A Smart Adaptation Method and System for Intangible Cultural Heritage Sports Courses Based on Spatial Safety Constraints
By extracting the uncontrolled active window of sports intangible cultural heritage projects and generating phase-gated time-varying risk domains, the phase of trainees' movements is adjusted, solving the problems of insufficient space utilization and teaching synchronicity caused by ignoring the locality of the uncontrolled phase of equipment in existing technologies, and realizing more efficient space utilization and synchronous teaching.
Patent Information
- Application Number
- CN202611305719.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-26
- Publication Date
- 2026-11-17
AI Technical Summary
Existing technologies, in offline teaching of intangible cultural heritage related to equipment sports, neglect the phase locality of equipment malfunction, leading to misjudgments as continuous spatial overlap and failing to effectively utilize venue capacity and teaching synchronicity.
By acquiring data on intangible cultural heritage sports projects, venue characteristics, and audience attributes, an out-of-control activity window is extracted to generate a phase-gated time-varying risk domain. Furthermore, by adjusting the phase of trainees' movements using command phase offset data, the out-of-control phases of adjacent trainees are prevented from aligning, thus generating a course adaptation strategy.
It improved the safe capacity and teaching synchronization of offline venues, identified pseudo-conflicts that could be staggered, and achieved increased teaching synchronization without increasing the spacing between stations or reducing the number of students.
Smart Images

Figure CN123117789A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology, specifically to a method and system for intelligent adaptation of sports intangible cultural heritage courses based on spatial security constraints. Background Technology
[0002] In offline lightweight experiential teaching of intangible cultural heritage sports using apparatus (such as diabolo and soft ball), in order to arrange as many students as possible to practice apparatus movements simultaneously within a limited space, this field usually adopts a course adaptation method based on spatial safety constraints: First, generate the motion envelope occupied by the normal movement of the apparatus for each candidate movement, and superimpose the uncontrollable reachable domain that may be affected if the apparatus is released, bounces, flies out, or gets tangled around it. The two together constitute the fusion risk space domain of the movement; then, map the fusion risk space domain of each movement to the field according to the students' positions, and determine whether the movement can be performed simultaneously by multiple students by detecting whether the risk space domains of adjacent students overlap; at the same time, in order to ensure teaching order, the teacher often issues a unified command to instruct all students to perform the same movement simultaneously.
[0003] However, equipment malfunctions (disengagement, bouncing, flying out, entanglement) physically concentrate within a very narrow release phase of the movement cycle. This means the malfunction reachable domain is only truly activated within this release phase window; during the remaining time, the equipment is under control, and the malfunction reachable domain does not actually exist. Existing technologies model the fusion risk space domain as a statically activated space volume throughout the entire movement cycle, ignoring the phase locality of equipment malfunctions. When multiple participants' movements are perfectly aligned under unified commands, the model may misjudge local transient risks that only overlap momentarily as persistent spatial overlaps. This leads to the misjudgment of actions that could be safely performed synchronously as insufficient space, forcing the use of increased spacing, reduced numbers of participants, or mandatory group rotations to mitigate the risks, sacrificing space capacity and teaching synchronicity. Summary of the Invention
[0004] To address the problems in related technologies, this invention provides a method and system for intelligent adaptation of sports intangible cultural heritage courses based on spatial safety constraints, thereby overcoming the aforementioned technical problems existing in existing related technologies.
[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a method for intelligent adaptation of intangible cultural heritage sports courses based on spatial safety constraints, comprising the following steps:
[0006] Acquire data on the target sports intangible cultural heritage project, venue characteristics, audience attributes, and equipment specifications, and parse the target sports intangible cultural heritage project data into multiple action units;
[0007] For each action unit, an out-of-control active window is extracted; the out-of-control active window is the phase interval in which the device has the actual probability of going out of control within a single action cycle;
[0008] Based on the action unit and the equipment specification data, normal motion envelope data and runaway reachability domain are generated, and the runaway reachability domain is only incorporated into the normal motion envelope data within the phase interval defined by the runaway active window to obtain the phase-gated time-varying risk domain;
[0009] A site grid is generated based on the site feature data, and a station matrix is generated based on the target number of performers in the audience attribute data.
[0010] The phase-gated time-varying risk domain is mapped to the site grid according to the coordinates and orientation of the station matrix to generate the global time-varying risk domain for each station.
[0011] Spatiotemporal joint interferometry detection is performed on adjacent stations to screen out overlapping station pairs that are spatially intersecting and whose associated out-of-control active windows coincide in time;
[0012] Based on the overlapping station pairs, solve for the password phase offset data that separates the out-of-control active windows of adjacent stations in the time dimension;
[0013] Based on the solution results of the password phase offset data, a course adaptation strategy is generated, and a target sports intangible cultural heritage adapted course is output accordingly.
[0014] This invention also includes a smart adaptation system for sports intangible cultural heritage courses based on spatial safety constraints, comprising:
[0015] The data acquisition module is used to acquire data on the target sports intangible cultural heritage project, venue characteristics, audience attributes, and equipment specifications, and to parse the target sports intangible cultural heritage project data into multiple action units;
[0016] The feature window extraction module is used to extract the out-of-control active window for each action unit; the out-of-control active window is the phase interval in which the device has the true probability of losing control within a single action cycle;
[0017] The time-varying risk domain construction module is used to generate normal motion envelope data and runaway reachability domain based on the action unit and the equipment specification data, and to incorporate the normal motion envelope data into the runaway reachability domain only within the phase interval defined by the runaway active window, thereby obtaining a phase-gated time-varying risk domain;
[0018] The spatial mapping module is used to generate a site grid based on the site feature data, generate a station matrix based on the target number of performers in the audience attribute data, and map the phase-gated time-varying risk domain to the site grid according to the coordinates and orientation of the station matrix to generate a global time-varying risk domain for each station.
[0019] The joint interferometry detection module is used to perform spatiotemporal joint interferometry detection on adjacent stations to filter out overlapping station pairs that are spatially intersecting and whose associated out-of-control active windows coincide in time.
[0020] The phase staggered peak solving module is used to solve the password phase offset data that separates the out-of-control active windows of adjacent stations in the time dimension based on the overlapping station pairs.
[0021] The strategy output module is used to generate a course adaptation strategy based on the solution results of the password phase offset data, and output the target sports intangible cultural heritage adapted course accordingly.
[0022] By employing the above technical solution, the present invention provides a method and system for intelligent adaptation of sports intangible cultural heritage courses based on spatial safety constraints, which has at least the following beneficial effects:
[0023] 1. This invention establishes runaway phase profile data for each action unit and extracts runaway active windows accordingly. It reconstructs the fusion risk space domain from a statically activated space volume throughout the entire process into a phase-gated time-varying risk domain that couples the runaway reachable domain only within the runaway active window. This removes the distortion caused by the full activation of the runaway reachable domain and makes the risk space assessment fit the phase locality of the device runaway.
[0024] 2. The password rhythm, which was originally caused by the implicit password and just exacerbated the uncontrolled phase alignment, is reversed to the password phase offset data that is explicitly solved by the system. This actively breaks up the temporal alignment of the high-incidence phases of adjacent students' uncontrolled phases, thereby identifying a type of pseudo-conflict where the spatial overlaps but the uncontrolled phases can be staggered.
[0025] 3. To address pseudo-conflicts where spaces overlap but out-of-control phases can be staggered, an access strategy of staggered synchronous execution is added. This allows for the reuse of the same risk space in the time dimension without increasing the spacing between positions, reducing the number of trainees, or decreasing the range of motion, thereby improving the safe capacity and teaching synchronicity of the offline venue.
[0026] 4. By using a closed-form criterion between the active duty cycle and the total number of stations in the overlapping cluster, the feasibility of peak shifting can be quickly determined and the password phase offset data can be solved. The phase-separated password timing table and peak shifting station phase diagram are output, providing a quantifiable and executable spatiotemporal safety adaptation basis for large-scale offline promotion. Attached Figure Description
[0027] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.
[0028] Figure 1 A flowchart illustrating the intelligent adaptation method for sports intangible cultural heritage courses based on spatial safety constraints provided by this invention.
[0029] Figure 2 The logical framework diagram of the intelligent adaptation method for sports intangible cultural heritage courses based on spatial safety constraints provided by the present invention is shown.
[0030] Figure 3 A schematic diagram of the modules of the intelligent adaptation system for sports intangible cultural heritage courses based on spatial safety constraints provided by the present invention. Detailed Implementation
[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0032] Exemplary method:
[0033] To address the problem that existing course adaptation methods based on spatial safety constraints model the fusion risk spatial domain as a statically activated spatial volume throughout the process, ignore the phase locality of equipment malfunction, and superimpose synchronous commands to cause phase alignment, thus misjudging potentially staggered instantaneous malfunctions as continuous spatial overlap and forcing them to expand distance or group, this embodiment proposes an intelligent adaptation method for sports intangible cultural heritage courses based on spatial safety constraints. Figures 1-2 As shown, the method includes steps S1 to S8.
[0034] To facilitate understanding, the following example is a lightweight in-person diabolo experience class for adults with no prior experience. Assume the target sport / intangible cultural heritage activity is diabolo, and the throwing and catching motion is used as a single action unit to be evaluated. The venue is a community cultural activity room with a usable area approximately 12m long, 8m wide, and 4m high. The target audience is an introductory class for adults with no prior experience, with a target of 12 participants. The equipment is a standard double-wheeled bamboo diabolo. Assume the single-action cycle of this throwing and catching motion is approximately 2 seconds, corresponding to an angular frequency of approximately πrad / s. Subsequent steps will be explained using this project, venue, target audience, and equipment configuration as examples.
[0035] like Figure 1 As shown, in step S1, target sports intangible cultural heritage project data, venue characteristic data, audience attribute data and equipment specification data are obtained, and the target sports intangible cultural heritage project data is parsed into multiple action units;
[0036] Specifically, the purpose of this step is to provide a unified input data foundation for subsequent steps: the action unit is the evaluation object for extracting the out-of-control active window and constructing the risk domain; the equipment specification data is used to correct the out-of-control reach domain; the site feature data is used to generate the site grid; and the target number of performers in the audience attribute data is used to generate the station matrix.
[0037] Specifically, the acquisition of data and the analysis of action units involved in this step can be achieved using conventional data access methods: data on the target sports intangible cultural heritage project, venue characteristics, audience attributes, and equipment specifications can be obtained through project data entry, venue measurement or drawing import, registration information collection, and equipment ledger reading, respectively; among them, venue characteristics data include available plane dimensions, clearance height, and the locations of obstacles, doors and windows, entrances and exits, and waiting areas; audience attributes data include at least the target number of performers; and equipment specifications data include at least the physical dimensions, mass, and related component parameters (such as rope length) of the equipment used. The target sports intangible cultural heritage project data is analyzed into multiple action units, that is, the complete set of movements is broken down into the smallest teaching unit that can be independently evaluated, and each action unit corresponds to a candidate movement that can be individually risk-assessed and positioned.
[0038] Following the previous example, the target sports intangible cultural heritage project data entered in this step is diabolo and its complete set of movements, and multiple movement units including the throwing and catching movements are analyzed. At the same time, the venue characteristic data of the activity room (12m long, 8m wide, and 4m clear height), the audience attribute data of the target number of 12 people, and the equipment specification data of the standard double-wheel bamboo diabolo are obtained.
[0039] return Figure 1 In step S2, for each action unit, an out-of-control active window is extracted; the out-of-control active window is the phase interval of the device within a single action cycle that represents the actual probability of out-of-control behavior.
[0040] Specifically, this step treats existing methods as a general risk of runaway that is active throughout the entire action cycle, quantifying it as a runaway active window and an active duty cycle. This provides a basis for step S3 to incorporate the runaway reachable domain into the risk domain by phase gating, and for step S7 to determine whether phase staggering is feasible.
[0041] Extracting the out-of-control active window includes:
[0042] Acquire the kinematic characteristic data of the device within a single action cycle of the action unit, wherein the kinematic characteristic data of the device includes at least instantaneous velocity data, acceleration data, and grip constraint strength data;
[0043] Among these methods, acquiring kinematic characteristic data of the apparatus can be achieved through kinematic analysis of standard demonstration movements, or through motion capture, high-speed photography, and other means. It should be noted that the movement phase refers to the normalized amount of movement over time over a complete movement cycle, with values ranging from [a certain range]. The phase variable of the grip constraint strength approaches zero the instant the device is released from the hand.
[0044] Based on the kinematic feature data of the device, the out-of-control phase profile data is calculated, and the out-of-control phase profile data represents the continuous distribution of the out-of-control probability as the action phase changes;
[0045] Specifically, the runaway phase profile data is obtained by mapping the kinematic characteristic data of the machine using the following formula:
[0046] ;
[0047] in, For the first Each action unit in the action phase Out-of-control phase profile data at the location, , , Phases Instantaneous velocity data, acceleration data, and grip constraint strength data at the location. Category of loss of control mode (such as slipping out of hand, bouncing, flying out, entanglement). This is a mapping function that maps the aforementioned kinematic feature data to the probability of runaway.
[0048] Specifically, the greater the device's velocity and acceleration, and the lower the grip constraint strength in a given phase, the easier it is for the device to escape control and the higher the probability of loss of control. Therefore, the loss of control phase profile data reaches its peak near the device's release from the grip, and its peak phase... That is, the high-incidence phase points corresponding to release and flight; the mapping function This can be achieved using an empirical function that weights the above-mentioned kinematic feature parameters, or a regression model that uses historical runaway samples as training data.
[0049] As the mapping function One specific implementation can be achieved by using the following logistic function form, which compresses the above kinematic feature parameters into a weighted combination. The interval is used to represent the probability of running out of control:
[0050] ;
[0051] in, , , The magnitudes of instantaneous velocity and acceleration, respectively, and the grip constraint strength are determined by reference values. , , The dimensionless quantity obtained after normalization , The weights of the velocity term and the acceleration term are respectively. To hold the weights of the constraint terms and ensure that all three are positive, This is a bias term that takes values based on the runaway mode category. This is a natural exponential function. The above equation treats the instrument's velocity and acceleration as driving factors that cause the instrument to tend towards loss of control and takes a positive sign, while the grip restraint strength is treated as a stabilizing factor that inhibits loss of control and takes a negative sign. Therefore, when the instrument is released from the grip, the grip restraint strength... When the exponent approaches zero and the velocity and acceleration are large, the power value within the exponent tends to a large positive value. It approaches 1 and reaches its peak. The above weights... , , Bias with each runaway mode It can be obtained by fitting logistic regression to historical out-of-control samples;
[0052] It should be noted that the above-mentioned logistic function is only an optional form given for ease of implementation. Any function that can reflect the physical law that the greater the speed and acceleration and the lower the gripping constraint strength, the higher the probability of loss of control can be used instead.
[0053] The out-of-control phase profile data is truncated using a preset probability threshold. The phase intervals with an out-of-control probability greater than or equal to the preset probability threshold are extracted as out-of-control active windows, and the active duty cycle of the out-of-control active window in the overall action cycle is calculated.
[0054] Specifically, the uncontrolled active window and the active duty cycle are obtained by the following formulas:
[0055] ;
[0056] in, For uncontrolled active windows, For the preset probability threshold, To activate the duty cycle, The phase length covered by the runaway active window.
[0057] Wherein, the preset probability threshold The lower bound of the runaway probability allowed to be incorporated into the risk domain is defined as follows: a higher threshold results in a narrower runaway activity window and a more aggressive assessment, while a lower threshold results in a wider runaway activity window and a more conservative assessment. This threshold can be a certain percentage of the peak value of the runaway phase profile or pre-calibrated according to an acceptable runaway probability level. Active duty cycle. It is a calculable measure of the phase locality of instrument runaway. The smaller the value, the narrower the actual activation phase of the out-of-control movement and the longer the controlled period of the apparatus; for apparatus-based intangible cultural heritage sports movements, the out-of-control situation is often concentrated only at the moment of release, therefore It is usually much less than 1.
[0058] Following the previous example, for the diabolo throwing and catching action, the instantaneous velocity, acceleration, and grip constraint strength of the diabolo within a single action cycle are collected to calculate the runaway phase profile data, the peak of which occurs near the time the diabolo is released from the hand; a preset probability threshold is used to extract the runaway active window. The coverage phase length is approximately 0.94 rad (approximately 54°). Substituting this into the active duty cycle formula yields... That is, the out-of-control activation phase accounts for only about 15% of the action cycle, corresponding to a release window of about 0.3 seconds, while the diabolo is controlled for the remaining 85% of the time.
[0059] return Figure 1 In step S3, normal motion envelope data and runaway reachability domain are generated based on the action unit and the equipment specification data, and the runaway reachability domain is only incorporated into the normal motion envelope data within the phase interval defined by the runaway active window to obtain the phase-gated time-varying risk domain;
[0060] Specifically, this step, based on the generation of normal motion envelope data and out-of-control reachable domain, incorporates the out-of-control reachable domain into the risk domain according to the out-of-control active window, thereby expanding the originally statically activated fusion risk space domain throughout the entire motion cycle into a phase-gated time-varying risk domain in the time dimension.
[0061] The generation of normal motion envelope data and uncontrolled reachable domains includes:
[0062] Normal motion envelope data is generated based on the human range of motion requirements and the basic trajectory requirements of the device in the action unit, and a predetermined number of out-of-control trigger point data are extracted from it.
[0063] Among them, the normal motion envelope data represents the three-dimensional space occupied by the movement trajectory and human movement range of the device when it moves normally according to standard actions and is not out of control, which can be generated by spatial modeling; the out-of-control trigger point data is the spatial location point of the device most likely to go out of control within the normal motion envelope. It can be the spatial location of the device corresponding to the phase in which the out-of-control phase profile obtains a local peak within the out-of-control active window. The predetermined number is the number of such local peaks. When the profile only has a single peak within the active window, the predetermined number is 1. When the action contains multiple out-of-control high-incidence links (such as throwing and detaching and entanglement belonging to two different high-incidence phases), it is the number of such high-incidence links.
[0064] The beginner instability coefficient is calculated based on the audience attribute data and the preset weight model, and the equipment specification correction coefficient is calculated based on the equipment specification data.
[0065] Among them, the instability coefficient for beginners (denoted as ) This represents the degree to which the scope of loss of control due to the audience's lack of skill expands relatively. It can be obtained by weighting the audience's skill level and age composition using a preset weighted model. The lower the skill level, the larger the value. The preset weighted model is a pre-established model that uses skilled adult learners as a benchmark and assigns weighted scores to the degree of loss of control aggravation for each audience attribute. One specific form is as follows:
[0066] ;
[0067] in, For the first The loss of control over audience attributes (such as skill level and age group) exacerbates the scoring; a score of 0 is assigned when the user is skilled and of the appropriate age, while the score is closer to 1 the less skilled or the further away from the appropriate age group the user is. The weights for this attribute are normalized by summing the weights, and are set by statistical fitting of the contribution of each audience attribute to historical out-of-control events. When the audience consists of skilled adult learners, each score... All are taken as 0, Taking a baseline value of 1, the lower the audience's skill level, The larger The larger than 1.
[0068] It should be noted that, As a magnification factor for the baseline uncontrollable reachability, a larger value amplifies the uncontrollable reachability and provides a larger safety margin, thus enabling beginners with relatively poor control abilities to receive a more conservative risk assessment. Equipment specification correction factor (denoted as...) The influence of equipment size, mass, rope length, etc., on the runaway ripple range can be determined by the ratio of the equipment specifications to standard equipment. One specific form is... ,in, , These are the mass of the equipment and the length of the rope, respectively. , These are the mass and rope length of the standard equipment, respectively. , The corresponding indices (calibrated by fitting historical runaway experimental data, used to characterize the influence weights of mass and rope length on the runaway spread); when using standard equipment Take 1; the heavier the equipment and the longer the rope, the better. The larger the value, the greater the potential range of loss of control.
[0069] The runaway trigger point data, the beginner instability coefficient, the equipment specification correction coefficient, and the ground friction parameters in the site feature data are input into a preset runaway simulation algorithm to generate the runaway reachable domain.
[0070] Specifically, the pre-set runaway simulation algorithm used in this step takes the runaway trigger point as the starting point and uses the kinematics of projectile motion combined with frictional rolling after landing to simulate the spatial range that the device can affect after runaway. Specifically, it can be implemented as follows: at the runaway trigger point, the device uses the instantaneous velocity corresponding to the phase of that trigger point. The device is launched in a cone-shaped trajectory in an out-of-control direction, the cone having a half-angle of 1 / 2 with respect to the nominal release direction. ,in, The nominal half angle for skilled trainees (which can be obtained by sampling and statistically calibrating the standard demonstration movements of skilled trainees multiple times). For beginners, the instability coefficient is... The larger the velocity, the wider the directional cone and the more divergent the uncontrolled launch direction; along any direction within the uncontrolled directional cone, the device first undergoes projectile motion to reach the ground, and its horizontal flight range is determined by the launch velocity. The launch angle and trigger point height are obtained using projectile kinematics. After landing, the device moves at a landing speed... As it continues to roll or slide, it slows down due to ground friction until it stops, and the rolling distance is:
[0071] ;
[0072] in, The friction coefficient is determined from the ground friction parameters in the site characteristic data. For gravitational acceleration, the equipment specification correction factor The aspect ratio used to determine the reachable profile is the ratio of the reachable profile's extension along the injection direction to its lateral half-width. ,in, The reference aspect ratio when using standard instruments (which can be obtained by measuring and calibrating the standard instruments through runaway projectile experiments); Larger aspect ratio The larger the value, the more elongated the achievable profile is in the injection direction. This relates to the runaway direction cone (half-angle). The range and rolling distance of the projectile in each direction within the ( ) are calculated according to the aspect ratio. Extending along the emission direction, the resulting spatial region centered on the trigger point is the reachable profile of that trigger point. The union of the reachable profiles of all runaway trigger points is the runaway reachable domain. .
[0073] It should be noted that, The larger the value, the wider the directional cone and the more diffused the lateral contour. The larger the aspect ratio, the more the reachable profile extends along the launch direction. The greater the launch speed of the device, the longer the projectile range. The smaller the ground friction coefficient, the longer the rolling distance. The uncontrollable reachable domain is correspondingly more expanded in shape, thus quantitatively characterizing the uncontrollable ripple morphology under different release kinematics, different audience skills, different equipment specifications, and different field friction conditions.
[0074] It should be further explained that, as can be seen from the above formula, , The cone half angles in the direction of runaway respectively Aspect Ratio of Reachable Profile Impact on the reachability of the baseline runaway system The shape and orientation distribution, both of which are dimensionless morphological quantities, are not included here. Multiply by the overall scale.
[0075] After generating the normal motion envelope data and the baseline uncontrolled reachability region, the uncontrolled reachability region is further phase-gated and incorporated into the normal motion envelope data according to the uncontrolled activity window. The obtained phase-gated time-varying risk region includes:
[0076] Determine whether the current real-time phase of the action is within the phase range defined by the out-of-control active window; wherein, the current real-time phase of the action refers to the real-time phase of the action as the student performs the action unit over time.
[0077] If so, the uncontrolled reachable domain, the beginner instability coefficient, and the equipment specification correction coefficient are multiplied to obtain the dynamic extended domain, and the normal motion envelope data are combined with the dynamic extended domain to generate the phase-gated time-varying risk domain.
[0078] Specifically, this step only amplifies the baseline out-of-control reachable region into a dynamically expanded region and incorporates it into the risk region when the real-time phase falls within the out-of-control active window; when the real-time phase does not fall within the out-of-control active window, the dynamically expanded region is not incorporated, and the risk region is only... The phase-gated time-varying risk domain can be expressed as:
[0079] ;
[0080] in, For the first Each action unit at time Phase-gated time-varying risk domain, This is normal motion envelope data. For uncontrollable reachable domains, , These are the instability coefficient for beginners and the equipment specification correction coefficient, respectively. For this action at time The real-time phase, For uncontrolled active windows, This is a spatial union operation.
[0081] Therefore, normal motion envelope data occupies the risk space throughout the entire motion cycle, while the out-of-control reachable domain only extends outward within the release phase corresponding to the out-of-control active window. This unfolds the originally static risk domain in the time dimension, removing the distortion caused by the continuous activation of the out-of-control reachable domain. In contrast, if phase gating is not introduced and subsequent judgments are made directly using the static risk domain, the aforementioned distortion cannot be removed.
[0082] Using the previous example, normal motion envelope data is generated for the diabolo throwing and catching action. The system also extracts the point of loss of control near the moment the diabolo is released and calculates the instability coefficient for beginners. Equipment specification correction factor The baseline runaway reachability region is generated through the deduction algorithm. When the real-time phase falls into the out-of-control active window (Release window approximately 0.3s) Take the upper support from Get the dynamically extended domain and connect it with The risk domain is calculated and constructed; when the real-time phase is outside the release window, the risk domain is only [a certain value]. .
[0083] return Figure 1 In step S4, a site grid is generated based on the site feature data, and a station matrix is generated based on the target number of performers in the audience attribute data.
[0084] Specifically, this step applies the phase-gated time-varying risk domain to the absolute coordinate reference of the specific site and the arrangement of trainees' positions.
[0085] Specifically, this step can be achieved using conventional site gridding and station layout methods: the site grid is a two-dimensional grid obtained by discretizing the available area of the site according to a preset grid size and marking the positions of obstacles, doors and windows, etc., as the absolute coordinate reference for mapping and conflict detection; the station matrix is a set of standing positions of each trainee arranged in the site grid according to the target number of trainees, with each station corresponding to the standing coordinates and orientation of a trainee; for example, the site can be divided into 0.5m grids and the stations can be evenly distributed in rows and columns.
[0086] Following the previous example, the usable area of the activity room, which is 12m long and 8m wide, is discretized into a 24-column, 16-row grid using a 0.5m grid. The walls, doors, windows, and waiting areas are marked. A 3-row, 4-column matrix of 12 positions is generated based on the target number of 12 people, with each position facing the throwing direction.
[0087] return Figure 1 In step S5, the phase-gated time-varying risk domain is mapped to the site grid according to the coordinates and orientation of the station matrix to generate the global time-varying risk domain for each station.
[0088] Specifically, this step expresses the time-varying risk space occupied by each action at each station, which is phase-gated, in a unified absolute coordinate system of the same site grid.
[0089] The global time-varying risk domains generated for each station include:
[0090] Traverse the station matrix and extract the station coordinates and orientation of each station; that is, read the station coordinates and orientation of each station in the station matrix one by one as the transformation parameters for subsequent affine transformation.
[0091] Using the station coordinates as the origin and the station orientation as the reference direction, perform an affine transformation operation on the phase-gated time-varying risk domain;
[0092] Specifically, this step can be implemented using a two-dimensional rigid body affine transformation. Let the phase-gated time-varying risk domain be defined. The horizontal coordinate of any point in the action's local coordinate system is: The height coordinates are Based on station coordinates Using the origin as the reference point and the direction of the standing position as the reference point. After performing an affine transformation on the point with reference direction, its coordinates in the absolute coordinate system of the site grid are... We obtain the following formula:
[0093] ;
[0094] in, , The first The station coordinates and orientation of each station, and the rotation matrix. Achieve orientation around the vertical axis according to the station position rotation, translation vector To achieve translation to the station's coordinates, including elevation coordinates. It remains unchanged when placed horizontally. .Will The set of points obtained by transforming all points in the above formula is the set of points. The action unit in the first Each station is located at the time Global time-varying risk domain Since the above transformation is a point-by-point rigid body transformation, it only changes the position and orientation of the risk domain in the site without changing its shape. It still retains the time-varying characteristics of the reachable domain of real-time phase-gated runaway.
[0095] The phase-gated time-varying risk domain after affine transformation is superimposed onto the absolute coordinate system of the site grid to obtain the global time-varying risk domain;
[0096] Specifically, this step involves superimposing the phase-gated time-varying risk domain after affine transformation onto the absolute coordinate system of the site grid to obtain the global time-varying risk domain.
[0097] It should be noted that the global time-varying risk domain is obtained by affine transformation of the phase-gated time-varying risk domain, thus retaining the time-varying characteristics of the uncontrolled reachable domain with real-time phase gating. That is, the part corresponding to the normal motion envelope at each station always occupies space, and the part corresponding to the uncontrolled reachable domain only extends outward within the uncontrolled active window.
[0098] Following the previous example, we traverse the 3-row, 4-column station matrix. For each station, we take its station coordinates as the origin and the direction of throwing and catching as the reference direction. We then perform an affine transformation on the phase-gated time-varying risk domain of the throwing and catching action and superimpose it onto the absolute coordinate system of the activity room grid to obtain the global time-varying risk domain of each of the 12 stations.
[0099] return Figure 1 In step S6, spatiotemporal joint interference detection is performed on adjacent stations to screen out overlapping station pairs that are spatially intersecting and whose associated out-of-control active windows coincide in time.
[0100] Specifically, this step involves performing spatial and temporal joint conflict detection on the global time-varying risk domain of adjacent stations under the same site grid absolute coordinate system, distinguishing between real out-of-control superimposed conflicts and pseudo-conflicts that overlap spatially but whose out-of-control phases can be staggered, thus filtering out overlapping station pairs to be processed in step S7.
[0101] Among them, the spatiotemporal joint interferometry detection of adjacent stations includes:
[0102] Extract the spatial geometric envelopes from two adjacent global time-varying risk domains and perform an intersection comparison. If spatial geometric intersection occurs, mark the two adjacent global time-varying risk domains as a geometric interference pair.
[0103] Under the default phase alignment condition, it is determined whether the two runaway active windows associated with the geometric interference pair coincide in time. If they coincide, it is determined that a real runaway superposition has occurred, and the geometric interference pair is identified as an overlapping station pair.
[0104] Specifically, the above steps involve joint detection of adjacent stations in both spatial and temporal dimensions, and are performed in two levels: the first level is spatial geometric intersection comparison, which extracts the spatial geometric envelopes in the global time-varying risk domain of two adjacent stations for intersection comparison to determine whether there is spatial overlap between the two. If there is, it is marked as a geometric interference pair; the second level is temporal overlap judgment of the runaway active window, which, under the default phase alignment condition, determines whether the runaway active windows of the two action units associated with the geometric interference pair overlap in time.
[0105] The default phase alignment condition refers to the condition where no command phase offset is applied to each station and the action phase of each trainee at each station is completely aligned under the teacher's unified command. That is, the current state where the command phase offset of each station is zero and there is no peak shifting, which corresponds to the situation where the high-incidence phases of each trainee's loss of control are completely overlapped in time under the existing full-staff synchronous execution method.
[0106] It should be noted that the out-of-control impact ranges of the two trainees' equipment will only overlap at the same time when the two stations are geometrically intersecting and their out-of-control active windows coincide in time under the default phase alignment condition. In this case, a true out-of-control overlap is determined, and the geometric interference pair is identified as an overlapping station pair. The so-called true out-of-control overlap here means that the out-of-control impact ranges do indeed overlap at the same time under the current state of default phase alignment, i.e., before the application of command phase offset. This is used to distinguish it from the case where they only intersect spatially but are not activated simultaneously, and does not mean that the overlap is irremovable. Whether the overlapping station pair is a pseudo-conflict that can be eliminated by staggered execution is further determined by the closed-form criterion in the subsequent step S7. If the criterion is met, it is a pseudo-conflict where the spatial overlaps but the out-of-control phases can be staggered, and it can be eliminated by staggered synchronous execution. If the criterion is not met, it is a true conflict that cannot be eliminated by staggered execution, and it is handled by strategies such as group rotation.
[0107] It needs to be explained that this step distinguishes between three cases for adjacent stations: First, those that do not intersect spatially do not constitute a conflict; second, those that intersect spatially but whose out-of-control active windows do not coincide in time under the default phase alignment, although their out-of-control impact ranges overlap spatially, do not activate simultaneously at the same time, and therefore do not overlap and do not require staggering; third, those that intersect spatially and whose out-of-control active windows coincide in time are defined as overlapping station pairs and are subject to determination by step S7 regarding whether staggering is possible. The second case mentioned above occurs when adjacent stations execute different action units and their out-of-control active windows do not overlap in phase. In this case, the determination of the coincidence of out-of-control active windows has discriminative power and can directly exclude such station pairs; however, when adjacent stations execute the same action unit and are default phase aligned, those that intersect spatially have coincidence of out-of-control active windows and are all classified into the third case. Whether they can be reused for staggering is determined by the closed-form criterion in step S7.
[0108] Using the previous example, the spatial geometric intersection of each pair of adjacent positions in the activity room was compared. Because the 12 trainees were standing close together, many pairs of adjacent positions had spatial geometric intersection and were marked as geometric interference pairs. Under the default phase alignment condition, since the synchronous execution of all trainees made the throwing, catching and releasing phases of each trainee completely aligned, the out-of-control active windows associated with these geometric interference pairs all overlapped in time, and were therefore identified as overlapping position pairs.
[0109] return Figure 1 In step S7, based on the overlapping station pairs, the password phase offset data that separates the out-of-control active windows of adjacent stations in the time dimension is solved.
[0110] Specifically, this step targets overlapping station pairs. First, it uses a closed-form criterion to determine whether staggered peaks are feasible. Then, it solves for the password phase offset data that causes the uncontrolled active windows of adjacent stations to separate in the time dimension. This transforms the teacher's password from an implicit boundary condition that causes phase alignment into a decision variable that is explicitly solved by the system.
[0111] The password phase offset data used to separate the out-of-control activity windows of adjacent stations in the time dimension includes:
[0112] Several overlapping station pairs are grouped into overlapping station clusters, the total number of stations in the overlapping station clusters is counted, and the active duty cycle of the corresponding action unit is extracted.
[0113] Among them, the overlapping station cluster is the set of stations obtained by merging overlapping station pairs that have overlapping relationships according to their common stations, and the total number of stations is the number of stations in the cluster.
[0114] It should be noted that the following is the password phase offset data solved for each station within the cluster, used to offset the real-time phases of students at each station by the teacher's phase-separated password. The real-time phase of each student can be represented as... , For the first Each student at each station at any time The real-time phase, The angular frequency of the action is determined by the action period. according to Sure, To be assigned to the Password phase offset data for each station.
[0115] Determine whether the active duty cycle is less than or equal to the reciprocal of the total number of stations;
[0116] Specifically, this step uses a closed-form criterion between the active duty cycle and the total number of stations to determine the feasibility of peak shifting, as shown in the following formula:
[0117] ;
[0118] in, This represents the active duty cycle of the action unit corresponding to the overlapping station cluster. This represents the total number of stations within the cluster. This corresponds to the phase length covered by the runaway active window. The meaning of this criterion is: within the cluster. Each station needs to have its own out-of-control active window within one action cycle (corresponding phase). The elements are arranged in a staggered manner without overlapping, only when... A feasible phase assignment exists only when the sum of the phase lengths of the out-of-control active windows does not exceed one action cycle.
[0119] It should be noted that the smaller the active duty cycle, the more staggered stations can be accommodated within the same cluster, and the easier it is for staggering to be established. If the active duty cycle is too large, exceeding the reciprocal of the total number of stations, then the uncontrolled active windows that cannot accommodate all stations within the cluster in one action cycle will not overlap, and the solution will be judged as a failure. Therefore, it is possible to quickly eliminate infeasible situations using closed inequalities without actually solving the problem.
[0120] If so, then an independent time compensation variable is assigned to each station in the overlapping station cluster, a solution model is constructed with decorrelation constraints as conditions, and the solution model is solved to obtain a set of time compensation variables as password phase offset data; wherein, the decorrelation constraints are used to limit the intersection of the runaway active windows of any adjacent stations after superimposing the time compensation variables to an empty set;
[0121] Specifically, this step assigns an independent time compensation variable (i.e., password phase offset data) to each station within the cluster when the above criterion is met, and constructs a solution model with decorrelation constraints as conditions. These decorrelation constraints can be expressed as:
[0122] ;
[0123] in, , Adjacent stations within the cluster , Time compensation variable, , These are the phase intervals occupied by the superposition of their respective time-compensated variables over the out-of-control active windows of the two stations. Solving this model yields a set of time-compensated variables that ensures the out-of-control active windows of any adjacent stations within the cluster do not overlap, serving as the password phase offset data; a feasible construction is to... The time compensation variables for each station are evenly distributed within one action cycle, i.e. This causes the uncontrolled active windows of adjacent stations to be spaced apart in phase. .
[0124] It should be noted that in the criteria When established, this uniform arrangement ensures that the out-of-control active windows of adjacent stations within the cluster do not overlap, thus satisfying decorrelation constraints and obtaining feasible password phase offset data. Furthermore, to obtain... This can be implemented as a set of phased command issuance times that teachers can execute, according to... Converted to the command issuance time delay relative to the reference station, the teacher uses this to assign commands to each station according to the time difference. The start-up commands are issued sequentially at specific times, which means that the command phase offset data is converted into a closed loop into a sequence of phase commands that can actually be issued.
[0125] If not, the password phase offset data calculation is deemed to have failed;
[0126] Specifically, this step corresponds to the situation where the criterion is not met, namely, the active duty cycle is greater than the reciprocal of the total number of stations, and all the out-of-control active windows in the cluster cannot be accommodated without overlapping within one action cycle. In this case, the solution is judged to have failed.
[0127] It should be noted that existing methods can only adopt coarse-grained time separation by increasing the station spacing or grouping and rotating after detecting spatial overlap. However, this step uses the password phase offset data as an explicit decision variable to solve the problem. By decorrelation constraints, it performs fine-grained peak shifting on the active windows of adjacent trainees in the continuous phase dimension, so that the high-incidence phases of adjacent trainees who are geometrically bound to overlap will never overlap in time. Thus, the same risk space can be reused in time without increasing the station spacing or reducing the number of trainees.
[0128] Using the previous example, let the total number of stations in a certain overlapping station cluster be... Corresponding active duty cycle First, judge according to the criteria. (equivalent land) The criteria are valid and staggered peak times are feasible; time compensation variables are allocated to four stations with uniform distribution. , , , Phase spacing of each out-of-control active window ;according to ( The command issuance delay can be calculated using rad / s. , , , The commands for adjacent stations are staggered. Since the release window is greater than 0.3s, the out-of-control active windows of any adjacent stations within the cluster do not overlap, satisfying the decorrelation constraint, and thus the password phase offset data and the corresponding password issuance time delay of the cluster are obtained.
[0129] return Figure 1 In step S8, a course adaptation strategy is generated based on the solution results of the password phase offset data, and the target sports intangible cultural heritage adapted course is output accordingly.
[0130] Specifically, this step assigns corresponding course adaptation strategies to action units based on the solution results of the command phase offset data and assembles and outputs the adapted courses, thus turning the results of spatiotemporal joint evaluation and phase staggered peak solution into course arrangement and phase-separated command timing that can be implemented by teachers.
[0131] Among them, generating course adaptation strategies and outputting target sports intangible cultural heritage adapted courses includes:
[0132] If the password phase offset data is successfully solved, a first course adaptation strategy representing staggered synchronous execution is generated, and a phase-sequence password timing table and a station phase diagram with marked release window staggered execution are generated based on the password phase offset data.
[0133] Specifically, when the password phase offset data is successfully solved, the first course adaptation strategy is generated, and a phase-sequence table of passwords and a station phase diagram with marked release window peaks are generated based on the password phase offset data.
[0134] The phase-based command sequence table is arranged according to the phase offset data of each station, providing teachers with a staggered release sequence for adjacent students. The station phase diagram marking the staggered release window is an illustration on the station layout diagram showing the staggered relationship of the out-of-control active windows of each station. When feasible phase allocation exists, this first course adaptation strategy re-admits actions that were originally judged as group rotation or downgraded execution due to spatial overlap as staggered synchronous execution. Thus, in terms of admission logic, an admission strategy with continuous phase staggering is added between synchronous execution for all and group rotation execution. This allows the same risk space judged as spatial overlap to be reused by adjacent students in staggered time, improving the venue capacity and teaching synchronicity without increasing the station spacing or reducing the number of students.
[0135] If the password phase offset data fails to be solved, and the audience attribute data and the equipment specification data meet the preset grouping conditions, then a second course adaptation strategy representing the group rotation execution is generated.
[0136] Specifically, when the password phase offset data fails to be solved and the audience attribute data and equipment specification data meet the preset grouping conditions, a second course adaptation strategy representing the group rotation execution is generated, that is, the students are rotated to perform the action in batches, and the phase stagger that cannot be established is replaced by coarse-grained time separation.
[0137] It should be noted that the preset grouping conditions are used to determine whether trainees and equipment can be rotated in batches. This can be simply implemented as follows: determine whether there is a batching method that reduces the number of concurrent overlapping stations in each batch to the point where the phase peaks are staggered and a solution is found again (or the stations in the batch no longer overlap spatially), and the number of people executing in each batch does not exceed the number of equipment. If such a batching method exists, it is determined that the grouping conditions are met.
[0138] It should be further explained that batching reduces the number of concurrent overlapping stations in each batch, thereby transforming the situation where there is no solution for staggering the entire cluster into a situation where staggering or non-overlapping can be achieved within each batch, and uncontrolled superposition can be avoided between batches through coarse-grained time separation, thus ensuring a safety baseline. When the password phase offset data fails to be solved and the above grouping conditions are not met, that is, when both staggered synchronous execution and group rotation execution are not feasible, the synchronous or group execution strategy is no longer assigned to the action. Instead, the strategy of degraded execution or exclusion of the action is assigned in the manner described later, to ensure that each action unit has a clear entry or exit strategy and that there are no actions without a strategy to follow.
[0139] According to the first course adaptation strategy or the second course adaptation strategy, the corresponding visual positioning materials, safety reminder materials and teaching video materials are extracted synchronously, assembled and output as the target sports intangible cultural heritage adapted course;
[0140] Specifically, this step involves simultaneously extracting the corresponding visual positioning materials, safety tips materials, and teaching video materials according to the first or second course adaptation strategy, and then assembling and outputting the adapted course.
[0141] It should be added that for actions where password phase offset data calculation fails and grouping conditions are not met—that is, where both staggered synchronous execution and group rotation execution are not feasible—corresponding fallback strategies are assigned based on their degree of danger and cultural value: for actions that severely interfere with space or uncontrolled domains, involve normal motion envelope crossing boundaries, or have insufficient clearance, a downgraded execution strategy of calling a backup safe action is assigned; for actions with extremely high danger but core cultural value, a teacher demonstration or video demonstration strategy is assigned; for actions with irreconcilable safety conflicts, an exclusion strategy is assigned. Thus, each action unit is ultimately assigned a clear strategy of staggered synchronous execution, group rotation execution, downgraded execution, teacher demonstration or video demonstration, or exclusion.
[0142] Following the previous example, since step S7 successfully solved for the overlapping station cluster, this step generates a first-course adaptation strategy for the staggered synchronous execution of the diabolo throwing and catching action, based on... , , , A phased command timing table is generated, allowing the teacher to guide four adjacent students in the cluster to take turns throwing and catching the ball according to phased commands staggered by 0.5 seconds. At the same time, a phase diagram of the release windows of each station is generated, marking the staggered relationship. Then, the corresponding materials are extracted and the adapted course is output. Under the premise of 12 people, the venue and the range of motion remain unchanged, the same risk space is reused by adjacent students through staggered synchronous execution, which improves the venue capacity and teaching synchronicity while ensuring the bottom line of safety.
[0143] Exemplary system:
[0144] Please see Figure 3 A smart adaptation system for intangible cultural heritage sports courses based on spatial safety constraints, comprising:
[0145] The data acquisition module is used to acquire data on the target sports intangible cultural heritage project, venue characteristics, audience attributes, and equipment specifications, and to parse the target sports intangible cultural heritage project data into multiple action units;
[0146] The feature window extraction module is used to extract the out-of-control active window for each action unit; the out-of-control active window is the phase interval in which the device has the true probability of losing control within a single action cycle;
[0147] The time-varying risk domain construction module is used to generate normal motion envelope data and runaway reachability domain based on the action unit and the equipment specification data, and to incorporate the normal motion envelope data into the runaway reachability domain only within the phase interval defined by the runaway active window, thereby obtaining a phase-gated time-varying risk domain;
[0148] The spatial mapping module is used to generate a site grid based on the site feature data, generate a station matrix based on the target number of performers in the audience attribute data, and map the phase-gated time-varying risk domain to the site grid according to the coordinates and orientation of the station matrix to generate a global time-varying risk domain for each station.
[0149] The joint interferometry detection module is used to perform spatiotemporal joint interferometry detection on adjacent stations to filter out overlapping station pairs that are spatially intersecting and whose associated out-of-control active windows coincide in time.
[0150] The phase staggered peak solving module is used to solve the password phase offset data that separates the out-of-control active windows of adjacent stations in the time dimension based on the overlapping station pairs.
[0151] The strategy output module is used to generate a course adaptation strategy based on the solution results of the password phase offset data, and output the target sports intangible cultural heritage adapted course accordingly.
[0152] Exemplary computer-readable media:
[0153] Embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps described in the "Exemplary Methods" section above according to the various embodiments of this application.
[0154] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0155] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.
[0156] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.
[0157] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.
[0158] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.
[0159] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.
Claims
1. A method for intelligent adaptation of intangible cultural heritage sports courses based on spatial safety constraints, characterized in that, Includes the following steps: Acquire data on the target sports intangible cultural heritage project, venue characteristics, audience attributes, and equipment specifications, and parse the target sports intangible cultural heritage project data into multiple action units; For each action unit, an out-of-control active window is extracted; the out-of-control active window is the phase interval in which the device has the actual probability of going out of control within a single action cycle; Based on the action unit and the equipment specification data, normal motion envelope data and runaway reachability domain are generated, and the runaway reachability domain is only incorporated into the normal motion envelope data within the phase interval defined by the runaway active window to obtain the phase-gated time-varying risk domain; A site grid is generated based on the site feature data, and a station matrix is generated based on the target number of performers in the audience attribute data. The phase-gated time-varying risk domain is mapped to the site grid according to the coordinates and orientation of the station matrix to generate the global time-varying risk domain for each station. Spatiotemporal joint interferometry detection is performed on adjacent stations to screen out overlapping station pairs that are spatially intersecting and whose associated out-of-control active windows coincide in time; Based on the overlapping station pairs, solve for the password phase offset data that separates the out-of-control active windows of adjacent stations in the time dimension; Based on the solution results of the password phase offset data, a course adaptation strategy is generated, and a target sports intangible cultural heritage adapted course is output accordingly.
2. The intelligent adaptation method for sports intangible cultural heritage courses based on spatial safety constraints according to claim 1, characterized in that, The extraction of the out-of-control active window includes: Acquire the kinematic characteristic data of the device within a single action cycle of the action unit, wherein the kinematic characteristic data of the device includes at least instantaneous velocity data, acceleration data, and grip constraint strength data; Based on the kinematic feature data of the device, the out-of-control phase profile data is calculated, and the out-of-control phase profile data represents the continuous distribution of the out-of-control probability as the action phase changes; The out-of-control phase profile data is truncated using a preset probability threshold. The phase intervals with an out-of-control probability greater than or equal to the preset probability threshold are extracted as out-of-control active windows, and the active duty cycle of the out-of-control active window in the overall action cycle is calculated.
3. The intelligent adaptation method for sports intangible cultural heritage courses based on spatial safety constraints according to claim 1, characterized in that, The generation of normal motion envelope data and uncontrolled reachable domains includes: Normal motion envelope data is generated based on the human range of motion requirements and the basic trajectory requirements of the device in the action unit, and a predetermined number of out-of-control trigger point data are extracted from it. The beginner instability coefficient is calculated based on the audience attribute data and the preset weight model, and the equipment specification correction coefficient is calculated based on the equipment specification data. The runaway trigger point data, the beginner instability coefficient, the equipment specification correction coefficient, and the ground friction parameters in the site feature data are input into a preset runaway simulation algorithm to generate the runaway reachable domain.
4. The intelligent adaptation method for sports intangible cultural heritage courses based on spatial safety constraints according to claim 3, characterized in that, The obtained phase-gated time-varying risk domain includes: Determine whether the current real-time phase of the action is within the phase range defined by the out-of-control active window; If so, the uncontrolled reachable domain, the beginner instability coefficient, and the equipment specification correction coefficient are multiplied to obtain the dynamic extended domain, and the normal motion envelope data are combined with the dynamic extended domain to generate the phase-gated time-varying risk domain.
5. The intelligent adaptation method for sports intangible cultural heritage courses based on spatial safety constraints according to claim 1, characterized in that, The global time-varying risk domain generated for each station includes: Traverse the station matrix and extract the station coordinates and orientation of each station. Using the station coordinates as the origin and the station orientation as the reference direction, perform an affine transformation operation on the phase-gated time-varying risk domain; The phase-gated time-varying risk domain after affine transformation is superimposed onto the absolute coordinate system of the site grid to obtain the global time-varying risk domain.
6. The intelligent adaptation method for sports intangible cultural heritage courses based on spatial safety constraints according to claim 1, characterized in that, The spatiotemporal joint interferometry detection of adjacent stations includes: Extract the spatial geometric envelopes from two adjacent global time-varying risk domains and perform an intersection comparison. If spatial geometric intersection occurs, mark the two adjacent global time-varying risk domains as a geometric interference pair. Under the default phase alignment condition, it is determined whether the two runaway active windows associated with the geometric interference pair coincide in time. If they coincide, it is determined that a real runaway superposition has occurred, and the geometric interference pair is identified as an overlapping station pair.
7. The intelligent adaptation method for sports intangible cultural heritage courses based on spatial safety constraints according to claim 2, characterized in that, The password phase offset data that separates the out-of-control activity windows of adjacent stations in the time dimension includes: Several overlapping station pairs are grouped into overlapping station clusters, the total number of stations in the overlapping station clusters is counted, and the active duty cycle of the corresponding action unit is extracted. Determine whether the active duty cycle is less than or equal to the reciprocal of the total number of stations; If so, then an independent time compensation variable is assigned to each station in the overlapping station cluster, a solution model is constructed with decorrelation constraints as conditions, and the solution model is solved to obtain a set of time compensation variables as password phase offset data; wherein, the decorrelation constraints are used to limit the intersection of the runaway active windows of any adjacent stations after superimposing the time compensation variables to an empty set; If not, the password phase offset data calculation is deemed to have failed.
8. The intelligent adaptation method for sports intangible cultural heritage courses based on spatial safety constraints according to claim 7, characterized in that, The generated course adaptation strategy and the output of target sports intangible cultural heritage adapted courses include: If the password phase offset data is successfully solved, a first course adaptation strategy representing staggered synchronous execution is generated, and a phase-sequence password timing table and a station phase diagram with marked release window staggered execution are generated based on the password phase offset data. If the password phase offset data fails to be solved, and the audience attribute data and the equipment specification data meet the preset grouping conditions, then a second course adaptation strategy representing the group rotation execution is generated. According to the first course adaptation strategy or the second course adaptation strategy, the corresponding visual positioning materials, safety reminder materials and teaching video materials are extracted simultaneously, assembled and output as the target sports intangible cultural heritage adapted course.
9. A smart adaptation system for intangible cultural heritage sports courses based on spatial safety constraints, characterized in that, include: The data acquisition module is used to acquire data on the target sports intangible cultural heritage project, venue characteristics, audience attributes, and equipment specifications, and to parse the target sports intangible cultural heritage project data into multiple action units; The feature window extraction module is used to extract the out-of-control active window for each action unit; the out-of-control active window is the phase interval in which the device has the true probability of losing control within a single action cycle; The time-varying risk domain construction module is used to generate normal motion envelope data and runaway reachability domain based on the action unit and the equipment specification data, and to incorporate the normal motion envelope data into the runaway reachability domain only within the phase interval defined by the runaway active window, thereby obtaining a phase-gated time-varying risk domain; The spatial mapping module is used to generate a site grid based on the site feature data and to generate a station matrix based on the target number of performers in the audience attribute data. The phase-gated time-varying risk domain is mapped to the site grid according to the coordinates and orientation of the station matrix to generate the global time-varying risk domain for each station. The joint interferometry detection module is used to perform spatiotemporal joint interferometry detection on adjacent stations to filter out overlapping station pairs that are spatially intersecting and whose associated out-of-control active windows coincide in time. The phase staggered peak solving module is used to solve the password phase offset data that separates the out-of-control active windows of adjacent stations in the time dimension based on the overlapping station pairs. The strategy output module is used to generate a course adaptation strategy based on the solution results of the password phase offset data, and output the target sports intangible cultural heritage adapted course accordingly.
10. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: When the computer-executable instructions are executed by a processor, they implement the steps of the method as described in any one of claims 1-8.
