0047] It should be noted that the normal diagnosis data obtained through this application is determined based on the server's similarity comparison between historical symptom data and normal symptom data. Therefore, the actual diagnosis situation may have a certain degree of accuracy discrepancy with the predicted normal diagnosis data. Therefore, in response to the occurrence of such a situation, the medical staff can be given corresponding modification rights based on the contraceptive monitoring platform. That is, if the medical staff determines that the normal diagnosis data filled in the normal display area has a certain degree of inaccuracy based on their own medical experience, they can use the corresponding medical terminal to modify the normal diagnosis data at any time to ensure that the user can accurately know their actual status and determine the subsequent diagnosis method.

[0048] It should be noted that, in this embodiment, the medical terminal can be understood as a terminal used by medical personnel, such as a mobile phone or computer with data processing function.

[0049] In step S103, the following contents are included: In response to the user end creating an interaction with the private display area of ​​the contraceptive monitoring platform, an initial private map is created in the private display area, and the initial private map is updated based on the adjustment interaction of the user end to obtain a current private map.

[0050] For example, in this embodiment, based on the above content, it can be known that for "normal" data, since its privacy requirements are relatively low, it can be directly displayed in the normal display area of ​​the corresponding contraceptive monitoring platform based on the user's upload; and for "private" data, in order to ensure that the user has a certain privacy and help the corresponding medical staff to clearly obtain the corresponding symptom description, a corresponding private display area can be created in the contraceptive monitoring platform at the same time, and the private display area is configured to create a corresponding initial private map in the private display area based on the creation interaction of the user end, so as to further update the initial private map according to the adjustment interaction of the user end to obtain the current private map displayed in the private display area.

[0051] Here, since the initial private map needs to be generated based on the creation interaction of the user side, when the initial private map is created, it can be expressed that the user believes that the private parts corresponding to his own may have adverse effects due to the use of the corresponding contraceptive device, and the user can also update the initial private map according to the specific circumstances of the adverse effects, so that the current private map obtained can reflect the specific circumstances of the corresponding adverse effects as much as possible, thereby facilitating medical staff to make a diagnosis based on the displayed current private map, thereby improving the corresponding diagnostic efficiency and diagnostic accuracy.

[0052] It should be noted that in this embodiment, since the generation of the current private image does not involve the image acquisition of the private parts of the corresponding user, the privacy of the user can be well determined, and thus the corresponding privacy leakage can be prevented.

[0053] Further, in this embodiment, the above "responding to the creation interaction of the user terminal with 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 adjustment interaction of the user terminal to obtain the current private image" may further include the following steps: Responding to the creation interaction of the user terminal with the private display area of the contraceptive monitoring platform, creating an initial private image in the private display area, where the initial private image includes a blood static display area and a blood dynamic display area for filling a human model; Responding to the adjustment interaction of the user terminal with the blood static display area, changing the standard blood pixel value corresponding to the blood static display area, and filling the blood static display area with pixels based on the obtained current blood pixel value; Responding to the adjustment interaction of the user terminal with the blood dynamic display area, positioning the private parts included in the human model, and adjusting the shape of the dynamic blood flow elements anchored to the private parts.

[0054] For example, in this embodiment, the specific implementation of updating the initial private image based on the adjustment interaction of the user terminal is executed based on the following content: First, the server responds to the request of the user terminal for creating an interaction with the private display area of the contraceptive monitoring platform, and automatically creates an initial private image in the private display area. This image includes two key areas, specifically the blood static display area and the blood dynamic display area for filling a human model. Among them, the blood static display area is used to statically display the standard blood status information of the user, that is, the blood color of the corresponding private parts of the user; while the blood dynamic display area creates a human model and dynamically simulates the blood flow situation based on the private parts of the human model, so as to help the user restore as much as possible the blood flow and the like corresponding to the private parts, such as the corresponding flow velocity and flow rate. Next, the server can respond to the adjustment interaction of the user terminal with the blood static display area, and select to adjust the standard blood pixel value according to the user's needs, such as increasing or decreasing pixel brightness, contrast, or color saturation, etc., to reflect the current blood status of the user; at the same time, the server receives these adjustment instructions in real time, and fills the blood static display area with pixels based on the obtained current blood pixel value, so as to generate a personalized static display effect to characterize the specific blood color of the bleeding situation that appears in the private parts of the user through the blood static display area. Finally, the server can also synchronously respond to the adjustment interaction of the client on the blood dynamic display area to accurately locate the private part in the human model, ensuring that the dynamic blood flow elements are accurately anchored to the private part; further, the user can select to adjust the form of the dynamic blood flow elements through the interaction interface, such as changing the blood flow speed, density, etc., to simulate different blood flow conditions, and when it is determined that the blood flow of the corresponding human model is roughly the same as the actual flow of the user's private part, the form of the dynamic blood flow elements anchored to the private part is adjusted accordingly, so as to generate a realistic and personalized dynamic display effect, and respectively display the blood conditions of the user's private part in different states and different dimensions based on the blood static display area and the blood dynamic display area, so that medical staff can quickly obtain the corresponding conditions of the corresponding user.

[0055] It should be noted that in this embodiment, the above-mentioned "standard blood pixel value" can be understood as the corresponding pixel value of the blood flowing out of the private part in a healthy state, and the above-mentioned "human model" is a model with a human shape pre-created by the server. By creating corresponding dynamic blood flow elements, it can express that the private part of the corresponding user is in a state of abnormal bleeding.

[0056] Furthermore, in this embodiment, the above-mentioned "responding to the adjustment interaction of the client on the blood static display area, changing the pixel value of the standard blood pixel value corresponding to the blood static display area, and performing pixel filling on the blood static display area based on the obtained current blood pixel value" may further include the following steps: Retrieve the standard blood pixel value to perform pixel filling on the blood static display area, and divide the blood static display area based on the region center line of the corresponding blood static display area to obtain a change display area and an interaction display area; Respond to the adjustment interaction of the client on the interaction display area, determine the vertical movement amount of the client towards the region center line based on the adjustment interaction, and determine the movement ratio of the vertical movement amount corresponding to the interaction display area; Multiply the movement ratio by the retrieved preset adjustment value to obtain an interaction adjustment value; Perform a summation calculation based on the obtained interaction adjustment value and the standard pixel value, and perform pixel filling on the change display area based on the obtained current blood pixel value.

[0057] For example, in this embodiment, the adjustment of the standard blood pixel value can be specifically implemented based on the following method steps: First, the server can retrieve the standard blood pixel values to fill the pixels of the blood static display area, so as to present a state display of a healthy and standardized blood color. Further, based on the regional center line of the corresponding blood static display area, the server can divide the display area, thus dividing the display area into two major 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 perform adjustment operations; Next, the server responds to the adjustment interaction performed by the client on the interactive display area to determine the vertical movement amount of the client towards the regional center line based on the adjustment interaction. Based on this movement amount, the server can further calculate the movement ratio, that is, the movement ratio of the interactive display area relative to its original position caused by the user based on the adjustment interaction; Then, the server can perform a multiplication operation on the calculated movement ratio and a preset adjustment value to obtain an interactive adjustment value, and further perform a summation operation on the interactive adjustment value and the standard pixel value to obtain the current blood pixel value; Finally, the server can fill the pixels of the variable display area based on this current blood pixel value, so as to update the blood state of the display area in real time to reflect the user's personalized adjustment results. And because during the adjustment interaction process, only the variable display area will perform corresponding pixel changes with the obtained current blood pixel value, while the corresponding interactive display area will always ensure the corresponding color of the corresponding standard blood pixel value, thus enabling a corresponding visual comparison between the current blood pixel value and the standard blood pixel value, so that users and medical staff can quickly determine the blood condition and improve the usability.

[0058] In addition, after completing the corresponding adjustment interaction process of the corresponding blood static display area based on the above content, the relevant introduction of the adjustment interaction of the corresponding blood dynamic display area can be further carried out. That is, in this embodiment, the above "responding to the adjustment interaction of the client on the blood dynamic display area, positioning the private part included in the human model, and adjusting the morphology of the dynamic blood flow elements anchored to the private part" can further include the following steps: Establish a regional coordinate system for the corresponding blood dynamic display area with the model center point of the human model as the origin, and determine the respective model coordinate points that make up the human model based on the regional coordinate system; Determine the model coordinate points that make up the private part contour as the private part coordinate group, and establish a horizontal connection line based on the model coordinate points corresponding to the maximum and minimum horizontal coordinates in the private part coordinate group; Map the vertical horizontal connection line to the regional frame line of the blood dynamic display area in the direction perpendicular to the horizontal connection line, and form an element anchoring area based on the obtained mapped connection line and the horizontal connection line; Anchor the retrieved dynamic blood flow elements with corresponding standard flow rates and standard quantities to the element anchoring area, and when a dynamic blood flow element overlaps with any model coordinate point, hide the model coordinate point; In response to the adjustment interaction of the client on the dynamic blood flow elements, adjust the numerical values of the standard flow rate and / or the standard quantity, and adjust the shape of the dynamic blood flow elements based on the numerical adjustment.

[0059] For example, in this embodiment, for the adjustment interaction of the blood dynamic display area, it can be specifically executed based on the following implementation method: First, the server can use the model center point of the human body model as the origin to construct a regional coordinate system corresponding to the blood dynamic display area, providing a basis for subsequent spatial positioning and dynamic element adjustment. Further, based on the established regional coordinate system, the server accurately determines each model coordinate point 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, each model coordinate point can also be obtained based on the two-dimensional form of the corresponding human body model; Next, the server can screen out the coordinate points that make up the private part contour of the corresponding private part from all model coordinate points and define them as the private part coordinate group, so that the corresponding horizontal connection line can be constructed based on the model coordinate points corresponding to the maximum and minimum horizontal coordinates in the private part coordinate group; Subsequently, the server maps this line to the regional frame line of the blood dynamic display area in a direction perpendicular to the horizontal connection line to form a mapped connection line. These two connection lines jointly define the element anchoring area, providing accurate spatial positioning for the placement of dynamic blood flow elements; Then, the server retrieves the dynamic blood flow elements with corresponding preset standard flow rates and standard quantities and anchors them to the element anchoring area. When a dynamic blood flow element overlaps with any model coordinate point, the server automatically performs a hiding process to ensure that the display of dynamic elements is not interfered by the model framework, thus keeping the interface clear and intuitive; Finally, the server responds to the adjustment interaction of the client on the 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 numerical values of the standard flow rate and / or the standard quantity according to the operation results, based on these adjusted numerical values, the server can synchronously adjust the shape of the dynamic blood flow elements, such as changing the speed of the flow rate and the density distribution of the elements, etc., to reflect the dynamic needs of the user in real time.

[0060] It should be noted that in this embodiment, the user can adjust the dynamic blood flow elements, for example, by means of voice input or text input, etc., to input the corresponding adjustment parameters into the contraceptive monitoring platform to complete the precise adjustment of the dynamic blood flow elements, ensuring that the dynamic blood flow elements can display the shape expected by the user as accurately as possible, so as to improve the subsequent diagnostic accuracy.

[0061] For example, Figure 2 Also shown is a schematic diagram of the private display area in this embodiment. It can be seen that the corresponding private display area includes a static blood display area and a corresponding dynamic blood display area arranged adjacent to each other on the left and right.

[0062] In step S104, the following contents are included: Based on the private diagnosis, determine the private diagnosis data corresponding to the current private picture, and upload the private diagnosis data to the private display area.

[0063] For example, in this embodiment, after obtaining the current private picture, since the user's private part is of higher importance compared to the normal part corresponding to the normal symptom data, the diagnosis of the private part can be completed based on the medical staff's professional experience, and the obtained private diagnosis data is synchronously uploaded to the private display area, so that the user can know their symptom situation and facilitate the implementation of corresponding treatment methods according to the symptom situation.

[0064] In summary, according to the solution of this embodiment, through the intelligent online monitoring and dynamic display functions, this embodiment effectively alleviates the burden on users to frequently go to medical institutions for offline examinations, greatly saves time and transportation costs, and especially provides great convenience for users in remote areas or with inconvenient mobility; at the same time, this embodiment creates a digital health data recording method based on the contraceptive monitoring platform, replacing the 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; In addition, this embodiment also provides a corresponding interaction adjustment mechanism, enabling users to adjust the private display area in real time according to their own situations, 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, discover and respond to potential health risks in a timely manner, thereby improving the overall effect of reproductive health management during contraception.

[0065] Figure 3 Shows a system block diagram of a monitoring data processing system for contraceptive devices proposed in another embodiment of the present invention, as Figure 3As shown, the system includes: A vocabulary extraction module, configured to obtain the normal symptom data uploaded by the user terminal, and perform vocabulary extraction on the normal symptom descriptions included in the normal symptom data to obtain feature vocabulary; A normal diagnosis module, configured to perform region extraction on the normal symptom images included in the normal symptom data based on the feature vocabulary, and determine the normal diagnosis data corresponding to the obtained normal symptom regions based on normal diagnosis, and upload the normal symptom data and the normal diagnosis data to the normal display area of the contraceptive monitoring platform; A private part display module, configured to respond to the user terminal to create an interaction with the private display area of the contraceptive monitoring platform, create an initial private image in the private display area, and update the initial private image based on the adjustment interaction of the user terminal to obtain the current private image; A private diagnosis module, configured to determine the private diagnosis data corresponding to the current private image based on private diagnosis, and upload the private diagnosis data to the private display area.

[0066] 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 in conjunction with the examples of the present invention. Based on the above description, the structure required to construct such a system is obvious. In addition, the present invention is not directed to any particular programming language. It should be understood that the content of the present invention described herein can be implemented using various programming languages, and the description of the specific language above is for the purpose of disclosing the preferred embodiments of the present invention.

[0067] In the specification provided herein, a large number of specific details are set forth. However, it can be understood that the embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures, and technologies have not been shown in detail so as not to obscure the understanding of this specification.

[0068] Similarly, it should be understood that, in order to streamline the present disclosure and assist in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof.

[0069] Those skilled in the art should understand that the modules or units or components of the devices in the examples disclosed herein can be arranged in the devices as described in the embodiments, or alternatively can be located in one or more devices different from the devices in the examples. The modules in the foregoing examples can be combined into one module or further divided into multiple sub-modules.

[0070] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components.

[0071] In addition, those skilled in the art can understand that although some of the embodiments described herein include certain features included in other embodiments rather than other features, the combination of the features of different embodiments means that it is within the scope of the present invention and forms different embodiments.

[0072] In addition, some of the embodiments herein are described as a combination of methods or method elements that can be implemented by a processor of a computer system or by other devices performing the functions. Therefore, a processor having the necessary instructions for implementing the method or method element forms a device for implementing the method or method element. In addition, the elements described herein in the device embodiments are examples of the following devices: the device is used to implement the functions performed by the elements for the purpose of implementing the invention.

[0073] As used herein, unless otherwise specified, the use of ordinal numbers "first", "second", "third", etc. to describe ordinary objects only represents different instances of similar objects, and does not intend to imply that the objects so described must have a given order in terms of time, space, sorting, or in any other way.

[0074] Although the present invention has been described based on a limited number of embodiments, those skilled in the art in this technical field understand that other embodiments can be conceived within the scope of the present invention described herein. In addition, it should be noted that the language used in this specification is mainly selected for the purpose of readability and teaching, rather than for the purpose of explaining or limiting the subject matter of the present invention.

Claims

1. A method for processing monitoring data of contraceptive devices, characterized in that: The following steps are involved: Acquire the normal symptom data uploaded by the user, and perform vocabulary extraction on the normal symptom descriptions included in the normal symptom data to obtain characteristic vocabulary; Extracting regions of normal symptom images included in the normal symptom data based on the characteristic vocabulary, determining normal diagnosis data corresponding to the obtained normal symptom regions based on normalized diagnosis, and uploading the normal symptom data and normal diagnosis data to the normal display area of ​​the contraceptive monitoring platform; In response to the user end creating an interaction with the private display area of ​​the contraceptive monitoring platform, an initial private map is created in the private display area, and the initial private map is updated based on the adjustment interaction of the user end to obtain a current private map; Based on the private diagnosis, private diagnostic data corresponding to the current private graph is determined, and the private diagnostic data is uploaded to the private display area.

2. The monitoring data processing method for contraceptive devices according to claim 1, characterized in that: The normal symptom descriptions included in the normal symptom data are subjected to vocabulary extraction to obtain characteristic vocabulary, including: Obtain the number of horizontal characters in the horizontal arrangement direction corresponding to the normal symptom description and the number of vertical characters in the vertical arrangement direction corresponding to the normal symptom description, and determine the arrangement direction with the larger number of corresponding characters as the character arrangement order; In response to the presence of description characters indicating the meaning of segmentation in the description of normal symptoms, segmentation of the description is performed based on the order of character arrangement to obtain various description sub-paragraphs; Performing semantic recognition on each description character in the same description subparagraph, and determining the word attribute of each description word based on the comparison result between each description word obtained and the retrieved preset feature table; In response to the word attribute of any description word being a swelling attribute, the description word is determined as a characteristic word of the corresponding description subparagraph; In response to the word attribute of any description word being a dark color attribute, the description word is determined as a characteristic word of the corresponding description subparagraph.

3. The monitoring data processing method for contraceptive devices according to claim 2, characterized in that: Extracting a region of a normal symptom image included in the normal symptom data based on the characteristic vocabulary, and determining normal diagnosis data corresponding to the obtained normal symptom region based on normalized diagnosis, including: Retrieving a preset region extraction strategy corresponding to a word attribute to perform region extraction on a normal symptom image included in the normal symptom data to obtain a normal symptom region; Retrieving historical symptom descriptions based on the traceability information of the corresponding user's contraceptive device, and performing similarity comparison between all historical symptom descriptions containing characteristic words and the description sub-paragraphs; In response to a paragraph similarity of a historical symptom description being greater than a preset similarity, it is determined as normal diagnosis data; In response to the paragraph similarity of the plurality of historical symptom descriptions being greater than a preset similarity, the retrieved historical diagnosis data having a diagnosis relationship with the historical symptom description having the greatest paragraph similarity is determined as the normal diagnosis data corresponding to the normal symptom region; If all the paragraph similarities obtained in response are less than or equal to the preset similarity, a historical symptom image having a graphic relationship with the historical symptom description is retrieved, and normal diagnosis data is determined based on a similarity comparison between the historical symptom image and the normal symptom area.

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 attribute is called to perform region extraction on the normal symptom image included in the normal symptom data to obtain the normal symptom region, including: The attribute of the response word is the attribute of swelling, the mean of each image pixel located at the edge of the normal symptom image is calculated, and the first normal interval is established with the obtained pixel mean as the interval center value; In response to any image pixel located inside the normal symptom image corresponding to being outside the first normal interval, it is determined as a swelling pixel; Connecting all swollen pixel points at adjacent positions to obtain a first connection area; In response to the area size of the connected area being greater than a preset swelling size, the connected area is determined as a normal symptom area corresponding to the 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 attribute is called to perform region extraction on the normal symptom image included in the normal symptom data to obtain the normal symptom region, including: The attribute of the response word is the sulphur attribute, the mean of each image pixel located at the edge of the normal symptom image is calculated, and the second normal interval is established with the obtained pixel mean as the interval center value; In response to any image pixel located inside the normal symptom image corresponding to being outside the second normal interval, it is determined as a dark-colored pixel; Based on the coordinate processing of the normal symptom image, the sludge coordinate points corresponding to all the sludge pixel points are obtained, and the vertical area line extending along the Y axis and the horizontal area line extending along the X axis are generated. Based on the vertical area lines and the horizontal area lines, normal symptom areas with corresponding turbidity attributes are formed.

6. The monitoring data processing method for contraceptive devices according to claim 3, characterized in that: Normal diagnostic data is determined based on similarity comparison between historical symptom images and normal symptom areas, including: Determine a historical symptom region in the historical symptom image that has the same word attributes as the normal symptom region, and perform a similarity comparison between the historical symptom region and the normal symptom region; The obtained regional similarity and paragraph similarity corresponding to the same historical symptom image are respectively multiplied by the retrieved regional weight value and paragraph weight value, and the obtained first confidence value and second confidence value are summed to obtain a comprehensive confidence value of the corresponding historical symptom image; The retrieved historical diagnosis data having a diagnosis relationship with the historical symptom image having the largest corresponding comprehensive confidence value is determined as the normal diagnosis data corresponding to the normal symptom area.

7. The monitoring data processing method for contraceptive devices according to claim 1, characterized in that: In response to the user end creating an interaction with the private display area of ​​the contraceptive monitoring platform, an initial private map is created in the private display area, and the initial private map is updated based on the adjustment interaction of the user end to obtain a current private map, including: In response to the user end creating an interaction with the private display area of ​​the contraceptive monitoring platform, an initial private map is created in the private display area, wherein the initial private map includes a blood static display area and a blood dynamic display area filled with a human body model; In response to the user terminal adjusting the blood static display area, the standard blood pixel value corresponding to the blood static display area is changed, and the blood static display area is filled with pixels based on the obtained current blood pixel value; In response to the user's interaction with adjusting the blood dynamic display area, the private part of the human body model is positioned, and the dynamic blood flow elements anchored in the private part are morphologically adjusted.

8. The monitoring data processing method for contraceptive devices according to claim 7, characterized in that: In response to the user end adjusting the blood static display area, the standard blood pixel value corresponding to the blood static display area is changed, and the blood static display area is filled with pixels based on the obtained current blood pixel value, including: Retrieving standard blood pixel values ​​to fill pixels in the blood static display area, and dividing the blood static display area based on the area center line corresponding to the blood static display area to obtain a changing display area and an interactive display area; In response to the user terminal adjusting the interactive display area, determining the vertical movement amount of the user terminal toward the center line of the area based on the adjustment interaction, and determining the movement proportion of the interactive display area corresponding to the vertical movement amount; The mobile ratio is multiplied by the retrieved preset adjustment value to obtain the interactive adjustment value; A sum calculation is performed based on the obtained interactive adjustment value and the standard pixel value, and pixel filling is performed on the change display area based on the obtained current blood pixel value.

9. The monitoring data processing method for contraceptive devices according to claim 8, characterized in that: In response to the user end adjusting and interacting with the blood dynamic display area, the private part of the human body model is positioned, and the dynamic blood flow elements anchored in the private part are morphologically adjusted, including: A regional coordinate system corresponding to the blood dynamic display area is established with the model center point of the human body model as the origin, and each model coordinate point constituting the human body model is determined based on the regional coordinate system; Determine the model coordinate points constituting the private part contour as a private part coordinate group, and establish a transverse connecting line based on the model coordinate points corresponding to the transverse coordinate maximum value and the transverse coordinate minimum value in the private part coordinate group; Mapping the vertical and horizontal connecting lines to the regional frame lines of the blood dynamic display area in the direction perpendicular to the horizontal connecting lines, and forming an element anchoring area based on the obtained mapped connecting lines and horizontal connecting lines; Anchor the retrieved dynamic blood flow elements corresponding to the standard flow rate and standard quantity to the element anchoring area, and when the dynamic blood flow elements overlap with any model coordinate point, hide the model coordinate point; In response to the user terminal's interaction to adjust the dynamic blood flow element, the standard flow rate and / or the standard quantity are numerically adjusted, and the dynamic blood flow element is morphologically adjusted based on the numerical adjustment.

10. A monitoring data processing system for contraceptive devices, characterized in that: include: The vocabulary extraction module is configured to obtain the normal symptom data uploaded by the user end, and perform vocabulary extraction on the normal symptom description included in the normal symptom data to obtain characteristic vocabulary; A normal diagnosis module is configured to extract a region of a normal symptom image included in the normal symptom data based on a characteristic vocabulary, determine normal diagnosis data corresponding to the obtained normal symptom region based on normalized diagnosis, and upload the normal symptom data and the normal diagnosis data to a normal display area of ​​the contraceptive monitoring platform; The private part display module is configured to privately respond to the user end to create an interaction with the private display area of ​​the contraceptive monitoring platform, create an initial private map in the private display area, and update the initial private map based on the adjustment interaction of the user end to obtain a current private map; The private diagnosis module is configured to determine private diagnosis data corresponding to the current private graph based on the private diagnosis, and upload the private diagnosis data to the private display area.

Images