Intelligent Scheduling Method for Activities and Events in Sports Complexes

Abstract

The present invention discloses an intelligent scheduling method for activities and events in a sports complex. Through a pose key point network, the busy degree of staff members and whether they are suitable for the current work are judged based on the poses and positions of the staff members, and the staff members are scored accordingly to obtain the staff status rating. By using the staff category score, the staff status rating, and the staff position map, the technical effect of being able to perform personnel scheduling in real time and accurately with the distance of the staff members to the scheduling position, the adaptability of the staff members to the current work, the busy degree of the staff members, and the matching degree of the staff members with the category of the required staff members at the scheduling position as the judgment conditions is achieved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to an intelligent scheduling method for activities and events in a sports complex. Background Art

[0002] Currently, large-scale sports events have a long duration, a tight schedule, involve a large variety and quantity of types of work, and require a large number of various service personnel to carry out reasonable division of labor and cooperation to be completed. Therefore, an effective method must be available to calculate the demand scale of various service personnel and reasonably organize and dispatch these personnel to provide decision-making support for managers. The current calculation of personnel requirements and organization and dispatch of large-scale sports events mainly rely on the experience of managers, and there is still a lack of a strict and efficient scientific decision-making method. The empirical method is difficult to quickly and effectively evaluate the quality of decision-making schemes, so it is easy to cause decision-making deviations or mistakes. When facing new situations or new scenarios, it is also impossible to make scientific, timely, and efficient decision-making responses according to new changes.

[0003] Since a staff member has the ability to undertake multiple work modules. Therefore, during the activities and events in the sports complex, staff members can be flexibly dispatched to perform multiple tasks. However, how to determine whether a staff member is suitable for the current work and the busy or idle state of the staff member, so as to dispatch the staff member is a problem that needs to be solved. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent scheduling method for activities and events in a sports complex to solve the above problems existing in the prior art.

[0005] In a first aspect, an embodiment of the present invention provides an intelligent scheduling method for activities and events in a sports complex, including:

[0006] Obtain the staff location map and the corresponding staff monitoring images at multiple time points; the staff location map represents the locations of the staff corresponding to a time point; the staff monitoring images represent the images containing the staff captured by multiple camera devices at a time point;

[0007] Based on the staff monitoring images at multiple time points through a pose key point network, judge the staff status according to the staff pose to obtain multiple staff key point maps and the pose cycle length; the key points in the staff key point maps represent the positions of the parts in contact with the goods and the parts of the sinking pose; one staff monitoring image at a time point corresponds to multiple staff key point maps at a time point;

[0008] Based on the posture cycle length, the key point maps of the staff at multiple time points, and the position maps of the staff, determine whether the staff is busy or idle, and obtain the staff status rating;

[0009] Based on the staff status rating and the position map of the staff at the current time point, perform personnel scheduling.

[0010] Optionally, the posture key point network includes a human detection network, a key point detection network, and a change detection network.

[0011] Optionally, based on the staff monitoring image, judging the staff status by the staff posture, and obtaining multiple staff key point maps and the posture cycle length, including:

[0012] Input the staff monitoring image into the human detection network to segment the position of the human body and obtain multiple single human body images;

[0013] Input the single human body image into the key point detection network to detect the key parts of the human body, and obtain the first key point image to be judged for exertion and the key point bounding box; the key point bounding box represents a rectangular frame containing the key parts of the human body; the first key point image to be judged for exertion is an image containing key points; the key point is the center point of the key point bounding box;

[0014] Multiple first key point images to be judged for exertion corresponding to the single human body images at multiple time points are obtained for multiple time points;

[0015] Based on the first key point images to be judged for exertion at the multiple time points, detect the changes of the staff key points to obtain the posture cycle length;

[0016] Based on the first key point images to be judged for exertion, the key point bounding boxes, and the posture cycle length at multiple time points, judge the key points in the continuous working state through the change detection network to obtain multiple staff key point maps.

[0017] Optionally, based on the posture cycle length, the key point maps of the staff at multiple time points, and the position maps of the staff, judging whether the staff is busy or idle, and obtaining the staff status rating, including:

[0018] Take the absolute value of the difference between the ordinates of the corresponding key points in the key point maps of the staff at the multiple time points as the key point change value; multiple key point change values are obtained corresponding to multiple key points in one key point map of one staff at one time point;

[0019] Average the multiple key point change values to judge the burden of the work on the staff and obtain the first staff rating;

[0020] Based on the staff position maps at multiple time points, detect the changes in the staff positions to obtain the position cycle length;

[0021] Based on the posture cycle length and the position cycle length, obtain the second staff rating;

[0022] Add the first staff rating and the second staff rating to obtain the staff status rating.

[0023] Optionally, based on the first key points map to be discriminated for exertion, key point bounding boxes, and posture cycle length at multiple time points, through a change detection network, judge the key points in the continuous working state to obtain multiple staff key points maps, including:

[0024] Arrange the first key points maps to be discriminated for exertion at multiple time points into different sets in order of time from early to late according to the posture cycle length to obtain multiple sets of the first key points maps to be discriminated for exertion;

[0025] Input the multiple first key points maps to be discriminated for exertion in the set of the first key points maps to be discriminated for exertion into a working change detection network in order of time from early to late to detect the changes in the key points during the working process and obtain the key point change features;

[0026] Multiple sets of the key points maps to be discriminated for exertion correspond to obtain multiple key point change features;

[0027] Through the change detection network, based on multiple key point change features, multiple sets of the first key points maps to be discriminated for exertion, and the corresponding key point bounding boxes, adjust the positions of the key points to obtain multiple staff key points maps.

[0028] Optionally, the obtaining of the second staff rating based on the posture cycle length and the position cycle length includes:

[0029] Arrange the staff position maps at multiple time points into different sets in order of time from early to late according to the posture cycle length to obtain multiple sets of periodic posture images; each set of periodic posture images contains multiple staff key points maps of a repeated action;

[0030] Calculate the distances between the corresponding key points of the staff key points maps at two adjacent time points in the set of periodic posture images to obtain the key point change values; w - 1 key point change values are obtained corresponding to the w staff key points maps in the set of periodic posture images;

[0031] Cluster the w - 1 key point change values to obtain the clustered key point change values;

[0032] Based on the clustered key point change values and the position cycle length, obtain the second staff rating.

[0033] Optionally, obtaining the second staff rating based on the clustering key point change value and the position cycle length includes:

[0034] Obtain a position change threshold and a key point change threshold;

[0035] If the position cycle length is less than the position change threshold and the clustering key point change value is less than the key point change threshold, set the second staff rating to 0; a second staff rating of 0 indicates that the staff is on break;

[0036] If the position cycle length is less than the position change threshold and the clustering key point change value is greater than or equal to the key point change threshold, set the second staff rating to 0.5; a second staff rating of 0.5 indicates that scheduling can be completed in a short time;

[0037] If the position cycle length is greater than or equal to the position change threshold and the clustering key point change value is greater than or equal to the key point change threshold, set the second staff rating to 0; a second staff rating of 0 indicates that the staff is not suitable for the current position and needs to be scheduled to another position;

[0038] If the position cycle length is greater than or equal to the position change threshold and the clustering key point change value is less than the key point change threshold, set the second staff rating to 1; a second staff rating of 1 indicates that the staff is suitable for the current position and scheduling requires a long time.

[0039] Optionally, through the change detection network, based on multiple key point change features, multiple first sets of key points to be discriminated for exertion maps, and corresponding key point bounding boxes, adjusting the positions of the key points to obtain multiple staff key point maps includes:

[0040] Input the first key points to be discriminated for exertion maps in the first set of key points to be discriminated for exertion maps into the first convolutional network to obtain first convolutional features;

[0041] Input the first convolutional features, the corresponding key point change features, and the corresponding key point bounding boxes into the first neural network to obtain adjustment features;

[0042] Input the adjustment features into the reconstruction network to adjust the positions of the key points within the key point bounding boxes to obtain staff key point maps; the key points in the staff key point maps represent the positions where the human body exerts force;

[0043] One first key point to be discriminated for exertion map corresponds to one staff key point map.

[0044] Optionally, the first key point graph to be discriminated based on the multiple time points, which detects the changes of the key points of the staff to obtain the pose cycle length, includes:

[0045] Obtain multiple segmentation lengths;

[0046] According to the time points from early to late, and based on the segmentation lengths, put the first key point graphs to be discriminated at the multiple time points into different sets to obtain multiple segmented key point graph sets; each segmented key point graph set contains the first key point graphs to be discriminated corresponding to the number of the segmentation lengths;

[0047] Calculate the similarity between the first key point graphs to be discriminated corresponding to the subscripts of the multiple segmented key point graph sets to obtain multiple key point similarity values;

[0048] Take the average of the multiple key point similarity values to obtain the average key point similarity value;

[0049] Multiple segmentation lengths correspond to multiple average key point similarity values;

[0050] Among the multiple average key point similarity values, take the average key point similarity value that is greater than other average key point similarity values as the pose cycle similarity value;

[0051] Take the segmentation length corresponding to the pose cycle similarity value as the pose cycle length.

[0052] Optionally, the personnel scheduling based on the staff status rating and the staff position map at the current time point includes:

[0053] Obtain the staff category score, the number of required staff, and the scheduling position; the staff category score represents the score of the category of the staff required at the scheduling position; the scheduling position represents the position where the staff needs to be scheduled in the current staff position image;

[0054] Obtain the staff position image at the current time point as the current staff position image;

[0055] According to the current staff position image, calculate the distance between the position of the staff at the current time point and the scheduling position to obtain the staff distance;

[0056] Multiply the staff category score, the staff distance, and the staff status rating according to a fixed ratio to obtain the scheduling value;

[0057] Sort the scheduling values from large to small to obtain the sequence to be scheduled;

[0058] Divide the sequence to be scheduled by the number of staff to obtain the scheduling sequence;

[0059] Associate the staff corresponding to the scheduling sequence with the scheduling positions and send scheduling signals.

[0060] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects:

[0061] The embodiments of the present invention also provide an intelligent scheduling method for activities and events in a sports complex.

[0062] In the present invention, since many staff members in a sports complex activity and event are temporarily hired and there is no running-in period with the work they are engaged in, the burden of the current position on the staff is judged according to the changes in the key points of the staff. If the burden is large, it means that the staff is not suitable for the current position and needs to be scheduled. The change characteristics of the key points are judged by detecting the positions of the parts in contact with the goods and the posture parts that sink. For accurate detection, a change detection network is also used. Inside the key point bounding box, the changes in the key points in one working cycle are used to adjust the key points. If the cycle of the staff's position change is less than the position change threshold, it means that the staff can complete the scheduling in a short time. If the length of the position cycle is greater than or equal to the position change threshold, the staff needs a long time to be scheduled.

[0063] In summary, through the pose key point network, the busyness of the staff and whether the staff is suitable for the current work are judged based on the pose and position of the staff, and the staff is scored accordingly to obtain the staff status rating. By using the staff category score, the staff status rating, and the staff position map, the technical effect of being able to perform personnel scheduling in real time and accurately with the distance from the staff to the scheduling position, the adaptability of the staff to the current work, the busyness of the staff, and the matching degree between the staff and the category of the staff required at the scheduling position as the judgment conditions is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 is a flowchart of an intelligent scheduling method for activities and events in a sports complex provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] The present invention will be described in detail below with reference to the accompanying drawings. Embodiment

[0066] As Figure 1 shown, the embodiments of the present invention provide an intelligent scheduling method for activities and events in a sports complex, and the method includes:

[0067] S101: Obtain the location maps of staff at multiple time points and the corresponding staff monitoring images; the staff location maps represent the locations of staff corresponding to a time point; the staff monitoring images represent the images containing staff captured by multiple camera devices at a time point.

[0068] Among them, one time point corresponds to one staff location map and multiple staff monitoring images.

[0069] S102: Through the pose key point network, based on the staff monitoring images at multiple time points, judge the staff status by the staff pose, and obtain multiple staff key point maps and the pose cycle length; the key points in the staff key point maps represent the positions of the parts in contact with the goods and the parts of the sinking pose; one staff monitoring image at a time point corresponds to multiple staff key point maps at a time point.

[0070] S103: Based on the pose cycle length, the staff key point maps at multiple time points and the staff location maps, judge whether the staff is busy or idle, and obtain the staff status rating;

[0071] S104: Based on the staff status rating and the staff location map at the current time point, perform personnel scheduling.

[0072] Optionally, the pose key point network includes a human detection network, a key point detection network, a work change detection network, and a change detection network.

[0073] Optionally, the step of judging the staff status by the staff pose through the pose key point network based on the staff monitoring images at multiple time points to obtain multiple staff key point maps and the pose cycle length includes:

[0074] Input the staff monitoring images into the human detection network to segment the positions of the human bodies, and obtain multiple single human body images.

[0075] Among them, in this embodiment, yolov5 is used for human detection to find the location of a human body, and the human body at this location is extracted to obtain a single human body image.

[0076] Among them, if a staff monitoring image contains p staff members, p single human body images are obtained. P is a natural number greater than 0.

[0077] Input the single human body image into the key point detection network to detect the key parts of the human body, obtaining the first key point image to be judged for exertion force and the key point bounding box; the key point bounding box represents a rectangular border containing the key parts of the human body; the first key point image to be judged for exertion force is an image containing key points; the key point is the center point of the key point bounding box.

[0078] Among them, the first key point image to be judged for exertion force contains one or more key points.

[0079] Among them, the first key point image to be judged for exertion force is an image marked with the key points of the human body. The key points represent the positions where contact is made with the goods or the positions where the posture is lowered due to supporting the goods. In this embodiment, the key points are the elbows, wrists, ankles, and knees.

[0080] The single human body images at multiple time points respectively obtain the first key point images to be judged for exertion force at multiple time points.

[0081] Among them, if there are n staff monitoring images at one time point, then p*n first key point images to be judged for exertion force are obtained at one time point. The single human body images at m time points respectively obtain the first key point images to be judged for exertion force at m time points, that is, the number of the first key point images to be judged for exertion force is p*n*m. n and m are natural numbers greater than 0.

[0082] Based on the first key point images to be judged for exertion force at the multiple time points, detect the changes of the staff key points to obtain the posture cycle length.

[0083] Based on the first key point images to be judged for exertion force at multiple time points, the key point bounding boxes, and the posture cycle length, through the change detection network, judge the key points in the continuous working state to obtain multiple staff key point images.

[0084] Among them, the number of the staff key point images is p*n*m.

[0085] Optionally, based on the posture cycle length, the staff key point images at multiple time points, and the staff position images, judge whether the staff is busy or idle to obtain the staff status rating, including:

[0086] Take the absolute value of the difference between the ordinates of the corresponding key points in the staff key point images at the multiple time points as the key point change value; multiple key point change values are respectively obtained for the multiple key points in one staff key point image at one time point.

[0087] Among them, if there are q key points on the key point map of a staff member, such as 4 key points of the elbow, wrist, ankle, and knee in this embodiment. Then, q key point change values are obtained corresponding to the key point map of a staff member at m time points. p*n key point change values are obtained corresponding to the p*n key point maps of a staff member at m time points. That is, it means that one staff member corresponds to q key point change values, and p*n staff members correspond to p*n*q key point change values. q is a natural number greater than 0.

[0088] Calculate the average value of multiple key point change values, judge the burden on the staff, and obtain the first staff rating.

[0089] Among them, the ordinate of the key point can represent the change of the force on the position of the human key point.

[0090] Based on the staff position maps at multiple time points, detect the change of the staff position to obtain the position cycle length.

[0091] Among them, the method for obtaining the position cycle length is the same as the method for obtaining the posture cycle length.

[0092] Among them, the detecting the change of the staff position based on the staff position maps at multiple time points to obtain the position cycle length includes:

[0093] Obtain multiple position segmentation lengths.

[0094] According to the time points from early to late, and according to the position segmentation length, put the staff position maps at the multiple time points into different sets to obtain multiple segmented position key point map sets; each segmented position key point map set contains the number of staff key point maps corresponding to the position segmentation length;

[0095] Calculate the similarity between the staff key point maps corresponding to the subscripts of the multiple segmented position key point map sets to obtain multiple position key point similarity values.

[0096] Among them, the Euclidean distance is used to calculate the similarity of the positions of the key points in the staff key point map.

[0097] Calculate the average value of the multiple position key point similarity values to obtain the average position key point similarity value;

[0098] Multiple position segmentation lengths correspond to multiple average position key point similarity values;

[0099] Among the multiple average position key point similarity values, take the average position key point similarity value that is greater than the other average position key point similarity values as the position cycle similarity value;

[0100] Take the position segmentation length corresponding to the position cycle similarity value as the position cycle length.

[0101] Based on the posture cycle length and the position cycle length, obtain a second staff rating;

[0102] Add the first staff rating and the second staff rating to obtain a staff status rating.

[0103] Optionally, based on the first key point map to be discriminated, the key point bounding box, and the posture cycle length at multiple time points, use a change detection network to determine the key points in the continuous working state, and obtain multiple staff key point maps, including:

[0104] Arrange the first key point maps to be discriminated at multiple time points into different sets in order of time from early to late according to the posture cycle length, and obtain multiple sets of the first key point maps to be discriminated.

[0105] Among them, the number of elements in the set of key point maps to be discriminated is the same.

[0106] Arrange the multiple first key point maps to be discriminated in the set of the first key point maps to be discriminated into the working change detection network in order of time from early to late, detect the changes of the key points during the working process, and obtain the key point change features.

[0107] Among them, the working change detection network is a temporal convolutional network (TCN).

[0108] Multiple sets of key point maps to be discriminated correspond to obtain multiple key point change features.

[0109] Among them, one set of key point maps to be discriminated corresponds to obtain one key point change feature.

[0110] Use a change detection network to adjust the positions of the key points based on multiple key point change features, multiple sets of the first key point maps to be discriminated, and the corresponding key point bounding boxes, and obtain multiple staff key point maps.

[0111] Optionally, the obtaining of the second staff rating based on the posture cycle length and the position cycle length includes:

[0112] Arrange the staff position maps at multiple time points into different sets in order of time from early to late according to the posture cycle length, and obtain multiple sets of periodic posture images; the set of periodic posture images contains multiple staff key point maps of a repeated action.

[0113] Among them, the number of staff position maps in the multiple sets of periodic posture images is the same.

[0114] Calculate the distances between the corresponding key points of the staff key point maps at two adjacent time points in the periodic pose image set to obtain the key point change values; w - 1 key point change values are obtained corresponding to the w staff key point maps in the periodic pose image set.

[0115] Among them, in this embodiment, the time length between two time points is 5 seconds.

[0116] Cluster the w - 1 key point change values to obtain the clustered key point change values;

[0117] Among them, w is a natural number greater than 0.

[0118] Among them, the k - means method is used for clustering.

[0119] Based on the clustered key point change values and the position cycle length, obtain the second staff rating.

[0120] Optionally, the obtaining the second staff rating based on the clustered key point change values and the position cycle length includes:

[0121] Obtain the position change threshold and the key point change threshold.

[0122] Among them, in this embodiment, the position change threshold is 1.5 meters, and the key point change threshold is 1 centimeter.

[0123] If the position cycle length is less than the position change threshold and the clustered key point change value is less than the key point change threshold, set the second staff rating to 0; the second staff rating of 0 indicates that the staff is resting;

[0124] If the clustered position change value is less than the position change threshold and the clustered key point change value is greater than or equal to the key point change threshold, set the second staff rating to 0.5; the second staff rating of 0.5 indicates that scheduling can be completed in a short time;

[0125] If the position cycle length is greater than or equal to the position change threshold and the clustered key point change value is greater than or equal to the key point change threshold, set the second staff rating to 0; the second staff rating of 0 indicates that the staff is not suitable for the current position and needs to be scheduled to other positions;

[0126] If the position cycle length is greater than or equal to the position change threshold and the clustered key point change value is less than the key point change threshold, set the second staff rating to 1; the second staff rating of 1 indicates that the staff is suitable for the current position and scheduling requires a long time.

[0127] Optionally, the change detection network adjusts the positions of the key points based on multiple key point change features, multiple first key point graphs to be discriminated for exertion, and corresponding key point bounding boxes, and obtains multiple staff key point graphs, including:

[0128] Input the first key point graph to be discriminated for exertion in the first key point graph set to be discriminated for exertion into the first convolutional network to obtain a first convolutional feature.

[0129] Among them, the first convolutional network is a Convolutional Neural Networks (CNN).

[0130] Input the first convolutional feature, the corresponding key point change feature, and the corresponding key point bounding box into the first neural network to obtain an adjustment feature.

[0131] Among them, the first convolutional feature and the corresponding key point change feature are one-dimensional vectors stretched in ascending order of row numbers, ascending order of column numbers, and ascending order of channel numbers.

[0132] Among them, the first neural network is a Fully-connected neural network (FCNN).

[0133] Input the adjustment feature into the reconstruction network, adjust the positions of the key points within the key point bounding box, and obtain a staff key point graph; the key points in the staff key point graph represent the positions where the human body exerts force.

[0134] Among them, the reconstruction network is a network obtained by performing deconvolution on a Convolutional Neural Networks (CNN).

[0135] Among them, the first convolutional network, the first neural network, and the reconstruction network are trained with the points under the pressure of heavy objects marked at multiple time points as key points.

[0136] One first key point graph to be discriminated for exertion corresponds to one staff key point graph.

[0137] Optionally, the detection of the changes in the staff key points based on the first key point graphs to be discriminated for exertion at the multiple time points to obtain the pose cycle length includes:

[0138] Obtain multiple segmentation lengths;

[0139] Among them, in this embodiment, the position segmentation lengths are 1, 2, 3, 4, 5, 6, 7, 8, 9, 10.

[0140] According to the time points from early to late, and according to the segmentation length, put the first key points to be discriminated for exertion at the multiple time points into different sets to obtain multiple sets of segmented key points; each set of segmented key points contains the number of first key points to be discriminated for exertion corresponding to the segmentation length.

[0141] Calculate the similarity between the first key points to be discriminated for exertion with corresponding subscripts in the multiple sets of segmented key points to obtain multiple key point similarity values.

[0142] Take the average of the multiple key point similarity values to obtain the average key point similarity value.

[0143] Multiple segmentation lengths correspond to multiple average key point similarity values.

[0144] Among the multiple average key point similarity values, take the average key point similarity value that is greater than other average key point similarity values as the pose period similarity value.

[0145] Take the segmentation length corresponding to the pose period similarity value as the pose period length.

[0146] Optionally, the personnel scheduling based on the staff status rating and the staff position map at the current time point includes:

[0147] Obtain the staff category score, the required number of staff, and the scheduling position; the staff category represents the score of the category of staff required for the scheduling position; the scheduling position represents the position where the staff needs to be scheduled in the current staff position image.

[0148] Wherein, in this embodiment, if it is the same as the category of staff required for the scheduling position, set the staff category score to 1. If it is different from the category of staff required for the scheduling position, set the staff category score to 0.5.

[0149] Obtain the staff position image at the current time point as the current staff position image.

[0150] According to the current staff position image, calculate the distance between the position of the staff at the current time point and the scheduling position to obtain the staff distance.

[0151] Among them, the Euclidean distance method is used to calculate the distance.

[0152] Multiply the staff category score, the staff distance, and the staff status rating according to a fixed ratio to obtain the scheduling value.

[0153] Among them, in this embodiment, the fixed ratios corresponding to the staff category score, the staff distance, and the staff status rating are 0.3:0.4:0.3, that is, it means that the sum of the product of the staff category score multiplied by 0.3, the product of the staff distance multiplied by 0.4, and the product of the staff status rating multiplied by 0.3 is used as the scheduling value.

[0154] Sort the scheduling values from largest to smallest to obtain the sequence to be scheduled;

[0155] Divide the sequence to be scheduled according to the number of staff to obtain the scheduling sequence.

[0156] Among them, in this embodiment, the subscript of the sequence to be scheduled starts from 0. The scheduling sequence is the sequence obtained by dividing the sequence to be scheduled with the subscript 0 as the starting point and the subscript corresponding to the difference between the number of staff minus one as the end point. The number of elements in the scheduling sequence is equal to the number of staff.

[0157] Associate the staff corresponding to the scheduling sequence with the scheduling positions and send scheduling signals.

[0158] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings provided herein. The structure required to construct such a system will be apparent from the above description. In addition, the present invention is not directed to any particular programming language. It should be understood that the content of the present invention described herein can be implemented using various programming languages, and the description of the specific language above is for the purpose of disclosing the best mode of the present invention.

[0159] Each component embodiment of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the device according to the embodiments of the present invention. The present invention can also be implemented as a device or device program for executing part or all of the methods described herein (for example, a computer program and a computer program product). Such a program for implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

Claims

1. A method for intelligent scheduling of activities and events for sports complexes, characterized in that: include: Obtaining worker location maps and corresponding worker monitoring images at multiple time points; The staff position graph represents the position of the staff corresponding to a time point; The staff monitoring image refers to an image containing staff taken by multiple cameras at a time point; Through the posture key point network, based on the staff monitoring images at multiple time points, the staff status is judged by the staff posture, and multiple staff key point graphs and posture cycle lengths are obtained; the key points in the staff key point graph represent the positions of the parts in contact with the goods and the positions of the sinking posture parts; one staff monitoring image at one time point corresponds to multiple staff key point graphs at one time point; Based on the length of the posture cycle, the key point diagram of the staff at multiple time points and the staff position diagram, it is judged whether the staff is busy or idle, and the staff status rating is obtained; Personnel scheduling is performed based on the worker status rating and the worker location map at the current time point.

2. The method for intelligent scheduling of activities and events for sports complexes according to claim 1 is characterized in that: The posture key point network includes a human body detection network, a key point detection network, a work change detection network and a change detection network.

3. The method for intelligent scheduling of activities and events for sports complexes according to claim 2 is characterized in that: The method uses a posture key point network to judge the status of a worker based on the worker monitoring images at multiple time points, and obtains multiple worker key point graphs and posture cycle lengths, including: Inputting the worker monitoring image into a human body detection network, segmenting the position of the human body, and obtaining a plurality of single human body images; Input the single human body image into a key point detection network, detect key parts of the human body, and obtain a first key point image to be determined and a key point boundary box; the key point boundary box represents a rectangular frame containing key parts of the human body; the first key point image to be determined is an image containing key points; the key point is the center point of the key point boundary box; A single human body image at multiple time points corresponds to obtaining a first force key point map to be determined at multiple time points; Based on the first force key point graph to be determined at the plurality of time points, detecting changes in the key points of the staff member to obtain the posture cycle length; Based on the first key point graph to be determined at multiple time points, the key point bounding box and the posture cycle length, the key points of the continuous working state are determined through the change detection network to obtain multiple key point graphs of the staff.

4. The method for intelligent scheduling of activities and events for sports complexes according to claim 1 is characterized in that: The method of judging whether a worker is busy or idle based on the posture cycle length, the worker key point graph at multiple time points, and the worker position graph, and obtaining a worker status rating includes: The absolute value of the difference between the ordinates of the corresponding key points in the staff key point graphs at the multiple time points is used as the key point change value; multiple key point change values ​​are correspondingly obtained for multiple key points in a staff key point graph at a time point; The change values ​​of multiple key points are averaged to determine the burden of the work on the staff and obtain the first staff rating; Based on the worker position graphs at multiple time points, detect the change of worker positions and obtain the position cycle length; obtaining a second staff rating based on the attitude cycle length and the position cycle length; The first staff rating is added to the second staff rating to obtain a staff status rating.

5. The method for intelligent scheduling of activities and events for sports complexes according to claim 3 is characterized in that: The first force key point map to be determined based on multiple time points, the key point boundary box and the posture cycle length, through the change detection network, determines the key points of the continuous working state, and obtains multiple staff key point maps, including: According to the time from morning to night and the length of the posture cycle, the first key point graphs to be determined at multiple time points are sequentially filled into different sets to obtain multiple sets of first key point graphs to be determined; Inputting a plurality of first key point graphs to be determined in the first key point graph set to a work change detection network in order from morning to night, detecting changes of key points in the work process, and obtaining key point change features; A plurality of key point graph sets to be determined correspond to obtaining a plurality of key point change features; Through the change detection network, based on multiple key point change features, multiple first key point map sets to be determined and corresponding key point bounding boxes, the positions of key points are adjusted to obtain multiple staff key point maps.

6. The method for intelligent scheduling of activities and events for sports complexes according to claim 4 is characterized in that: The step of obtaining a second staff rating based on the posture cycle length and the position cycle length comprises: According to the time from morning to night and the length of the posture cycle, the position images of the staff at multiple time points are sequentially filled into different sets to obtain multiple periodic posture image sets; the periodic posture image sets include multiple key point images of the staff for a repeated action; Calculate the distance between the key points corresponding to the key point graphs of the staff at two adjacent time points in the periodic posture image set to obtain the key point change value; obtain w-1 key point change values ​​corresponding to the w key point graphs of the staff in the periodic posture image set; Cluster the w-1 key point change values ​​to obtain the clustered key point change values; Based on the cluster key point change values ​​and location cycle lengths, a second staff rating is obtained.

7. The method for intelligent scheduling of activities and events for sports complexes according to claim 6 is characterized in that: The second staff rating is obtained based on the cluster key point change value and the position cycle length, including: Get the position change threshold and key point change threshold; If the position cycle length is less than the position change threshold, and the cluster key point change value is less than the key point change threshold, the second staff rating is set to 0; the second staff rating of 0 indicates that the staff is resting; If the position cycle length is less than the position change threshold, and the cluster key point change value is greater than or equal to the key point change threshold, the second worker rating is set to 0.5; the second worker rating of 0.5 indicates that the scheduling can be completed in a short time; If the position cycle length is greater than or equal to the position change threshold, and the cluster key point change value is greater than or equal to the key point change threshold, the second staff rating is set to 0; the second staff rating of 0 indicates that the staff is not suitable for the current position and needs to be dispatched to other positions; If the position cycle length is greater than or equal to the position change threshold, and the cluster key point change value is less than the key point change threshold, the second staff rating is set to 1; the second staff rating of 1 indicates that the staff is suitable for the current position and scheduling requires a long time.

8. The method for intelligent scheduling of activities and events for sports complexes according to claim 5 is characterized in that: The change detection network is used to adjust the positions of the key points based on the multiple key point change features, the multiple first force key point graph sets to be determined and the corresponding key point bounding boxes to obtain multiple staff key point graphs, including: Inputting the first key point graph to be determined in the first set of key point graphs to be determined into a first convolutional network to obtain a first convolutional feature; Inputting the first convolution feature, the corresponding key point change feature and the corresponding key point bounding box into a first neural network to obtain an adjustment feature; Inputting the adjusted features into a reconstruction network, adjusting the positions of the key points within the key point boundary box, and obtaining a worker key point map; the key points in the worker key point map represent positions where the human body exerts force; A first key point diagram of force to be determined corresponds to a key point diagram of a staff member.

9. The method for intelligent scheduling of activities and events for sports complexes according to claim 3 is characterized in that: The first force key point map to be determined based on the multiple time points detects changes in the key points of the staff member to obtain the posture cycle length, including: Get multiple split lengths; According to the time points from early to late, and according to the segmentation length, the first key point graphs to be determined at the multiple time points are put into different sets to obtain multiple segmentation key point graph sets; the segmentation key point graph sets include the first key point graphs to be determined corresponding to the segmentation length; Calculate the similarity between the first force key point graphs to be determined corresponding to the subscripts of the plurality of segmentation key point graph sets to obtain a plurality of key point similarity values; The average of multiple key point similarity values ​​is calculated to obtain an average key point similarity value; Multiple segmentation lengths correspond to multiple average key point similarity values; Among multiple average key point similarity values, an average key point similarity value that is greater than other average key point similarity values ​​is used as a posture cycle similarity value; The segmentation length corresponding to the posture cycle similarity value is taken as the posture cycle length.

10. The method for intelligent scheduling of activities and events for sports complexes according to claim 1, characterized in that: The personnel scheduling based on the worker status rating and the worker location map at the current time point includes: Obtaining a worker category score, a required number of workers, and a dispatch position; the worker category score indicates a score of a category of workers required for the dispatch position; the dispatch position indicates a position of a worker to be dispatched in a current worker position image; Obtaining a staff position image at a current time point as a current staff position image; According to the current worker position image, the distance between the worker's position at the current time point and the scheduling position is calculated to obtain the worker distance; According to the worker category score, worker distance and worker status rating, the worker category score, worker distance and worker status rating are multiplied according to a fixed ratio to obtain a scheduling value; Sort the scheduling values ​​from large to small to obtain the sequence to be scheduled; Divide the sequence to be dispatched by the number of staff members to obtain the dispatch sequence; Associate the staff corresponding to the scheduling sequence with the scheduling position and send a scheduling signal.

Images