Health detection data processing method and device based on large model, equipment and medium

Abstract

The present disclosure provides a large model-based health detection data processing method, device, equipment and medium, the method comprising: obtaining a target detection image input by a user; obtaining a first analysis result and first indication information from the target detection image according to a large model, the first indication information being used to indicate a next interaction operation; in response to the next interaction operation being a display result, displaying the first analysis result to the user; or, in response to the next interaction operation being a follow-up interaction, dynamically generating at least one question according to a large model and displaying the at least one question to the user; obtaining a question answer input by the user for the at least one question, generating a second analysis result from the target detection image, the first analysis result, the at least one question and the question answer according to a large model, and displaying the second analysis result to the user. The present disclosure improves the detection accuracy of the target detection image.

Description

Technical Field

[0001] This disclosure relates to the fields of health management and artificial intelligence technology, specifically to a method, apparatus, equipment, and medium for processing health monitoring data based on a large model. Background Technology

[0002] With the development of internet-based healthcare, users can upload test strip images to health applications or smart agents via mobile devices. The health applications or smart agents can then detect the test strip images and display the test results to the user.

[0003] However, current health-related applications or AI agents can only perform simple image recognition on test strip images, resulting in inaccurate test results. Furthermore, most health-related applications only support specific brands of test strips, lacking universal applicability. Additionally, the test results displayed by current health-related applications or AI agents are limited, leaving users unsure of subsequent steps after receiving the results, negatively impacting user experience. Moreover, there is currently a lack of systematic management of test results. Summary of the Invention

[0004] This disclosure aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, the purpose of this disclosure is to propose a health detection data processing method, apparatus, electronic device, and storage medium based on a large model. The embodiments of this disclosure do not simply perform image recognition on the target detection image (such as a test strip image or test strip packaging image). Instead, after the initial analysis of the target detection image, further interaction with the user is conducted to ask at least one question and obtain the user's input answer. Based on the initial analysis result, at least one question, and the answer, the target detection image is analyzed again to obtain the final analysis result. Thus, through two rounds of image analysis and the introduction of follow-up interaction with the user, the actual situation of the user using the test strip is supplemented, which is beneficial for further analysis and judgment by the large model and can greatly improve the detection accuracy of the target detection image.

[0006] To achieve the above objectives, the health monitoring data processing method based on a large model proposed in the first aspect of this disclosure includes:

[0007] Acquire the target detection image input by the user; Based on the analysis of the target detection image using the large model, a first analysis result and a first indication information are obtained. The first indication information is used to indicate the next interactive operation. In response to the next interactive operation being to display the result, the first analysis result is displayed to the user; or, in response to the next interactive operation being to ask follow-up questions, at least one question is dynamically generated based on the large model, and the at least one question is displayed to the user. Obtain the answer to the question input by the user for the at least one question, generate a second analysis result based on the target detection image, the first analysis result, the at least one question, and the answer to the question using a large model, and display the second analysis result to the user.

[0008] To achieve the above objectives, the second aspect of this disclosure provides a health monitoring data processing apparatus based on a large model, comprising: The acquisition module is used to acquire the target detection image input by the user; The analysis module is used to analyze the target detection image according to the large model to obtain a first analysis result and a first indication information, wherein the first indication information is used to indicate the next interactive operation; The first processing module is configured to, in response to the next interactive operation being to display the result, display the first analysis result to the user; or, in response to the next interactive operation being to ask follow-up questions, dynamically generate at least one question based on the large model and display the at least one question to the user. The second processing module is used to obtain the answer to the question input by the user for the at least one question, generate a second analysis result based on the target detection image, the first analysis result, the at least one question, and the answer to the question according to the large model, and display the second analysis result to the user.

[0009] An electronic device according to a third aspect of this disclosure includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method as described in the first aspect of this disclosure.

[0010] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method as described in the first aspect of this disclosure.

[0011] A fifth aspect of this disclosure provides a computer program product that, when instructions in the computer program product are executed by a processor, performs the method as described in the first aspect of this disclosure.

[0012] The health detection data processing method, apparatus, electronic device, and storage medium based on a large model disclosed herein can acquire a target detection image input by a user, analyze the target detection image according to the large model to obtain a first analysis result and a first indication information, wherein the first indication information is used to indicate the next interactive operation; in response to the next interactive operation, if the result is displayed, the first analysis result is displayed to the user; or, in response to the next interactive operation, if the question is followed up, at least one question is dynamically generated according to the large model and displayed to the user; the answer to the question input by the user for the at least one question is acquired, and a second analysis result is generated according to the target detection image, the first analysis result, the at least one question, and the question answer based on the large model, and the second analysis result is displayed to the user. Therefore, it can be seen that the embodiments of this disclosure do not simply perform image recognition on the target detection image (such as the test strip image or the test strip packaging image), but after the initial analysis of the target detection image, further interaction with the user is conducted to ask the user at least one question and obtain the answer to the question input by the user. Based on the initial analysis result, at least one question, and the answer to the question, the target detection image is analyzed again to obtain the final analysis result. Thus, through two rounds of image analysis and the introduction of interaction with the user to supplement the actual situation of the user's use of the test strip, it is beneficial to the further analysis and judgment of the large model, which can greatly improve the detection accuracy of the target detection image.

[0013] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0014] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which: Figure 1A This is a flowchart illustrating a health monitoring data processing method based on a large model, as proposed in an embodiment of this disclosure. Figure 1B This is a schematic diagram of a real-time shooting mode proposed in an embodiment of this disclosure; Figure 1C This is a schematic diagram showing the first analysis result of a test strip image according to an embodiment of the present disclosure; Figure 1D This is a schematic diagram showing the first analysis result of a test strip packaging image according to an embodiment of the present disclosure; Figure 1E This is a schematic diagram illustrating at least one problem addressed by an embodiment of this disclosure; Figure 2A This is a flowchart illustrating a health monitoring data processing method based on a large model, as proposed in another embodiment of this disclosure. Figure 2BThis is a schematic diagram of a re-entry image prompt according to an embodiment of this disclosure; Figure 2C This is a schematic diagram of a re-entry image prompt according to an embodiment of this disclosure; Figure 3A This is a flowchart illustrating a health monitoring data processing method based on a large model, as proposed in another embodiment of this disclosure. Figure 3B This is a schematic diagram of a detection record list proposed in an embodiment of this disclosure; Figure 3C This is a schematic diagram of an edit detection record according to an embodiment of this disclosure; Figure 3D This is a schematic diagram of a detection calendar proposed in an embodiment of this disclosure; Figure 3E and Figure 3F This is a schematic diagram of a retest reminder creation page according to an embodiment of this disclosure; Figure 4 This is a schematic diagram of the structure of a detection device according to an embodiment of this disclosure; Figure 5 This is a block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0015] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are used only to explain this disclosure, and should not be construed as limiting this disclosure. Rather, embodiments of this disclosure include all variations, modifications, and equivalents falling within the spirit and scope of the appended claims.

[0016] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0017] Optionally, it should be noted that the execution subject of the health detection data processing method based on the large model in this embodiment is a detection device. The device can be implemented by software and / or hardware. The device can be configured in an electronic device, which may include, but is not limited to, a terminal, a server, etc. For example, the terminal may be a mobile phone, a PDA, etc.

[0018] Figure 1AThis is a flowchart illustrating a health monitoring data processing method based on a large model, as proposed in one embodiment of this disclosure. Figure 1A As shown, this health monitoring data processing method based on a large model includes: S101: Acquire the target detection image input by the user.

[0019] Optionally, the type of target detection image may include a test strip image or a test strip packaging image.

[0020] Optionally, in some embodiments, the acquisition mode of the target detection image may include, for example, a real-time shooting mode or an album selection mode. Optionally, Figure 1B This is a schematic diagram of a real-time shooting mode proposed in an embodiment of this disclosure, as shown below. Figure 1B As shown, the real-time shooting mode may include, for example, in response to detecting a user's selection of the "take a picture" button, calling the built-in camera module to display... Figure 1B The camera page shown on the right allows users to take pictures of the test strip or test strip packaging on-site. In response to the detection of the user's selection of the "Shoot" button on the camera page, the camera page captures an image of the test strip or test strip packaging and identifies the captured image as the target detection image.

[0021] Optionally, the album selection mode may include: in response to detecting a user's selection operation on the "Album" button, retrieving the local album image library for the user to select a saved test strip image or test strip packaging photo from it; and in response to detecting a user's selection operation on any test strip image or any test strip packaging photo in the local album image library, determining the image selected by the user as the target detection image.

[0022] Optionally, the "selection operation" mentioned above may include, for example, a click operation, a double-click operation, a long-press operation, etc.

[0023] Optionally, Figure 1B The display page shown on the left could be, for example, a "Test Management Homepage". Optionally, accessing the "Test Management Homepage" could include: when a user selects a "Test Management Card" in the "Health Management Homepage", the user is redirected to... Figure 1B The detection management homepage shown allows users to obtain target detection images input by the user through either real-time shooting mode or album selection mode.

[0024] S102: Analyze the target detection image based on the large model to obtain the first analysis result and the first indication information.

[0025] Optionally, the first indication information can be used to indicate the next interactive operation, which may include, for example, displaying the result or asking follow-up questions.

[0026] Optionally, when analyzing the target detection image, the analysis can be based on at least one of preset information, user profile information, and the user's historical testing records (such as testing records from the past month) to obtain a first analysis result and first indication information. Optionally, the preset information can be used, for example, to indicate the testing standards and / or usage steps of different brands of test strips. By introducing preset information to analyze the target detection image, compatibility with various brands of test strips is achieved, not limited to the identification of specific brands, thereby improving the universality of the method disclosed herein. Furthermore, targeted identification and detection of various brands of test strips can be performed based on their testing standards, improving the accuracy of identification and detection.

[0027] Optionally, a first prompt word can be determined first, which may include, for example, a classified image and an analyzed image. Then, a large model (e.g., a multimodal model) can be invoked based on the first prompt word to classify and analyze the target detection image. Optionally, the input of the large model may include at least one of preset information, user profile information, the user's historical detection records, and target detection images. The output of the large model may include a first analysis result and a first indication information.

[0028] In some embodiments, the process of classifying and analyzing target detection images using a large model may include, for example, the large model first identifying the type of the target detection image. Optionally, when a single or double-line result region is identified in the target detection image, the target detection image type can be determined to be a test strip image. When a packaging kit containing brand information, operation instructions, etc., is identified in the target detection image, the target detection image type can be determined to be a test strip packaging image. Optionally, the large model analyzes different types of target detection images in different ways. In some embodiments, when the target detection image type is a test strip image, the test strip brand and test strip type can be analyzed and identified. Based on preset information, the detection standard of the test strip brand can be determined. Based on the detection standard, test strip type, and target detection image, the test strip is detected and a first analysis result is output. In other embodiments, when the target detection image type is a test strip packaging image, the test strip type corresponding to the test strip packaging, the test strip brand corresponding to the test strip packaging, and the test strip purpose corresponding to the test strip packaging can be analyzed and identified. Based on preset information, the usage steps and precautions of the test strip brand corresponding to the test strip packaging are determined and a first analysis result is output.

[0029] Optionally, in some embodiments, the first analysis result may include, for example, the type of the target detection image and / or sub-results. Optionally, the sub-results may differ for different types of target detection images. In some embodiments, when the target detection image type is a test strip image, the sub-result may include at least one of the following: test strip detection result, test strip type, health advice, and the status of the test strip detection result; optionally, the status may include a normal status or an abnormal status. In other embodiments, when the target detection image type is a test strip packaging image, the sub-result may include at least one of the following: the test strip type corresponding to the test strip packaging, the test strip brand corresponding to the test strip packaging, the test strip purpose corresponding to the test strip packaging, the test strip usage steps corresponding to the test strip packaging, and precautions for using the test strip corresponding to the test strip packaging.

[0030] Optionally, in some embodiments, when the large model analyzes key information such as the test strip type, test strip brand, and test strip purpose corresponding to the target detection image, it can first determine whether the target detection image includes relevant text recordings of the test strip type, test strip brand, and test strip purpose. If relevant text recordings are included, the large model can directly determine the test strip type, test strip brand, and test strip purpose based on the text recordings. If relevant text recordings are not included, the large model can extract relevant features of the test strip or test strip packaging (such as the shape and structure of the test strip) based on the target detection image, and compare the similarity of these features with feature templates in a pre-built sample library of test strips or test strip packaging to identify the test strip type, test strip brand, and test strip purpose corresponding to the target detection image.

[0031] Optionally, in some embodiments, the confidence level of the first analysis result can be determined. For example, when any key information such as test strip type, test strip brand, or test strip purpose is missing in the first analysis result, or when the similarity between the relevant features of the test strip or test strip packaging in the target detection image and the feature template in the sample library is lower than a predetermined value, the confidence level of the first analysis result is determined to be low, such as lower than a first threshold. Optionally, when the similarity between the relevant features of the test strip or test strip packaging in the target detection image and the feature template in the sample library is higher than a predetermined value, the confidence level of the first analysis result is determined to be high, such as higher than the first threshold. Optionally, when the confidence level of the first analysis result is higher than the first threshold, it indicates that the first analysis result is relatively accurate, and the next interactive operation is determined to be displaying the result; or, when the confidence level of the first analysis result is lower than the first threshold, it indicates that the first analysis result is inaccurate or missing key information, and the next interactive operation is determined to be follow-up questioning.

[0032] It should be noted that the above-mentioned "confidence level determination method" is only an exemplary introduction to this disclosure, and other similar determination methods should also fall within the scope of protection of this disclosure.

[0033] S103: In response to the next interactive operation, display the results and show the first analysis result to the user.

[0034] Optionally, Figure 1C This is a schematic diagram showing the first analysis result of a test strip image according to an embodiment of the present disclosure, as shown below. Figure 1C As shown, it can display whether the test strip result is positive, whether the test strip result is abnormal, and it can also display health advice (i.e., Figure 1C (The interpretation shown).

[0035] Optionally, Figure 1D This is a schematic diagram showing the first analysis result of a test strip packaging image according to an embodiment of the present disclosure, as shown below. Figure 1D As shown, it can display the brand of the test strip corresponding to the packaging, as well as the usage steps for the test strip.

[0036] S104: In response to the next interactive action being a follow-up question, dynamically generate at least one question based on the large model and display at least one question to the user.

[0037] Optionally, the at least one question can be dynamically generated by a large model. Optionally, the total number of questions can be less than or equal to a second threshold, such as 5. By setting a smaller number of questions, excessive interruptions to the user flow can be avoided. Optionally, the at least one question can include at least one or more of the following: test strip brand, test item, test time. Each question includes question text, option name, default value, etc. For example, the option names corresponding to the aforementioned test items can include at least one or more of the following: pregnancy test, ovulation test, Helicobacter pylori test, lactose intolerance test, influenza / COVID-19 test, kidney damage test, vitamin D test, calcium test, myocarditis test, vaginal inflammation test, hepatitis B / C test, sexually transmitted disease test, HPV test, and other tests.

[0038] Optionally, the method for dynamically generating at least one question in a large model may include: when the confidence level of the first analysis result is low due to missing key information, and a follow-up interaction is required, the generated question can be determined based on the missing key information in the first analysis result. For example, when the first analysis result lacks the test strip brand, the generated question should at least include "test strip brand"; when the first analysis result lacks the test strip type or test strip purpose, the generated question should at least include "test item". Alternatively, when the confidence level of the first analysis result is low due to the similarity between the relevant features of the test strip or test strip packaging in the target detection image and the feature templates in the sample library being lower than a predetermined value, and a follow-up interaction is required, the generated question should at least include the test strip brand and the test item.

[0039] Optionally, the generated option name for the "test strip brand" question may include, for example, the test strip brands corresponding to the top N test strips in the sample library that have the highest similarity to the test strips in the target detection image. The default value for the "test strip brand" question may be: the test strip brand corresponding to the test strip in the sample library that has the highest similarity to the test strips in the target detection image, where N is a positive integer, and N is less than or equal to a first value, such as 5.

[0040] Optionally, the option name generated for the "Detection Item" question may include, for example, the detection items corresponding to the top M test strips in the sample library that have the highest similarity to the test strips in the target detection image. The default value for the "Detection Item" question may be: the detection items corresponding to the test strips in the sample library that have the highest similarity to the test strips in the target detection image, where M is a positive integer, M is less than or equal to a second value, such as 6.

[0041] Optionally, the option name generated for the "detection time" issue may include at least one time period, where the time difference between each time period and the current time does not exceed a preset time threshold. This at least one time period may include, for example, within 10 minutes before the current time, or 10-20 minutes from the current time. Optionally, the default value for the "detection time" issue can be: the time period closest to the current time, for example, within 10 minutes before the current time.

[0042] Optionally, Figure 1E This is a schematic diagram illustrating at least one problem addressed by an embodiment of this disclosure, such as... Figure 1E As shown, the question options support single selection or multiple options laid out side-by-side. Each question corresponds to a different option style. All questions are required fields. The displayed page includes the question text, option names, and default values ​​determined by the overall model. Optionally, users can select an option in the question text to input the answer. If no option is selected, the default value of the question text will be used as the answer. Optionally, a "Go to Analysis" button is displayed at the bottom of the page. It is not selectable by default. After all required questions are selected, the "Go to Analysis" button supports selection operations, such as clicking, double-clicking, and long-pressing.

[0043] S105: Obtain the answer to the question input by the user for at least one question, generate a second analysis result based on the target detection image, the first analysis result, at least one question, and the question answer, and display the second analysis result to the user.

[0044] Optionally, in response to receiving a user's selection of the "Go to Analyze" button, the "Go to Analyze" button is changed to an unselectable state. At the same time, the user's answer to at least one question is obtained, and a second analysis result is determined based on at least one of the following: the target detection image, the first analysis result, at least one question, the answer to the question, preset information, user profile information, and historical detection records.

[0045] Optionally, in some embodiments, the aforementioned large model can be invoked to determine the second analysis result. For example, a second prompt word can be determined first, which may be used to determine the final analysis result. Based on the second prompt word, the large model is invoked again to analyze the target detection image to determine the final analysis result (i.e., the second analysis result). Optionally, the input to the large model can be at least one of the following: the target detection image, the analysis context (analysis_context) from the last analysis of the target detection image, at least one question, the question answer, preset information, user profile information, and historical detection records. The output of the large model can be the second analysis result. Optionally, the aforementioned analysis context may include the first analysis result.

[0046] Optionally, the process of the large model determining the second analysis result may include: the large model first determines the type of the target detection image based on the first analysis result in the analysis context; when the target detection image type is a test strip image, the large model determines key information such as the test strip brand and test strip type based on at least one question and the question answer; determines the detection standard of the test strip brand based on preset information; and performs detection on the test strip based on the detection standard, test strip type, analysis context, and target detection image, and outputs the second analysis result. In other embodiments, when the target detection image type is a test strip packaging image, the large model determines the test strip type corresponding to the test strip packaging, the test strip brand corresponding to the test strip packaging, and the test strip purpose corresponding to the test strip packaging based on at least one question and the question answer; determines the usage steps and precautions of the test strip brand corresponding to the test strip packaging based on preset information and analysis context, and outputs the second analysis result.

[0047] Optionally, in the above process, the large model can directly reuse the target detection image type of the first analysis result in the analysis context without redetermining the target detection image type. Furthermore, the large model can continue to infer the target detection image based on the analysis context. This can save the analysis steps and computing power of the large model's secondary calls, thereby improving efficiency and saving costs.

[0048] Optionally, the second analysis result may include the type of the target detection image and / or sub-results. Optionally, the sub-results may differ for different types of target detection images. In some embodiments, when the target detection image is a test strip image, the sub-result may include at least one of the following: test strip detection result, test strip type, health advice, and the status of the test strip detection result; optionally, the status may include a normal status or an abnormal status. In other embodiments, when the target detection image is a test strip packaging image, the sub-result may include at least one of the following: the test strip type corresponding to the test strip packaging, the test strip brand corresponding to the test strip packaging, the test strip purpose corresponding to the test strip packaging, the test strip usage steps corresponding to the test strip packaging, and the precautions for using the test strip corresponding to the test strip packaging.

[0049] Optionally, in some embodiments, when at least one question is displayed to the user, a first analysis result can be cached. Furthermore, when an answer to the question is obtained, it can be determined whether the caching duration of the first analysis result exceeds a third threshold, such as 30 minutes. Optionally, the caching duration can be the time between the initial caching time (i.e., the time when at least one question is displayed to the user) and the current time. Optionally, if the caching duration does not exceed the third threshold, a second analysis result is determined and displayed to the user. Optionally, if the caching duration exceeds the third threshold, a timeout prompt is displayed to the user, such as "Analysis has timed out, please take another photo."

[0050] Optionally, without a "cache timeout re-analysis" mechanism, when a user exits midway through answering a question, the first analysis result of the target detection image will be shelved for a long time and will continue to accumulate, occupying cloud database or memory storage space. However, in this embodiment of the disclosure, a cache timeout automatic invalidation rule is set by a third threshold. When the cache times out, it is determined that the first analysis result is invalid, so the first analysis result is no longer retained, realizing automatic clearing of cached data, controlling storage resource occupation, and ensuring long-term stable operation of the system.

[0051] Optionally, in some embodiments, during steps S101-S105 above, if the network is interrupted and image upload fails, an error message can be displayed, such as "Network error, please check your network and try again." When timeout occurs, if the analysis time of the target detection image exceeds a threshold, such as 10 seconds, an error message can be displayed, such as "Network is malfunctioning, please try again later." When an error occurs while calling the large model interface, an error message can be displayed, such as "Service error, please try again later." Optionally, after a period of time (e.g., 3 seconds), the page automatically redirects back to the detection management homepage. Users can return to the health management homepage by clicking the "x" in the upper right corner of the form on the detection management homepage.

[0052] In summary, the health detection data processing method based on a large model provided in this disclosure can acquire a target detection image input by a user, the type of which includes a test strip image or a test strip packaging image; analyze the target detection image to obtain a first analysis result and first indication information, the first indication information being used to indicate the next interactive operation; in response to the next interactive operation, display the result by showing the first analysis result to the user; or, in response to the next interactive operation, ask follow-up questions by determining at least one question and displaying at least one question to the user; acquire the answer to the question input by the user for the at least one question; determine a second analysis result based on the target detection image, the first analysis result, the at least one question, and the question answer; and display the second analysis result to the user. Therefore, it can be seen that the embodiments of this disclosure do not simply perform image recognition on the test strip image or test strip packaging image. Instead, after the initial analysis of the test strip image or test strip packaging image, further interaction with the user is conducted to ask the user at least one question and obtain the answer to the question input by the user. Based on the initial analysis result, at least one question, and the answer to the question, the test strip image or test strip packaging image is analyzed again to obtain the final analysis result (i.e., the second analysis result). Thus, through two rounds of image analysis and the introduction of interaction with the user, the detection accuracy of the test strip or test strip packaging can be greatly improved.

[0053] Furthermore, in the above embodiments, the first or second analysis results displayed include health advice. Based on this health advice, users can determine subsequent actions, avoiding the situation in related technologies where users cannot understand the results after completing the test strip test and do not know what to do next, thus improving the user experience.

[0054] Figure 2A This is a flowchart illustrating a health monitoring data processing method based on a large model, as proposed in one embodiment of this disclosure. Figure 2A As shown, this health monitoring data processing method based on a large model includes: S201: Obtain the target detection image input by the user.

[0055] For a detailed description of step S201, please refer to the description of step S101 above.

[0056] S202: Determine whether the target detection image is a valid image.

[0057] Optionally, in some embodiments, a third prompt word can be determined first. This third prompt word can be, for example, a validity judgment or validity verification. Then, based on the third prompt word, a large model can be invoked to determine whether the target detection image is a valid image. For example, the large model can identify whether the target detection image is clear and whether it contains a valid region. Optionally, the valid region can include at least one of the following: a single / double line result area on the test strip, a brand information area on the test strip packaging, or an instruction diagram area on the test strip packaging.

[0058] Optionally, the input to the large model can be a target detection image, and the output can be a valid boolean value. Optionally, when the large model determines that the target detection image is not clear or does not contain a valid region, it determines that the target detection image is not a valid image, and the large model outputs valid=false. When the large model determines that the target detection image is clear and contains a valid region, it determines that the target detection image is a valid image, and the large model outputs valid=true.

[0059] S203: In response to the target detection image being invalid, display a rejection prompt or a prompt to re-enter an image to the user.

[0060] Optionally, when the target detection image is not a valid image, it indicates that the large model cannot analyze and process the target detection image. In this case, a rejection prompt can be displayed to the user, such as directly displaying: valid=false, etc.; or, a prompt can be displayed to the user to re-enter the image. Optionally, Figure 2B This is a schematic diagram of a re-entry image prompt according to an embodiment of this disclosure, as shown below. Figure 2B As shown, the message "No valid test strip information detected, please re-upload the image" may be displayed. If the user remains on this page, the process will terminate; if the user selects the "Retake Photo" button, the process can return to the previous screen. Figure 1B The camera page is shown. Optionally, the selected command may include, for example, a single-click command, a double-click command, a long-press command, etc.

[0061] S204: In response to the target detection image being a valid image, analyze the target detection image based on the large model to obtain a first analysis result and a first indication information.

[0062] S205: In response to the next interactive operation, display the results and show the first analysis result to the user.

[0063] S206: In response to the next interactive action being a follow-up question, dynamically generate at least one question based on the large model and display at least one question to the user.

[0064] S207: Obtain the answer to the question input by the user for at least one question, generate a second analysis result based on the target detection image, the first analysis result, at least one question, and the question answer, and display the second analysis result to the user.

[0065] For a detailed description of steps S204-207, please refer to the description of steps S102-105 above.

[0066] Optionally, based on the aforementioned steps S201-S206, after acquiring the target detection image input by the user, the next display page that the detection device jumps to displays the first analysis result, at least one problem, a rejection prompt, or a prompt to re-enter the image. Optionally, a progress bar can be displayed in real time during the jump to the next display page, for example: a. Progress ranges from 0-60%, with a time interval of 0-1.5 seconds, changing at a constant rate; b. Progress 60-85%, time range 1.5s-4s; c. Progress 85%-99%, time interval 4 seconds minus interface timeout. d. Progress is 100%, and the content to be displayed on the next page changes instantaneously. Optionally, in step 207 above, after obtaining the answer to the question entered by the user for at least one question, the next display page that the detection device jumps to is to display the second analysis result. Optionally, during the jump to the second analysis result display page, a jump progress bar can also be displayed in the manner described above.

[0067] Optionally, Figure 2C This is a flowchart illustrating a health monitoring data processing method based on a large model, as proposed in one embodiment of this disclosure. Figure 2C The detailed process of "using different prompt words to invoke a large model to achieve multi-stage analysis" is shown in detail, such as... Figure 2CAs shown, the system can first acquire the target detection image uploaded by the user and then redirect to the analysis page. During the redirection, a thumbnail of the target detection image and a progress bar can be displayed. Furthermore, a large model can be invoked based on a third prompt to verify the validity of the target detection image. For details regarding the input and output of the large model and how validity verification is performed, please refer to the description of step S202 above. Optionally, if the target detection image is determined to be invalid, the user can be prompted to retake the photo. If the target detection image is determined to be valid, a large model can be invoked based on the first prompt to perform deep analysis on the target detection image, and the first analysis result and first indication information can be output. For details regarding this part, please refer to the description of step S102 above. Furthermore, in some embodiments, when the first instruction information indicates that the next interactive operation is to display the result, the first analysis result can be directly displayed to the user. When the first instruction information indicates that the next interactive operation is to ask follow-up questions, at least one question can be determined, at least one question can be displayed to the user, and the first analysis result can be cached. In response to obtaining the answer to the question from the user and detecting the user's selection of the "Go to Analysis" button, the large model is called again based on the second prompt word to perform depth analysis on the target detection image to determine the second analysis result, and the second analysis result is displayed to the user. For details on the "determine the second analysis result" part, please refer to the description of the aforementioned step S105.

[0068] In summary, in this embodiment of the present disclosure, before performing depth analysis on the target detection image, an initial image screening and verification is performed to determine whether the target detection image is a recognizable and valid image. Only when the target detection image is a valid image is subsequent depth analysis performed on it. This initial image screening mechanism filters out invalid images without recognition value, avoids performing multimodal model analysis on invalid images, reduces unnecessary computational power consumption, improves processing efficiency, and saves computing resources.

[0069] Figure 3A This is a flowchart illustrating a health monitoring data processing method based on a large model, as proposed in one embodiment of this disclosure. Figure 3A As shown, this health monitoring data processing method based on a large model includes: S301: Acquire the target detection image input by the user.

[0070] S302: Analyze the target detection image based on the large model to obtain the first analysis result and the first indication information.

[0071] S303: In response to the next interactive operation, display the results and show the first analysis result to the user.

[0072] S304: In response to the next interactive action being a follow-up question, dynamically generate at least one question based on the large model and display at least one question to the user.

[0073] S305: Obtain the answer to the question input by the user for at least one question, generate a second analysis result based on the target detection image, the first analysis result, at least one question, and the question answer, and display the second analysis result to the user.

[0074] For a detailed description of steps 301-305, please refer to the description of steps 101-105 above.

[0075] S306: Generate detection records.

[0076] Optionally, a test record can be generated based on the displayed first or second analysis result. Optionally, the test record may include at least one of the following: test strip type, test time, test strip test result, and the status of the test strip test result (e.g., normal or abnormal status).

[0077] Figure 3B This is a schematic diagram of a detection record list proposed in one embodiment of this disclosure. For example... Figure 3B As shown, optionally, the test record list can display all historical test records in reverse chronological order. Optionally, the test record can record either the first or second analysis result corresponding to the test strip image, but not the first or second analysis result corresponding to the test strip packaging image. Optionally, each test record displays the test strip type, test time, test result, and the status of the test result (normal / abnormal). Optionally, users can access the corresponding historical result analysis page by selecting a specific record entry (e.g., ...). Figure 1C and Figure 1D Optionally, the test record list can be filtered into all, normal (including negative, normal, catch-all, and mild), and abnormal (including positive, weak positive, invalid, moderate, and severe) options. Users can switch between these filters to view test records with different result types.

[0078] Optionally, Figure 3C This is a schematic diagram of an edit detection record according to an embodiment of this disclosure. For example... Figure 3C As shown, when a user selects the edit button in the upper right corner, they enter edit mode. Optionally, the user can select a single detection record or select all records on the current page. Optionally, the delete button is not selectable by default; after the user selects any detection record, the delete button becomes selectable. Optionally, when the user selects delete, a secondary confirmation pop-up appears. The user confirms delete again, removing the selected detection record from the list. If the user cancels, the pop-up closes. Optionally, after successful deletion, the user exits edit mode. Optionally, in edit mode, the user can select all, normal, or abnormal filter options to maintain the current edit state.

[0079] S307: Implement retest reminders and maintain the test calendar based on the test calendar.

[0080] Optionally, in response to receiving a retest reminder creation instruction triggered by the user, a retest reminder creation page is displayed. The retest configuration information is determined based on the information entered by the user on the retest reminder creation page. The retest configuration information may include the retest items and the retest time. When the retest time arrives, a retest reminder message is pushed to the user. The retest reminder message can be used to remind the user to perform the detection operation corresponding to the retest items.

[0081] Optionally, the date with corresponding test records in the test calendar can be determined as the first date, and the date with retest configuration information set in the test calendar but without a retest reminder message can be determined as the second date. The first date and the second date can be the same or different. The first date is marked in the test calendar using the first marker, and the second date is marked in the test calendar using the second marker.

[0082] In some embodiments, the first date may also correspond to retest configuration information, and the second date may also correspond to detection records. Optionally, in response to receiving a user's selection instruction for the first date, the detection records corresponding to the first date are displayed, or the detection records corresponding to the first date and the retest configuration information are displayed; optionally, in response to receiving a user's selection instruction for the second date, the retest configuration information corresponding to the second date is displayed, or the retest configuration information corresponding to the second date and the detection records are displayed.

[0083] Optionally, the entry point for the detection calendar can be: Detection Management Homepage - Function Area Floor - Detection Calendar Entry Point; or, the entry point for the detection calendar can be: Figure 3B The calendar entry is located in the upper right corner of the detection record page. Optionally, Figure 3D This is a schematic diagram of a detection calendar proposed in one embodiment of this disclosure. Figure 3D As shown, the testing calendar can present the user's historical testing records in a monthly view. Optionally, after entering the testing calendar page, the current date is selected by default. Swiping left or right on the testing calendar or selecting the arrow on the calendar allows switching months. Optionally, dates with testing records (i.e., the aforementioned first date) display a first marker at the bottom, and dates with set retest reminders but not yet reminded (i.e., the aforementioned second date) display a second marker in the upper right corner. Optionally, when the user selects the first date, the bottom panel displays a list of testing records for that day and retest configuration information. Optionally, the testing records for that day can include the testing time, test strip type, test strip test result, and status (normal / abnormal). Optionally, the user can select a specific record item to enter the historical results analysis page (e.g., ...). Figure 1C and Figure 1DOptionally, the retest configuration information may include the retest item and retest time. Optionally, the user can select the "Cancel" button to delete the retest configuration information. Optionally, retest configuration information that has exceeded the retest time will be displayed as "Reminded". Optionally, the test record list and retest configuration information are sorted in reverse chronological order. Optionally, if both test records and retest configuration information are included on the same day, the sorting rule from high to low is: retest configuration information > test records. Optionally, within the same category, they are sorted in reverse chronological order; for example, different retest configuration information and different test records are sorted in reverse chronological order. Optionally, if there are no records on a given date, the message "No test records or retest reminders available" will be displayed.

[0084] Optionally, users can set retest reminders for specific test types in the test calendar. Optionally, the "Set Retest Reminder" button is displayed only at the bottom of the page for the current day and dates thereafter (see reference). Figure 3D (As shown), optionally, the user can select the "Set Retest Reminder" button to jump to the retest reminder creation page. Figure 3E and Figure 3F This is a schematic diagram of a retest reminder creation page according to an embodiment of this disclosure, as shown below. Figure 3E and Figure 3F As shown, the retest time can include a reminder date and a reminder time. Optionally, the selected reminder date is displayed by default, and it supports selecting the current date and subsequent dates as reminder dates. Optionally, users can bring up a drop-down selection time component by selecting the "Reminder Date" button. The time component allows users to slide up and down to select the reminder date. Optionally, users can bring up a list of test items by selecting the "Test Item" button. The list includes test item names, such as pregnancy test, ovulation test, Helicobacter pylori test, lactose intolerance test, influenza / COVID-19 test, kidney damage test, vitamin D test, calcium test, myocardial inflammation test, vaginal inflammation test, hepatitis B / C test, sexually transmitted disease test, HPV test, and other tests. The list allows users to slide up and down to select the retest item. Optionally, users can bring up a time selector by selecting the "Reminder Time" button. The time selector allows users to slide up and down to select the reminder time. Optionally, Figure 3E and Figure 3F The "Test Items, Reminder Date, and Reminder Time" fields are all required. After selecting these fields, the "Set Reminder" button can be selected. Selecting the "Set Reminder" button will display a "Setting Successful" message. Optionally, selecting the "Cancel" button will return the user to the test calendar page.

[0085] Optionally, in this embodiment of the disclosure, it is supported to set a single reminder date and a single reminder time. After the reminder date and reminder time are reached, a retest reminder message can be pushed to the user. Optionally, the retest reminder message can be pushed in multiple places, such as pushing the retest reminder message below the test management card on the health management homepage, and pushing the retest reminder message in the recent test floor on the test management homepage. Optionally, in response to the user selecting any place to push the retest reminder message, the retest reminder message pushed in multiple places can be canceled.

[0086] It should be noted that the above steps S306 and S307 can be executed independently and are not bound to other steps. For example, step S306 can be executed alone, or step S307 can be executed alone.

[0087] In summary, this embodiment allows for the archiving of test records and the setting of retest reminders, achieving a closed loop of test records and calendar retest reminders based on PID (User Identifier) ​​profiles. It enables unified archiving, visual viewing, and integrated management of periodic health monitoring reminders for the same user's test data. Furthermore, it allows for the association of historical test records with PIDs and the creation of customized retest plans. This addresses the shortcomings of scattered test data and the lack of long-term tracking and reminder mechanisms in related technologies, facilitating long-term tracking of various test indicators by users. Simultaneously, it provides complete data support for multimodal image recognition models to retrieve user profile information and historical test records, improving recognition accuracy.

[0088] Figure 4 This is a schematic diagram of the structure of a detection device proposed in an embodiment of this disclosure.

[0089] like Figure 4 As shown, the detection device 40 includes: The acquisition module is used to acquire the target detection image input by the user, wherein the type of the target detection image includes a test strip image or a test strip packaging image; The acquisition module is used to acquire the target detection image input by the user; The analysis module is used to analyze the target detection image according to the large model to obtain a first analysis result and a first indication information, wherein the first indication information is used to indicate the next interactive operation; The first processing module is configured to, in response to the next interactive operation being to display the result, display the first analysis result to the user; or, in response to the next interactive operation being to ask follow-up questions, dynamically generate at least one question based on the large model and display the at least one question to the user. The second processing module is used to obtain the answer to the question input by the user for the at least one question, generate a second analysis result based on the target detection image, the first analysis result, the at least one question, and the answer to the question according to the large model, and display the second analysis result to the user.

[0090] It should be noted that the foregoing explanation of the health monitoring data processing method based on large models also applies to the health monitoring data processing device based on large models in this embodiment, and will not be repeated here.

[0091] As one possible implementation, the type of the target detection image includes a test strip image or a test strip packaging image.

[0092] As one possible implementation, the device is also used for: Determine whether the target detection image is a valid image; In response to the target detection image being a valid image, the target detection image is analyzed to obtain the first analysis result and the first indication information; In response to the target detection image being invalid, a rejection prompt or a prompt to re-enter an image is displayed to the user.

[0093] As one possible implementation, the analysis module is also used for: Obtain at least one of the following: preset information, user profile information, and the user's historical test records; wherein the preset information is used to indicate the testing standards and / or usage steps for different brands of test strips; The first analysis result and the first indication information are obtained by analyzing the target detection image based on at least one of the preset information, the user profile information, and the historical detection records using a large model.

[0094] As one possible implementation, the device is also used for: Determine the confidence level of the first analysis result; If the confidence level of the first analysis result is higher than a first threshold, the first indication information indicates that the next interactive operation is to display the result; If the confidence level of the first analysis result is lower than the first threshold, the first indication information indicates that the next interactive operation is: follow-up questioning.

[0095] As one possible implementation, the total number of the at least one problem is less than or equal to a second threshold; The at least one issue includes at least one or more of the following: test strip brand, test items, and test time.

[0096] As one possible implementation, the device is also used for: In response to displaying the at least one question to the user, the first analysis result is cached; In response to obtaining the answer to the question, determine whether the caching time of the first analysis result exceeds a third threshold; In response to the cache duration not exceeding the third threshold, a second analysis result is determined based on at least one of the target detection image, the first analysis result, the at least one question, the question answer, the preset information, the user profile information, and the historical detection record, and the second analysis result is displayed to the user; In response to the cache duration exceeding the third threshold, a timeout prompt is displayed to the user.

[0097] As one possible implementation, the first analysis result or the second analysis result includes the type of the target detection image, and / or, sub-results; When the type of the target detection image is the test strip image, the sub-result includes at least one of the following: test strip detection result, test strip type, health advice, and the status of the test strip detection result, wherein the status includes a normal status or an abnormal status. When the type of the target detection image is a test strip packaging image, the sub-result includes at least one of the following: the test strip type corresponding to the test strip packaging, the test strip brand corresponding to the test strip packaging, the test strip purpose corresponding to the test strip packaging, the test strip usage steps corresponding to the test strip packaging, and the precautions for using the test strip corresponding to the test strip packaging.

[0098] As one possible implementation, the device is also used for: Generate a test record, which includes at least one of the following: test strip type, test time, test strip test result, and the status of the test strip test result.

[0099] As one possible implementation, the device is also used for: In response to receiving the retest reminder creation instruction triggered by the user, the retest reminder creation page is displayed; The retest configuration information is determined based on the information entered by the user on the retest reminder creation page. The retest configuration information includes the retest items and the retest time. When the retest time arrives, a retest reminder message is pushed to the user, which is used to remind the user to perform the detection operation corresponding to the retest item.

[0100] As one possible implementation, the device is also used for: The date with a corresponding test record in the test calendar is determined as the first date, and the date with retest configuration information set in the test calendar but without a retest reminder message is determined as the second date. The first date and the second date may be the same or different. The first date is marked in the detection calendar using a first marker, and the second date is marked in the detection calendar using a second marker.

[0101] As one possible implementation, the first date also corresponds to retest configuration information, and the second date also corresponds to test records; The device is also used for: In response to receiving the user's instruction to select the first date, the system displays the detection record corresponding to the first date, or displays the detection record and retest configuration information corresponding to the first date; In response to receiving the user's instruction to select the second date, the retest configuration information corresponding to the second date is displayed, or the retest configuration information and test records corresponding to the second date are displayed.

[0102] In the detection device of this embodiment, a target detection image input by the user can be acquired. The type of target detection image includes a test strip image or a test strip packaging image. The target detection image is analyzed to obtain a first analysis result and first indication information, the first indication information being used to indicate the next interactive operation. In response to the next interactive operation, the first analysis result is displayed to the user; or, in response to the next interactive operation, at least one question is determined and displayed to the user. The user's answer to the at least one question is obtained, and a second analysis result is determined based on the target detection image, the first analysis result, the at least one question, and the question answer, and the second analysis result is displayed to the user. In this embodiment, after analyzing the target detection image, an indication is given as to whether further follow-up interaction is required. When follow-up interaction is required, the question is displayed to the user, and the user's answer is obtained. Based on the question and the answer, the analysis is performed. Therefore, it can be seen that the embodiments of this disclosure do not simply perform image recognition on the test strip image or test strip packaging image. Instead, after the initial analysis of the test strip image or test strip packaging image, further interaction with the user is conducted to ask the user at least one question and obtain the answer to the question input by the user. Based on at least one question and the answer to the question, the test strip image or test strip packaging image is analyzed again to obtain the final analysis result (i.e., the second analysis result). Thus, through two rounds of image analysis and the introduction of interaction with the user, the detection accuracy of the test strip or test strip packaging can be greatly improved.

[0103] According to embodiments of this application, this application also provides an electronic device and a readable storage medium.

[0104] Figure 5 This is a block diagram of an electronic device according to an embodiment of this application.

[0105] like Figure 5 As shown, the electronic device includes: The memory 501, the processor 502, and the computer instructions stored in the memory 501 and executable on the processor 502.

[0106] When processor 502 executes instructions, it implements the health detection data processing method based on a large model provided in the above embodiments.

[0107] Furthermore, electronic devices also include: Communication interface 503 is used for communication between memory 501 and processor 502.

[0108] Memory 501 is used to store computer instructions that can be executed on processor 502.

[0109] Memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0110] The processor 502 is used to implement the health detection data processing method based on a large model in the above embodiments when executing the program.

[0111] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0112] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0113] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0114] This application also proposes a computer program product that, when executed by an instruction processor, implements the health detection data processing method based on a large model, as described in this application.

[0115] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0116] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0117] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0118] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0119] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0120] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0121] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0122] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for processing health monitoring data based on a large model, characterized in that, include: Acquire the target detection image input by the user; Based on the analysis of the target detection image using the large model, a first analysis result and a first indication information are obtained. The first indication information is used to indicate the next interactive operation. In response to the next interactive operation of displaying results, the first analysis result is displayed to the user; Alternatively, in response to the next interactive operation being a follow-up question, at least one question is dynamically generated based on the large model, and the at least one question is displayed to the user. Obtain the answer to the question input by the user for the at least one question, generate a second analysis result based on the target detection image, the first analysis result, the at least one question, and the answer to the question using a large model, and display the second analysis result to the user.

2. The method as described in claim 1, characterized in that, The types of target detection images include test strip images or test strip packaging images.

3. The method as described in claim 1, characterized in that, The method further includes: Determine whether the target detection image is a valid image; In response to the target detection image being a valid image, the target detection image is analyzed to obtain the first analysis result and the first indication information; In response to the target detection image being invalid, a rejection prompt or a prompt to re-enter an image is displayed to the user.

4. The method as described in claim 1, characterized in that, The step of analyzing the target detection image based on the large model to obtain the first analysis result and the first indication information includes: Obtain at least one of the following: preset information, user profile information, and the user's historical test records; wherein the preset information is used to indicate the testing standards and / or usage steps for different brands of test strips; The target detection image is analyzed based on the large model using at least one of the preset information, the user profile information, and the historical detection records to obtain the first analysis result and the first indication information.

5. The method as described in claim 1, characterized in that, The method further includes: Determine the confidence level of the first analysis result; If the confidence level of the first analysis result is higher than a first threshold, the first indication information indicates that the next interactive operation is to display the result; If the confidence level of the first analysis result is lower than the first threshold, the first indication information indicates that the next interactive operation is: follow-up questioning.

6. The method as described in claim 1, characterized in that, The total number of the at least one problem is less than or equal to the second threshold; The at least one of the following is included: test strip brand, test items, and test time.

7. The method as described in claim 4, characterized in that, The method further includes: In response to displaying the at least one question to the user, the first analysis result is cached; In response to obtaining the answer to the question, determine whether the caching time of the first analysis result exceeds a third threshold; In response to the cache duration not exceeding the third threshold, a second analysis result is determined based on at least one of the target detection image, the first analysis result, the at least one question, the question answer, the preset information, the user profile information, and the historical detection record, and the second analysis result is displayed to the user; In response to the cache duration exceeding the third threshold, a timeout prompt is displayed to the user.

8. The method as described in claim 2, characterized in that, The first analysis result or the second analysis result includes the type of the target detection image, and / or, sub-results; When the type of the target detection image is the test strip image, the sub-result includes at least one of the following: test strip detection result, test strip type, health advice, and the status of the test strip detection result, wherein the status includes a normal status or an abnormal status. When the type of the target detection image is a test strip packaging image, the sub-result includes at least one of the following: the test strip type corresponding to the test strip packaging, the test strip brand corresponding to the test strip packaging, the test strip purpose corresponding to the test strip packaging, the test strip usage steps corresponding to the test strip packaging, and the precautions for using the test strip corresponding to the test strip packaging.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: Generate a test record, which includes at least one of the following: test strip type, test time, test strip test result, and the status of the test strip test result.

10. The method according to any one of claims 1-8, characterized in that, The method further includes: In response to receiving the retest reminder creation instruction triggered by the user, the retest reminder creation page is displayed; The retest configuration information is determined based on the information entered by the user on the retest reminder creation page. The retest configuration information includes the retest items and the retest time. When the retest time arrives, a retest reminder message is pushed to the user, which is used to remind the user to perform the detection operation corresponding to the retest item.

11. The method as described in claim 10, characterized in that, The method further includes: The date with a corresponding test record in the test calendar is designated as the first date, and the date with retest configuration information set in the test calendar but without a retest reminder message is designated as the second date; The first date is marked in the detection calendar using a first marker, and the second date is marked in the detection calendar using a second marker.

12. The method as described in claim 11, characterized in that, The first date also corresponds to retest configuration information, and the second date also corresponds to test records; The method further includes: In response to receiving the user's instruction to select the first date, the system displays the detection record corresponding to the first date, or displays the detection record and retest configuration information corresponding to the first date; In response to receiving the user's instruction to select the second date, the retest configuration information corresponding to the second date is displayed, or the retest configuration information and test records corresponding to the second date are displayed.

13. A health monitoring data processing device based on a large model, characterized in that, include: The acquisition module is used to acquire the target detection image input by the user; The analysis module is used to analyze the target detection image according to the large model to obtain a first analysis result and a first indication information, wherein the first indication information is used to indicate the next interactive operation; The first processing module is configured to display the first analysis result to the user in response to the next interactive operation; Alternatively, in response to the next interactive operation being a follow-up question, at least one question is dynamically generated based on the large model, and the at least one question is displayed to the user. The second processing module is used to obtain the answer to the question input by the user for the at least one question, generate a second analysis result based on the target detection image, the first analysis result, the at least one question, and the answer to the question according to the large model, and display the second analysis result to the user.

14. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-12.

15. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, in, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-12.

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

Images