Yoga intelligent class schedule generated based on user preferences

Abstract

The invention discloses a yoga intelligent class schedule generated based on user preferences, and belongs to the field of yoga intelligent class schedules. Comprising a label generation module, a recommendation algorithm module, a course arrangement module, a fine adjustment module, a data import module, a statistical analysis module, a health data access module, a time management module, a course display interaction module, an intelligent error correction module and a yoga museum operation fusion module. By combining health risk assessment and applying an optimized recommendation algorithm, yoga courses meeting the requirements and health conditions of the user are accurately recommended to the user, and personalized learning and fitness requirements of the user are met; a course arrangement table is automatically generated based on multiple restrictions of coaches, classrooms and course arrangement, dynamic changes of resources such as classroom states and coach idle time are monitored in real time and automatically adjusted, various conflicts are effectively solved, and course arrangement efficiency and rationality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent yoga class schedules, and in particular to an intelligent yoga class schedule generated based on user preferences. Background Art

[0002] Traditional class schedule arrangement has a large workload, takes a long time, and is inefficient. There are many unreasonable places and need manual fine-tuning. It is difficult to take into account all these requirements by mental effort. There are also conflicts between venue classrooms and teachers, and it is difficult to count the weekly yoga courses, which are prone to errors. At the same time, the user's own yoga exercise plan cannot be reasonably arranged, and it is impossible to reasonably complete warm-up movements and progress to high-difficulty poses.

[0003] This intelligent class schedule is generated to solve the above problems, promoting the close combination of users and yoga studios, recommending more suitable weekly yoga courses for each user, enabling users to reasonably control their time, avoiding excessive unnecessary consumption, and training in a safer and healthier manner. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides an intelligent yoga class schedule generated based on user preferences, which solves the problems raised in the above background art.

[0005] Technical Solution: To solve the above technical problems, according to one aspect of the present invention, more specifically, an intelligent yoga class schedule generated based on user preferences includes a label generation module, a recommendation algorithm module, a class schedule module, a fine-tuning module, a data import module, a statistical analysis module, a health data access module, a time management module, a course display and interaction module, an intelligent error correction module, and a yoga studio operation integration module, with the following steps:

[0006] S1. Obtain the user's personal information, demand data, and health data, generate personalized labels for the user based on these data, and simultaneously conduct a health risk assessment on the user in combination with the health data;

[0007] S2. According to the labels generated by the user, in combination with the course database, recommend yoga courses that meet the user's needs and consider the health status to the user through an optimized personalized recommendation algorithm;

[0008] S3. Based on multiple restrictions of coaches, classrooms, and course arrangements, automatically generate a non-conflicting class schedule, and detect the dynamic changes of resources in real time during the class schedule process, and automatically adjust the class schedule according to the changes;

[0009] S4. Provide a manual fine-tuning function to allow manual adjustment of the automatic class schedule result in special cases;

[0010] S5. Provide a batch import function to allow batch import of coach, course, and classroom information to reduce the data entry workload;

[0011] S6. Provide a statistical analysis function, support viewing the class attendance of courses and coaches by dimensions such as monthly, quarterly, and annual, and at the same time provide statistical operations data such as financial statements and student consumption analysis;

[0012] S7. According to the time preferences and schedule set by the user, combined with the class schedule, automatically detect and avoid time conflicts, and remind the user of course information by means of text messages, APP push, etc. before the course starts;

[0013] S8. Provide users with course details, action demonstration video links, coach profiles, student evaluations, etc. on the class schedule display interface. After the course ends, guide the user to give evaluation feedback and provide social interaction functions to facilitate user communication;

[0014] S9. During the automatic course scheduling process, perform intelligent error correction on the abnormal data that appears, give timely warnings for serious abnormalities that cannot be solved and provide suggestions for temporary solutions, and at the same time provide recovery and retry functions;

[0015] S10. Provide a marketing and promotion channel for the yoga studio, release information such as course discount activities, new coach introductions, and promotion of special courses, and accurately push them to eligible users.

[0016] Furthermore, the label generation module is used to generate personalized labels according to the personal information, demand data, and health data input by the user, and at the same time conduct a health risk assessment in combination with the health data;

[0017] The recommendation algorithm module is used to recommend suitable yoga courses for the user according to the user labels, course information, and health risk assessment results, in combination with the optimized personalized recommendation algorithm;

[0018] The course scheduling module automatically generates a course scheduling result according to the coaches, classrooms, courses, and user requirements, solves various conflict situations, and monitors the dynamic changes of resources in real time and automatically adjusts the course schedule;

[0019] The fine-tuning module supports manual adjustment of the automatically generated course scheduling result in special cases;

[0020] The data import module supports batch import of coach, course, and classroom information;

[0021] The statistical analysis module is used to statistically analyze the course situation and coach teaching situation, support viewing relevant data by different time dimensions, and at the same time provide statistical operations data such as financial statements and student consumption analysis;

[0022] The health data access module is responsible for accessing wearable devices or docking with the hospital health system to obtain user health data;

[0023] The time management module automatically detects and avoids schedule time conflicts according to the user's time preference settings and schedule, and gives a reminder before the course starts;

[0024] The course display and interaction module provides content such as course details, action demonstration video links, coach profiles, and student evaluations on the course schedule display interface. After the course ends, it guides users to give feedback and provides social interaction functions;

[0025] The intelligent error correction module performs intelligent error correction on data anomalies during the automatic course scheduling, gives warnings for serious anomalies and provides suggestions for temporary solutions, and also provides recovery and retry functions;

[0026] The yoga studio operation integration module provides marketing and promotion channels for the yoga studio, publishes information such as preferential activities and pushes them accurately.

[0027] Furthermore, a personalized recommendation algorithm based on tags

[0028] A dataset of user tag behaviors is generally represented by a set of triples, where the record (u, i, b) means that user u has tagged course i with tag b. Of course, the real user tag behavior data is much more complex than that represented by triples, such as the time when the user tags, the user's attribute data, the attribute data of yoga courses, etc.

[0029] 1> Count the common tags of each user

[0030] 2> For each tag, count the course that has been tagged with this tag the most times

[0031] 3> For a specific user, find his most common tags and recommend the most popular yoga courses of these tags to him

[0032] 4> Recommendation ranking

[0033] The personalized recommendation algorithm:

[0034]

[0035] Where UserTags[u, t] represents the number of times user u has used tag t, and TagCourses[t, i]T represents the number of times course i has been tagged with tag t.

[0036] Furthermore, if a tag is very popular, it will result in a large UserTags[t]. Therefore, even if TagCourses[u,t] is small, it will still lead to a large score(u,i), causing popular yoga courses to be recommended to users and thus reducing the novelty of the recommendation results. Additionally, this formula models the user's interests using the user's tag vector, where each tag is a tag used by the user, and the weight of the tag is the number of times the user has used the tag. The drawback of this modeling method is that it gives too much weight to popular tags and thus cannot reflect the user's personalized interests. Here, we can draw on the idea of TF-IDF to improve this formula. Let TagUser[t] represent the number of different users who have used tag t:

[0037]

[0038] Furthermore, the health data can be obtained by connecting wearable devices to the hospital health system. The wearable devices include but are not limited to smart watches, bracelets, earphones, and glasses.

[0039] Furthermore, the dynamic changes of the resources include but are not limited to the classroom status and the free time of the coaches.

[0040] The beneficial effects of a yoga intelligent class schedule generated based on user preferences in the present invention are as follows:

[0041] (1) Personalized customization: By collecting the user's personal information, demand data, and health data to generate personalized tags, combined with health risk assessment, and using the optimized recommendation algorithm, yoga courses that meet the user's needs and health conditions are accurately recommended for the user, meeting the user's personalized learning and fitness needs.

[0042] (2) Intelligent class scheduling: Based on multiple restrictions on coaches, classrooms, and course arrangements, a class schedule is automatically generated, and the dynamic changes of resources such as classroom status and coaches' free time are monitored in real time and automatically adjusted, effectively solving various conflict situations and improving the efficiency and rationality of class scheduling.

[0043] (3) Convenient operation: A batch import function is provided to reduce the data entry workload of coaches, courses, and classroom information; manual fine-tuning is supported, and the class scheduling results can be manually adjusted in special cases, taking into account both automation and flexibility.

[0044] (4) Good user experience: Automatically detect and avoid time conflicts according to the user's time preferences and schedule, and push course information via text messages and the APP before class; the class schedule display interface provides rich course details, and after the course, it guides evaluation feedback and provides social interaction functions, enhancing the user's sense of participation and satisfaction.

[0045] (5) Operational management optimization: Provide statistical analysis functions, support viewing the class attendance of courses and coaches by different time dimensions, as well as statistical operations of operational data such as financial statements and student consumption analysis, providing data support for the operation decision-making of yoga studios; at the same time, provide marketing and promotion channels for yoga studios, accurately push information such as preferential activities, and contribute to business development.

[0046] (6) Data processing and exception handling: Adopt an improved personalized recommendation algorithm based on tags, reduce the weight of popular tags, and better reflect users' personalized interests; during the automatic class scheduling process, perform intelligent error correction on data anomalies, give early warnings for serious anomalies and provide suggestions for temporary solutions, and at the same time provide recovery and retry functions to ensure system stability and reliability. Brief Description of the Drawings

[0047] The present invention will be further described in detail below with reference to the drawings and specific implementation methods.

[0048] Figure 1 It is a structural schematic diagram of the present invention. Specific Embodiments

[0049] The present invention will be described in detail below with reference to the drawings and embodiments. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0050] To make the technical solution of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and specific embodiments.

[0051] Refer to Figure 1 , a yoga intelligent class schedule generated based on user preferences, including a tag generation module, a recommendation algorithm module, a class scheduling module, a fine-tuning module, a data import module, a statistical analysis module, a health data access module, a time management module, a course display and interaction module, an intelligent error correction module, and a yoga studio operation integration module, with the following steps:

[0052] S1. Obtain the user's personal information, demand data, and health data, generate personalized tags for the user based on these data, and at the same time perform a health risk assessment on the user in combination with the health data;

[0053] S2. According to the tags generated by the user, in combination with the course database, recommend yoga courses that meet the user's needs and consider the health status to the user through an optimized personalized recommendation algorithm;

[0054] S3. Based on multiple restrictions of coaches, classrooms, and course arrangements, automatically generate a non-conflicting class schedule, and detect the dynamic changes of resources in real time during the class scheduling process, and automatically adjust the class schedule according to the changes;

[0055] S4. Provide a manual fine-tuning function that allows manual adjustment of the automatic class scheduling results in special cases;

[0056] S5. Provide a batch import function that allows batch import of coach, course, and classroom information to reduce the data entry workload;

[0057] S6. Provide a statistical analysis function that supports viewing the class attendance of courses and coaches by dimensions such as monthly, quarterly, and annual, and at the same time provides statistical operations data such as financial statements and student consumption analysis;

[0058] S7. According to the time preferences and schedule set by the user, combined with the class schedule, automatically detect and avoid time conflicts, and remind the user of course information by means of text messages, APP push, etc. before the course starts;

[0059] S8. Provide content such as course details introduction, action demonstration video links, coach profiles, and student evaluations for users on the class schedule display interface. After the course ends, guide users to give evaluation feedback and provide social interaction functions to facilitate user communication;

[0060] S9. During the automatic class scheduling process, perform intelligent error correction on the abnormal data that appears, give timely warnings for serious abnormalities that cannot be solved and provide suggestions for temporary solutions, and at the same time provide recovery and retry functions;

[0061] S10. Provide a marketing and promotion channel for the yoga studio, publish information such as course discount activities, introduction of new coaches, and promotion of special courses, and accurately push it to eligible users.

[0062] Preferably, the label generation module is used to generate personalized labels based on the personal information, demand data, and health data input by the user, and at the same time perform a health risk assessment in combination with the health data;

[0063] The recommendation algorithm module is used to recommend suitable yoga courses for the user based on the user labels, course information, and health risk assessment results, in combination with the optimized personalized recommendation algorithm;

[0064] The class scheduling module automatically generates class scheduling results according to coaches, classrooms, courses, and user needs, solves various conflict situations, and monitors the dynamic changes of resources in real time and automatically adjusts the class schedule;

[0065] The fine-tuning module supports manual adjustment of the automatically generated class scheduling results in special cases;

[0066] The data import module supports batch import of coach, course, and classroom information;

[0067] The statistical analysis module is used to conduct statistics on course situations and coach teaching situations, support viewing relevant data according to different time dimensions, and at the same time provide statistical operations data such as financial statements and student consumption analysis;

[0068] The health data access module is responsible for accessing wearable devices or docking with the hospital health system to obtain user health data;

[0069] The time management module automatically detects and avoids schedule time conflicts according to user time preference settings and schedule arrangements, and gives reminders before the course starts;

[0070] The course display and interaction module provides content such as course details introduction, action demonstration video links, coach profiles, and student evaluations on the course schedule display interface. After the course ends, it guides users to give evaluation feedback and provides social interaction functions;

[0071] The intelligent error correction module conducts intelligent error correction on data anomalies during the automatic course scheduling process, gives early warnings for serious anomalies and provides suggestions for temporary solutions, and at the same time provides recovery and retry functions;

[0072] The yoga studio operation integration module provides marketing and promotion channels for the yoga studio, publishes information such as preferential activities and pushes them accurately.

[0073] Preferably, a personalized recommendation algorithm based on tags:

[0074] A dataset of user tag behaviors is generally represented by a set of triples, where the record (u, i, b) means that user u has tagged course i with tag b. Of course, the real tag behavior data of users is much more complex than that represented by triples, such as the time when users tag, the attribute data of users, the attribute data of yoga courses, etc.

[0075] 1> Statistically analyze the common tags of each user

[0076] 2> For each tag, statistically analyze the course that has been tagged with this tag the most times

[0077] 3> For a specific user, find his most common tags and recommend the most popular yoga courses of these tags to him

[0078] 4> Recommendation ranking

[0079] The personalized recommendation algorithm:

[0080]

[0081] Among them, UserTags[u, t] represents the number of times user u has used tag t, and TagCourses[t, i]T represents the number of times course i has been tagged with tag t.

[0082] 4. A yoga intelligent course schedule generated based on user preferences according to claim 1, wherein: if a tag is very popular, it will cause UserTags[t] to be very large. Therefore, even if TagCourses[u,t] is very small, it will cause score(u,i) to be very large. As a result, popular yoga courses will be recommended to users, thus reducing the novelty of the recommendation results. Additionally, this formula models the user's interests using the user's tag vector, where each tag is a tag used by the user, and the weight of the tag is the number of times the user uses the tag. The disadvantage of this modeling method is that it gives too much weight to popular tags, thus unable to reflect the user's personalized interests. Here, we can draw on the idea of TF-IDF to improve this formula. Let TagUser[t] represent the number of different users who use tag t:

[0083]

[0084] Preferably, the health data can be obtained by connecting a wearable device to the hospital health system. The wearable devices include but are not limited to smart watches, bracelets, earphones, and glasses; the dynamic changes of resources include but are not limited to classroom status and coach's free time.

[0085] The above embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the appended claims.

Claims

1. A yoga intelligent class schedule generated based on user preferences, including a tag generation module, a recommendation algorithm module, a class scheduling module, a fine-tuning module, a data import module, a statistical analysis module, a health data access module, a time management module, a course display and interaction module, an intelligent error correction module, and a yoga studio operation integration module. Characterized in that: The following steps: S1. Obtain the user's personal information, demand data, and health data, generate personalized tags for the user based on these data, and at the same time conduct a health risk assessment of the user in combination with the health data; S2. According to the tags generated by the user, combined with the course database, recommend yoga courses that meet the user's needs and consider the health status to the user through an optimized personalized recommendation algorithm; S3. Based on multiple restrictions on coaches, classrooms, and course arrangements, automatically generate a non-conflicting class schedule, and detect the dynamic changes of resources in real time during the class scheduling process, and automatically adjust the class schedule according to the changes; S4. Provide an artificial fine-tuning function to allow manual adjustment of the automatic class scheduling results in special cases; S5. Provide a batch import function to allow batch import of coach, course, and classroom information to reduce the data entry workload; S6. Provide a statistical analysis function to support viewing the class attendance of courses and coaches by dimensions such as monthly, quarterly, and annual, and at the same time provide statistical operations data such as financial statements and student consumption analysis; S7. According to the time preferences and schedule set by the user, combined with the class schedule, automatically detect and avoid time conflicts, and remind the user of course information by means of text messages, APP push, etc. before the course starts; S8. Provide content such as course details, action demonstration video links, coach profiles, and student evaluations for the user on the class schedule display interface. After the course ends, guide the user to give feedback on the evaluation, and provide a social interaction function to facilitate user communication; S9. During the automatic class scheduling process, perform intelligent error correction on the abnormal data that appears, give timely warnings for serious abnormalities that cannot be solved and provide suggestions for temporary solutions, and at the same time provide a recovery and retry function; S10. Provide a marketing and promotion channel for the yoga studio, publish information such as course discount activities, new coach introductions, and promotion of special courses, and accurately push it to eligible users.

2. A yoga intelligent class schedule generated based on user preferences according to claim 1, Characterized in that: The tag generation module is used to generate personalized tags according to the personal information, demand data, and health data input by the user, and at the same time conduct a health risk assessment in combination with the health data; The recommendation algorithm module is used to recommend suitable yoga courses for the user according to the user tags, course information, and health risk assessment results, in combination with an optimized personalized recommendation algorithm; The class scheduling module automatically generates class scheduling results according to coaches, classrooms, courses, and user needs, solves various conflict situations, and monitors the dynamic changes of resources in real time and automatically adjusts the class schedule; The fine-tuning module supports manual adjustment of the automatically generated class scheduling results in special cases; The data import module supports batch import of coach, course, and classroom information; The statistical analysis module is used to perform statistics on the course situation and the coach's teaching situation, support viewing relevant data according to different time dimensions, and at the same time provide statistical operations such as financial statements and student consumption analysis; The health data access module is responsible for accessing wearable devices or docking with the hospital health system to obtain user health data; The time management module automatically detects and avoids schedule time conflicts according to the user's time preference settings and schedule arrangements, and gives a reminder before the course starts; The course display and interaction module provides content such as course details, action demonstration video links, coach profiles, and student evaluations on the course schedule display interface. After the course ends, it guides users to give feedback and provides social interaction functions; The intelligent error correction module performs intelligent error correction on data anomalies during the automatic course scheduling process, gives early warnings for serious anomalies and provides suggestions for temporary solutions, and at the same time provides recovery and retry functions; The yoga studio operation integration module provides marketing and promotion channels for the yoga studio, publishes information such as preferential activities and pushes them accurately.

3. A yoga intelligent course schedule generated based on user preferences according to claim 1, characterized in that: Personalized recommendation algorithm based on tags A dataset of user tag behaviors is generally represented by a set of triples, where the record (u, i, b) means that user u has tagged course i with tag b. Of course, the real tag behavior data of users is much more complex than that represented by triples, such as the time when users tag, the attribute data of users, the attribute data of yoga courses, etc. 1> Count the common tags of each user 2> For each tag, count the course that has been tagged with this tag the most times 3> For a specific user, find his most common tags and recommend the most popular yoga courses of these tags to him 4> Recommendation sorting The personalized recommendation algorithm: where UserTags[u, t] represents the number of times user u has used tag t, and TagCourses[t, i]T represents the number of times course i has been tagged with tag t.

4. A yoga intelligent course schedule generated based on user preferences according to claim 1, characterized in that: If a tag is very popular, it will cause UserTags[t] to be very large. Therefore, even if TagCourses[u, t] is small, it will cause score(u, i) to be very large. As a result, it will recommend popular yoga courses to users, thus reducing the novelty of the recommendation results. In addition, this formula models the user's interests using the user's tag vector, where each tag is a tag used by the user, and the weight of the tag is the number of times the user has used the tag. The disadvantage of this modeling method is that it gives too much weight to popular tags, thus failing to reflect the user's personalized interests. Here we can draw on the idea of TF-IDF to improve this formula, and use TagUser[t] to represent the number of different users who have used tag t:

5. A yoga intelligent course schedule generated based on user preferences according to claim 1, characterized in that: The health data can be obtained by connecting wearable devices to the hospital health system. The wearable devices include but are not limited to smart watches, bracelets, earphones, and glasses.

6. A yoga smart class schedule generated based on user preferences according to claim 1, characterized in that: The dynamic change of the resources includes but is not limited to the classroom status and the free time of the coaches.

Images