Motion recommendation method and system based on big data analysis

Abstract

The invention discloses an exercise recommendation method and system based on big data analysis. The method comprises the steps of obtaining historical exercise data of a target exercise item corresponding to a target object; determining a basic level of the target object on the target exercise item based on the historical exercise data; pairing the target objects according to the number of people required by the target sports item in the preset group, and recommending a pairing result to the target objects; wherein the preset group comprises the moving objects with the same basic level. By means of the mode, the motion objects with similar motion levels can be recommended to the sportsman.

Description

Technical Field

[0001] This application relates to the field of big data technology, and particularly to a sports recommendation method and system based on big data analysis. Background Art

[0002] In order to improve the physical fitness of the public, it is necessary to improve the public's sports level. Especially with the increasing number of people with the four highs (hypertension, hyperlipidemia, hyperglycemia, and hyperuricemia) year by year, it is necessary to increase the sports interest of people with the four highs. In real life, people often have a significant difference in technical level with their sports partners during exercise, resulting in a decrease in sports interest, and then a reduction in exercise duration, which is beneficial to improving people's physical health level. Summary of the Invention

[0003] The main technical problem to be solved by this application is to provide a sports recommendation method and system based on big data analysis, which can recommend sports partners with similar sports levels to sports personnel.

[0004] To solve the above technical problem, one technical solution adopted by this application is: to provide a sports recommendation method based on big data analysis, including: obtaining historical sports data of a target sport item corresponding to a target object; determining the basic level of the target object in the target sport item based on the historical sports data; pairing the target object according to the number of people required for the target sport item in a preset group, and recommending the pairing result to the target object; wherein, the preset group includes sports objects with the same basic level.

[0005] To solve the above technical problem, another technical solution adopted by this application is: to provide a sports recommendation system based on big data analysis, including: an obtaining module, configured to obtain historical sports data of a target sport item corresponding to a target object; an evaluation module, configured to determine the basic level of the target object in the target sport item based on the historical sports data; a pairing module, configured to pair the target object according to the number of people required for the target sport item in a preset group, and recommend the pairing result to the target object; wherein, the preset group includes sports objects with the same basic level.

[0006] The beneficial effects of this application are as follows: Different from the prior art, a sports recommendation method based on big data analysis is provided, including: obtaining historical sports data of a target sports event corresponding to a target object, determining the basic level of the target object in the target sports event based on the historical sports data, pairing the target object according to the number of people required for the target sports event in a preset group, and recommending the pairing result to the target object, where the preset group includes sports objects with the same basic level. By determining the basic level of the target object in the target sports event based on the historical sports data of the target object, sports objects with the same basic level as the target object are paired for the target object during the sports recommendation process, which is beneficial to improving the fun and experience of the target object during the process of carrying out the target sports event, and further improving the sports enthusiasm of the target sports object. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a schematic flowchart of an embodiment of a sports recommendation method based on big data analysis of this application; Figure 2 is a schematic timing diagram of an embodiment of a sports recommendation method based on big data analysis of this application; Figure 3 is a system block diagram of an embodiment of a sports recommendation method based on big data analysis of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0008] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0009] To improve the physical fitness of the public, it is necessary to improve the sports level of the public. Especially with the increasing number of people with the four highs (hypertension, hyperlipidemia, hyperglycemia, and hyperuricemia) year by year, it is necessary to increase the sports interest of people with the four highs. In real life, people often have a significant gap in technical level with their sports partners during the sports process, or it is difficult to find objects with similar technical levels, resulting in a decrease in sports interest, and then the sports duration is reduced, which is beneficial to improving people's physical health level.

[0010] Such as Figure 1As shown in the figure, a sports recommendation method based on big data analysis in the present application may include the following steps: S100: Obtain historical sports data of a target sports item corresponding to a target object. S200: Determine the basic level of the target object in the target sports item based on the historical sports data. S300: Pair the target object according to the number of people required for the target sports item in a preset group, and recommend the pairing result to the target object; wherein, the preset group includes sports objects with the same basic level.

[0011] This embodiment provides a sports recommendation method based on big data analysis, including: obtaining historical sports data of a target sports item corresponding to a target object, determining the basic level of the target object in the target sports item based on the historical sports data, pairing the target object according to the number of people required for the target sports item in a preset group, and recommending the pairing result to the target object, wherein, the preset group includes sports objects with the same basic level. By determining the basic level of the target object in the target sports item based on the historical sports data of the target object in the target sports item, sports objects with the same basic level as the target object can be paired for the target object during the sports recommendation process, which is beneficial to improving the fun and experience of the target object during the process of carrying out the target sports item, and further improving the sports enthusiasm of the target sports object.

[0012] The following will explain this embodiment in detail. As Figure 2 shown, this embodiment may include: S100: Obtain historical sports data of a target sports item corresponding to a target object.

[0013] The target object may include people with four highs. Specifically, during the process of determining the target object, relevant physiological data of the medical record of the person seeking medical treatment can be obtained from a hospital or a physical examination institution, such as blood pressure value, blood lipid index, blood sugar level, uric acid content, etc. Through these data, it can be determined whether the person seeking medical treatment is a person with four highs and their specific health status, so that the historical sports data of the target sports item corresponding to the selected target object can be obtained, and then sports recommendations can be made to the target object based on the historical sports data.

[0014] The target sports item may include the sports item that the target object often engages in or the sports item that the target object likes. Since the target object often engages in or likes the target sports item, during the process of recommending sports to the target object, the historical sports data of the target sports item can be obtained, and then sports recommendations can be made based on the historical sports data to be more in line with the preferences of the target object, improve the probability of successful recommendation, and increase user dependence.

[0015] In one implementation manner, for how to obtain the historical sports data of the target sports item corresponding to the target object, the following steps included in S100 can be referred to: S110: Receive the motion data obtained through the motion wearable device worn by the target object.

[0016] In the process of obtaining the historical motion data of the target motion event corresponding to the target object, the motion data obtained through the motion wearable device worn by the target object can be received. Specifically, the target object can wear a motion wearable device during the motion process, including but not limited to other sensing devices such as a motion bracelet, a smart watch, a smart phone, etc.

[0017] S120: Divide the motion data according to the motion event to obtain the historical motion data of the target motion event.

[0018] The motion data can include motion posture data, motion force data, and motion pace data. Obtaining the motion posture data, motion force data, and motion pace data of the target object during the motion process through the motion wearable device facilitates obtaining the historical motion data of the target motion event corresponding to the target object based on the motion posture data, motion force data, and motion pace data.

[0019] After obtaining the motion posture data, motion force data, and motion pace data, they can be divided according to the motion event to obtain the historical motion data corresponding to the target motion event.

[0020] In one implementation, for how to divide the motion data according to the motion event to obtain the historical motion data of the target motion event, the following steps included in S120 can be referred to: S121: Determine the motion data related to the level evaluation of each motion event from the preset motion level evaluation table.

[0021] S122: Divide the motion data based on the determined result to obtain the historical motion data of the target motion event.

[0022] The preset motion level evaluation table can be used to evaluate the basic motion level of the motion personnel. After obtaining the motion data, the motion data related to the level evaluation of each motion event can be determined from the preset motion level evaluation table, and the motion data can be divided based on the determined result to obtain the historical motion data of the target motion event. The historical motion data can include at least two of the motion posture data, motion force data, and motion pace data.

[0023] For example, if the motion data includes motion posture data, motion force data, and motion pace data, and it is determined from a preset motion level assessment table that the motion data related to the level evaluation of swimming includes motion posture data, motion force data, and motion pace data, then the motion posture data and motion force data can be divided based on the determined result to obtain the historical motion data of swimming.

[0024] For another example, if the motion data includes motion posture data, motion force data, and motion pace data, and it is determined from a preset motion level assessment table that the motion data related to the level evaluation of badminton includes motion posture data and motion force data, then the motion posture data, motion force data, and motion pace data can be divided based on the determined result to obtain the historical motion data of badminton.

[0025] In one implementation, the target sports event may include badminton. For how to receive the motion data obtained through the motion wearable device worn by the target object, the following steps included in S110 can be referred to: S111: Receive the racket swing action data recognized by the sports bracelet worn by the target object.

[0026] S112: Receive the racket swing angle data measured by the level meter in the sports bracelet worn by the target object.

[0027] S113: Receive the racket swing force data measured by the dynamometer in the sports bracelet worn by the target object.

[0028] S114: Receive the foot displacement data read by the sensor on the sports shoes worn by the target object.

[0029] When the target sports event is badminton, during the process of receiving the motion data obtained through the motion wearable device worn by the target object, the racket swing action data recognized by the sports bracelet worn by the target object can be received. Specifically, the racket swing action data of the target object when hitting the badminton can be recognized by the camera on the sports bracelet, such as rubbing the ball, releasing the ball, hooking the ball, pouncing on the ball, pushing the ball, lifting the ball, and smashing the ball, etc.

[0030] When the target sports event is badminton, during the process of receiving the motion data obtained through the motion wearable device worn by the target object, the racket swing angle data measured by the level meter in the sports bracelet worn by the target object can be received. Specifically, the angle formed between the racket and the vertical direction during the racket swing of the target object can be measured by the level meter on the sports bracelet.

[0031] When the target sports event is badminton, during the process of receiving the sports data obtained by the sports wearable device worn by the target object, the racket swing force data measured by the dynamometer in the sports bracelet worn by the target object and the foot displacement data read by the sensor on the sports shoes worn by the target object can be received.

[0032] After obtaining the sports data obtained by the sports wearable device worn by the target object, the sports data related to the level evaluation of badminton can be determined from the preset sports level evaluation form, and the sports data can be divided based on the determined results to obtain the historical sports data of badminton.

[0033] S200: Determine the basic level of the target object in the target sports event based on the historical sports data.

[0034] After determining the historical sports data of the target sports event corresponding to the target object, the basic level of the target object in the target sports event can be determined based on the historical sports data, so that sports objects with similar basic levels can be paired to improve the sports fun and enthusiasm of the target object.

[0035] In one implementation, for how to determine the basic level of the target object in the target sports event based on the historical sports data, the following steps included in S200 can be referred to: S210: Input the historical sports data into the preset evaluation model.

[0036] S220: Determine the preset evaluation range in the preset sports level evaluation form corresponding to each sports data in the historical sports data through the preset evaluation model, and accumulate the hit times of all preset evaluation ranges.

[0037] S230: Determine the preset evaluation range with the highest hit times as the representative range of the historical sports data.

[0038] S240: Obtain the basic level of the target object in the target sports event corresponding to the representative range output by the preset evaluation model.

[0039] The preset evaluation model can be a model preset for evaluating the basic level based on the historical sports data, and this model can be obtained through big data training.

[0040] Specifically, in the process of determining the basic level of the target object in the target sports event based on historical motion data, the historical motion data can be input into a preset evaluation model. The preset evaluation model is used to determine the preset evaluation range in the preset motion level evaluation table corresponding to each motion data in the historical motion data, and accumulate the hit times of all preset evaluation ranges. The preset evaluation range with the highest hit times is determined as the representative range of the historical motion data, and the basic level of the target object in the target sports event corresponding to the representative range is output.

[0041] By inputting the historical motion data of the target object in the target sports event into the preset evaluation model to determine the basic level of the target object, the efficiency in the sports recommendation process can be improved, and the user experience can be enhanced.

[0042] In one implementation, the target sports event may include badminton. For how to determine the basic level of the target object's badminton through the preset evaluation model, the following steps can be referred to: S251: Input the racket swing motion data, racket swing angle data, racket swing force data, and foot displacement data into the preset evaluation model.

[0043] S252: The preset evaluation model is used to determine the preset evaluation range in the preset motion level evaluation table corresponding to each motion data among the racket swing motion data, racket swing angle data, racket swing force data, and foot displacement data, and accumulate the hit times of all preset evaluation ranges.

[0044] S253: Respectively determine the preset evaluation range with the highest hit times as the representative range of the racket swing motion data, racket swing angle data, racket swing force data, and foot displacement data.

[0045] S254: Based on the preset motion level evaluation table, respectively determine the basic levels corresponding to the representative ranges of the racket swing motion data, racket swing angle data, racket swing force data, and foot displacement data.

[0046] S255: Sum up the respective basic levels according to the corresponding preset scores and then take the average value.

[0047] S256: Based on the preset motion level evaluation table, determine the final basic level corresponding to the average value.

[0048] In the process of determining the basic level of the badminton movement of the target object through a preset evaluation model, the swing action data, swing angle data, swing force data, and foot displacement data can be input into the preset evaluation model. The preset evaluation model determines the preset evaluation ranges in the preset movement level evaluation table corresponding to each movement data in the swing action data, swing angle data, swing force data, and foot displacement data, and accumulates the hit times of all the preset evaluation ranges. For example, the swing angle data can include 5 data values, namely 12°, 17°, 34°, 55°, and 62°. The preset evaluation ranges corresponding to the swing angle data in the preset movement level evaluation table are 0 - 30°, 30 - 60°, and 60 - 90°, so as to determine that the hit times of each preset evaluation range are 2, 2, and 1 respectively.

[0049] After accumulating the hit times of all the preset evaluation ranges of all the movement data, the preset evaluation range with the highest hit times can be determined respectively as the representative range of the swing action data, swing angle data, swing force data, and foot displacement data. For example, if it is determined according to the hit times that the representative range of the swing action data is a lift, the representative range of the swing angle data is 30 - 60°, the representative range of the swing force data is 10 - 15 N, and the representative range of the foot displacement data is 5 - 10 cm.

[0050] After determining the representative range of each movement data, the basic level corresponding to the representative range of the swing action data, swing angle data, swing force data, and foot displacement data can be determined respectively based on the preset movement level evaluation table. Since there are basic levels corresponding to multiple movement data, in order to obtain a reasonable final basic level, the basic levels can be summed according to the corresponding preset scores and then averaged, and then the final basic level corresponding to the average value can be determined based on the preset movement level evaluation table. By summing and averaging multiple basic levels, the accuracy of the determined final basic level can be improved.

[0051] For example, if the basic level corresponding to the representative range of the swing action data being a lift is high, if the basic level corresponding to the representative range of the swing angle data being 30 - 60° is medium, if the basic level corresponding to the representative range of the swing force data being 10 - 15 N is medium, and if the basic level corresponding to the representative range of the foot displacement data being 5 - 10 cm is low. If the preset score corresponding to the basic level of low is 1, the preset score corresponding to the basic level of medium is 2, and the preset score corresponding to the basic level of high is 3. If the basic levels are summed according to the corresponding preset scores and then averaged, it is (3 + 2 + 2 + 1) ÷ 4 = 2, and the corresponding final basic level is medium.

[0052] S300: Pair the target objects according to the number of people required for the target sports event in the preset grouping, and recommend the pairing result to the target objects.

[0053] The preset grouping may include sports objects with the same basic level as the target object. Specifically, the preset grouping may include sports objects with the same final basic level as the target object. During the process of making sports recommendations for the target object, the target object can be paired according to the number of people required for the target sports event in the preset grouping, and the pairing result can be recommended to the target object. By selecting pairs from the preset grouping with the same final basic level as the target object, it is beneficial to recommend people with the same basic level to the target object, enhance the sports enjoyment, fairness, and sense of achievement of the target object, and improve the sports enthusiasm of the target object.

[0054] In one implementation, for how to pair the target objects according to the number of people required for the target sports event in the preset grouping, the following steps included in S300 can be referred to: S310: Determine the number of people required to carry out the sports event based on the target sports event.

[0055] S320: Identify the sports objects in the preset grouping that are consistent with the final basic level of the target object, and calculate the difference between the average value of the basic levels corresponding to each sports object and the average value of the basic level of the target object.

[0056] S330: Pair the target objects according to the determined sports objects and the number of people required.

[0057] During the process of pairing the target objects according to the number of people required for the target sports event in the preset grouping, the number of people required to carry out the sports event can be determined first based on the target sports event. For example, if the target sports event is badminton, it is determined that the number of people required to carry out badminton is 2; if the target sports event is tennis, it is determined that the number of people required to carry out tennis is 2.

[0058] After determining the number of people required to carry out the sports event, the sports objects in the preset grouping that are consistent with the final basic level of the target object can be determined, and the difference between the average value of the basic levels corresponding to each sports object and the average value of the basic level of the target object can be calculated. Specifically, the sports objects in the preset grouping can be sorted in ascending order according to the difference. Then, the target objects are paired according to the sorted sports objects and the number of people required.

[0059] In one implementation, for how to recommend the pairing result to the target object, the following steps can be referred to: S340: Recommend the information of the sports objects to the target object so that the target object can pair with the sports objects to carry out group sports.

[0060] After determining the moving objects for pairing from the preset groups, the information of the moving objects can be recommended to the target object so that the target object can pair with the moving objects to carry out group sports activities. Specifically, the information of the moving objects can be recommended to the target object on a preset sports recommendation platform. For example, the ID or business card of the moving objects can be pushed to the target object. After receiving the information of the recommended moving objects, the target object can carry out group sports activities with the moving objects based on this information.

[0061] In one implementation, after recommending the pairing result to the target object, the following steps may be included: S350: Obtain the competition result of the target object in the sports activity after completing the pairing.

[0062] S360: Adjust the basic level corresponding to the target object based on the competition result, and re-pair the target object based on the adjusted basic level.

[0063] After recommending the pairing result to the target object, the target object can pair with the moving objects to carry out group sports activities, obtain the competition result of the target object in the sports activity after completing the pairing, and adjust the basic level of the target object based on the competition result, so as to re-pair the target object based on the adjusted basic level. By adjusting the basic level of the target object according to the competition result, it is beneficial to improve the accuracy and timeliness of pairing in the sports recommendation process and improve the user experience.

[0064] In one implementation, for how to adjust the basic level corresponding to the target object based on the competition result, the following steps included in S360 can be referred to: S361: If the competition results of the first preset number of consecutive times are victories, increase the basic level of the target object by one level.

[0065] S362: If the competition results of the second preset number of consecutive times are defeats, lower the basic level of the target object by one level.

[0066] In the process of adjusting the basic level corresponding to the target object based on the competition results, if the competition results are victorious for the first preset number of consecutive times, the basic level of the target object can be raised by one level. If the competition results are defeated for the second preset number of consecutive times, the basic level of the target object can be lowered by one level. Specifically, the first preset number and the second preset number can be the same or different. The number of victories required for different levels of improvement can also be different. For example, the number of victories required to upgrade from a low level to a medium level is less than the number of victories required to upgrade from a medium level to a high level. Similarly, the number of defeats required for different levels of reduction can also be different. For example, the number of defeats required to downgrade from a high level to a medium level is less than the number of defeats required to downgrade from a medium level to a low level.

[0067] For example, if the target object competes in the same target sports event and the competition results are victorious for 5 consecutive times, the basic level of the target object can be upgraded from a low level to a medium level. If the target object competes in the same target sports event and the competition results are victorious for 10 consecutive times, the basic level of the target object can be upgraded from a medium level to a high level.

[0068] As Figure 3 shown, this embodiment also provides a sports recommendation system based on big data analysis. The system includes: an acquisition module 10 for acquiring historical sports data of the target sports event corresponding to the target object. An evaluation module 20 for determining the basic level of the target object in the target sports event based on the historical sports data. A pairing module 30 for pairing the target object according to the required number of people in the target sports event in a preset group and recommending the pairing result to the target object; wherein, the preset group includes sports objects with the same basic level as the target object.

[0069] The above are only embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of the present application.

Claims

1. A sports recommendation method based on big data analysis, characterized in that, Including: Obtaining historical motion data of a target motion event corresponding to a target object; Determining a basic level of the target object in the target motion event based on the historical motion data; Pairing the target object according to the required number of people for the target motion event in a preset grouping, and recommending the pairing result to the target object; wherein, the preset grouping includes motion objects with the same basic level as that of the target object.

2. The method according to claim 1, characterized in that, The obtaining of the historical motion data of the target motion event corresponding to the target object includes: Receiving motion data obtained by a motion wearable device worn by the target object; Dividing the motion data according to motion events to obtain the historical motion data of the target motion event.

3. The method according to claim 2, wherein The motion data includes motion posture data, motion strength data, and motion pace data. The dividing of the motion data according to motion events to obtain the historical motion data of the target motion event includes: Determining motion data related to the level evaluation of each motion event from a preset motion level evaluation table; Dividing the motion data based on the determined result to obtain the historical motion data of the target motion event; wherein, the historical motion data includes at least two of the motion posture data, the motion strength data, and the motion pace data.

4. The method according to claim 3, characterized in that, The determining of the basic level of the target object in the target motion event based on the historical motion data includes: Inputting the historical motion data into a preset evaluation model; Determining, by the preset evaluation model, a preset evaluation range in the preset motion level evaluation table corresponding to each motion data in the historical motion data, and accumulating the hit times of all the preset evaluation ranges; Determining the preset evaluation range with the highest hit times as the representative range of the historical motion data; Obtaining the basic level of the target object in the target motion event corresponding to the representative range output by the preset evaluation model.

5. The method according to claim 4, wherein The target motion event includes badminton. The receiving of the motion data obtained by the motion wearable device worn by the target object includes: Receiving swing action data identified by a motion bracelet worn by the target object; Receiving swing angle data measured by a level in the motion bracelet worn by the target object; Receiving swing force data measured by a dynamometer in the motion bracelet worn by the target object; Receiving foot displacement amount data read by a sensor on the sports shoes worn by the target object; The determining of the basic level of the target object in the target motion event based on the historical motion data includes: Inputting the swing action data, the swing angle data, the swing force data, and the foot displacement amount data into a preset evaluation model; Determining, by the preset evaluation model, a preset evaluation range in the preset motion level evaluation table corresponding to each motion data among the swing action data, the swing angle data, the swing force data, and the foot displacement amount data, and accumulating the hit times of all the preset evaluation ranges; Respectively determine the preset evaluation range with the highest number of hits as the representative range of the swing action data, the swing angle data, the swing force data, and the foot displacement data; Based on the preset sports level evaluation form, respectively determine the basic levels corresponding to the representative ranges of the swing action data, the swing angle data, the swing force data, and the foot displacement data; Sum up each of the basic levels according to the corresponding preset scores and then take the average value; Based on the preset sports level evaluation form, determine the final basic level corresponding to the average value.

6. The method according to claim 5, characterized in that, The pairing of the target object according to the required number of people for the target sports event in the preset grouping includes: Based on the target sports event, determine the required number of people to carry out the sport; Determine the sports objects in the preset grouping whose final basic levels are the same as that of the target object, and calculate the difference between the average value of the basic levels corresponding to each sports object and the average value of the basic level of the target object; Pair the target object according to the determined sports objects and the required number of people; among them, the sports objects are paired in ascending order of the difference.

7. The method according to claim 6, wherein The recommending the pairing result to the target object includes: Recommend the information of the sports object to the target object, so that the target object and the sports object can be paired to carry out group sports.

8. The method according to claim 7, characterized in that After the pairing result is recommended to the target object, it includes: Obtain the game result of the target object after completing the pairing and carrying out the sport; Adjust the basic level corresponding to the target object based on the game result, so as to re-pair the target object based on the adjusted basic level.

9. The method according to claim 8, wherein The basic level includes low, medium, and high. The adjusting the basic level corresponding to the target object based on the game result includes: If the game results of the first preset number of consecutive times are victories, then raise the basic level of the target object by one level; If the game results of the second preset number of consecutive times are defeats, then lower the basic level of the target object by one level.

10. A sports recommendation system based on big data analysis, characterized in that, It includes: An acquisition module, configured to acquire the historical sports data of the target sports event corresponding to the target object; An evaluation module, configured to determine the basic level of the target object in the target sports event based on the historical sports data; A pairing module, configured to pair the target object according to the required number of people for the target sports event in the preset grouping and recommend the pairing result to the target object; among them, the preset grouping includes sports objects with the same basic level as that of the target object.

Images