Intelligent sports event operation management method based on block chain

Abstract

The invention discloses an intelligent sports event operation management method based on a block chain. And a venue connected graph is constructed to judge the competition venues where the dispatching numbers can reach, so that the confidentiality and safety of the competition venues are enhanced. And enhancing the schedulable image of the competition venue in space and time to obtain an enhanced schedulable three-dimensional image. A to-be-dispatched state is acquired by using the enhanced dispatchable three-dimensional image to judge whether idle personnel or instruments exist in other competition venues except the serial number of the venue to be dispatched. An adjustable linear distance value is obtained by adopting an enhanced schedulable three-dimensional image to judge the working state of a person or an instrument, so that the person or the instrument working easily can be scheduled. The working states of all personnel or instruments in the competition venue, the working state of the personnel or instruments corresponding to one dispatching number, and the confidentiality and safety of the venue are considered.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a blockchain-based intelligent operation and management method for sports events. Background Art

[0002] At present, sports venues generally include multiple venues with different functions, such as basketball halls, ice hockey halls, track and field halls, etc. Multiple venues allow one person to work in multiple venues and reuse one piece of equipment. The management of the stadium is done manually, which is difficult and inefficient. Summary of the invention

[0003] The purpose of the present invention is to provide a blockchain-based sports event intelligent operation and management method and system to solve the above-mentioned problems existing in the prior art.

[0004] The embodiment of the present invention provides a blockchain-based intelligent operation and management method for sports events, including: Obtain a point map of the event venue, n*m images of event venues that can be dispatched, and corresponding dispatch numbers; the point map of the event venue represents a point map in which the geographical location of the event venue is represented by a midpoint; the image of the event venue that can be dispatched represents an image containing multiple dispatchable personnel or equipment; n represents n time points, and one time point corresponds to m images of the event venue that can be dispatched; Through a schedulable time-space enhancement network, based on n*m schedulable images of the event venue, an enhanced schedulable three-dimensional image is obtained; the enhanced schedulable three-dimensional image representation includes enhanced time and space positions; Based on the enhanced dispatchable three-dimensional image, the movement state of the personnel or equipment is detected to obtain a state to be dispatched; the state to be dispatched indicates the priority of the dispatchable personnel or equipment that can be dispatched; According to the dispatch number, the event venues accessible to the detection personnel or equipment are obtained to obtain a venue connectivity map; Based on the enhanced schedulable three-dimensional image, the correlation relationship of the dispatch number is detected to obtain an adjustable straight-line distance value; the adjustable straight-line distance value indicates the degree of tortuosity of the movement of the dispatch number; Personnel or equipment scheduling is performed based on the adjustable straight-line distance value, the status to be scheduled and the venue connectivity diagram.

[0005] Optionally, the detecting the association relationship of the scheduling numbers based on the enhanced schedulable three-dimensional image to obtain the adjustable straight-line distance value includes: Find the positions of the scheduling numbers in the enhanced schedulable three-dimensional image at multiple time points to obtain a scheduling number set; obtain multiple scheduling number sets corresponding to the multiple scheduling numbers; The dispatch number set and the corresponding time point are fitted to construct a three-dimensional straight line to obtain an adjustable straight line; multiple dispatch number sets correspond to multiple adjustable straight lines; Detecting the distance from the value in the dispatch number set to the adjustable straight line to obtain the adjustable straight line distance value; According to the adjustable straight line, a first slope, a second slope and a first intercept are obtained; Based on the first intercept, the first slope and the second slope, the relationship between the position change of the scheduling number is detected and an association relationship is constructed.

[0006] Optionally, the schedulable time-space enhancement network includes a time convolutional network, a first convolutional network, a first neural network and a reconstruction network.

[0007] Optionally, obtaining an enhanced schedulable three-dimensional image based on the schedulable image of the event venue through a schedulable time-space enhancement network includes: Based on the schedulable image of the event venue, a first marked enhanced image is obtained; the first marked enhanced image represents an image in which the positions of schedulable personnel or equipment are marked and enhanced in space; Inputting the first marked enhanced images at multiple time points into a temporal convolutional network, detecting the change of the position of the scheduling number over time, and obtaining a first change feature; The midpoint of the dispatchable position in the first marker enhanced image of two adjacent time points is obtained to obtain a center position image; the center position image represents the position of the dispatch number corresponding to the time point between the two adjacent time points under uniform linear motion; Inputting the center position image into a first convolutional network to extract features to obtain middle position features; Inputting the first change feature and the intermediate position feature into a first neural network, and adjusting the intermediate position feature using the first change feature to obtain an updated feature; Inputting the updated features into a reconstruction network, converting one dimension into two dimensions, and obtaining an adjusted intermediate image; Arrange the plurality of adjusted intermediate images and the first marked enhanced image in order from early to late time points to obtain an enhanced schedulable three-dimensional image.

[0008] Optionally, the training process of the schedulable time-space enhancement network includes: Acquire first marked enhanced images corresponding to multiple historical time points as historical images; Among the historical images corresponding to multiple time points, find the historical images of three adjacent time points as a historical image set; According to the order of time points from early to late, the historical image corresponding to the time point between the three time points in the historical image set is used as the annotated image; Using two historical images in the historical image set other than the annotated image as training images; Inputting the first labeled enhanced image into a schedulable temporal and spatial enhancement network to obtain a training adjusted intermediate image; The loss is calculated by adjusting the position of the corresponding scheduling number in the training intermediate image and the annotated image, and the schedulable time-space enhancement network is trained.

[0009] Optionally, obtaining a first marked enhanced image based on the event venue schedulable image includes: Based on the schedulable image of the event venue, detecting the center point of a person or equipment and expanding the center point to obtain a first expanded area; Inputting the event venue schedulable image into an enhancement network to perform image enhancement to obtain a first enhanced schedulable image; Obtain n*m first enhanced schedulable images corresponding to n time points; Inputting the first enhanced schedulable image into a schedulable detection network, detecting the positions of personnel or equipment that can be scheduled after the image enhancement, and obtaining a plurality of second schedulable detection positions; one second schedulable detection position corresponds to one first enlarged area; If the second schedulable detection position is not in the first enlarged area, the midpoint of the first enlarged area is used to replace the second schedulable detection position to obtain a schedulable position; the schedulable position represents the replaced or unreplaced second schedulable detection position; The schedulable position is marked on the first enhanced schedulable image to obtain a first marked enhanced image; and n*m first enhanced schedulable images correspond to obtaining n*m first marked enhanced images.

[0010] Optionally, the detecting the center point of a person or a device and expanding the center point based on the schedulable image of the event venue to obtain a first expanded area includes: Inputting the schedulable image of the event venue into a schedulable detection network, detecting the positions of schedulable personnel or equipment, and obtaining a plurality of first schedulable detection positions; Divide the length of the first enhanced schedulable image by the length of the event venue schedulable image to obtain an enhancement ratio; According to the enhancement ratio, the first schedulable detection position is expanded to obtain a first expanded area.

[0011] Optionally, the detecting the relationship between the position changes of dispatchable personnel or equipment based on the first intercept, the first slope, and the second slope, and constructing the association relationship includes: If the absolute value of the subtraction of the first slopes corresponding to the two adjustable straight lines is less than the first slope threshold, the absolute value of the subtraction of the second slopes is less than the second slope threshold, and the absolute value of the subtraction of the first intercepts is less than the first intercept threshold, the two adjustable straight lines are added to the cluster set; taking the adjustable straight line in the cluster set as the first adjustable straight line; Using the adjustable straight lines among the plurality of adjustable straight lines except the adjustable straight lines in the cluster set as second adjustable straight lines; The absolute value of the first slope corresponding to the first adjustable straight line minus the first slope corresponding to the second adjustable straight line is taken as the first phase difference value; taking the absolute value of the second slope corresponding to the second adjustable straight line minus the second slope corresponding to the first adjustable straight line as the second phase difference value; The absolute value of the first intercept corresponding to the second adjustable straight line subtracted from the first intercept corresponding to the first adjustable straight line is taken as the third phase difference value; Adding the first phase difference value, the second phase difference value and the third phase difference value in proportion to obtain a total phase difference value; The p adjustable straight lines in the cluster set and the q adjustable straight lines outside the cluster set correspond to obtain p*q total phase difference values; The total phase difference value among the p*q total phase difference values ​​that is smaller than other total phase difference values ​​is taken as a similar total phase difference value; If the first phase difference value corresponding to the total phase difference value is less than the first slope threshold, the second phase difference value is less than the second slope threshold, and the third phase difference value is less than the first intercept threshold, the adjustable straight line corresponding to the similar total phase difference value is added to the cluster set; Build associations between adjustable lines in a cluster set.

[0012] Optionally, the detecting the motion state of a person or a device based on the enhanced dispatchable three-dimensional image to obtain a state to be dispatched includes: Inputting the enhanced dispatchable three-dimensional image into the motion position discrimination network, judging the movement rate of dispatchable personnel or equipment, and obtaining multiple dispatchable motion values; one dispatch number corresponds to one dispatchable motion value; According to the geographical locations corresponding to the event venue point map, multiple dispatchable motion values ​​are divided into multiple position change sets; one point in the event venue point map corresponds to one position change set; the position change set represents the position change value corresponding to the corresponding dispatch number in one event venue; The multiple schedulable motion values ​​in the position change set are input into the predicted position change network, the state of position change in a competition venue is detected, and the state to be scheduled is obtained; the state to be scheduled includes a state requiring scheduling, a state capable of being scheduled, and a balanced state.

[0013] Optionally, the scheduling of personnel or equipment based on the adjustable straight-line distance value, the status to be scheduled and the venue connectivity diagram includes: Obtaining the dispatch quantity and the number of the venue to be dispatched; the dispatch quantity indicates the number of personnel or equipment to be dispatched; the number of the venue to be dispatched indicates the number of the event venue where personnel or equipment needs to be dispatched; According to the status to be dispatched, find the event venues that can be dispatched and get the number of the dispatchable venues; In the event venues corresponding to the schedulable venue numbers, multiple adjustable straight-line distance values ​​are arranged from small to large to obtain an adjustable straight-line distance ranking; Sequentially obtain the dispatch number in the adjustable straight-line distance sorting and the dispatch number associated with the dispatch number as the first prepared dispatch number; According to the venue connectivity map, determine whether the first preparation scheduling number can be moved to the event venue corresponding to the schedulable venue number, and if so, set the first preparation scheduling number as the preparation scheduling number; The quantity of the prepared dispatch number is used as the prepared dispatch quantity; If the prepared scheduling quantity is greater than or equal to the scheduling quantity, the prepared scheduling number is sent.

[0014] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects: The embodiment of the present invention also provides a blockchain-based intelligent operation and management method for sports events.

[0015] The present invention constructs a venue connectivity diagram to determine the event venues that can be reached by the dispatch number, thereby enhancing the confidentiality and security of the event venues. The schedulable image of the event venue is enhanced in space and time to obtain an enhanced schedulable three-dimensional image. The enhanced schedulable three-dimensional image is used to obtain the state to be dispatched to determine whether there are idle personnel or equipment in other event venues except the venue number to be dispatched. The enhanced schedulable three-dimensional image is used to obtain the adjustable straight-line distance value to determine the working state of the personnel or equipment, so that the personnel or equipment with easy work can be dispatched. The working state of all the personnel or equipment in the event venue, the working state of the personnel or equipment corresponding to a dispatch number, and the confidentiality and security of the venue are considered. The technical effect of accurately utilizing personnel or equipment, making the dispatch more in line with the needs of the event venue, and reducing costs is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a blockchain-based sports event intelligent operation and management method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The present invention will be described in detail below in conjunction with the accompanying drawings. Example

[0018] like Figure 1 As shown, an embodiment of the present invention provides a blockchain-based intelligent operation and management method for sports events, the method comprising: S101: Obtain a point map of event venues, n*m schedulable images of event venues and corresponding scheduling numbers; the point map of event venues represents a point map in which the geographical location of the event venues is represented by a midpoint; the schedulable image of the event venue represents an image containing multiple schedulable personnel or equipment; n represents n time points, and one time point corresponds to m schedulable images of the event venues.

[0019] The dispatch number indicates the number of the person or equipment that can be dispatched.

[0020] Wherein, n and m are natural numbers greater than 0.

[0021] The event venue personnel image also indicates the locations of dispatchable personnel or equipment.

[0022] The venue point map is a binary image, and a point in the binary image represents a location of a venue mapped to a two-dimensional image by a geographical location. The venue personnel image is a two-dimensional image of the interior of the venue taken by a camera.

[0023] S102: Obtain an enhanced schedulable three-dimensional image based on n*m schedulable images of the event venues through a schedulable time-space enhancement network; the enhanced schedulable three-dimensional image representation includes enhanced time and space positions.

[0024] The enhanced schedulable three-dimensional image also indicates changes in positions corresponding to multiple scheduling numbers at a time point.

[0025] The row of the enhanced schedulable three-dimensional image represents a time point, and the length and width represent the length and width of the enhanced schedulable image. An enhanced schedulable image corresponding to the enhanced schedulable three-dimensional image includes multiple schedulable positions.

[0026] S103: Based on the enhanced dispatchable three-dimensional image, the movement state of the personnel or equipment is detected to obtain a state to be dispatched; the state to be dispatched indicates the priority of the dispatchable personnel or equipment to be dispatched.

[0027] S104: According to the dispatch number, the event venues accessible to personnel or equipment are detected to obtain a venue connectivity map.

[0028] The positions corresponding to the two event venues in the venue connectivity graph are set to 1, indicating that the scheduling number can be moved from one event venue to another.

[0029] S105: Based on the enhanced schedulable three-dimensional image, detect the association relationship of the scheduling number to obtain an adjustable straight-line distance value; the adjustable straight-line distance value represents the degree of tortuosity of movement of the scheduling number.

[0030] S106: Perform personnel or equipment scheduling based on the adjustable straight-line distance value, the status to be scheduled and the venue connectivity diagram.

[0031] Optionally, the detecting the association relationship of the scheduling numbers based on the enhanced schedulable three-dimensional image to obtain the adjustable straight-line distance value includes: Find the positions of the scheduling numbers in the enhanced schedulable three-dimensional image at multiple time points to obtain a scheduling number set; obtain multiple scheduling number sets corresponding to the multiple scheduling numbers; The scheduling number set and the corresponding time point are fitted to construct a three-dimensional straight line to obtain an adjustable straight line; multiple scheduling number sets correspond to multiple adjustable straight lines.

[0032] In this embodiment, the least square method is used for fitting.

[0033] The distance from the value in the scheduling number set to the adjustable straight line is detected to obtain the adjustable straight line distance value.

[0034] According to the adjustable straight line, a first slope, a second slope and a first intercept are obtained.

[0035] In this embodiment, in the three-dimensional coordinate system, the first slope is the slope between the x-axis and the z-axis, the second slope is the slope between the y-axis and the z-axis, and the first intercept represents the length of the z-axis from the origin at the position where the x-axis is 0 and the y-axis is 0.

[0036] Based on the first intercept, the first slope and the second slope, the relationship between the position change of the scheduling number is detected and an association relationship is constructed.

[0037] Optionally, the schedulable time-space enhancement network includes a time convolutional network, a first convolutional network, a first neural network and a reconstruction network.

[0038] Optionally, obtaining an enhanced schedulable three-dimensional image based on the schedulable image of the event venue through a schedulable time-space enhancement network includes: Based on the schedulable image of the event venue, a first marked enhanced image is obtained; the first marked enhanced image represents an image in which the positions of schedulable personnel or equipment are marked and enhanced in space; The first marked enhanced images at multiple time points are input into the temporal convolutional network to detect the change of the position of the scheduling number over time and obtain the first change feature.

[0039] Among them, the temporal convolutional network (TCN).

[0040] Among them, the positions of different dispatchable personnel or equipment change differently with time points.

[0041] The first marked enhanced images at multiple time points are input into the target tracking network to track the positions of dispatchable personnel or equipment changing with time and obtain tracking features.

[0042] Among them, the target tracking network is a multi-target tracking algorithm (DeepSORT) The midpoint of the schedulable position in the first marked enhanced image of two adjacent time points is obtained to obtain a center position image; the center position image represents the position of the scheduling number corresponding to the time point between two adjacent time points under uniform linear motion.

[0043] The center position image is input into the first convolutional network to extract features to obtain middle position features.

[0044] Among them, the first convolutional network is a convolutional neural network (CNN).

[0045] The first change feature and the intermediate position feature are input into a first neural network, and the intermediate position feature is adjusted using the first change feature to obtain an updated feature.

[0046] Among them, the first neural network is a fully connected neural network (Fully Connected Neural Network, FCN).

[0047] The updated features are input into a reconstruction network, and the one-dimensional image is converted into a two-dimensional image to obtain an adjusted intermediate image.

[0048] Wherein, the reconstruction network is a convolutional neural network (CNN) that performs deconvolution.

[0049] Arrange the plurality of adjusted intermediate images and the first marked enhanced image in order from early to late time points to obtain an enhanced schedulable three-dimensional image.

[0050] Optionally, the training process of the schedulable time-space enhancement network includes: Acquire first marked enhanced images corresponding to multiple historical time points as historical images; Among the historical images corresponding to multiple time points, historical images of three adjacent time points are found as a historical image set.

[0051] If the time points corresponding to the historical images in the historical image set are set as the first time point, the second time point and the third time point from early to late, the first time point is adjacent to the second time point, and the second time point is adjacent to the third time point.

[0052] According to the order of time points from early to late, the historical image corresponding to the time point between the three time points in the historical image set is used as the labeled image.

[0053] For example, the historical image corresponding to the second time point is set as the annotated image.

[0054] Two historical images in the historical image set except the annotated image are used as training images.

[0055] Inputting the first labeled enhanced image into a schedulable temporal and spatial enhancement network to obtain a training adjusted intermediate image; The loss is calculated by adjusting the position of the corresponding scheduling number in the training intermediate image and the annotated image, and the schedulable time-space enhancement network is trained.

[0056] Among them, the cross entropy loss function is used to calculate the loss.

[0057] Optionally, obtaining a first marked enhanced image based on the event venue schedulable image includes: Based on the schedulable image of the event venue, the center point of the person or equipment is detected and expanded to obtain a first expanded area.

[0058] The event venue schedulable image is input into an enhancement network to perform image enhancement to obtain a first enhanced schedulable image.

[0059] The enhanced network is a super-resolution network, and in this embodiment, it is a super-resolution convolutional neural network (SRCNN).

[0060] At n time points, n*m first enhanced schedulable images are correspondingly obtained.

[0061] Inputting the first enhanced schedulable image into a schedulable detection network, detecting the positions of personnel or equipment that can be scheduled after the image enhancement, and obtaining a plurality of second schedulable detection positions; one second schedulable detection position corresponds to one first enlarged area; If the second schedulable detection position is not in the first enlarged area, the midpoint of the first enlarged area replaces the second schedulable detection position to obtain a schedulable position; the schedulable position represents the replaced or non-replaced second schedulable detection position.

[0062] If the second schedulable detection position is in the first enlarged area, the second schedulable detection position is used as the schedulable position. If the second schedulable detection position is not in the first enlarged area, the midpoint of the first enlarged area is used as the schedulable position.

[0063] The schedulable position is marked on the first enhanced schedulable image to obtain a first marked enhanced image; and n*m first enhanced schedulable images correspond to obtaining n*m first marked enhanced images.

[0064] Optionally, the detecting the center point of a person or a device and expanding the center point based on the schedulable image of the event venue to obtain a first expanded area includes: The schedulable image of the event venue is input into a schedulable detection network to detect positions of schedulable personnel or equipment, thereby obtaining a plurality of first schedulable detection positions.

[0065] The schedulable detection network is a target detection network, which is a yolov5 model in this embodiment.

[0066] Divide the length of the enhanced schedulable image by the length of the event venue schedulable image to obtain an enhancement ratio; According to the enhancement ratio, the first schedulable detection position is expanded to obtain a first expanded area.

[0067] Among them, if the enhancement ratio is 3, the 8 pixel points around the first schedulable detection position and the pixel points corresponding to the first schedulable detection position form a 3*3 area as the first enlarged area.

[0068] By the above method, the position of a person or a device is found in the schedulable image of the event venue as the first schedulable detection position, and the first schedulable detection position is enlarged to obtain a first enlarged area. The first enlarged area is used as a restriction condition for the position of an enhanced image detection, so that the position of the person or the device found by the enhanced image can be more accurate.

[0069] Optionally, the detecting the relationship between the position changes of dispatchable personnel or equipment based on the first intercept, the first slope, and the second slope, and constructing the association relationship includes: If the absolute value of the subtraction of the first slopes corresponding to the two adjustable straight lines is less than the first slope threshold, the absolute value of the subtraction of the second slopes is less than the second slope threshold, and the absolute value of the subtraction of the first intercepts is less than the first intercept threshold, the two adjustable straight lines are added to the cluster set.

[0070] The first slope threshold is 0.1, the second slope threshold is 0.1, and the first intercept threshold is 2. The schedulable image size of the event venue is 512*512.

[0071] taking the adjustable straight line in the cluster set as the first adjustable straight line; Using the adjustable straight lines among the plurality of adjustable straight lines except the adjustable straight lines in the cluster set as second adjustable straight lines; The absolute value of the first slope corresponding to the first adjustable straight line minus the first slope corresponding to the second adjustable straight line is taken as the first phase difference value; taking the absolute value of the second slope corresponding to the second adjustable straight line minus the second slope corresponding to the first adjustable straight line as the second phase difference value; The absolute value of the first intercept corresponding to the second adjustable straight line subtracted from the first intercept corresponding to the first adjustable straight line is taken as the third phase difference value; The first phase difference value, the second phase difference value and the third phase difference value are added in proportion to obtain a total phase difference value.

[0072] In this embodiment, the ratio is 0.4*0.4*0.2. The sum of the product of the first phase difference value multiplied by 0.4 plus the product of the second phase difference value multiplied by 0.4 plus the product of the third phase difference value multiplied by 0.2 is the total phase difference value.

[0073] The p adjustable straight lines in the cluster set and the q adjustable straight lines outside the cluster set correspond to obtain p*q total phase difference values.

[0074] Wherein, p and q are natural numbers greater than 0.

[0075] The total phase difference value among the p*q total phase difference values ​​that is smaller than other total phase difference values ​​is taken as a similar total phase difference value; If the first phase difference value corresponding to the total phase difference value is less than the first slope threshold, the second phase difference value is less than the second slope threshold, and the third phase difference value is less than the first intercept threshold, the adjustable straight line corresponding to the similar total phase difference value is added to the cluster set; Build associations between adjustable lines in a cluster set.

[0076] Optionally, the detecting the motion state of a person or a device based on the enhanced dispatchable three-dimensional image to obtain a state to be dispatched includes: Inputting the enhanced dispatchable three-dimensional image into the motion position discrimination network, judging the movement rate of dispatchable personnel or equipment, and obtaining multiple dispatchable motion values; one dispatch number corresponds to one dispatchable motion value; According to the geographical locations corresponding to the event venue point map, multiple dispatchable motion values ​​are divided into multiple position change sets; one point in the event venue point map corresponds to one position change set; the position change set represents the position change value corresponding to the corresponding dispatch number in one event venue; The position change value is used to indicate whether a person or a device moves slowly or quickly in the time length between two adjacent time points.

[0077] The position change value indicates whether the dispatchable personnel or equipment are working at a certain point in time, and the working speed, that is, whether they can be dispatched to other venues.

[0078] According to the geographical locations corresponding to the event venue point map, multiple dispatchable motion values ​​are divided into multiple position change sets; a point in the event venue point map corresponds to a position change set; the position change set represents the position change value corresponding to the corresponding dispatch number in a event venue.

[0079] The multiple position change values ​​in the position change set are input into the predicted position change network to detect the state of position change in a competition venue and obtain the state to be dispatched; the state to be dispatched includes the state requiring dispatch, the state capable of being dispatched and the balance state.

[0080] The state of needing to be dispatched indicates that a venue needs to dispatch personnel or equipment. The state of being able to be dispatched indicates that a venue can be dispatched personnel or equipment. The state of being balanced indicates that it is not necessary to dispatch personnel or equipment from other venues, nor is it possible to dispatch personnel or equipment to other venues.

[0081] Optionally, the scheduling of personnel or equipment based on the adjustable straight-line distance value, the status to be scheduled and the venue connectivity diagram includes: Obtaining the dispatch quantity and the number of the venue to be dispatched; the dispatch quantity indicates the number of personnel or equipment to be dispatched; the number of the venue to be dispatched indicates the number of the event venue where personnel or equipment needs to be dispatched; According to the status to be dispatched, find the event venues that can be dispatched and get the number of the dispatchable venues; In the event venues corresponding to the schedulable venue numbers, multiple adjustable straight-line distance values ​​are arranged from small to large to obtain an adjustable straight-line distance ranking.

[0082] Sequentially obtain the dispatch number in the adjustable straight-line distance sorting and the dispatch number associated with the dispatch number as the first prepared dispatch number; According to the venue connectivity map, determine whether the first preparation scheduling number can be moved to the event venue corresponding to the schedulable venue number, and if so, set the first preparation scheduling number as the preparation scheduling number; The quantity of the prepared dispatch number is used as the prepared dispatch quantity; If the prepared scheduling quantity is greater than or equal to the scheduling quantity, the prepared scheduling number is sent.

[0083] Among them, the first dispatch number in the adjustable straight-line distance sorting is obtained as the first dispatch number, and the dispatch number corresponding to the first dispatch number is obtained according to the association relationship. The first dispatch number is added to the number of associated dispatch numbers to obtain the first dispatch number number, and it is judged whether the first dispatch number number is greater than or equal to the dispatch number. If the first dispatch number number is less than the dispatch number, the second dispatch number in the adjustable straight-line distance sorting is obtained as the second dispatch number, and the dispatch number corresponding to the second dispatch number is obtained according to the association relationship. The second dispatch number is added to the number of associated dispatch numbers to obtain the second dispatch number number, and it is judged whether the sum of the first dispatch number number plus the second dispatch number number is greater than or equal to the dispatch number. Repeated detection until The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0084] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

Claims

1. A blockchain-based intelligent operation and management method for sports events, characterized in that: include: Obtain the event venue point map, n*m event venue dispatchable images and corresponding dispatch numbers; The event venue point map represents a point map in which the geographical location of the event venue is represented by the midpoint; the event venue dispatchable image represents an image containing multiple dispatchable personnel or equipment; n represents n time points, and one time point corresponds to m event venue dispatchable images; Through a schedulable time-space enhancement network, based on n*m schedulable images of the event venue, an enhanced schedulable three-dimensional image is obtained; the enhanced schedulable three-dimensional image representation includes enhanced time and space positions; Based on the enhanced dispatchable three-dimensional image, the movement state of the personnel or equipment is detected to obtain a state to be dispatched; the state to be dispatched indicates the priority of the dispatchable personnel or equipment that can be dispatched; According to the dispatch number, the event venues accessible to the detection personnel or equipment are obtained to obtain a venue connectivity map; Based on the enhanced schedulable three-dimensional image, the correlation relationship of the dispatch number is detected to obtain an adjustable straight-line distance value; the adjustable straight-line distance value indicates the degree of tortuosity of the movement of the dispatch number; Personnel or equipment scheduling is performed based on the adjustable straight-line distance value, the status to be scheduled and the venue connectivity diagram.

2. The blockchain-based intelligent operation and management method for sports events according to claim 1 is characterized in that: The detecting the association relationship of the scheduling numbers based on the enhanced schedulable three-dimensional image to obtain the adjustable straight-line distance value includes: Find the positions of the scheduling numbers in the enhanced schedulable three-dimensional image at multiple time points to obtain a scheduling number set; obtain multiple scheduling number sets corresponding to the multiple scheduling numbers; The dispatch number set and the corresponding time point are fitted to construct a three-dimensional straight line to obtain an adjustable straight line; multiple dispatch number sets correspond to multiple adjustable straight lines; Detecting the distance from the value in the dispatch number set to the adjustable straight line to obtain the adjustable straight line distance value; According to the adjustable straight line, a first slope, a second slope and a first intercept are obtained; Based on the first intercept, the first slope and the second slope, the relationship between the position change of the scheduling number is detected and an association relationship is constructed.

3. The blockchain-based intelligent operation and management method for sports events according to claim 1 is characterized in that: The schedulable time-space enhancement network includes a time convolutional network, a first convolutional network, a first neural network and a reconstruction network.

4. The blockchain-based intelligent operation and management method for sports events according to claim 3 is characterized in that: The method of obtaining an enhanced schedulable three-dimensional image based on the schedulable image of the event venue through the schedulable time-space enhancement network includes: Based on the schedulable image of the event venue, a first marked enhanced image is obtained; the first marked enhanced image represents an image in which the positions of schedulable personnel or equipment are marked and enhanced in space; Inputting the first marked enhanced images at multiple time points into a temporal convolutional network, detecting the change of the position of the scheduling number over time, and obtaining a first change feature; The midpoint of the dispatchable position in the first marker enhanced image of two adjacent time points is obtained to obtain a center position image; the center position image represents the position of the dispatch number corresponding to the time point between the two adjacent time points under uniform linear motion; Inputting the center position image into a first convolutional network to extract features to obtain middle position features; Inputting the first change feature and the intermediate position feature into a first neural network, and adjusting the intermediate position feature using the first change feature to obtain an updated feature; Inputting the updated features into a reconstruction network, converting one dimension into two dimensions, and obtaining an adjusted intermediate image; Arrange the plurality of adjusted intermediate images and the first marked enhanced image in order from early to late time points to obtain an enhanced schedulable three-dimensional image.

5. The blockchain-based intelligent operation and management method for sports events according to claim 4 is characterized in that: The training process of the schedulable time-space enhancement network includes: Acquire first marked enhanced images corresponding to multiple historical time points as historical images; Among the historical images corresponding to multiple time points, find the historical images of three adjacent time points as a historical image set; According to the order of time points from early to late, the historical image corresponding to the time point between the three time points in the historical image set is used as the annotated image; Using two historical images in the historical image set other than the annotated image as training images; Inputting the first labeled enhanced image into a schedulable temporal and spatial enhancement network to obtain a training adjusted intermediate image; The loss is calculated by adjusting the position of the corresponding scheduling number in the training intermediate image and the annotated image, and the schedulable time-space enhancement network is trained.

6. The blockchain-based intelligent operation and management method for sports events according to claim 4 is characterized in that: The step of obtaining a first marked enhanced image based on the event venue schedulable image includes: Based on the schedulable image of the event venue, detecting the center point of a person or equipment and expanding the center point to obtain a first expanded area; Inputting the event venue schedulable image into an enhancement network to perform image enhancement to obtain a first enhanced schedulable image; Obtain n*m first enhanced schedulable images corresponding to n time points; Inputting the first enhanced schedulable image into a schedulable detection network, detecting the positions of personnel or equipment that can be scheduled after the image enhancement, and obtaining a plurality of second schedulable detection positions; one second schedulable detection position corresponds to one first enlarged area; If the second schedulable detection position is not in the first enlarged area, the midpoint of the first enlarged area is used to replace the second schedulable detection position to obtain a schedulable position; the schedulable position represents the replaced or unreplaced second schedulable detection position; The schedulable position is marked on the first enhanced schedulable image to obtain a first marked enhanced image; and n*m first enhanced schedulable images correspond to obtaining n*m first marked enhanced images.

7. The blockchain-based intelligent operation and management method for sports events according to claim 6 is characterized in that: The method of detecting the center point of a person or a device based on the schedulable image of the event venue and expanding the center point to obtain a first expanded area includes: Inputting the schedulable image of the event venue into a schedulable detection network, detecting the positions of schedulable personnel or equipment, and obtaining a plurality of first schedulable detection positions; Divide the length of the first enhanced schedulable image by the length of the event venue schedulable image to obtain an enhancement ratio; According to the enhancement ratio, the first schedulable detection position is expanded to obtain a first expanded area.

8. The blockchain-based intelligent operation and management method for sports events according to claim 2 is characterized in that: The detecting the relationship between the position change of the dispatchable personnel or equipment based on the first intercept, the first slope and the second slope, and establishing the association relationship, comprises: If the absolute value of the subtraction of the first slopes corresponding to the two adjustable straight lines is less than the first slope threshold, the absolute value of the subtraction of the second slopes is less than the second slope threshold, and the absolute value of the subtraction of the first intercepts is less than the first intercept threshold, the two adjustable straight lines are added to the cluster set; taking the adjustable straight line in the cluster set as the first adjustable straight line; Using the adjustable straight lines among the plurality of adjustable straight lines except the adjustable straight lines in the cluster set as second adjustable straight lines; The absolute value of the first slope corresponding to the first adjustable straight line minus the first slope corresponding to the second adjustable straight line is taken as the first phase difference value; taking the absolute value of the second slope corresponding to the second adjustable straight line minus the second slope corresponding to the first adjustable straight line as the second phase difference value; The absolute value of the first intercept corresponding to the second adjustable straight line subtracted from the first intercept corresponding to the first adjustable straight line is taken as the third phase difference value; Adding the first phase difference value, the second phase difference value and the third phase difference value in proportion to obtain a total phase difference value; The p adjustable straight lines in the cluster set and the q adjustable straight lines outside the cluster set correspond to obtain p*q total phase difference values; The total phase difference value among the p*q total phase difference values ​​which is smaller than other total phase difference values ​​is taken as the similar total phase difference value; If the first phase difference value corresponding to the total phase difference value is less than the first slope threshold, the second phase difference value is less than the second slope threshold, and the third phase difference value is less than the first intercept threshold, the adjustable straight line corresponding to the similar total phase difference value is added to the cluster set; Build associations between adjustable lines in a cluster set.

9. The blockchain-based intelligent operation and management method for sports events according to claim 1 is characterized in that: The step of detecting the motion state of a person or a device based on the enhanced dispatchable three-dimensional image to obtain a state to be dispatched includes: Inputting the enhanced dispatchable three-dimensional image into the motion position discrimination network, judging the movement rate of dispatchable personnel or equipment, and obtaining multiple dispatchable motion values; one dispatch number corresponds to one dispatchable motion value; According to the geographical locations corresponding to the event venue point map, multiple dispatchable motion values ​​are divided into multiple position change sets; one point in the event venue point map corresponds to one position change set; the position change set represents the position change value corresponding to the corresponding dispatch number in one event venue; The multiple schedulable motion values ​​in the position change set are input into the predicted position change network, the state of position change in a competition venue is detected, and the state to be scheduled is obtained; the state to be scheduled includes a state requiring scheduling, a state capable of being scheduled, and a balanced state.

10. The blockchain-based intelligent sports event operation and management method according to claim 1 is characterized in that: The scheduling of personnel or equipment based on the adjustable straight-line distance value, the status to be scheduled and the venue connectivity diagram includes: Obtaining the dispatch quantity and the number of the venue to be dispatched; the dispatch quantity indicates the number of personnel or equipment to be dispatched; the number of the venue to be dispatched indicates the number of the event venue where personnel or equipment needs to be dispatched; According to the status to be dispatched, find the event venues that can be dispatched and get the number of the dispatchable venues; In the event venues corresponding to the schedulable venue numbers, multiple adjustable straight-line distance values ​​are arranged from small to large to obtain an adjustable straight-line distance ranking; Sequentially obtain the dispatch number in the adjustable straight-line distance sorting and the dispatch number associated with the dispatch number as the first prepared dispatch number; According to the venue connectivity map, determine whether the first preparation scheduling number can be moved to the event venue corresponding to the schedulable venue number, and if so, set the first preparation scheduling number as the preparation scheduling number; The quantity of the prepared dispatch number is used as the prepared dispatch quantity; If the prepared scheduling quantity is greater than or equal to the scheduling quantity, the prepared scheduling number is sent.

Images