Body health platform health tutor behavior standard monitoring method and system
By designing a health tutor behavioral norm monitoring system on the physical health platform, using the camera to collect data, compare features and set alarm thresholds, combined with cloud servers and monitoring clients, the problems of low efficiency and subjective impact of traditional monitoring methods are solved, and the problem of inefficiency and subjective influence of traditional monitoring methods is realized. Real-time and accurate behavioral supervision and standardized management are provided.
Patent Information
- Application Number
- CN202411076862.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-11-22
AI Technical Summary
Traditional health tutor behavior monitoring methods are inefficient and susceptible to subjective factors, and have problems with reporting fraud and behavioral incompleteness, making it difficult to achieve real-time, comprehensive and accurate behavioral data collection and monitoring.
A health tutor behavioral norm monitoring system was designed on the health tutor's behavioral code, including obtaining the tutor's behavior module, characteristic behavior extraction module and alarm statistics module, collecting the tutor's behavior data through the camera, and using the preset non-standard action feature database for comparison. Set the alarm threshold and perform cumulative points, and combine the cloud server and supervision client to perform secondary supervision and data management to ensure the accuracy and completeness of the data.
Real-time and comprehensive supervision of health tutor behaviors has been achieved, the degree of standardization has been improved, the continuity and reliability of data has been ensured, subjective interference has been reduced, the mentor's guidance ability and supervision efficiency have been improved, and irregular behaviors have been promptly reported.
Smart Images

Figure CN119011776A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of network monitoring systems, and in particular to a method and system for monitoring the behavior norms of health mentors on a physical health platform. Background Art
[0002] With the rapid development of science and technology, advanced technologies such as big data, artificial intelligence, and machine learning have been widely used in various fields. The emergence of these technologies has provided new possibilities for solving the problem of standardized monitoring of health mentors' behaviors on the physical health platform. Through big data technology, we can collect the behavioral data of users and health mentors in real time and comprehensively; through artificial intelligence and machine learning technology, we can conduct in-depth analysis of these data, extract the characteristics of health mentors' behaviors, and automatically compare them with the preset health mentors' behavioral norms.
[0003] As people's health awareness increases, more and more people are starting to use health platforms for health management. However, how to ensure that health mentors on health platforms behave in a standardized manner and avoid misleading users is an urgent problem to be solved. Traditional monitoring methods mainly rely on manual review, which is inefficient and easily affected by subjective factors. Therefore, it is urgent to develop an automatic and efficient health mentor behavior monitoring method and system.
[0004] In the process of implementing the health tutor behavior standard monitoring method and system on the physical health platform, some places use sampling monitoring or submit tutor behavior reports to constrain tutor behavior, which is prone to report fraud or incomplete behavior, so they face the following technical difficulties:
[0005] How to collect behavioral data of users and health mentors in real time and comprehensively, and ensure the accuracy and completeness of the data. Summary of the invention
[0006] In view of the above-mentioned shortcomings (problems) of the prior art, in order to monitor the behavior of health mentors on a physical health platform and improve the degree of standardization, the present application provides a method and system for monitoring the behavior of health mentors on a physical health platform.
[0007] To achieve the above objectives and other related objectives, this application adopts the following technical solutions:
[0008] A health tutor behavior standard monitoring system for a physical health platform includes a field system, the field system includes a tutor behavior acquisition module, a characteristic behavior extraction module, a selection module, and an alarm statistics module.
[0009] The module for obtaining tutor behavior includes installing a camera in each tutor studio, collecting tutor behavior in each tutor studio by the camera, converting it into a tutor behavior data packet, and sending the tutor behavior data packet to the feature behavior extraction module;
[0010] The characteristic behavior extraction module includes comparing the tutor behavior data packet with the preset non-standard action feature database, extracting a characteristic data packet with the highest matching degree in the non-standard action feature database and transmitting it to the selection module;
[0011] The selection module is set with an alarm threshold, and the alarm level is selected according to the corresponding label in the received characteristic data packet. The selection is made according to the alarm threshold, and the data below the alarm threshold are discarded. The data above the alarm threshold will generate a correct signal, and the correct signal will be transmitted to the alarm statistics module;
[0012] The alarm statistics module, after receiving the correct signal, will issue the corresponding alarm and accumulate points.
[0013] Optionally, the feature behavior extraction module also includes a training set, which includes positive samples of standard action features and negative samples of non-standard actions. The target features of the tutor behavior data packet are compared with the positive samples and negative samples in the training set to calculate the positive sample score and the negative sample score.
[0014] Optionally, also include:
[0015] Cloud servers, used to receive information and data from on-site systems;
[0016] A monitoring client is connected to the cloud server and is used to check the video data obtained from the on-site system or the alarm data fed back by the on-site system;
[0017] The selection module in the on-site system also uploads the identified warning tutor behavior data packets to the cloud server for storage.
[0018] Optionally, the monitoring client logs in after passing the monitor identity authentication and obtains the tutor behavior data packets with warning marks stored on the cloud server, and performs secondary monitoring on the tutor behavior data packets with warning marks, and deletes the tutor behavior data packets that meet the behavioral specifications.
[0019] Optionally, the monitoring client deletes the tutor behavior data packet after the monitor logs in, including inputting supplementary positive samples, and associating and matching the positive samples with the tutor behavior data packets that meet the behavioral specifications, or putting the tutor behavior data packets that meet the behavioral specifications into the training set as positive samples.
[0020] Optionally, the monitoring client generates an approval form for the operation of the tutor's behavior data packet, and the approval form has an anti-counterfeiting barcode. After the monitoring client approves the approval form, the newly added positive samples are marked.
[0021] On the other hand, a method for monitoring the behavioral norms of health mentors on a physical health platform is also provided, using the above-mentioned system for monitoring the behavioral norms of health mentors on a physical health platform.
[0022] Among them, a method for monitoring the behavior norms of health mentors on a physical health platform has the following specific steps:
[0023] a Collection: The camera in each tutor's studio collects tutor's behavior and forms tutor's behavior data packet in the form of video or photo.
[0024] b Identification: Compare the pre-set non-standard action feature database with the tutor's behavior data packet, extract the feature data packet with the highest matching degree in the non-standard action feature database and transmit it to the selection module;
[0025] c Processing: Selection module, set the alarm threshold, select the alarm level according to the corresponding label in the received feature data packet, select according to the alarm threshold, discard those below the alarm threshold, and generate a correct signal above the alarm threshold. The correct signal is transmitted to the alarm statistics module. After receiving the correct signal, the alarm statistics module will issue the corresponding alarm and accumulate points.
[0026] Preferably, step d modification is also included: using the monitoring client to log in after passing the monitor identity authentication and obtain the tutor behavior data packet with warning marks stored on the cloud server, and implement secondary monitoring of the tutor behavior data packet with warning marks, and delete or modify the tutor behavior data packet that meets the behavioral specifications.
[0027] Preferably, the monitoring client generates an approval form for the operation of the tutor behavior data packet, and the approval form has an anti-counterfeiting barcode. After the monitoring client approves the approval form, the newly added positive samples are marked.
[0028] In summary, the present application includes at least one of the following beneficial technical effects:
[0029] 1. The health instructors on the physical health platform usually guide users (registrants) in their own offices. In order to avoid irregular guidance movements or other irregular behaviors, cameras are added to the on-site system for real-time monitoring to ensure the continuity and reliability of data. The instructors' behaviors can also be identified, so that standardized movements and non-standard movements can be effectively distinguished, so as to improve the instructors' guidance ability and standardize the instructors' work;
[0030] 2. Classify the tutor's behavior and collect comparison samples through the verified training set to improve the efficiency of action recognition and processing;
[0031] 3. By monitoring the behavioral norms of health mentors and avoiding arbitrary modification of behavioral data, a monitoring client is added to further achieve secondary monitoring, and the training library can be supplemented to improve recognition capabilities. The system runs efficiently and can provide timely feedback. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Figure 1 It is a system block diagram of an embodiment of the present application.
[0033] Description of main component reference numerals:
[0034] 1. On-site system; 11. Module for obtaining tutor behavior; 12. Feature behavior extraction module; 13. Selection module; 131. Training set; 14. Alarm statistics module; 2. Cloud server; 3. Monitoring client. DETAILED DESCRIPTION
[0035] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.
[0036] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The illustrations only show the components related to the present application rather than being drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.
[0037] The specific implementation methods of the present application will be further described below in conjunction with the accompanying drawings.
[0038] Embodiment 1:
[0039] The present application embodiment discloses a health platform health tutor behavior norms monitoring system. Figure 1 As shown, the health tutor behavior standard monitoring system of the physical health platform includes a field system 1, and the field system 1 includes a tutor behavior acquisition module 11, a characteristic behavior extraction module 12, a selection module 13, and an alarm statistics module 14.
[0040] The module for obtaining tutor behavior 11 includes installing a camera in each tutor studio, collecting tutor behavior in each tutor studio by the camera, and converting it into a tutor behavior data packet, and sending the tutor behavior data packet to the feature behavior extraction module 12. The data packet here can be a photo data packet or a video data packet. Since the tutor wears work clothes, the tutor can be quickly identified through video or photo. Here, data collection is triggered when the tutor is working, so data collection can be stopped when not working. That is, when a registrant enters the tutor's studio, data collection begins, and when the registrant leaves the studio, data collection stops. On the physical health platform, the tutor guides the registrant on how to exercise, as well as the adjustment and teaching of exercise posture based on the registrant's physical examination report, exercise prescription, and other data.
[0041] The characteristic behavior extraction module 12 includes comparing the tutor behavior data packet with the preset non-standard action feature database, extracting a characteristic data packet with the highest matching degree in the non-standard action feature database and transmitting it to the selection module 13. The characteristic behavior extraction module 12 has a pre-stored non-standard action feature database and a standard action feature database. The tutor's behavior in the tutor behavior data packet is analyzed, and whether the tutor's teaching behavior is standard can be analyzed. The recognized action posture can be analyzed, and the tutor's posture feature data can be uploaded, or a characteristic data packet in a corresponding database that matches it can be uploaded to the selection module 13.
[0042] In the training set 131 (database), the training set 131 includes positive samples of standard action features and negative samples of non-standard actions. The target features of the tutor behavior data packet are compared with the positive samples and negative samples in the training set 131 to calculate the positive sample score and the negative sample score. The action samples in the training set 131 have corresponding labels. The positive samples are labeled in even numbers, and the negative samples are labeled in odd numbers. Multiple negative samples are divided into high and low alarm levels according to the situation, such as samples with labels (1, 3, 5, 7, 9) for low alarm levels, samples with labels (11, 13, 15, 17, 19) for medium alarm levels, and samples with labels (21, 23, 25, 27, 29) for high alarm levels.
[0043] The selection module 13 is set with an alarm threshold. The alarm level is selected according to the corresponding label in the received feature data packet. The alarm threshold is selected, and the ones below the alarm threshold are discarded. The ones above the alarm threshold will generate a correct signal, and the correct signal is transmitted to the alarm statistics module 14. In one example, the alarm threshold is set to 60 points. The positive sample score and the negative sample score in the training set 131 are respectively the similarity between an action and the negative sample, ranging from (0-100 points). If the similarity score of a behavior data and the negative sample matching it is 70 points, then this label is selected for alarm. If this label is 7, the alarm mode of the low alarm level is triggered, such as voice prompt.
[0044] The alarm statistics module 14, after receiving the correct signal, performs the corresponding alarm and accumulates the integral. The accumulated integral is a weighted calculation of the number of alarms and the alarm level. The number of times the alarm is triggered is n1, n2 and n3, and the alarm weights of the three levels of low, medium and high are a<b<c. The total score W=a×n1+b×n2+c×n3.
[0045] Embodiment 2:
[0046] Further, based on Example 1, it also includes:
[0047] The cloud server 2 is used to receive information and data from the field system 1 .
[0048] The monitoring client 3 (app on the mobile phone) is connected to the cloud server 2 and is used to check the video data obtained from the on-site system 1 or the alarm data fed back by the on-site system 1.
[0049] The selection module 13 in the on-site system 1 also uploads the identified tutor behavior data packets with warnings to the cloud server 2 for storage.
[0050] In this way, the data can be uploaded to the cloud server 2, thereby improving the reliability of monitoring. The monitor can act as another senior person to conduct remote supervision or spot checks, and can check the alarm status or data on the on-site system 1 at any time through the monitoring client 3.
[0051] Specifically, the monitoring client 3 logs in after passing the monitor identity authentication and obtains the tutor behavior data packets with warning marks stored on the cloud server 2, and performs secondary monitoring on the tutor behavior data packets with warning marks, and deletes the tutor behavior data packets that meet the behavioral norms.
[0052] After the monitor logs in, the monitoring client 3 deletes the tutor behavior data package, including inputting supplementary positive samples, and associating and matching the positive samples with the tutor behavior data package that meets the behavior norms, or putting the tutor behavior data package that meets the behavior norms into the training set 131 as positive samples.
[0053] The monitoring client 3 generates an approval form for the operation of the tutor's behavior data packet, and the approval form has an anti-counterfeiting barcode. After the monitoring client 3 approves the approval form, the newly added positive samples are marked.
[0054] In this way, the behavior data packets that need to be modified can be subject to additional review processes to avoid illegal operations.
[0055] Embodiment three:
[0056] On the other hand, a method for monitoring the behavior norms of health tutors on a physical health platform is also provided, which uses the above-mentioned system for monitoring the behavior norms of health tutors on a physical health platform. A method for monitoring the behavior norms of health tutors on a physical health platform has the following specific steps:
[0057] a Collection: The camera in each tutor's studio collects tutor's behavior and forms tutor's behavior data packet in the form of video or photo.
[0058] b Identification: comparing the tutor's behavior data packet with the preset non-standard action feature database, extracting a feature data packet with the highest matching degree in the non-standard action feature database and transmitting it to the selection module 13;
[0059] c Processing: Selection module 13 is set with an alarm threshold. The alarm level is selected according to the corresponding label in the received feature data packet. The selection is made according to the alarm threshold. Those below the alarm threshold are discarded, and those above the alarm threshold will generate a correct signal, which is transmitted to the alarm statistics module 14. After receiving the correct signal, the alarm statistics module 14 will issue a corresponding alarm and accumulate points.
[0060] d Modification: Use the monitoring client 3 to log in after passing the monitor identity authentication and obtain the tutor behavior data packet with warning marks stored on the cloud server 2, and implement secondary monitoring of the tutor behavior data packet with warning marks, delete or modify the tutor behavior data packet that meets the behavioral norms.
[0061] The monitoring client 3 generates an approval form for the operation of the tutor's behavior data packet, and the approval form has an anti-counterfeiting barcode. After the monitoring client 3 approves the approval form, the newly added positive samples are marked.
[0062] Embodiment 4:
[0063] Based on the above embodiments, the following technical problems can also be solved:
[0064] Behavioral feature extraction: How to extract the characteristics of health mentor behavior from the collected data and classify and label them.
[0065] Behavioral norms comparison: How to compare the extracted behavioral characteristics with the preset health mentor behavioral norms and ensure the accuracy and objectivity of the comparison.
[0066] Result output: How to present the comparison results in the form of an evaluation report and ensure the timeliness and readability of the report.
[0067] The specific plan is as follows:
[0068] Step 1: Data Collection
[0069] 1.1 Start the data acquisition module and configure the data acquisition parameters.
[0070] 1.2 Obtain user behavior data and health instructor’s guidance behavior data in real time through the API interface or directly from the database of the health platform.
[0071] 1.3 The data acquisition module stores the collected data in a temporary database for subsequent processing.
[0072] Step 2: Behavioral feature extraction
[0073] 2.1 Extract the collected data from the temporary database.
[0074] 2.2 Use natural language processing technology to conduct text analysis on the health mentors’ guidance behavior data and extract the characteristics of the health mentors’ behavior.
[0075] 2.3 Classify and label the extracted behavioral features for subsequent comparison.
[0076] Step 3: Comparison of behavioral norms
[0077] 3.1 Load the preset health mentor behavioral norms.
[0078] 3.2 Compare the extracted behavioral features with the preset health mentor behavioral norms. The comparison can be done by using rule-based matching, machine learning models, or deep learning models.
[0079] 3.3 Based on the comparison results, generate a judgment result of compliance with the specifications or non-compliance with the specifications.
[0080] Step 4: Output results
[0081] 4.1 Based on the comparison results, generate an evaluation report on the health mentor’s behavior. The report should include behaviors that meet the standards, behaviors that do not meet the standards, and corresponding improvement suggestions.
[0082] 4.2 The evaluation report will be notified to relevant personnel via email, SMS or user interface.
[0083] 4.3 Store the evaluation report in the results database for subsequent analysis and audit.
[0084] The system is composed as follows: The system of the present invention includes the following modules: field system 1, cloud server 2 and monitoring client 3. The modules are connected through a data bus or network to achieve data sharing and interaction.
[0085] It can be seen that the advantages and innovations of this solution are:
[0086] High degree of automation: The entire monitoring process does not require human intervention, which can greatly improve monitoring efficiency.
[0087] Strong objectivity: By comparing with the preset health mentor behavior standards, the subjectivity of manual review is effectively avoided.
[0088] Real-time monitoring: Able to collect and analyze data in real time, and promptly discover and correct irregular behaviors of health mentors.
[0089] Improvement (modification) suggestions: It not only provides judgment on whether the regulations are met, but also provides improvement (modification) suggestions, which can help health mentors improve the quality of their services.
[0090] The above embodiments are only illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application shall be included in the protection scope of the present application.
Claims
1. A health platform health tutor behavior norm monitoring system, including a field system (1), characterized in that: The on-site system (1) includes a tutor behavior acquisition module (11), a characteristic behavior extraction module (12), a selection module (13), and an alarm statistics module (14). The module for acquiring tutor behavior (11) includes installing a camera in each tutor studio, collecting tutor behavior in each tutor studio by the camera, converting the tutor behavior data packet into a tutor behavior data packet, and sending the tutor behavior data packet to the feature behavior extraction module (12); The characteristic behavior extraction module (12) includes comparing the tutor behavior data packet with the preset non-standard action characteristic database, extracting a characteristic data packet with the highest matching degree in the non-standard action characteristic database and transmitting it to the selection module (13); A selection module (13) is set with an alarm threshold, selects an alarm level according to the corresponding number in the received characteristic data packet, selects according to the alarm threshold, discards those below the alarm threshold, and generates a correct signal for those above the alarm threshold, and transmits the correct signal to the alarm statistics module (14); The alarm statistics module (14) issues corresponding alarms and accumulates points after receiving a correct signal.
2. According to claim 1, a health platform health tutor behavior norm monitoring system is characterized by: The feature behavior extraction module (12) also includes a training set (131), wherein the training set (131) includes positive samples of standard action features and negative samples of non-standard actions. The target features of the tutor behavior data packet are compared with the positive samples and negative samples in the training set (131), and the positive sample score and the negative sample score are calculated.
3. According to claim 2, a health platform health tutor behavior norm monitoring system is characterized by: Also includes: A cloud server (2) for receiving information and data from the field system (1); A monitoring client (3) is connected to the cloud server (2) and is used to check the video data obtained from the field system (1) or the alarm data fed back by the field system (1); The selection module (13) in the on-site system (1) also uploads the identified tutor behavior data packets with warnings to the cloud server (2) for storage.
4. According to claim 3, a health platform health tutor behavior norm monitoring system is characterized by: The monitoring client (3) logs in after passing the monitor identity authentication and obtains the tutor behavior data packets with warning marks stored on the cloud server (2), and performs secondary monitoring on the tutor behavior data packets with warning marks, and deletes the tutor behavior data packets that meet the behavior specifications.
5. According to claim 4, a health platform health tutor behavior norm monitoring system is characterized by: The monitoring client (3) performs a deletion operation on the tutor behavior data packet after the monitor logs in, including inputting a supplementary positive sample, and associating and matching the positive sample with the tutor behavior data packet that meets the behavior norm, or putting the tutor behavior data packet that meets the behavior norm into the training set (131) as a positive sample.
6. A health platform health tutor behavior norm monitoring system according to claim 5, characterized in that: The monitoring client (3) generates an approval form for the operation of the tutor's behavior data packet, and the approval form has an anti-counterfeiting barcode. After the monitoring client (3) approves the approval form, the newly added positive samples are marked.
7. A method for monitoring the behavior norms of health tutors on a physical health platform, characterized by: A health platform health mentor behavior norms monitoring system adopting any one of claims 1-6 above.
8. A method for monitoring the behavior norms of health tutors on a physical health platform, characterized by: The specific steps are as follows: a Collection: The camera in each tutor's studio collects tutor's behavior and forms tutor's behavior data packet in the form of video or photo. b Identification: Compare the pre-set non-standard action feature database with the tutor's behavior data packet, extract the feature data packet with the highest matching degree in the non-standard action feature database and transmit it to the selection module (13); c Processing: A selection module (13) is set with an alarm threshold, and an alarm level is selected according to the corresponding label in the received characteristic data packet. The selection is made according to the alarm threshold, and those below the alarm threshold are discarded. Those above the alarm threshold will generate a correct signal, and the correct signal is transmitted to the alarm statistics module (14). After receiving the correct signal, the alarm statistics module (14) performs corresponding alarms and accumulates points.
9. The method for monitoring the behavior norms of health instructors on a physical health platform according to claim 8 is characterized by: The method also includes modifying step d: using the monitoring client (3) to log in after passing the monitor identity authentication and obtain the tutor behavior data packets with warning marks stored on the cloud server (2), and performing secondary monitoring on the tutor behavior data packets with warning marks, deleting or modifying the tutor behavior data packets that meet the behavioral norms.
10. The method for monitoring the behavior norms of health instructors on a physical health platform according to claim 9, characterized in that: The monitoring client (3) generates an approval form for the operation of the tutor's behavior data packet, and the approval form has an anti-counterfeiting barcode. After the monitoring client (3) approves the approval form, the newly added positive samples are marked.
