Intelligent terminal operation scenario optimization system and method based on multi-dimensional behavior data

Abstract

The present invention relates to the field of terminal control technology, and is a system and method for optimizing the operation scenarios of smart terminals based on multi-dimensional behavior data. The specific method includes: dividing the operation area of ​​the smart terminal into a first scene verification sub-area and a plurality of second scene verification sub-areas; identifying the identity attributes of each user according to a gait recognition strategy; collecting behavior conversion data, importing the behavior conversion data into an access intention prediction strategy, and obtaining the user's access intention; and optimizing the operation scenarios of all IoT devices in the second scene verification sub-area according to the identity attributes of each user. The present invention solves the problems in the prior art that the equipment needs to be kept online at any time, resulting in energy waste, a single control strategy that cannot achieve personalized control, and poor user experience.

Description

Technical Field

[0001] The present invention relates to the field of terminal control technology, and is a system and method for optimizing operation scenarios of intelligent terminals based on multi-dimensional behavior data. Background Art

[0002] In today's era of rapid development of smart homes and the Internet of Things, intelligent control of terminal devices has become one of the key technologies to improve the quality of life. Existing terminal control technologies usually require all devices to remain online at all times in order to respond to user operation needs at any time. However, this "always online" mode causes the device to continue to consume power, even when not in use, resulting in significant energy waste; in addition, the existing control strategies are usually relatively simple, mainly limited to the switch control of the device, lacking a deep understanding of user behavior and personalized response, which means that regardless of the user's specific needs, the device operates in a preset unified mode, which not only reduces the user experience, but may also lead to ineffective energy consumption. For example, in some cases, the user may only need some of the functions of the device, or may only have a need to use one or several devices, but the existing control system will start all devices in the operating area to full load.

[0003] In summary, existing terminal control technologies have obvious deficiencies in terms of energy efficiency and user personalized needs. Summary of the invention

[0004] The technical problem to be solved by the present invention is to address the problems in the prior art, such as the need for devices to remain online at all times, resulting in energy waste, a single control strategy that cannot achieve personalized control, and poor user experience. A smart terminal operation scenario optimization system and method based on multi-dimensional behavioral data are proposed.

[0005] In order to achieve the above-mentioned purpose, the technical solution of the intelligent terminal operation scene optimization method based on multi-dimensional behavior data of the present invention comprises the following steps:

[0006] Divide the operation area of ​​the smart terminal into a first scenario verification sub-area and a plurality of second scenario verification sub-areas;

[0007] Acquire gait behavior data of each user entering the first scene verification sub-area, and identify the identity attributes of each user according to the gait recognition strategy;

[0008] Collecting the behavior conversion data of each user when moving from the first scene verification sub-area to the second scene verification sub-area, importing the behavior conversion data into the access intention prediction strategy, and obtaining the user's access intention;

[0009] According to the identity attributes of each user, the operating modes of all IoT devices in the second scenario verification sub-area are adaptively optimized.

[0010] Specifically, the area entrance of the first scenario verification sub-area includes an intelligent mother terminal, and each area entrance of the second scenario verification sub-area includes an intelligent sub-terminal;

[0011] The gait recognition strategy includes: a gait characterization cycle confirmation strategy;

[0012] The gait characterization cycle confirmation strategy is specifically as follows:

[0013] S11: When the intelligent mother terminal detects that the user enters the first scene verification sub-area, the gait behavior data of each user in the first 20 sampling periods are obtained according to the preset sampling period to form a gait behavior data sequence, wherein the gait behavior data includes: step width data and foot rotation angle data;

[0014] S12: Calculate the difference between the step width data of each adjacent sampling period as the step width fluctuation value , get the step width fluctuation value sequence , remove the step width fluctuation value sequence In , extract the two sampling periods corresponding to the subscript index of the minimum step width fluctuation value in the step width fluctuation value sequence, intercept the previous sampling period and the next sampling period of the above two sampling periods, and the four sampling periods obtained by interception together constitute the gait representation period; where, ; Indicates the step width fluctuation value of the i-th sampling period and the i+1-th sampling period;

[0015] It should be noted that if the minimum step width fluctuation value in the fluctuation value sequence is or When , the sampling period obtained is only 3, so by eliminating the step width fluctuation value sequence In , so that each intercepted gait representation cycle includes 4 sampling cycles.

[0016] Specifically, the gait recognition strategy also includes: identity attribute confirmation strategy;

[0017] The identity attribute confirmation strategy is as follows:

[0018] S13: Calculate the average value of the step width data and the foot rotation angle data in the gait characterization cycle to obtain the step width characterization average value and foot rotation angle characterize the average ;

[0019] S14: Retrieve gait behavior data of all historical users in the smart mother terminal within the previous 20 historical sampling periods, where the total number of historical users is M, and m is the historical user index;

[0020] S15: importing the step width representation average value and the foot rotation angle representation average value into the gait recognition strategy to identify the identity attribute of each user, and calculating and obtaining the gait difference value between the current user and the historical users;

[0021] Preferably, the calculation formula of the gait difference value is specifically:

[0022] ;

[0023] in, is a subscript, indicating the jth historical sampling period corresponding to the historical user with index m;

[0024] is the step width data of historical users collected in the jth historical sampling period;

[0025] They represent the maximum step width and minimum step width of the historical user with index m in 20 historical sampling periods respectively;

[0026] The foot rotation angle data of the historical user collected in the j-th historical sampling period;

[0027] They represent the maximum foot rotation angle and the minimum foot rotation angle of the historical user with index m in 20 historical sampling periods respectively;

[0028] is the gait difference value between the gait behavior data of the current user and the gait behavior data of the historical user with index m in the jth historical sampling period;

[0029] S16: Preset a gait difference threshold, select historical sampling periods less than the gait difference threshold from the gait difference values ​​corresponding to the 20 historical sampling periods, and when the selected historical sampling periods are greater than or equal to 15, determine that the gait of the current user is similar to that of the historical user with index m, output the identity attribute of the current user as the cumulative access attribute, traverse all historical users, compare the number of periods of the historical sampling periods selected by all historical users, and associate the identity of the historical user corresponding to the maximum number of periods with the current user;

[0030] When the filtered historical sampling periods are less than 15, it is determined that the user's gait is not similar to that of the historical user with index m, and all historical users are traversed. If the filtered historical sampling periods of all historical users are less than 15, the identity attribute of the current user is output as the first visit attribute.

[0031] Specifically, the behavior conversion data includes: first behavior conversion data and second behavior conversion data;

[0032] The first behavior conversion data includes: a horizontal angle, wherein the horizontal angle is the angle between a line connecting the center of gravity of the user's body and the center of the head and the horizontal direction;

[0033] The second behavior conversion data includes: a shoulder angle and an offset distance, wherein the shoulder angle is the angle between a line connecting the vertices of the two shoulders of the user and the central axis of the user's body, and the offset distance is the moving distance of the footstep pressure center;

[0034] The access intention prediction strategy includes: a first behavior trend prediction strategy;

[0035] The first behavior trend prediction strategy specifically includes:

[0036] S21: after confirming the user identity attribute, extracting the horizontal angle, and drawing a function curve between the horizontal angle and the user movement time with the user movement time as the horizontal axis and the horizontal angle as the vertical axis, and calculating the derivative of the function curve;

[0037] S22: Continuously record the difference between the derivative value of the function curve and the derivative value of the previous unit movement time in each unit movement time. When it is monitored that the derivative differences of three consecutive adjacent unit movement times are decreasing, execute the second access trend prediction strategy. Otherwise, continue to monitor the user.

[0038] Specifically, the access intention prediction strategy also includes: a second access trend prediction strategy, specifically:

[0039] S23: Calculate and obtain the user's access intention index zh according to the second behavior conversion data;

[0040] Preferably, the calculation formula of the user's access intention index zh is:

[0041] ;

[0042] Among them, zh is the user's access intention index;

[0043] r is the index of the last unit movement time among three consecutive unit movement times whose derivative differences are decreasing, r+1 and r+2 represent the indexes of the next unit movement time and the next next unit movement time of the rth unit movement time, respectively;

[0044] are the shoulder angles during the rth, r+1th, and r+2th unit movement time respectively;

[0045] are the offset distances in the rth, r+1th, and r+2th unit moving time respectively;

[0046] are the intention ratios of shoulder intention and sole intention, .

[0047] S24: extracting the user's access intention index, and when it is detected that the user's access intention index is negative, determining that the user has an access intention to enter the second scene verification sub-area;

[0048] When it is detected that the user's access intention index is a positive number or zero, it is determined that the user has no access intention.

[0049] Specifically, the adaptive operation scenario optimization includes:

[0050] S31: extracting identity attributes corresponding to users with access intentions;

[0051] S32: When the user's identity attribute is a first access attribute, first access control is performed on the operation modes of all IoT devices in the second scenario verification sub-area according to the user's access intention, and the first access control includes:

[0052] Adjust all IoT devices in the second scenario verification sub-area to the pre-use mode;

[0053] The furthest historical service range of all IoT devices in the second scenario verification sub-area is extracted as the usage trigger range of the IoT device. When it is detected that a user enters the usage trigger range, the corresponding IoT device is adjusted to the full usage mode; wherein the furthest historical service range is: the farthest distance between the center of gravity of the user's body and the center of gravity of the IoT device when the IoT device can be used by historical users.

[0054] Specifically, the adaptive operation scenario optimization also includes:

[0055] S41: When the user's identity attribute is a cumulative access attribute, in the storage module of the smart sub-terminal in the second scenario verification sub-area, extract the historical movement trajectory of the historical user associated with the current user's identity from the area entrance of the second scenario verification sub-area to each IoT device, where the total number of historical movement trajectories is U, and u is the index of the historical movement trajectory;

[0056] S42: constructing a second scene verification model according to the historical movement trajectory, marking the intersection of each historical movement trajectory in the second scene verification sub-area as a state stationary point, wherein the verification space in the second scene verification model includes V state stationary points, wherein v is the index of the state stationary point;

[0057] S43: For each state stationary point, statistics from the state stationary point The number of all historical moving trajectories from the start to the station of other states And the total movement time of all historical movement tracks ;

[0058] S44: Select two different state stationary points with indexes k and g from the V state stationary points to form a state transition evaluation combination, and calculate the state transition probability of the two different state stationary points with indexes k and g , traverse all state transition evaluation combinations and obtain the state transition probabilities of all state transition evaluation combinations;

[0059] Preferably, the calculation formula of the state transition probability is specifically:

[0060] ;

[0061] Among them, k and g are subscripts, indicating that the indexes of two different state stationary points are k and g respectively;

[0062] represents the number of transitions of the historical user from the state station with index k to the state station with index g in the u-th historical movement trajectory;

[0063] It represents the transfer time taken by the historical user to move from the state station with index k to the state station with index g in the u-th historical movement trajectory;

[0064] S45: Obtain a state transition probability matrix P based on the state transition probabilities of all state transition evaluation combinations, where P is The matrix of .

[0065] Specifically, the adaptive operation scenario optimization also includes:

[0066] S46: Obtaining the coordinates of the user's real-time position in the second scene verification sub-area in real time , where the position coordinates of each state stationary point are ;

[0067] S47: Calculate the Euclidean distance between the user's real-time location and each state stationary point, and use a Gaussian kernel function to assign a contribution weight to each state stationary point;

[0068] Preferably, the contribution weight The calculation formula is: , is the control parameter for controlling the speed of contribution weight decay, where: is the Euclidean distance between the user's real-time location and the state station point with index v; is the contribution weight of the state stationary point with index v;

[0069] S48: Calculate the probability distribution of the user's real-time position relative to each state stationary point to obtain a probability distribution sequence ,in, is the probability distribution of the user's real-time position relative to the state station point with index v, the probability distribution The specific calculation strategy is: the ratio of the contribution weight of the state stationary point with index v to the sum of the contribution weights of all state stationary points;

[0070] S49: Predict the probability distribution sequence of the user's next state station ;

[0071] in, ;

[0072] Select The state stationary point with the largest probability distribution is used as the prediction result of the user's next state stationary point.

[0073] Specifically, the adaptive operation scenario optimization also includes:

[0074] S410: Predict the user's next status point in real time based on the user's real-time position in the second scenario verification sub-area. When it is detected that the user's next status point enters the usage trigger range of the IoT device, determine that the user has an actual usage demand for the IoT device, retrieve the targeted usage mode of the IoT device when the historical user whose identity is associated with the current user last ended use, and adjust the IoT device to the above-mentioned targeted usage mode.

[0075] In addition, the intelligent terminal operation scenario optimization system based on multi-dimensional behavior data of the present invention includes the following modules:

[0076] Area division module, identity confirmation module, intention prediction module and optimization module;

[0077] The area division module is used to divide the operation area of ​​the smart terminal into a first scene verification sub-area and a plurality of second scene verification sub-areas;

[0078] The identity confirmation module is used to obtain gait behavior data of each user entering the first scene verification sub-area, and identify the identity attributes of each user according to the gait recognition strategy;

[0079] The intention prediction module is used to collect the behavior conversion data of each user when moving from the first scene verification sub-area to the second scene verification sub-area, import the behavior conversion data into the access intention prediction strategy, and obtain the user's access intention;

[0080] The optimization module adaptively optimizes the operation scenarios of the operation modes of all IoT devices in the second scenario verification sub-area according to the identity attributes of each user.

[0081] Compared with the prior art, the technical effects of the present invention are as follows:

[0082] 1. The present invention divides the operation area of ​​the smart terminal into multiple scene verification sub-areas and dynamically adjusts the operation mode of the device according to the user's behavior data and access intention, thereby reducing unnecessary constant online status of the device and significantly reducing energy consumption.

[0083] 2. The present invention can accurately identify the user's identity attributes and access intentions through gait recognition and analysis of behavior conversion data, thereby achieving personalized control of different users. For example, for users who visit for the first time, the IoT device will be adjusted to the pre-use mode and quickly switch to the full-use mode when the user approaches; and for users who have visited for a long time, the system will predict their possible activity paths and device usage needs based on their historical behavior data, adjust the device's operating mode in advance, and improve user comfort and usage experience.

[0084] 3. The present invention achieves in-depth analysis and prediction of user behavior by introducing multi-dimensional behavioral data, such as gait data, horizontal angle, shoulder angle and offset distance, and combining it with access intention prediction strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0086] Figure 1 It is a flow chart of the intelligent terminal operation scenario optimization method based on multi-dimensional behavior data of the present invention;

[0087] Figure 2 It is a structural schematic diagram of the intelligent terminal operation scenario optimization system based on multi-dimensional behavior data of the present invention;

[0088] Figure 3 This is a diagram of an implementation scenario example of the method for optimizing smart terminal operation scenarios based on multi-dimensional behavior data of the present invention. DETAILED DESCRIPTION

[0089] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0090] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0091] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0092] Embodiment 1:

[0093] like Figure 1 As shown, the intelligent terminal operation scenario optimization method based on multi-dimensional behavior data of the embodiment of the present invention is as follows: Figure 1 As shown, the specific steps are as follows:

[0094] Divide the operation area of ​​the smart terminal into a first scenario verification sub-area and a plurality of second scenario verification sub-areas;

[0095] For example, Figure 3 As shown, in this embodiment, the operation area of ​​the smart terminal includes: a first scene verification sub-area and four second scene verification sub-areas, and the first scene verification sub-area is an area within the rectangular area in the figure that does not include the four dotted boxes;

[0096] like Figure 3 As shown, the regional entrance of the first scene verification sub-area includes an intelligent mother terminal, namely Figure 3 The cube terminal in the second scene verification sub-area includes an intelligent sub-terminal at the entrance, which is Figure 3 The cylindrical terminal in the

[0097] Acquire gait behavior data of each user entering the first scene verification sub-area, and identify the identity attributes of each user according to the gait recognition strategy;

[0098] The gait recognition strategy includes: a gait characterization cycle confirmation strategy;

[0099] The gait characterization cycle confirmation strategy is specifically as follows:

[0100] For example, Figure 3As shown, in this embodiment, the intelligent mother terminal monitors a total of three users entering the first scene verification sub-area;

[0101] S11: When the intelligent mother terminal detects that the user enters the first scene verification sub-area, the gait behavior data of each user in the first 20 sampling periods are obtained according to the preset sampling period to form a gait behavior data sequence, wherein the gait behavior data includes: step width data and foot rotation angle data;

[0102] Exemplarily, in this embodiment, the sampling period of the gait behavior data is: the interval between two adjacent ground contact actions completed by the heel of the right foot of the user;

[0103] S12: Calculate the difference between the step width data of each adjacent sampling period as the step width fluctuation value , get the step width fluctuation value sequence , extract the two sampling periods corresponding to the subscript index of the minimum step width fluctuation value in the step width fluctuation value sequence, intercept the previous sampling period and the next sampling period of the above two sampling periods, and the four sampling periods obtained by interception together constitute the gait representation period; where, ; Indicates the step width fluctuation value of the i-th sampling period and the i+1-th sampling period.

[0104] The gait recognition strategy also includes: identity attribute confirmation strategy;

[0105] The identity attribute confirmation strategy is as follows:

[0106] S13: Calculate the average value of the step width data and the foot rotation angle data in the gait characterization cycle to obtain the step width characterization average value and foot rotation angle characterize the average ;

[0107] S14: Retrieve gait behavior data of all historical users in the smart mother terminal within the previous 20 historical sampling periods, where the total number of historical users is M, and m is the historical user index;

[0108] S15: importing the step width representation average value and the foot rotation angle representation average value into the gait recognition strategy to identify the identity attribute of each user, and calculating and obtaining the gait difference value between the current user and the historical users;

[0109] The calculation formula of the gait difference value is specifically:

[0110] ;

[0111] in, is a subscript, indicating the jth historical sampling period corresponding to the historical user with index m;

[0112] is the step width data of historical users collected in the jth historical sampling period;

[0113] They represent the maximum step width and minimum step width of the historical user with index m in 20 historical sampling periods respectively;

[0114] The foot rotation angle data of the historical user collected in the j-th historical sampling period;

[0115] They represent the maximum foot rotation angle and the minimum foot rotation angle of the historical user with index m in 20 historical sampling periods respectively;

[0116] is the gait difference value between the gait behavior data of the current user and the gait behavior data of the historical user with index m in the jth historical sampling period;

[0117] S16: Preset a gait difference threshold, select historical sampling periods less than the gait difference threshold from the gait difference values ​​corresponding to the 20 historical sampling periods, and when the selected historical sampling periods are greater than or equal to 15, determine that the gait of the current user is similar to that of the historical user with index m, output the identity attribute of the current user as the cumulative access attribute, traverse all historical users, compare the number of periods of the historical sampling periods selected by all historical users, and associate the identity of the historical user corresponding to the maximum number of periods with the current user;

[0118] When the filtered historical sampling periods are less than 15, it is determined that the user's gait is not similar to that of the historical user with index m, and all historical users are traversed. If the filtered historical sampling periods of all historical users are less than 15, the identity attribute of the current user is output as the first visit attribute.

[0119] Collecting the behavior conversion data of each user when moving from the first scene verification sub-area to the second scene verification sub-area, importing the behavior conversion data into the access intention prediction strategy, and obtaining the user's access intention;

[0120] The behavior conversion data includes: first behavior conversion data and second behavior conversion data;

[0121] The first behavior conversion data includes: a horizontal angle, wherein the horizontal angle is the angle between a line connecting the center of gravity of the user's body and the center of the head and the horizontal direction;

[0122] The second behavior conversion data includes: a shoulder angle and an offset distance, wherein the shoulder angle is the angle between a line connecting the vertices of the two shoulders of the user and the central axis of the user's body, and the offset distance is the moving distance of the footstep pressure center;

[0123] The access intention prediction strategy includes: a first behavior trend prediction strategy;

[0124] The first behavior trend prediction strategy specifically includes:

[0125] S21: after confirming the user identity attribute, extracting the horizontal angle, and drawing a function curve between the horizontal angle and the user movement time with the user movement time as the horizontal axis and the horizontal angle as the vertical axis, and calculating the derivative of the function curve;

[0126] S22: Continuously record the difference between the derivative value of the function curve and the derivative value of the previous unit movement time in each unit movement time. When it is monitored that the derivative differences of three consecutive adjacent unit movement times are decreasing, execute the second access trend prediction strategy. Otherwise, continue to monitor the user.

[0127] The access intention prediction strategy also includes: a second access trend prediction strategy, specifically:

[0128] S23: Calculate and obtain the user's access intention index zh according to the second behavior conversion data;

[0129] The calculation formula of the user's access intention index zh is:

[0130] ;

[0131] Among them, zh is the user's access intention index;

[0132] r is the index of the last unit movement time among three consecutive unit movement times whose derivative differences are decreasing, r+1 and r+2 represent the indexes of the next unit movement time and the next next unit movement time of the rth unit movement time, respectively;

[0133] are the shoulder angles during the rth, r+1th, and r+2th unit movement time respectively;

[0134] are the offset distances in the rth, r+1th, and r+2th unit moving time respectively;

[0135] are the intention ratios of shoulder intention and sole intention, .

[0136] S24: extracting the user's access intention index, and when it is detected that the user's access intention index is negative, determining that the user has an access intention to enter the second scene verification sub-area;

[0137] When it is detected that the user's access intention index is a positive number or zero, it is determined that the user has no access intention.

[0138] According to the identity attributes of each user, the operating modes of all IoT devices in the second scenario verification sub-area are adaptively optimized.

[0139] The adaptive operation scenario optimization includes:

[0140] S31: extracting identity attributes corresponding to users with access intentions;

[0141] S32: When the user's identity attribute is a first access attribute, first access control is performed on the operation modes of all IoT devices in the second scenario verification sub-area according to the user's access intention, and the first access control includes:

[0142] Adjust all IoT devices in the second scenario verification sub-area to the pre-use mode;

[0143] The furthest historical service range of all IoT devices in the second scenario verification sub-area is extracted as the usage trigger range of the IoT device. When it is detected that a user enters the usage trigger range, the corresponding IoT device is adjusted to the full usage mode; wherein the furthest historical service range is: the farthest distance between the center of gravity of the user's body and the center of gravity of the IoT device when the IoT device can be used by historical users.

[0144] The adaptive operation scenario optimization includes:

[0145] S41: When the user's identity attribute is a cumulative access attribute, in the storage module of the smart sub-terminal in the second scenario verification sub-area, extract the historical movement trajectory of the historical user associated with the current user's identity from the area entrance of the second scenario verification sub-area to each IoT device, where the total number of historical movement trajectories is U, and u is the index of the historical movement trajectory;

[0146] S42: constructing a second scene verification model according to the historical movement trajectory, marking the intersection of each historical movement trajectory in the second scene verification sub-area as a state stationary point, wherein the verification space in the second scene verification model includes V state stationary points, wherein v is the index of the state stationary point;

[0147] S43: For each state stationary point, statistics from the state stationary point The number of all historical moving trajectories from the start to the station of other states And the total movement time of all historical movement tracks ;

[0148] S44: Select two different state stationary points with indexes k and g from the V state stationary points to form a state transition evaluation combination, and calculate the state transition probability of the two different state stationary points with indexes k and g , traverse all state transition evaluation combinations and obtain the state transition probabilities of all state transition evaluation combinations;

[0149] The calculation formula of the state transition probability is specifically:

[0150] ;

[0151] Among them, k and g are subscripts, indicating that the indexes of two different state stationary points are k and g respectively;

[0152] represents the number of transitions of the historical user from the state station with index k to the state station with index g in the u-th historical movement trajectory;

[0153] It represents the transfer time taken by the historical user to move from the state station with index k to the state station with index g in the u-th historical movement trajectory;

[0154] S45: Obtain a state transition probability matrix P based on the state transition probabilities of all state transition evaluation combinations, where P is The matrix of .

[0155] S46: Obtaining the coordinates of the user's real-time position in the second scene verification sub-area in real time , where the position coordinates of each state stationary point are ;

[0156] S47: Calculate the Euclidean distance between the user's real-time location and each state stationary point, and use a Gaussian kernel function to assign a contribution weight to each state stationary point;

[0157] The contribution weight The calculation formula is: , is the control parameter for controlling the speed of contribution weight decay, where: is the Euclidean distance between the user's real-time location and the state station point with index v; is the contribution weight of the state stationary point with index v;

[0158] S48: Calculate the probability distribution of the user's real-time position relative to each state stationary point to obtain a probability distribution sequence ,in, is the probability distribution of the user's real-time position relative to the state station point with index v, the probability distribution The specific calculation strategy is: the ratio of the contribution weight of the state stationary point with index v to the sum of the contribution weights of all state stationary points;

[0159] S49: Predict the probability distribution sequence of the user's next state station ,in, ;

[0160] Select The state stationary point with the largest probability distribution is used as the prediction result of the user's next state stationary point.

[0161] S410: Predict the user's next status point in real time based on the user's real-time position in the second scenario verification sub-area. When it is detected that the user's next status point enters the usage trigger range of the IoT device, determine that the user has an actual usage demand for the IoT device, retrieve the targeted usage mode of the IoT device when the historical user whose identity is associated with the current user last ended use, and adjust the IoT device to the above-mentioned targeted usage mode.

[0162] Embodiment 2:

[0163] like Figure 2 As shown, the intelligent terminal operation scene optimization system based on multi-dimensional behavior data of the embodiment of the present invention is as follows Figure 2 As shown, it includes the following modules:

[0164] Area division module, identity confirmation module, intention prediction module and optimization module;

[0165] The area division module is used to divide the operation area of ​​the smart terminal into a first scene verification sub-area and a plurality of second scene verification sub-areas;

[0166] The identity confirmation module is used to obtain gait behavior data of each user entering the first scene verification sub-area, and identify the identity attributes of each user according to the gait recognition strategy;

[0167] The intention prediction module is used to collect the behavior conversion data of each user when moving from the first scene verification sub-area to the second scene verification sub-area, import the behavior conversion data into the access intention prediction strategy, and obtain the user's access intention;

[0168] The optimization module adaptively optimizes the operation scenarios of the operation modes of all IoT devices in the second scenario verification sub-area according to the identity attributes of each user.

[0169] Embodiment three:

[0170] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0171] The processor executes the above-mentioned smart terminal operation scenario optimization method based on multi-dimensional behavior data by calling the computer program stored in the memory.

[0172] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the smart terminal operation scenario optimization method based on multi-dimensional behavior data provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device. For example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0173] Embodiment 4:

[0174] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0175] When the computer program runs on a computer device, the computer device executes the above-mentioned smart terminal operation scenario optimization method based on multi-dimensional behavior data.

[0176] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0177] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0178] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0179] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0180] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0181] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0182] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0183] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0184] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0185] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0186] In summary, compared with the prior art, the technical effects of the present invention are as follows:

[0187] 1. The present invention divides the operation area of ​​the smart terminal into multiple scene verification sub-areas and dynamically adjusts the operation mode of the device according to the user's behavior data and access intention, thereby reducing unnecessary constant online status of the device and significantly reducing energy consumption.

[0188] 2. The present invention can accurately identify the user's identity attributes and access intentions through gait recognition and analysis of behavior conversion data, thereby achieving personalized control of different users. For example, for users who visit for the first time, the IoT device will be adjusted to the pre-use mode and quickly switch to the full-use mode when the user approaches; and for users who have visited for a long time, the system will predict their possible activity paths and device usage needs based on their historical behavior data, adjust the device's operating mode in advance, and improve user comfort and usage experience.

[0189] 3. The present invention achieves in-depth analysis and prediction of user behavior by introducing multi-dimensional behavioral data, such as gait data, horizontal angle, shoulder angle and offset distance, and combining it with access intention prediction strategy.

[0190] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for optimizing operation scenarios of smart terminals based on multi-dimensional behavior data, characterized in that: The method comprises: Divide the operation area of ​​the smart terminal into a first scenario verification sub-area and a plurality of second scenario verification sub-areas; Acquire gait behavior data of each user entering the first scene verification sub-area, and identify the identity attributes of each user according to the gait recognition strategy; Collecting the behavior conversion data of each user when moving from the first scene verification sub-area to the second scene verification sub-area, importing the behavior conversion data into the access intention prediction strategy, and obtaining the user's access intention; The behavior conversion data includes: first behavior conversion data and second behavior conversion data; The first behavior conversion data includes: a horizontal angle, wherein the horizontal angle is the angle between a line connecting the center of gravity of the user's body and the center of the head and the horizontal direction; The second behavior conversion data includes: a shoulder angle and an offset distance, wherein the shoulder angle is the angle between a line connecting the vertices of the two shoulders of the user and the central axis of the user's body, and the offset distance is the moving distance of the footstep pressure center; The access intention prediction strategy includes: a first behavior trend prediction strategy; The first behavior trend prediction strategy specifically includes: S21: after confirming the user identity attribute, extracting the horizontal angle, and drawing a function curve between the horizontal angle and the user movement time with the user movement time as the horizontal axis and the horizontal angle as the vertical axis, and calculating the derivative of the function curve; S22: continuously record the difference between the derivative value of the function curve and the derivative value of the previous unit movement time in each unit movement time, and when it is monitored that the derivative differences of three consecutive adjacent unit movement times are all decreasing, execute the second access trend prediction strategy, otherwise, continue to monitor the user; The access intention prediction strategy also includes: a second access trend prediction strategy, specifically: S23: Calculate and obtain the user's access intention index zh according to the second behavior conversion data; S24: extracting the user's access intention index, and when it is detected that the user's access intention index is negative, determining that the user has an access intention to enter the second scene verification sub-area; When it is detected that the user's access intention index is positive or zero, it is determined that the user has no access intention; According to the identity attributes of each user, the operating modes of all IoT devices in the second scenario verification sub-area are adaptively optimized.

2. The method for optimizing operation scenarios of smart terminals based on multi-dimensional behavior data according to claim 1, characterized in that: The area entrance of the first scenario verification sub-area includes an intelligent mother terminal, and each area entrance of the second scenario verification sub-area includes an intelligent sub-terminal; The gait recognition strategy includes: a gait characterization cycle confirmation strategy; The gait characterization cycle confirmation strategy is specifically as follows: S11: When the intelligent mother terminal detects that the user enters the first scene verification sub-area, the gait behavior data of each user in the first 20 sampling periods are obtained according to the preset sampling period to form a gait behavior data sequence, wherein the gait behavior data includes: step width data and foot rotation angle data; S12: Calculate the difference between the step width data of each adjacent sampling period as the step width fluctuation value , get the step width fluctuation value sequence , extract the two sampling periods corresponding to the subscript index of the minimum step width fluctuation value in the step width fluctuation value sequence, intercept the previous sampling period and the next sampling period of the above two sampling periods, and the four sampling periods obtained by interception together constitute the gait representation period; where, ; Indicates the step width fluctuation value of the i-th sampling period and the i+1-th sampling period.

3. The method for optimizing operation scenarios of smart terminals based on multi-dimensional behavior data according to claim 2 is characterized in that: The gait recognition strategy also includes: identity attribute confirmation strategy; The identity attribute confirmation strategy is as follows: S13: Calculate the average value of the step width data and the foot rotation angle data in the gait characterization cycle to obtain the step width characterization average value and foot rotation angle characterize the average ; S14: Retrieve the gait behavior data of all historical users in the smart mother terminal within the previous 20 historical sampling periods, where the total number of historical users is M, and m is the historical user index; S15: importing the step width representation average value and the foot rotation angle representation average value into the gait recognition strategy to identify the identity attribute of each user, and calculating and obtaining the gait difference value between the current user and the historical users; S16: Preset a gait difference threshold, select historical sampling periods less than the gait difference threshold from the gait difference values ​​corresponding to the 20 historical sampling periods, and when the selected historical sampling periods are greater than or equal to 15, determine that the gait of the current user is similar to that of the historical user with index m, output the identity attribute of the current user as the cumulative access attribute, traverse all historical users, compare the number of periods of the historical sampling periods selected by all historical users, and associate the identity of the historical user corresponding to the maximum number of periods with the current user; When the filtered historical sampling periods are less than 15, it is determined that the user's gait is not similar to that of the historical user with index m, and all historical users are traversed. If the filtered historical sampling periods of all historical users are less than 15, the identity attribute of the current user is output as the first visit attribute.

4. The method for optimizing operation scenarios of smart terminals based on multi-dimensional behavior data according to claim 3 is characterized in that: The adaptive operation scenario optimization includes: S31: extracting identity attributes corresponding to users with access intentions; S32: When the user's identity attribute is a first access attribute, first access control is performed on the operation modes of all IoT devices in the second scenario verification sub-area according to the user's access intention, and the first access control includes: Adjust all IoT devices in the second scenario verification sub-area to the pre-use mode; The furthest historical service range of all IoT devices in the second scenario verification sub-area is extracted as the usage trigger range of the IoT device. When it is detected that a user enters the usage trigger range, the corresponding IoT device is adjusted to the full usage mode; wherein the furthest historical service range is: the farthest distance between the center of gravity of the user's body and the center of gravity of the IoT device when the IoT device can be used by historical users.

5. The method for optimizing operation scenarios of smart terminals based on multi-dimensional behavior data according to claim 4 is characterized in that: The adaptive operation scenario optimization also includes: S41: When the user's identity attribute is a cumulative access attribute, in the storage module of the smart sub-terminal in the second scenario verification sub-area, extract the historical movement trajectory of the historical user associated with the current user's identity from the area entrance of the second scenario verification sub-area to each IoT device, where the total number of historical movement trajectories is U, and u is the index of the historical movement trajectory; S42: constructing a second scene verification model according to the historical movement trajectory, marking the intersection of each historical movement trajectory in the second scene verification sub-area as a state stationary point, wherein the verification space in the second scene verification model includes V state stationary points, wherein v is the index of the state stationary point; S43: For each state stationary point, statistics from the state stationary point The number of all historical moving trajectories from the start to the station of other states And the total movement time of all historical movement tracks ; S44: Select two different state stationary points with indexes k and g from the V state stationary points to form a state transition evaluation combination, and calculate the state transition probability of the two different state stationary points with indexes k and g , traverse all state transition evaluation combinations and obtain the state transition probabilities of all state transition evaluation combinations; S45: Obtain a state transition probability matrix P based on the state transition probabilities of all state transition evaluation combinations, where P is The matrix of .

6. The method for optimizing operation scenarios of smart terminals based on multi-dimensional behavior data according to claim 5 is characterized in that: The adaptive operation scenario optimization also includes: S46: Obtaining the coordinates of the user's real-time position in the second scene verification sub-area in real time , where the position coordinates of each state stationary point are ; S47: Calculate the Euclidean distance between the user's real-time location and each state stationary point, and use a Gaussian kernel function to assign a contribution weight to each state stationary point; S48: Calculate the probability distribution of the user's real-time position relative to each state stationary point to obtain a probability distribution sequence ,in, is the probability distribution of the user's real-time position relative to the state station point with index v, the probability distribution The specific calculation strategy is: the ratio of the contribution weight of the state stationary point with index v to the sum of the contribution weights of all state stationary points; S49: Predict the probability distribution sequence of the user's next state station , in, ; Select The state stationary point with the largest probability distribution is used as the prediction result of the user's next state stationary point.

7. The method for optimizing operation scenarios of smart terminals based on multi-dimensional behavior data according to claim 6 is characterized in that: The adaptive operation scenario optimization also includes: S410: Predict the user's next status point in real time based on the user's real-time position in the second scenario verification sub-area. When it is detected that the user's next status point enters the usage trigger range of the IoT device, determine that the user has an actual usage demand for the IoT device, retrieve the targeted usage mode of the IoT device when the historical user whose identity is associated with the current user last ended use, and adjust the IoT device to the above-mentioned targeted usage mode.

8. A smart terminal operation scenario optimization system based on multi-dimensional behavior data, used to implement the smart terminal operation scenario optimization method based on multi-dimensional behavior data as described in any one of claims 1 to 7, characterized in that: include: Area division module, identity confirmation module, intention prediction module and optimization module; The area division module is used to divide the operation area of ​​the smart terminal into a first scene verification sub-area and a plurality of second scene verification sub-areas; The identity confirmation module is used to obtain gait behavior data of each user entering the first scene verification sub-area, and identify the identity attributes of each user according to the gait recognition strategy; The intention prediction module is used to collect the behavior conversion data of each user when moving from the first scene verification sub-area to the second scene verification sub-area, import the behavior conversion data into the access intention prediction strategy, and obtain the user's access intention; The optimization module adaptively optimizes the operation scenarios of the operation modes of all IoT devices in the second scenario verification sub-area according to the identity attributes of each user.

Images