Intelligent footpath interactive large screen data management system

Abstract

The present application relates to the technical field of wisdom walkway interaction, and discloses a wisdom walkway interaction large-screen data management system, the system process includes: the interactive large-screen system network identifies and processes the motion data monitored by the wisdom walkway, obtains the motion state and motion level of different users, carries out cluster analysis on the users, obtains the motion mode category of the users, and recommends the motion track based on the user preference based on the walkway motion network. The present application calculates the motion imbalance and motion intensity of the user by using the wisdom walkway, carries out cluster processing on the user based on the local density information selected so that the motion state difference between different motion mode category users reaches the maximum cut-off distance, the users with the same motion mode category have similar motion habits, the preference characteristic value of different category users for different walkway regions is combined to calculate the motion track recommendation result, and the interactive large screen is used to present the motion level and motion track recommendation result.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of smart trail interaction, and in particular to a smart trail interaction large-screen data management system. BACKGROUND

[0002] With the improvement of people's living standards and the enhancement of health awareness, hiking has gradually become a popular leisure activity. Trails, as the infrastructure of hiking, not only allow people to access nature and breathe fresh air, but also exercise their bodies and relieve stress. However, in today's society, people have a fast-paced life and high work pressure, and many people lack regular exercise habits, leading to health problems. Therefore, by scientifically and reasonably planning the trail route, people can better engage in outdoor exercise and improve their quality of life. In view of this, the present application proposes a smart trail interaction large-screen data management method, which uses wearable devices and interactive large-screen technology to analyze the individual's exercise state, including gait, heart rate, exercise intensity and other indicators, to understand the user's exercise needs and ability level, and can recommend suitable trail routes for them. SUMMARY

[0003] Therefore, the present application provides a smart trail interaction large-screen data management system, which aims to: 1) use the smart trail to monitor the user's gait, heart rate, pace, and movement trajectory data, and calculate the user's exercise imbalance and exercise intensity as the user's exercise state, and cluster analyze the users currently on the smart trail based on the user's exercise state. In the clustering analysis process, the maximum difference in exercise state between users of different exercise mode categories is selected based on local density information to obtain the exercise mode category of the user, wherein users with the same exercise mode category have similar exercise habits, the calculation and classification of the user's exercise state are realized, the same exercise trajectory recommendation result is provided for users of the same category, and exercise exchange is facilitated for users of the same category; 2) combine the preference characteristic values of users of different categories for different trail areas to construct an adaptability function representing the smoothness of the exercise trajectory recommendation result, and iteratively process the exercise trajectory recommendation result, wherein the adaptability function will tend to select more preferred trail areas as the recommendation result, and the distance between adjacent exercise trajectory points in the exercise trajectory recommendation result will not be too long. In the iteration process, a variety of iteration methods are mixed to effectively ensure the diversity of the exercise trajectory recommendation result, have better exploration performance, avoid missing the optimal solution, and the interactive large-screen system network transmits the exercise trajectory recommendation result and the user's exercise level to the interactive large-screen, the interactive large-screen displays the exercise level and exercise trajectory recommendation result of different users, and sends the exercise trajectory recommendation result and exercise level to the user's wearable device, realizing the smart trail interaction large-screen data management.

[0004] To achieve the above object, the application provides a running process of a smart path interactive large screen data management system, which comprises the following steps:

[0005] S1: connecting the wearable device to the interactive large screen system network, and transmitting the motion data of the user on the smart path to the interactive large screen system by the wearable device, wherein the motion data comprises gait, heart rate, pace and motion trajectory data;

[0006] S2: the interactive large screen system network identifies and processes the received motion data to obtain the motion state and motion level of different users;

[0007] S3: combining the motion state of the user to cluster and analyze the user currently on the smart path to obtain the motion mode category of the user, wherein the users with the same motion mode category have similar exercise habits, and the motion mode clustering of the motion state analysis is the main implementation method of the user clustering analysis;

[0008] S4: constructing a path motion network and analyzing the motion trajectory preference of the users with the same motion mode category, wherein the improved attention mechanism is the main implementation method for constructing the path motion network;

[0009] S5: recommending the motion trajectory based on the user preference based on the path motion network to obtain the motion trajectory recommendation result of the user group corresponding to different motion mode categories;

[0010] S6: transmitting the motion trajectory recommendation result and the motion level of the user to the interactive large screen, and the interactive large screen presents the motion level and the motion trajectory recommendation result of the user.

[0011] As a further improved method of the application:

[0012] Optionally, the S1 step of connecting the wearable device to the interactive large screen system network and transmitting the motion data of the user on the smart path to the interactive large screen system by the wearable device comprises:

[0013] connecting the wearable device to the interactive large screen system network, the user wearing the wearable device and moving on the smart path, the smart path monitoring the motion data of the user, and transmitting the motion data of the user on the smart path to the interactive large screen system by the wearable device, wherein the motion data comprises gait, heart rate, pace and motion trajectory data, and the motion data of the user on the smart path is in the form of:

[0014]

[0015] wherein:

[0016] s n represents the motion data of the nth user on the smart path, and N represents the number of users on the smart path;

[0017] indicates the gait, heart rate, pace and motion trajectory data of the nth user on the smart walkway in sequence;

[0018] indicates the average pressure of the left foot of the nth user on the ground perceived by the smart walkway, indicates the average pressure of the right foot of the nth user on the ground perceived by the smart walkway;

[0019] indicates the heart rate skewness, average heart rate and heart rate standard deviation of the nth user in sequence;

[0020] indicates the pace skewness, average pace and pace standard deviation of the nth user in sequence;

[0021] indicates the motion trajectory data num n indicates the number of motion trajectory coordinate points in the motion trajectory data n indicates the number of motion trajectory coordinate points in the motion trajectory data In the embodiment of the application, the smart walkway monitors the gait, heart rate, pace and motion trajectory of the user every Δ time and updates the motion data of the user.

[0022] Optionally, the interactive large-screen system network identifies the received motion data in the S2 step, including:

[0023] The interactive large-screen system network identifies the received motion data to obtain the motion state and motion level of different users, and the identification process of the motion data is as follows:

[0024] S21: calculating the motion imbalance degree of the user motion, wherein the motion imbalance degree calculation formula of the nth user is:

[0025]

[0026] wherein:

[0027] ban n indicates the motion imbalance degree of the nth user;

[0028] S22: calculating the motion intensity of the user motion, wherein the motion intensity calculation formula of the nth user is:

[0029] st n =(st n (1),st n (2))

[0030]

[0031] wherein:

[0032] st n represents the exercise intensity of the nth user, st n (1) represents the exercise heart rate intensity of the nth user, st n (2) represents the exercise pace intensity of the nth user; the interactive large screen divides the users into 7 exercise levels according to the exercise intensity of the users, and if the exercise intensity of a user reaches the preset intensity threshold of the exercise level, the user is assigned to the corresponding exercise level, and the higher the exercise intensity, the higher the exercise level;

[0033] time n represents the current exercise duration of the nth user on the intelligent walkway;

[0034] exp(·) represents an exponential function with a natural constant as the base;

[0035] S23: taking the exercise imbalance degree and the exercise intensity of the user exercise as the exercise state of the user, wherein the exercise state of the nth user is R n =[ban n ,st n ].

[0036] Optionally, the S3 step combines the exercise state of the user to perform clustering analysis on the users currently on the intelligent walkway, to obtain the exercise mode category of the user, including:

[0037] The clustering analysis process is as follows:

[0038] S31: calculating the exercise mode similarity between any two users in the N users, wherein the exercise mode similarity calculation formula between the nth user and the ith user is:

[0039]

[0040] wherein:

[0041] p(n,i) represents the exercise mode similarity between the nth user and the ith user, i∈[1,N];

[0042] R i represents the exercise state of the ith user;

[0043] ||·|| represents the L1 norm;

[0044] The motion pattern similarity between different users is taken as the distance between users, and K users with the closest distance to each user are marked;

[0045] S32: The truncation distance in the clustering process is calculated based on the local density information:

[0046]

[0047] wherein:

[0048] The local density information of N users is represented, wherein the greater the local density information is, the smaller the local distance density difference between different users is, and the less obvious the distribution difference is;

[0049] The dist c is taken as the truncation distance, and the local distance density of the nth user is represented;

[0050] The dit c is taken as the truncation distance, and the local distance density ratio of the nth user is represented;

[0051] The truncation distance calculated based on the local density information is represented;

[0052] S33: The weighted local distance density of each user is calculated according to the calculated truncation distance, wherein the weighted local distance density of the nth user is:

[0053]

[0054] wherein:

[0055] ρ n represents the weighted local distance density of the nth user;

[0056] Sim(j, n) represents the number of coincident users between the K users with the closest distance to the nth user and the K users with the closest distance to the jth user;

[0057] represents the influence weight of the jth user on the local distance density of the nth user;

[0058] S34: The clustering center weight of each user is calculated, wherein the clustering center weight of the nth user is:

[0059]

[0060] wherein:

[0061] weight na cluster center weight representing an nth user;

[0062] δ n represents the distance to the nth user in the user set with a higher weighted local distance density than the nth user; if the weighted local distance density of the nth user is the maximum value, then δ n is the maximum value of the distance between the nth user and other users;

[0063] S35: Select G users with the highest cluster center weights as cluster centers, where G represents the number of motion mode categories, calculate the distance from non-cluster center users to cluster centers, and merge non-cluster center users into the cluster cluster where the nearest cluster center is located, as users of the same motion mode category, where the cluster analysis result is:

[0064]

[0065] wherein:

[0066] L g represents a user set of the gth motion mode category, represents the count g th user in the gth motion mode category, count g represents the number of users in the gth motion mode category.

[0067] Optionally, the step S4 of constructing the sidewalk movement network comprises:

[0068] constructing a sidewalk movement network, wherein the sidewalk movement network divides the smart sidewalk into Q sidewalk areas:

[0069] (area1, area2,..., area q ,..., area Q )

[0070] wherein:

[0071] area q represents the qth sidewalk area obtained by division;

[0072] performing preference analysis on the motion trajectories of the users of the same motion mode category based on the sidewalk movement network.

[0073] Optionally, the step of performing preference analysis on the motion trajectories of the users of the same motion mode category based on the sidewalk movement network comprises:

[0074] performing preference analysis on the motion trajectories of the users of the same motion mode category based on the sidewalk movement network, wherein the preference analysis process of the gth motion mode category user is:

[0075] S41: Extract the motion trajectory data of each user in the g-th motion pattern category, and map the motion trajectory data onto Q trail regions in the trail motion network to obtain the user's motion region vector, where the user... The motion region vector is:

[0076]

[0077] in:

[0078] Indicates user The motion region vector, Indicates user The characteristics of the movement trajectory in the q-th trail region. This indicates that the user The motion trajectory data does not contain the motion trajectory coordinates of the q-th trail area. This indicates that the user The motion trajectory data exists at the coordinate points of the motion trajectory located in the q-th trail area;

[0079] This represents the r-th user in the g-th motion pattern category, where r∈[1, count]. g ];

[0080] S42: Generate the attention preference weights for each user in the g-th motion pattern category, where the user... The attention preference weights are:

[0081]

[0082] in:

[0083] Indicates user Attention preference weights;

[0084] S43: Calculate the user preferences of users in the g-th type of motion pattern:

[0085]

[0086] in:

[0087] F g F represents the user preferences of users in the g-th type of exercise mode category. g (1),F g (2),...,F g (q),...,F g (Q) represents the preference feature values ​​of users of the g-th exercise mode category for the 1st to Qth trail areas.

[0088] Optionally, the step S5 utilizes the footpath motion network to recommend the motion trajectory based on the user preference, comprising:

[0089] The step of utilizing the footpath motion network to recommend the motion trajectory based on the user preference obtains the motion trajectory recommendation result of the user of different motion mode categories, wherein the motion trajectory recommendation process of the user of the gth motion mode category is as follows:

[0090] S51: setting the length of the motion trajectory recommendation result as M;

[0091] S52: initializing U pieces of motion trajectory recommendation results of the user of the gth motion mode category, wherein the u th piece of the initialized motion trajectory recommendation result is as follows:

[0092]

[0093] wherein:

[0094] denotes the u th piece of the initialized motion trajectory recommendation result;

[0095] denotes the M pieces of motion trajectory points in the motion trajectory recommendation result denotes the m th piece of motion trajectory point in the motion trajectory recommendation result , wherein each motion trajectory point corresponds to a footpath area,

[0096] S53: setting the current iteration number of each piece of motion trajectory recommendation result as t and the maximum iteration number as Max, and the t th iteration result of the u th piece of the generated motion trajectory recommendation result is as follows:

[0097] S54: constructing a fitness function taking the motion trajectory recommendation result as the input, inputting the motion trajectory recommendation result into the fitness function to obtain the fitness function value of the motion trajectory recommendation result, wherein the fitness function value of the motion trajectory recommendation result is as follows:

[0098]

[0099] wherein:

[0100] denotes the fitness function value of the motion trajectory recommendation result ; and

[0101] denotes the preference feature value of the footpath area corresponding to the m th piece of motion trajectory point in the motion trajectory recommendation result ; and ​

[0102] DIS represents a distance threshold, represents a motion trajectory point Euclidean distance between the corresponding central regions of the footpath; in the embodiment of the present application, represents the Euclidean distance between the current average position coordinates of all users of the gth motion mode category and

[0103] S55: taking the U motion trajectory recommendation results obtained in the tth iteration as inputs of the fitness function in turn, and selecting the motion trajectory recommendation result with the maximum fitness function value as the optimal motion trajectory recommendation result obtained in the tth iteration

[0104] S56: iterating each motion trajectory recommendation result, wherein the iteration process of the motion trajectory recommendation result is as follows:

[0105] If t is even, the following iteration formula is adopted for iteration:

[0106]

[0107] wherein:

[0108] rand(0,1) represents a random number between 0 and 1;

[0109] median t represents the median of the fitness function values of the U motion trajectory recommendation results obtained in the tth iteration;

[0110] represents any one of the motion trajectory recommendation results obtained in the tth iteration and different from

[0111] If t is odd, the following iteration formula is adopted for iteration:

[0112]

[0113] S57: setting t=t+1, returning to step S55 until the maximum number of iterations is reached, and taking the U motion trajectory recommendation results at this time as inputs of the fitness function in turn, and selecting the motion trajectory recommendation result with the maximum fitness function value and the trajectory coordinate points in the range of [1, Q] as the motion trajectory recommendation result of the user of the gth motion mode category.

[0114] Optionally, the S6 step transmits the motion trajectory recommendation result and the motion level to an interactive large screen, and the interactive large screen presents the motion level and the motion trajectory recommendation result for the user, including: ​​

[0115] The interactive large screen system network transmits the motion trajectory recommendation result and the motion level of the user to the interactive large screen, the interactive large screen displays the motion levels and the motion trajectory recommendation results of different users, and sends the motion trajectory recommendation result and the motion level to the wearable device of the user.

[0116] In order to solve the above problems, the present application provides a smart walkway interactive large screen data management system, characterized in that the system comprises:

[0117] A motion data acquisition and processing module is configured to transmit the motion data of the user on the smart walkway to the interactive large screen system by using the wearable device, and the interactive large screen system network identifies and processes the received motion data to obtain the motion state and the motion level of different users.

[0118] A user clustering module is configured to cluster and analyze the users currently on the smart walkway in combination with the motion state of the users to obtain the motion mode category of the users, construct a walkway motion network, and analyze the motion trajectory preference of the users of the same motion mode category.

[0119] A motion trajectory recommendation device is configured to recommend the motion trajectory based on the user preference based on the walkway motion network to obtain the motion trajectory recommendation result of the user group corresponding to different motion mode categories, transmit the motion trajectory recommendation result and the motion level of the user to the interactive large screen, and present the motion level and the motion trajectory recommendation result for the user.

[0120] In order to solve the above problems, the present application further provides an electronic device, which comprises:

[0121] A memory is configured to store at least one instruction;

[0122] A communication interface is configured to realize the communication of the electronic device; and

[0123] A processor is configured to execute the instruction stored in the memory to realize the running process of the smart walkway interactive large screen data management system.

[0124] In order to solve the above problems, the present application further provides a computer readable storage medium, which stores at least one instruction, and the at least one instruction is executed by the processor in the electronic device to realize the smart walkway interactive large screen data management system.

[0125] Compared with the prior art, the present application provides a smart walkway interactive large screen data management system, which has the following advantages:

[0126] Firstly, the scheme proposes a user clustering method fusing user motion state, which combines the user motion state to cluster analyze N users currently on the intelligent sidewalk, and obtains the motion mode category of the user. The clustering analysis process is as follows: the motion mode similarity between any two users in N users is calculated, and the motion mode similarity calculation formula between the nth user and the ith user is as follows:

[0127]

[0128] Wherein: p(n,i) represents the motion mode similarity between the nth user and the ith user, i∈[1,N]; R i represents the motion state of the ith user; ||·|| represents L1 norm; the motion mode similarity between different users is taken as the distance between users, and the K users closest to each user are marked; the local density information in the clustering process is calculated based on the local density information:

[0129]

[0130] Wherein: represents the local density information of N users; represents that dist c is taken as the local distance density of the nth user; represents that dist c is taken as the local distance density ratio of the nth user; represents the local density information based on the local density information. According to the calculated local density information, the weighted local distance density of each user is calculated, and the weighted local distance density of the nth user is as follows:

[0131]

[0132] Wherein: p n represents the weighted local distance density of the nth user; Sim(j,n) represents the number of coincident users between the K users closest to the nth user and the K users closest to the jth user; denotes the influence weight of the jth user on the nth user local distance density; the cluster center weight of each user is calculated, and the user with the highest G cluster center weights is taken as the cluster center, where G represents the number of motion mode categories, the distance from the non-cluster center user to the cluster center is calculated, and the non-cluster center user is merged into the cluster cluster where the nearest cluster center is located. The scheme utilizes the intelligent walkway to monitor the gait, heart rate, pace and motion trajectory data of the user, and calculates the motion imbalance degree and motion intensity of the user motion as the motion state of the user, and combines the motion state of the user to perform cluster analysis on the user currently in the intelligent walkway. In the cluster analysis process, the maximum difference of the motion state between different motion mode categories of users is selected based on the local density information to obtain the motion mode category of the user, wherein the users with the same motion mode category have similar exercise habits, the calculation and classification processing of the user motion state are realized, the same motion trajectory recommendation result is provided for the users of the same category, and the motion exchange of the users of the same category is facilitated.

[0133] Meanwhile, the scheme proposes a motion trajectory recommendation method fusing user preference features, which utilizes the walkway motion network to perform user preference-based motion trajectory recommendation to obtain motion trajectory recommendation results of users of different motion mode categories. The motion trajectory recommendation process for the gth motion mode category user is as follows: the length of the motion trajectory recommendation result is set as M; U motion trajectory recommendation results of the gth motion mode category user are initialized, wherein the u th initialized motion trajectory recommendation result is as follows:

[0134]

[0135] wherein: denotes the u th initialized motion trajectory recommendation result;

[0136] denotes the M motion trajectory points in the motion trajectory recommendation result denotes the m th motion trajectory point in the motion trajectory recommendation result , wherein each motion trajectory point corresponds to a walkway area, the current iteration number of each motion trajectory recommendation result is set as t, and the maximum iteration number is Max, so the t th iteration result of the u th generated motion trajectory recommendation result is a fitness function taking the motion trajectory recommendation result as the input is constructed, the motion trajectory recommendation result is input into the fitness function, and the fitness function value of the motion trajectory recommendation result is obtained, wherein the fitness function value of the motion trajectory recommendation result is as follows:

[0137] ​

[0138] wherein:

[0139] represents the fitness function value of the motion trajectory recommendation result

[0140] represents the preference feature value of the stepway region corresponding to the mth motion trajectory point in the motion trajectory recommendation result DIS represents a distance threshold, represents the Euclidean distance between the stepway region centers corresponding to the motion trajectory points of the tth iteration, and the U motion trajectory recommendation results obtained in the tth iteration are sequentially taken as the input of the fitness function, and the motion trajectory recommendation result with the maximum fitness function value is selected as the optimal motion trajectory recommendation result obtained in the tth iteration Each motion trajectory recommendation result is iterated. The present scheme combines the preference feature values of different categories of users for different stepway regions, constructs a fitness function representing the smoothness of the motion trajectory recommendation result, and iteratively processes the motion trajectory recommendation result, wherein the fitness function tends to select more preferred stepway regions as the recommendation result, and makes the distance between adjacent motion trajectory points in the motion trajectory recommendation result not too long. In the iteration process, a plurality of iteration methods are mixed for hybrid iteration, effectively ensuring the diversity of the motion trajectory recommendation result, having better exploration performance, avoiding missing the optimal solution, the interactive large screen system network transmits the motion trajectory recommendation result and the motion level of the user to the interactive large screen, the interactive large screen displays the motion levels and motion trajectory recommendation results of different users, and sends the motion trajectory recommendation result and the motion level to the wearable device of the user, realizing the data management of the intelligent stepway interactive large screen. BRIEF DESCRIPTION OF DRAWINGS

[0141] Figure 1 The running flowchart of the data management system of the intelligent stepway interactive large screen provided by an embodiment of the present application is shown in the figure.

[0142] Figure 2 The functional module diagram of the data management system of the intelligent stepway interactive large screen provided by an embodiment of the present application is shown in the figure.

[0143] Figure 2 In the figure: 100 is the data management system of the intelligent stepway interactive large screen, 101 is a motion data acquisition and processing module, 102 is a user clustering module, and 103 is a motion trajectory recommendation device.

[0144] Figure 3 The structural diagram of the electronic device for realizing the data management system of the intelligent stepway interactive large screen provided by an embodiment of the present application is shown in the figure.

[0145] ​Figure 3 The electronic device, the processor, the memory, the program, and the communication interface are denoted as 1, 10, 11, 12, and 13, respectively.

[0146] The implementation, functional features, and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0147] It should be understood that the specific embodiments described herein are merely illustrative of the present application and do not limit the present application.

[0148] Embodiments of the present application provide a smart trail interactive large screen data management system. The execution subject of the smart trail interactive large screen data management system includes but is not limited to at least one of the electronic devices that can be configured to execute the method provided by the embodiments of the present application, such as a server and a terminal. In other words, the smart trail interactive large screen data management system can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server, or a cloud server cluster.

[0149] Embodiment 1:

[0150] S1: Access the wearable device to the interactive large screen system network, and use the wearable device to transmit the motion data of the user on the smart trail to the interactive large screen system, wherein the motion data includes gait, heart rate, pace, and motion trajectory data.

[0151] In the S1 step, the wearable device is accessed to the interactive large screen system network, and the wearable device is used to transmit the motion data of the user on the smart trail to the interactive large screen system, including:

[0152] The wearable device is accessed to the interactive large screen system network, the user wears the wearable device and moves on the smart trail, the smart trail monitors the motion data of the user, and the wearable device is used to transmit the motion data of the user on the smart trail to the interactive large screen system, wherein the motion data includes gait, heart rate, pace, and motion trajectory data, and the motion data of the user on the smart trail is in the form of:

[0153]

[0154] Wherein:

[0155] s n The motion data of the nth user on the smart trail is denoted as s n, and N represents the number of users on the smart trail;

[0156] The gait, heart rate, pace, and motion trajectory data of the nth user on the smart trail are denoted as g n, h n, p n, and t n, respectively; represents the average pressure of the left foot of the nth user on the ground perceived by the smart trail; represents the average pressure of the right foot of the nth user on the ground perceived by the smart trail;

[0157] represents the skewness of the heart rate, the average heart rate and the standard deviation of the heart rate of the nth user in turn;

[0158] represents the skewness of the pace, the average pace and the standard deviation of the pace of the nth user in turn;

[0159] represents the number of motion trajectory coordinate points in the motion trajectory data n represents the number of motion trajectory coordinate points in the motion trajectory data n

[0160] S2: The interactive large-screen system network identifies the received motion data to obtain the motion state and the motion level of different users.

[0161] The identification processing of the received motion data by the interactive large-screen system network in the S2 step includes:

[0162] The interactive large-screen system network identifies the received motion data to obtain the motion state and the motion level of different users, and the identification processing flow of the motion data is:

[0163] S21: The motion imbalance degree of user motion is calculated, and the motion imbalance degree calculation formula of the nth user is:

[0164]

[0165] Wherein:

[0166] ban n represents the motion imbalance degree of the nth user;

[0167] S22: The motion intensity of user motion is calculated, and the motion intensity calculation formula of the nth user is:

[0168] st n =(st n (1),st n (2))

[0169]

[0170] Wherein:

[0171] st n ​​​represents the exercise intensity of the nth user, st n (1) represents the exercise heart rate intensity of the nth user, st n (2) represents the exercise pace intensity of the nth user; the interactive large screen divides users into 7 exercise levels according to the exercise intensity of the users, and if the exercise intensity of a user reaches the preset intensity threshold of the exercise level, the user is assigned to the corresponding exercise level, and the higher the exercise intensity, the higher the exercise level;

[0172] time n represents the current exercise duration of the nth user on the intelligent walkway;

[0173] exp(·) represents an exponential function with a natural constant as the base;

[0174] S23: The exercise imbalance degree and the exercise intensity of the user exercise are taken as the exercise state of the user, wherein the exercise state of the nth user is R n =[ban n ,st n ].

[0175] S3: The users currently on the intelligent walkway are analyzed by clustering in combination with the exercise state of the users, to obtain the exercise mode category of the users, wherein the users with the same exercise mode category have similar exercise habits.

[0176] The S3 step of analyzing the users currently on the intelligent walkway by clustering in combination with the exercise state of the users to obtain the exercise mode category of the users includes:

[0177] The N users currently on the intelligent walkway are analyzed by clustering in combination with the exercise state of the users, to obtain the exercise mode category of the users, wherein the clustering analysis process is:

[0178] S31: The exercise mode similarity between any two users in the N users is calculated, wherein the exercise mode similarity calculation formula between the nth user and the i-th user is:

[0179]

[0180] wherein:

[0181] p(n,i) represents the exercise mode similarity between the nth user and the i-th user, i∈[1,N];

[0182] R i represents the exercise state of the i-th user;

[0183] ||·|| represents the L1 norm;

[0184] The motion pattern similarity between different users is taken as the distance between the users, and K users closest to each user are marked;

[0185] S32: Calculate the truncation distance in the clustering process based on the local density information:

[0186]

[0187]

[0188] Wherein:

[0189] The local density information of N users is represented, wherein the greater the local density information, the smaller the difference in local distance density between different users, and the less obvious the distribution difference;

[0190] The local distance density of the nth user is represented as dist c The local distance density of the nth user is represented as dist

[0191] The local distance density of the nth user is represented as dist c The local distance density of the nth user is represented as dist

[0192] The truncation distance calculated based on the local density information is represented;

[0193] S33: Calculate the weighted local distance density of each user according to the calculated truncation distance, wherein the weighted local distance density of the nth user is:

[0194]

[0195] Wherein:

[0196] The weighted local distance density of the nth user is represented as p n The weighted local distance density of the nth user is represented as p

[0197] Sim(j,n) represents the number of coincident users between the K users closest to the nth user and the K users closest to the jth user;

[0198] The influence weight of the jth user on the local distance density of the nth user is represented as w

[0199] S34: Calculate the clustering center weight of each user, wherein the clustering center weight of the nth user is:

[0200]

[0201] Wherein:

[0202] weight n denotes the cluster center weight of the nth user;

[0203] δ n denotes the distance from the nth user to the nearest user in the user set whose weighted local distance density is higher than that of the nth user; if the weighted local distance density of the nth user is the maximum, then δ n is the maximum distance between the nth user and other users;

[0204] S35: Select the user with the highest cluster center weight as the cluster center, where G represents the number of motion mode categories, calculate the distance from the non-cluster center user to the cluster center, and merge the non-cluster center user into the cluster cluster where the nearest cluster center is located, as the user of the same motion mode category, and the cluster analysis result is:

[0205]

[0206] wherein:

[0207] L g denotes the user set of the gth motion mode category, denotes the count g th user in the gth motion mode category, count g denotes the number of users in the gth motion mode category.

[0208] S4: Construct a stepway motion network and perform preference analysis on the motion trajectories of the users of the same motion mode category.

[0209] The step of constructing a stepway motion network in the S4 step comprises:

[0210] Constructing a stepway motion network, wherein the stepway motion network divides the intelligent stepway into Q stepway areas:

[0211] (area1, area2,..., area q ,..., area Q )

[0212] wherein:

[0213] area q denotes the qth stepway area obtained by division;

[0214] Performing preference analysis on the motion trajectories of the users of the same motion mode category based on the stepway motion network.

[0215] The step of performing preference analysis on the motion trajectories of the users of the same motion mode category based on the stepway motion network comprises:

[0216] Based on the trail motion network, preference analysis is performed on the motion trajectories of users with the same motion mode category. The preference analysis process for users in the g-th motion mode category is as follows:

[0217] S41: Extract the motion trajectory data of each user in the g-th motion pattern category, and map the motion trajectory data onto Q trail regions in the trail motion network to obtain the user's motion region vector, where the user... The motion region vector is:

[0218]

[0219] in:

[0220] Indicates user The motion region vector, Indicates user The characteristics of the movement trajectory in the q-th trail region. This indicates that the user The motion trajectory data does not contain the coordinates of the motion trajectory located in the q-th trail area. This indicates that the user The motion trajectory data exists at the coordinate points of the motion trajectory located in the q-th trail area;

[0221] This represents the r-th user in the g-th motion pattern category, where r∈[1, count]. g ];

[0222] S42: Generate the attention preference weights for each user in the g-th motion pattern category, where the user... The attention preference weights are:

[0223]

[0224] in:

[0225] Indicates user Attention preference weights;

[0226] S43: Calculate the user preferences of users in the g-th type of motion pattern:

[0227]

[0228] in:

[0229] F g F represents the user preferences of users in the g-th type of exercise mode category. g (1),F g (2),...,Fg (q),...,F g (Q) represents the preference feature values ​​of users of the g-th exercise mode category for the 1st to Qth trail areas.

[0230] S5: Based on the trail movement network, recommend movement trajectories based on user preferences to obtain movement trajectory recommendation results for user groups corresponding to different movement mode categories.

[0231] Step S5 utilizes a trail motion network to recommend motion trajectories based on user preferences, including:

[0232] Using a trail motion network, motion trajectory recommendation based on user preferences is performed to obtain motion trajectory recommendation results for users of different motion mode categories. The motion trajectory recommendation process for users of the g-th motion mode category is as follows:

[0233] S51: Set the length of the motion trajectory recommendation result to M;

[0234] S52: Initialize and generate U recommended motion trajectories for users in the g-th motion pattern category, where the initially generated u-th motion trajectory recommendation result is:

[0235]

[0236] in:

[0237] This represents the recommended motion trajectory of the uth element generated during initialization.

[0238] Indicates the motion trajectory recommendation results The M motion trajectory points in the middle, Indicates the motion trajectory recommendation results The m-th movement trajectory point in the map, where each movement trajectory point corresponds to a trail area.

[0239] S53: Set the current iteration number of each motion trajectory recommendation result to t, and the maximum iteration number to Max. Then, the t-th iteration result of the generated u-th motion trajectory recommendation result is:

[0240] S54: Construct a fitness function that takes the motion trajectory recommendation results as input. Input the motion trajectory recommendation results into the fitness function to obtain the fitness function value of the motion trajectory recommendation results. The fitness function value is:

[0241]

[0242] in:

[0243] a fitness function value of the motion trajectory recommendation result

[0244] a fitness function value of the motion trajectory recommendation result

[0245] DIS represents a distance threshold, a Euclidean distance between the centers of the corresponding walkway regions of the motion trajectory points

[0246] S55: taking the U motion trajectory recommendation results obtained in the tthiteration as inputs of the fitness function in turn, and selecting the motion trajectory recommendation result with the largest fitness function value as the optimal motion trajectory recommendation result obtained in the tthiteration

[0247] S56: iterating each motion trajectory recommendation result, wherein the iteration process of the motion trajectory recommendation result

[0248] If t is even, the following iteration formula is adopted for iteration:

[0249]

[0250] wherein:

[0251] rand(0,1) represents a random number between 0 and 1;

[0252] median t

[0253]

[0254] If t is odd, the following iteration formula is adopted for iteration:

[0255]

[0256] S57: setting t=t+1, returning to step S55 until the maximum iteration number is reached, and taking the U motion trajectory recommendation results at this time as inputs of the fitness function in turn, and selecting the motion trajectory recommendation result with the largest fitness function value and the trajectory coordinate points in the range of [1, Q] as the motion trajectory recommendation result of the user of the gthmotion mode category. ​​​​​​​

[0257] S6: transmit the motion trajectory recommendation result and the motion level of the user to the interactive large screen, and the interactive large screen presents the motion level and the motion trajectory recommendation result for the user.

[0258] The S6 step transmits the motion trajectory recommendation result and the motion level to the interactive large screen, and the interactive large screen presents the motion level and the motion trajectory recommendation result for the user, including:

[0259] The interactive large screen system network transmits the motion trajectory recommendation result and the motion level of the user to the interactive large screen, the interactive large screen displays the motion levels and the motion trajectory recommendation results of different users, and sends the motion trajectory recommendation result and the motion level to the wearable device of the user.

[0260] Embodiment 2:

[0261] As Figure 2 shown in FIG. 1, it is a functional module diagram of the intelligent path interactive large screen data management system provided by an embodiment of the present application, which can realize the intelligent path interactive large screen data management system in embodiment 1.

[0262] The intelligent path interactive large screen data management system 100 can be installed in an electronic device. According to the realized function, the intelligent path interactive large screen data management system can include a motion data acquisition and processing module 101, a user clustering module 102, and a motion trajectory recommendation device 103. The module of the present application can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, which is stored in the memory of the electronic device.

[0263] The motion data acquisition and processing module 101 is used for transmitting the motion data of the user on the intelligent path to the interactive large screen system by the wearable device, and the interactive large screen system network identifies and processes the received motion data to obtain the motion state and the motion level of different users.

[0264] The user clustering module 102 is used for clustering and analyzing the users currently on the intelligent path in combination with the motion state of the user to obtain the motion mode category of the user, constructing the path motion network, and analyzing the motion trajectory preference of the users of the same motion mode category.

[0265] The motion trajectory recommendation device 103 is used for recommending the motion trajectory based on the user preference based on the path motion network to obtain the motion trajectory recommendation result of the user group corresponding to different motion mode categories, and transmits the motion trajectory recommendation result and the motion level of the user to the interactive large screen. The interactive large screen presents the motion level and the motion trajectory recommendation result for the user.

[0266] In detail, the modules in the intelligent footpath interactive large-screen data management system 100 in the embodiments of the present application adopt the same technical means as the intelligent footpath interactive large-screen data management system in the above Figure 1 and can produce the same technical effects, which will not be described here again.

[0267] Embodiment 3

[0268] As Figure 3 shown in FIG. 1, is a structural schematic diagram of an electronic device for implementing the intelligent footpath interactive large-screen data management system according to an embodiment of the present application.

[0269] The electronic device 1 can include a processor 10, a memory 11, a communication interface 13 and a bus, and can further include a computer program, such as a program 12, stored in the memory 11 and executable on the processor 10.

[0270] The memory 11 includes at least one type of readable storage medium, such as a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 11 can include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 can be used not only to store application software and various data, such as the code of the program 12, installed in the electronic device 1, but also to temporarily store data that has been output or will be output.

[0271] The processor 10 can be composed of integrated circuits in some embodiments, for example, can be composed of a single packaged integrated circuit, or can be composed of multiple packaged integrated circuits with the same function or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, etc. The processor 10 is the control core of the electronic device, which connects various components of the entire electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (programs 12 for implementing intelligent sidewalk interactive large-screen data management, etc.), and calls data stored in the memory 11 to perform various functions and process data of the electronic device 1.

[0272] The communication interface 13 can include wired interfaces and / or wireless interfaces (such as WI-FI interfaces, Bluetooth interfaces, etc.), which are usually used to establish communication connections between the electronic device 1 and other electronic devices, and to realize connection and communication between internal components of the electronic device.

[0273] The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11, the at least one processor 10, etc.

[0274] Figure 3 Only an electronic device with components is shown, and those skilled in the art can understand that, Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and can include fewer or more components than shown, or combine certain components, or different component arrangements.

[0275] For example, although not shown, the electronic device 1 can also include a power supply (such as a battery) for powering various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, so as to realize functions such as charge management, discharge management, and power consumption management through the power management device. The power supply can also include one or more direct current or alternating current power supplies, recharging devices, power supply fault detection circuits, power supply converters or inverters, power supply status indicators, etc. The electronic device 1 can also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not described here.

[0276] Optionally, the electronic device 1 can further comprise a user interface, which can be a display, an input unit such as a keyboard, and optionally a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch screen, and the like. The display can also be appropriately referred to as a display screen or a display unit, and is used to display information processed in the electronic device 1 and to display a visualized user interface.

[0277] It should be understood that the above-described embodiments are merely illustrative, and the patent application scope is not limited by the structure.

[0278] It should be noted that the above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments. And the terms "include", "contain" or any other variants in this paper are intended to cover non-exclusive inclusion, so that the process, device, article or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, device, article or method. Without more limitations, the element defined by the sentence "including a" does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0279] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and necessary general hardware platforms, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, an optical disk) as described above, and includes a plurality of instructions for making a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the methods described in various embodiments of the present application.

[0280] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation made by using the contents of the present application specification and drawings, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A smart sidewalk interactive large screen data management system, characterized in that, The system process comprises: S1: connecting the wearable device to the interactive large screen system network, and transmitting the motion data of the user on the smart walkway to the interactive large screen system by using the wearable device, wherein the motion data comprises gait, heart rate, pace and motion trajectory data; S2: the interactive large screen system network identifies the received motion data to obtain the motion state and motion level of different users; S3: clustering analysis is performed on the users currently on the smart walkway in combination with the motion state of the users to obtain the motion mode category of the users, wherein the users with the same motion mode category have similar exercise habits; S4: constructing a walkway motion network and performing preference analysis on the motion trajectory of the users with the same motion mode category; S5: recommending the motion trajectory based on the user preference based on the walkway motion network to obtain the motion trajectory recommendation result of the user group corresponding to different motion mode categories; S6: transmitting the motion trajectory recommendation result and the motion level of the user to the interactive large screen, and the interactive large screen presents the motion level and the motion trajectory recommendation result for the user; The S4 step of constructing the walkway motion network comprises: Constructing a walkway motion network, wherein the walkway motion network divides the smart walkway into Q walkway areas: Wherein: represents the qth divided stair area; Preference analysis is performed on the motion trajectory of the users with the same motion mode category based on the walkway motion network; The preference analysis on the motion trajectory of the users with the same motion mode category based on the walkway motion network comprises: The preference analysis is performed on the motion trajectories of users with the same motion mode category based on the footpath motion network, wherein the first motion mode category is a walking mode, the second motion mode category is a running mode, and the third motion mode category is a cycling mode. The preference analysis flow of the users with the same motion mode category is as follows: S41: extract the first the motion trajectory data of each of the users in the sports mode category, and map the motion trajectory data in the Q path areas in the path motion network to obtain a motion area vector of the user, wherein the motion area vector of the user is: Wherein: Indicates user The motion region vector, Indicates user The characteristics of the movement trajectory in the q-th trail region. This indicates that the user The motion trajectory data does not contain the motion trajectory coordinates of the q-th trail area. This indicates that the user The motion trajectory data exists at the coordinate points of the motion trajectory located in the q-th trail area; representing the rth user in the class of motion patterns, ; S42: generating the first the attention preference weight of each user in the motion pattern category, wherein the user the attention preference weight of each user in the motion pattern category, wherein the user Wherein: representing a user's attention preference weight; S43: Calculate the first Class of motion pattern class user's user preference: Wherein: representing the first user preference of the user of the class motion pattern category, representing the first characteristic value of the preference of the user of the class motion pattern category to the first Q-1 stepway regions.

2. The intelligent sidewalk interactive large-screen data management system of claim 1, wherein, The S1 step of connecting the wearable device to the interactive large screen system network and transmitting the motion data of the user on the smart walkway to the interactive large screen system by using the wearable device comprises: Connecting the wearable device to the interactive large screen system network, the user wearing the wearable device and exercising on the smart walkway, the smart walkway monitoring the motion data of the user, and transmitting the motion data of the user on the smart walkway to the interactive large screen system by using the wearable device, wherein the motion data comprises gait, heart rate, pace and motion trajectory data, and wherein the motion data of the user on the smart walkway is in the form of: Wherein: represents the motion data of the nth user on the smart sidewalk, and N represents the number of users on the smart sidewalk; In succession, the gait, heart rate, pace and movement trajectory data of the nth user on the smart sidewalk are represented. represents the average pressure of the left foot of the nth user on the ground as perceived by the smart sidewalk, represents the average pressure of the right foot of the nth user on the ground as perceived by the smart sidewalk; successively represent the heart rate skewness, the average heart rate and the heart rate standard deviation of the nth user; Pn, Pn, σn represent the skewness, mean pace, and pace standard deviation of the n th user, respectively. a number of motion trajectory coordinate points in the motion trajectory data a number of motion trajectory coordinate points in the motion trajectory data a number of motion trajectory coordinate points in the motion trajectory data a number of motion trajectory coordinate points in the motion trajectory data a number of motion trajectory coordinate points in the motion trajectory data 3. The intelligent sidewalk interactive large-screen data management system of claim 2, wherein, The S2 step of the interactive large screen system network identifying the received motion data comprises: The interactive large screen system network identifies the received motion data to obtain the motion state and motion level of different users, wherein the identification process of the motion data is as follows: S21: calculating the motion imbalance degree of the user motion, wherein the motion imbalance degree calculation formula of the nth user is: Wherein: represents the motion imbalance degree of the nth user; S22: calculating the motion intensity of the user motion, wherein the motion intensity calculation formula of the nth user is: Wherein: represents the exercise intensity of the nth user, represents the exercise heart rate intensity of the nth user, represents the exercise pace intensity of the nth user; the large interactive screen divides the users into 7 exercise levels according to the exercise intensity of the users, and if the exercise intensity of a user reaches the preset intensity threshold of the exercise level, the corresponding exercise level is assigned to the user, and the higher the exercise intensity, the higher the exercise level. represents the current motion duration of the nth user on the smart sidewalk; denotes an exponential function with base the natural constant; S23: taking the motion imbalance degree and the motion intensity of the user motion as the motion state of the user, wherein the motion state of the nth user is .

4. The intelligent sidewalk interactive large-screen data management system of claim 3, wherein, The S3 step of clustering analysis on the users currently on the smart walkway in combination with the motion state of the users to obtain the motion mode category of the users comprises: Clustering analysis is performed on the N users currently on the smart walkway in combination with the motion state of the users to obtain the motion mode category of the users, wherein the clustering analysis process is as follows: S31: calculating the motion mode similarity between any two users in the N users, wherein the motion mode similarity calculation formula between the nth user and the ith user is: Wherein: represents the motion pattern similarity between the nth user and the i-th user, ; represents the motion state of the i-th user; denotes the L1 norm; The motion pattern similarity between different users is taken as the distance between the users, and K users closest to each user are marked; S32: The truncation distance in the clustering process is calculated based on the local density information: Wherein: represents the local density information of N users, wherein the greater the local density information is, the smaller the difference in local distance density between different users is, and the less obvious the distribution difference is; denotes the distance between the user and the nth user as the truncation distance, the local distance density of the nth user; denotes the distance between the user and the nth user as the truncated distance, the local distance density proportion of the nth user; represents the cut-off distance calculated based on the local density information; S33: The weighted local distance density of each user is calculated according to the calculated truncation distance, wherein the weighted local distance density of the nth user is: Wherein: represents the weighted local distance density of the nth user; the number of coincident users between the K users closest to the nth user and the K users closest to the jth user; represents the influence weight of the jth user on the local distance density of the nth user; S34: The cluster center weight of each user is calculated, wherein the cluster center weight of the nth user is: Wherein: represents the cluster center weight of the nth user; represents the distance to the nth user in the user set whose weighted local distance density is higher than that of the nth user; if the weighted local distance density of the nth user is the maximum, then is the maximum distance between the nth user and other users; S35: G users with the highest cluster center weight are selected as the cluster centers, wherein G represents the number of motion pattern categories, the distance from the non-cluster center user to the cluster center is calculated, and the non-cluster center user is merged into the cluster cluster where the distance to the cluster center is closest, as the user in the same motion pattern category, wherein the clustering analysis result is: Wherein: Indicates the first The user set of the sports mode category, Indicates the first The first in the category of motion patterns User name Indicates the first Number of users in the sports mode category.

5. The intelligent sidewalk interactive large-screen data management system of claim 1, wherein, The S5 step utilizes the walking path motion network to recommend the motion trajectory based on user preferences, including: The user preference based exercise trajectory recommendation is performed by using the exercise path network, and exercise trajectory recommendation results of users in different exercise mode categories are obtained, wherein the exercise trajectory recommendation process for the first exercise mode category user is as follows. The exercise trajectory recommendation process for the first exercise mode category user is as follows. S51: The length of the motion trajectory recommendation result is set to M; S52: initialize the generation of the u-th motion trajectory recommendation result The Uth motion trajectory recommendation result is initialized and generated, and the Uth motion trajectory recommendation result is obtained. Wherein: represents the u-th motion trajectory recommendation result generated by initialization; representing a motion trajectory recommendation result M motion trajectory points in the motion trajectory recommendation result, representing a motion trajectory recommendation result the mth motion trajectory point in the motion trajectory recommendation result, wherein each motion trajectory point corresponds to a stepway region, ; S53: set the current iteration number of each motion trajectory recommendation result as t, the maximum iteration number as Max, and the tth iteration result of the u th generated motion trajectory recommendation result as ; S54: a fitness function is constructed with the motion trajectory recommendation result as input, the motion trajectory recommendation result is input into the fitness function, and a fitness function value of the motion trajectory recommendation result is obtained, wherein the fitness function value of the motion trajectory recommendation result is: Wherein: representing a motion trajectory recommendation result a fitness function value; representing the motion trajectory recommendation result a preference feature value of the mth motion trajectory point in the path area a distance threshold, a motion trajectory point a Euclidean distance between the corresponding center of the sidewalk region; S55: taking the U motion trajectory recommendation results obtained in the tth iteration as inputs of the fitness function in turn, and selecting the motion trajectory recommendation result with the maximum fitness function value as the optimal motion trajectory recommendation result obtained in the tth iteration ; S56: Each motion trajectory recommendation result is iterated; S57: Let , return to step S55 until the maximum number of iterations is reached, and sequentially input the U trajectory recommendation results at this time as the input of the fitness function, and select the trajectory recommendation result with the trajectory coordinate points all within the range and the maximum fitness function value as the trajectory recommendation result of the first type of motion mode category user.

6. The intelligent sidewalk interactive kiosk data management system of claim 1, wherein, The S6 step transmits the motion trajectory recommendation result and the motion level to the interactive large screen, and the interactive large screen presents the motion level and the motion trajectory recommendation result for the user, including: The interactive large screen system network transmits the motion trajectory recommendation result and the user's motion level to the interactive large screen, and the interactive large screen displays the motion level and the motion trajectory recommendation result of different users, and sends the motion trajectory recommendation result and the motion level to the user's wearable device.

7. A smart sidewalk interactive large screen data management system, characterized in that, The system comprises: A motion data acquisition and processing module for transmitting the motion data of the user on the intelligent walking path to the interactive large screen system by the wearable device, and the interactive large screen system network identifies and processes the received motion data to obtain the motion state and the motion level of different users; A user clustering module for clustering analysis of the users currently on the intelligent walking path in combination with the motion state of the users to obtain the motion pattern category of the users, constructing a walking path motion network, and performing preference analysis on the motion trajectory of the users in the same motion pattern category; A motion trajectory recommendation device for recommending the motion trajectory based on user preferences based on the walking path motion network to obtain the motion trajectory recommendation result of the user group corresponding to different motion pattern categories, and transmitting the motion trajectory recommendation result and the motion level of the user to the interactive large screen, and the interactive large screen presents the motion level and the motion trajectory recommendation result for the user, to realize an intelligent walking path interactive large screen data management system as claimed in any one of claims 1-6.

Images