Personnel configuration method, device and equipment based on safety protection tool and storage medium

Abstract

The invention discloses a personnel configuration method and device based on a safety protector, equipment and a storage medium, and relates to the technical field of industrial internet technology system services. According to the method, the ratio of the time progress percentage to the construction progress percentage of each construction point serves as the weight value of the current construction point, the completion condition of the construction point is visually reflected through the weight value, and the ratio serves as the weight value of the construction point and the completion condition of the construction point. And a quantifiable basis is provided for personnel arrangement, dispatching and management in the past. According to the method, the distribution condition of the weight values of the multiple tasks is analyzed, and then the weight values of the multiple tasks are subjected to repeated weighted averaging based on the random labels of the construction points and the respective distance correction coefficients, so that the constructors can reach the construction points where the large weight values are located as early as possible; and finally, the shortest route is searched according to the construction point sequence corresponding to the minimum value, so that the constructors can arrive at the construction point with the maximum weight value at the earliest, and the construction efficiency is further improved.

Description

Technical Field

[0001] The present application relates to the field of industrial Internet technology system service technology, and in particular to a personnel configuration method, device, equipment and storage medium based on safety gear. Background Art

[0002] Engineering construction is the most basic and important part of social development. For example, construction projects, highway projects, water conservancy projects, mining projects, etc., all provide strong guarantees for social development. The aforementioned projects generally have the characteristics of large construction areas, diverse terrains, a large number of types and quantities of construction facilities, tools and materials, and a large number of construction personnel. Therefore, it is necessary to formulate different construction plans for different projects in advance according to the actual situation. The basis for the preparation of the construction plan mainly includes design documents, technical standards, contract agreements, feasibility study reports, construction management requirements, actual site conditions, laws, regulations and policy requirements, etc. Among them, the design document means that the construction plan should be based on the design documents such as construction drawings, technical specifications, construction process flow, etc. provided by the designer, and the technical requirements and construction measures therein should be reasonably applied; the technical standards mean that the construction plan must comply with the relevant technical standards issued by the government, industry, and local governments to ensure the quality, safety, and economic requirements during the construction process; the contractual agreement means that the construction plan must comply with the engineering content, quality standards, progress requirements, and safety requirements agreed in the contract to ensure that the goals agreed in the contract can be achieved; the feasibility study report means that the construction plan must comprehensively consider the technical, economic, environmental and other factors in the feasibility study report to ensure the feasibility and feasibility of the plan; the construction management requirements mean that the construction plan must comply with the project management requirements, such as the construction schedule, quality control requirements, and safety production management requirements to ensure that the project can be completed on time, in quality, and in quantity; the actual situation on site means that the construction plan must be combined with the characteristics of the actual project site and the on-site environment, and the actual situation of construction conditions, human resources, materials and equipment must be considered to formulate a feasible construction plan; the laws, regulations, and policy requirements mean that the construction plan must comply with the laws, regulations, and policy requirements related to construction issued by the government and local governments, such as the "Construction Project Quality Management Regulations" and the "Construction Project Safety and Civilized Construction Management Regulations".

[0003] From the above, we can see that the current existing construction plans are basically formulated based on subjective experience and past references under the premise of laws, regulations and industry norms. The core theme running through the project is the arrangement, dispatch and management of relevant personnel from the beginning to the end of the project. The accurate arrangement, dispatch and management of relevant personnel can ensure the rational use of human resources and good construction efficiency.

[0004] Due to the different project scales, delivery deadlines, and technical applications involved in different engineering projects, the arrangements, dispatches, and management of relevant personnel involved in different engineering projects are all different. Moreover, the arrangements, dispatches, and management of relevant personnel are also based on subjective experience and past reference. Enterprises with rich engineering experience have richer and more accurate measures in personnel arrangements, but subjective experience and past reference are prone to subjective errors, which may lead to redundancy or deficiency in the arrangements, dispatches, and management of relevant personnel. For example, different construction plans under the same engineering project have different delivery dates. Usually, redundant construction personnel will be arranged in the construction plan closest to the delivery date, while fewer construction personnel will be arranged in the construction plan that is farther away from the delivery date. Finally, it is easy for the construction plan that was initially far away from the delivery date to be redundantly arranged with construction personnel when it is close to the delivery date, forming a vicious circle. This may easily lead to a waste of human resources, thereby affecting construction efficiency.

[0005] Application Contents

[0006] The main purpose of this application is to provide a personnel configuration method, device, equipment and storage medium based on safety protective gear, so as to solve the problem that the arrangement, dispatch and management of relevant personnel at the construction site in the prior art are based on subjective experience and past reference, and there are subjective errors, which makes the arrangement, dispatch and management of relevant personnel redundant or deficient, thereby causing waste of human resources and affecting construction efficiency.

[0007] In order to achieve the above objectives, this application provides the following technical solutions:

[0008] A personnel configuration method based on safety gear, the personnel configuration method is applied to construction personnel wearing safety gear, the safety gear is equipped with a navigation module, the edge of the construction site has at least one entrance and exit, the construction site has at least one construction point, and the personnel positioning method includes:

[0009] Step S1, obtaining the elevation coordinates of all entrances and exits, all construction points, and all roads of the construction site;

[0010] Step S2, respectively obtaining the ratio of the time progress percentage to the construction progress percentage of each construction point, and defining the ratio of the current construction point as the weight value of the current construction point;

[0011] Step S3, responding to an entry signal of the navigation module based on any entrance or exit;

[0012] Step S4, obtaining the preset construction requirements of the construction personnel that match the navigation module, and marking all the construction points that need to be entered as construction points to be entered according to the preset construction requirements;

[0013] Step S5, obtaining the distance between the navigation module and each construction point to be entered based on all roads, and using the value of each distance as a distance correction coefficient for each construction point to be entered;

[0014] Step S6, all the construction points to be entered are numbered in sequence with natural numbers, all the construction points to be entered are numbered once as a group of numbering sequences, and the group of numbering sequences is weighted averaged once using the weight values ​​of all the construction points to be entered and the distance correction coefficient, and a weighted average value is obtained based on the group of numbering sequences;

[0015] Step S7, calculating the minimum value of the weighted average value by a global optimization algorithm;

[0016] Step S8, obtaining the label sequence corresponding to the minimum value and obtaining the shortest path passing through the label sequence in sequence through a path search algorithm;

[0017] Step S9: sending the shortest path to the navigation module.

[0018] As a further improvement of the present application, step S9, sending the shortest path to the navigation module, then includes:

[0019] Step S10, defining a world coordinate system based on any horizontal plane and any vertical plane of the construction site;

[0020] Step S20, in response to the entry signal, obtaining a person detection frame matching the entry signal based on a target detection algorithm;

[0021] Step S30, mapping the person detection frame to the world coordinate system through a homography matrix to form a two-dimensional person detection frame, and the two-dimensional person detection frame is parallel to or coplanar with any vertical plane;

[0022] Step S40, obtaining a symmetry axis of the two-dimensional person detection frame in a vertical direction, and rotating the two-dimensional person detection frame based on the symmetry axis;

[0023] Step S50, obtaining a complete rotation trajectory of the two-dimensional person detection frame, and defining the complete rotation trajectory as a three-dimensional person detection frame;

[0024] Step S60, acquiring the elevation coordinates of the three-dimensional person detection frame based on the relative position of the three-dimensional person detection frame and the construction site;

[0025] Step S70, obtaining the elevation coordinates of the navigation module and determining whether the elevation coordinates of the navigation module are within a preset range of the elevation coordinates of the three-dimensional person detection frame, if not, executing step S80;

[0026] Step S80, generating a warning of improper wearing of safety gear and sending it to an external decision-making end.

[0027] As a further improvement of the present application, step S20, in response to the entry signal, obtaining a person detection frame matching the entry signal based on a target detection algorithm, includes:

[0028] Step S201, in response to the entry signal, acquiring image data matching the entry signal through an external preset camera terminal;

[0029] Step S202, dividing the image data into a preset number of grids on average;

[0030] Step S203, predicting a plurality of first-order bounding boxes for the moving object in the image data based on all the grids according to the object detection algorithm, each first-order bounding box including at least one grid;

[0031] Step S204, defining the construction worker as having the highest confidence level;

[0032] Step S205, respectively obtaining the confidence of each first-order bounding box, and obtaining the bounding box with the largest confidence and marking it as the second-order bounding box;

[0033] Step S206, calculating the intersection-over-union ratio between the second-order bounding box and each other first-order bounding box;

[0034] Step S207, selecting a bounding box whose intersection-over-union ratio is greater than or equal to a preset threshold as a third-order bounding box;

[0035] Step S208: Obtain a third-order bounding box with the highest confidence and define it as the person detection box.

[0036] As a further improvement of the present application, step S7, calculating the minimum value of the weighted average value by a global optimization algorithm, includes:

[0037] Step S71, defining a plurality of random solutions for the minimum value according to formula (1), and defining the optimization result of all random solutions as the weighted average of all labels reaching the minimum;

[0038]

[0039] Among them, X i is the set of all random solutions, x1,x2,…,x i ,…,x N-1, x N are each random solution, i is the number of the random solution, and N is the number of all random solutions; V i is the set of velocities of all random solutions, v1,v2,…,v i ,…,vN-1 ,v N are the speeds of each random solution respectively;

[0040] Step S72, initialize the position of each random solution, and update the current position and current speed respectively based on the same random solution according to formula (2):

[0041]

[0042] Among them, v id is the speed of the ith random solution at step d, ω·v id-1 is the velocity inertia of the ith random solution at step d-1, ω is the inertia coefficient, c1·random()·(p best,i -x i ) is the self-perception representation of the i-th random solution, c2·random()·(g best,i -x i ) is the social cognitive representation of the i-th random solution; c1 and c2 are both learning factors, random() is a random number in the preset value range, p best,i is the individual optimal solution obtained by the i-th random solution, g best,i is the global optimal solution obtained by the i-th random solution, x id is the ith random solution of the dth step, x id-1 is the i-th random solution of step d-1;

[0043] Step S73, iterate each random solution a preset number of times according to formula (2) to update each p best,i And each g best,i ;

[0044] Step S74, determine each p best,i Comparing the first difference values ​​of the previous iteration to see whether they are less than or equal to the first preset adaptation threshold, if all the first difference values ​​are less than or equal to the first preset adaptation threshold, executing step S75;

[0045] Step S75, determine each g best,i Comparing the second difference values ​​of the previous iteration to see whether they are less than or equal to the second preset adaptation threshold, if all the second difference values ​​are less than or equal to the second preset adaptation threshold, executing step S76;

[0046] Step S76, determining that the optimal solution for the minimum value has been obtained.

[0047] As a further improvement of the present application, step S8, obtaining the label sequence corresponding to the minimum value and obtaining the shortest path passing through the label sequence in sequence through a path search algorithm, includes:

[0048] Step S81, dividing the construction site into grids of preset density;

[0049] Step S82, deleting grids without any construction points and any roads, and defining them as candidate grid sets;

[0050] Step S83, defining each grid in the candidate grid set as a node;

[0051] Step S84, defining the entrance and exit where the entry signal is detected as the starting point, defining the corresponding construction points in the order of the numbers as waypoints, and defining the construction point at the end of the order of the numbers as the end point;

[0052] Step S85, calculating the minimum number of grids required for the starting point to pass through each waypoint in sequence according to the numbering sequence and finally reach the end point by using the A-star algorithm;

[0053] Step S86, obtaining grids corresponding to the minimum number of grids, and connecting them in sequence to form the shortest path.

[0054] As a further improvement of the present application, step S85, calculating the minimum number of grids required from the starting point to the end point by using the A-star algorithm, includes:

[0055] Step S851, creating a grid set to be checked;

[0056] Step S852, adding the starting point to the grid set to be checked, and setting the priority of the starting point to the highest;

[0057] Step S853, determining whether the grid set to be checked is empty, if the grid set to be checked is not empty, executing step S854;

[0058] Step S854, selecting a node n with the highest priority from the grid set to be checked;

[0059] Step S855, determining whether the node n is the end point, if the node n is the end point, executing step S856;

[0060] Step S856, starting from the end point, gradually tracing the parent node until reaching the start point;

[0061] Step S857, obtaining the parent node of each tracking step, which is the minimum number of grids.

[0062] As a further improvement of the present application, step S853, determining whether the grid set to be checked is empty, then includes:

[0063] Step S100, if the grid set to be checked is empty, execute step S200;

[0064] Step S200, traversing all neighboring nodes m of the node n, and adding all neighboring nodes m to the grid set to be checked;

[0065] Step S300, obtaining the neighboring node m with the highest priority among all neighboring nodes m as the parent node for the next traversal;

[0066] Step S400, starting from the current parent node, gradually tracing the parent node of the next traversal until reaching the end point;

[0067] Step S500, obtaining the parent node of each tracking step, which is the minimum number of grids.

[0068] In order to achieve the above objectives, this application also provides the following technical solutions:

[0069] A personnel configuration device based on safety gear, the personnel configuration device based on safety gear is applied to the above-mentioned personnel configuration method based on safety gear, the personnel configuration device comprises:

[0070] An elevation coordinate acquisition module is used to acquire the elevation coordinates of all entrances and exits, all construction points, and all roads of the construction site;

[0071] The construction point weight value acquisition module is used to obtain the ratio of the time progress percentage to the construction progress percentage of each construction point, and define the ratio of the current construction point as the weight value of the current construction point;

[0072] An entry signal response module, used to respond to the entry signal of the navigation module based on any entrance and exit;

[0073] A construction point marking module to be entered is used to obtain the preset construction requirements of the construction personnel that match the navigation module, and mark all construction points to be entered as construction points to be entered according to the preset construction requirements;

[0074] A distance correction coefficient acquisition module is used to acquire the distance between the navigation module and each construction point to be entered based on all roads, and use the value of each distance as the distance correction coefficient of each construction point to be entered;

[0075] The construction point label weighted average module is used to label all the construction points to be entered in order with natural numbers, and all the construction points to be entered are labeled once as a group of labeling sequences, and the group of labeling sequences is weighted averaged once with the weight values ​​of all the construction points to be entered, and a weighted average value is obtained based on the group of labeling sequences;

[0076] A weighted average minimum value calculation module, used to calculate the minimum value of the weighted average value by a global optimization algorithm;

[0077] A shortest path acquisition module, used to acquire the label sequence corresponding to the minimum value and acquire the shortest path passing through the label sequence in sequence through a path search algorithm;

[0078] The shortest path sending module is used to send the shortest path to the navigation module.

[0079] In order to achieve the above objectives, this application also provides the following technical solutions:

[0080] An electronic device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the personnel configuration method based on safety gear as described above is implemented.

[0081] To achieve the above objectives, this application also provides the following technical solutions:

[0082] A storage medium stores program instructions, and when the program instructions are executed by a processor, the personnel configuration method based on safety gear as described above can be implemented.

[0083] This application obtains the elevation coordinates of all entrances and exits, all construction points, and all roads of the construction site; obtains the ratio of the time progress percentage to the construction progress percentage of each construction point, and defines the ratio of the current construction point as the weight value of the current construction point; responds to the entry signal of the navigation module based on any entrance and exit; obtains the preset construction requirements of the construction personnel matching the navigation module, and marks all the construction points that need to be entered as the construction points to be entered according to the preset construction requirements; all the construction points to be entered are numbered in sequence with natural numbers, and all the construction points to be entered are numbered once as a group of numbering sequences, and a group of numbering sequences are weighted averaged once with the weight values ​​of all the construction points to be entered, and a weighted average value is obtained based on a group of numbering sequences; the minimum value of the weighted average value is calculated by a global optimization algorithm; the numbering sequence corresponding to the minimum value is obtained and the shortest path that passes through the numbering sequence in sequence is obtained by a path search algorithm; and the shortest path is sent to the navigation module. This application uses the ratio of the time progress percentage to the construction progress percentage of each construction point as the weight value of the current construction point, and is intended to intuitively reflect the completion status of the construction point through the weight value. For example, when the ratio of the time progress percentage to the construction progress percentage is greater than 1, it means that the actual construction progress lags behind the expected construction progress and is in a state of needing to speed up the progress; when the ratio of the time progress percentage to the construction progress percentage is less than 1, it means that the actual construction progress is ahead of the expected construction progress and is in a state of not needing to speed up the progress. At this time, the ratio is used as the weight value of the construction point to reflect the completion status of the construction point. That is, the larger the weight value, the more manpower is needed to further increase the construction speed, which provides a quantifiable basis for the previous personnel arrangement, dispatch, and management. This application also supports the situation where a single construction worker is responsible for multiple tasks. By analyzing the distribution of weight values ​​of multiple tasks, the weight values ​​of multiple tasks are repeatedly weighted averaged based on the random numbers of the construction points and their respective distance correction coefficients, and iterated with the minimum weighted average as the target. The purpose is to make the weight values ​​with larger values ​​move closer to the smaller numbers, so that the construction workers can reach the construction points with large weight values ​​as early as possible, and finally find the shortest route in the order of construction points corresponding to the minimum value. This not only allows the construction workers to reach the construction point with the largest weight value first, and the second largest construction point second earliest, but also avoids detours, thereby further improving construction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 A schematic diagram of the process steps of an embodiment of a personnel configuration method based on safety protective gear of the present application;

[0085] Figure 2 This is a functional module diagram of an embodiment of a personnel configuration device based on safety gear of the present application;

[0086] Figure 3This is a schematic diagram of the structure of an embodiment of the electronic device of the present application;

[0087] Figure 4 This is a schematic diagram of the structure of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0088] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0089] The terms "first", "second" and "third" in this application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications in the embodiments of the present application (such as up, down, left, right, front, back...) are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0090] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0091] like Figure 1 As shown, this embodiment provides an embodiment of a personnel configuration method based on safety gear. In this embodiment, the personnel configuration method is applied to construction workers wearing safety gear, the safety gear is equipped with a navigation module, the edge of the construction site has at least one entrance and exit, and there is at least one construction point in the construction site.

[0092] Preferably, the safety protective gear is mainly safety protective gear worn on the body such as a helmet and protective clothing; the navigation module is an existing technology, and can adopt a short-range Bluetooth solution or a long-range 4G solution.

[0093] Among them, the short-range Bluetooth solution can install Bluetooth on the inner edge of the helmet. Bluetooth can be connected to the construction workers' mobile phone Bluetooth, and users can view positioning information, map information, and the shortest path generated later through the mobile phone. This embodiment can use frequency hopping to expand the spectrum, dividing the 2.402-2.48GHz frequency band into 79 frequency points, with an interval of 1MHz between adjacent frequency points. After the Bluetooth device sends data at a certain frequency point, it jumps to another frequency point to send, and the arrangement order of the frequency points is pseudo-random, with the frequency changing 1600 times per second, and each frequency lasting 625us.

[0094] Among them, the long-distance 5G solution can provide a network foundation for the wireless transmission of images and videos, and 4G communication has a significant bandwidth advantage over WiFi, 4G, NB-IOT and other communication methods. In addition, 5G technology has been commercially available for many years, and its maturity and stability can be interconnected with almost any network, and most types of terminal devices can access the 5G communication network. The long-distance 5G communication solution can realize additional functions such as voice interaction, video monitoring, and location reporting. This embodiment uses the Cat.1 communication module as the basis to reduce the size of the device and simplify program design. ML307A-GSLN is selected as the functional module for long-distance 5G communication. The communication module supports multiple frequency bands such as B1 / B3 / B5 / B8, with a maximum transmission rate of 5Mbps for upload and 10Mpbs for download, which can meet the needs of image and video transmission. It supports GPS, audio playback / recording and text-to-speech functions, and supports multiple network transmission protocols such as HTTP / HTTPS, MQTT, TCP / UDP, etc.

[0095] Specifically, the personnel positioning method of this embodiment includes the following steps:

[0096] Step S1, obtaining the elevation coordinates of all entrances and exits, all construction points, and all roads of the construction site.

[0097] Preferably, the elevation coordinates are derived from a digital elevation model (DEM), which can be obtained directly from public channels (download of high-precision 5-12-30-meter DEM terrain data nationwide). Among them, all entrances and exits, all construction points, and all roads can obtain their own boundary coordinate sets.

[0098] Step S2, respectively obtain the ratio of the time progress percentage to the construction progress percentage of each construction point, and define the ratio of the current construction point as the weight value of the current construction point.

[0099] Preferably, the time progress percentage can be directly obtained based on the ratio of the current date to the construction period in the construction plan, and the construction progress percentage can be obtained by comparing the actual construction progress with the proposed construction period schedule, or by the ratio of the used materials to the total materials. For example, two buildings and an outdoor facility need to be completed on a specific date. According to the construction plan, a total of 500 tons of materials are required for the two buildings and the outdoor facility. Currently, 300 tons of materials have been put into use, so the actual construction progress is 60%. In order to further refine the percentage value, a correction factor can be defined based on the remaining or insufficient amount of materials in previous constructions of the same specifications. For example, if 500 tons of materials were planned for the construction of two buildings and an outdoor facility of the same specifications in the past, and 10 tons of materials were left after completion, the correction factor is 10 / 500=0.02, which is 60% multiplied by 1+0.02; for example, if 10 tons of materials are needed to complete the construction of two buildings and an outdoor facility of the same specifications in the past, it means that 10 tons of materials are missing, and the correction factor is -10 / 500=-0.02, which is 60% multiplied by 1-0.02.

[0100] Step S3, responding to an entry signal from the navigation module based on any entrance or exit.

[0101] Preferably, the entry signal is generated when the GPS position of the navigation module coincides with or is sufficiently close to the map position of any entrance or exit, or when the elevation coordinates of the navigation module are within the elevation coordinate set of any entrance or exit.

[0102] Preferably, the entrances and exits of current construction sites are generally equipped with gates, and construction workers can also pass through the gates to enter the construction site to generate an entry signal.

[0103] Step S4, obtaining the preset construction requirements of the construction personnel that match the navigation module, and marking all the construction points that need to be entered as construction points to be entered according to the preset construction requirements.

[0104] Step S5, obtaining the distance between the navigation module and each construction point to be entered based on all roads, and using the value of each distance as the distance correction coefficient of each construction point to be entered.

[0105] Step S6, all the construction points to be entered are numbered in sequence with natural numbers, all the construction points to be entered are numbered once as a group of numbering sequences, and the group of numbering sequences is weighted averaged once with the weight values ​​of all the construction points to be entered and the distance correction coefficient, and a weighted average value is obtained based on the group of numbering sequences.

[0106] Step S7, calculating the minimum value of the weighted average value by a global optimization algorithm.

[0107] Step S8, obtaining the label sequence corresponding to the minimum value and obtaining the shortest path passing through the label sequence in sequence through a path search algorithm.

[0108] Step S9, sending the shortest path to the navigation module.

[0109] For example, there are a total of 8 construction points in the construction site of a certain engineering project, namely construction point A, construction point B, construction point C, construction point D, construction point E, construction point F, construction point G, and construction point H.

[0110] The preset construction requirements of the construction personnel are to enter the construction site at construction point A, construction point C, and construction point E to complete the construction tasks they have received. In the past, the order of priority was usually determined by the construction manager based on his own experience or by the construction personnel's own experience. Through step S2 of this embodiment, the weight values ​​of construction point A, construction point C, and construction point E are obtained as 0.94, 1.09, and 1.01, respectively, and the distances are 1.2 km, 1.0 km, and 0.8 km, respectively. At this time, the values ​​of 1.2 km, 1.5 km, and 0.8 km, 1.2, 1.5, and 0.8, are used as distance correction coefficients. All numbers of construction point A, construction point C, and construction point E are iterated according to the following formula to find the minimum value of the weighted average:

[0111]

[0112] in, is the weighted average, w A 、w C 、w E They are the weight values ​​of construction point A, construction point C, and construction point E, respectively, and they are all known quantities; d A ,d C ,d E They are the distance correction coefficients of construction point A, construction point C, and construction point E, respectively, and are all known quantities; N A 、N C 、N E They are construction point A, construction point C, and construction point E respectively. They are all unknown quantities and are numbered as consecutive natural numbers 1, 2, 3...

[0113] Preferably, this embodiment uses a global optimization algorithm to iterate the number of values ​​to find The minimum value of N A 、N C 、N E When it is 1, 2, and 3, Reached minimum value.

[0114] It can be seen that construction points A, C, and E are not directly sorted as 1, 3, and 2 according to the weight values, but the time spent at non-construction points such as the walking distance of construction workers and the transportation distance of materials are taken into consideration, making the personnel allocation more comprehensive and accurate.

[0115] It should be noted that the above calculation process is only a principle explanation through simple examples and does not represent the actual application process. In the actual application process, the construction tasks of construction workers may be more complicated, the construction points may be more numerous, and the data forms of weight values ​​and distances may be more complicated, so this embodiment introduces an algorithm to replace manual calculations.

[0116] It is worth noting that after the current construction workers complete their own construction tasks, the progress of the construction point changes, causing subsequent weights and iterations to change accordingly. During the entire construction process, this embodiment changes in real time with the changes in the construction progress, so it is necessary to introduce an algorithm for repeated and rapid calculations.

[0117] Furthermore, in step S9, the shortest path is sent to the navigation module, and this step also includes the following steps:

[0118] Step S10: defining a world coordinate system based on any horizontal plane and any vertical plane of the construction site.

[0119] Step S20, in response to the entry signal, obtaining a person detection frame matching the entry signal based on a target detection algorithm.

[0120] Preferably, the target detection algorithm can be implemented by target detection algorithms VJ, HOG, DPMDetector; deep learning two-stage target detection algorithms RCNN, SPPNet, FastRCNN, FasterRCNN; target detection trick algorithms FPN, CascadeRCNN; deep learning one-stage target detection algorithms Yolo, X, SSD, RetinaNet; deep learning anchor-free target detection algorithms CornerNet, CenterNet, FCOS; Transformer-based target detection algorithm DETR, etc.

[0121] Preferably, this embodiment prefers the Yolo algorithm.

[0122] Step S30 , mapping the person detection frame to the world coordinate system through the homography matrix to form a two-dimensional person detection frame, and the two-dimensional person detection frame is parallel to or coplanar with any vertical plane.

[0123] Preferably, in practical applications, the two-dimensional detection frame obtained by the YOLO algorithm is converted into a three-dimensional detection frame and mapped to the world coordinate system. Usually, radar is required for assistance, and radar data of the same scene needs to be added to ensure the accuracy of the mapping of the person detection frame.

[0124] Preferably, the homography matrix can be obtained by express.

[0125] Where a and b are the location information of the current navigation module, x and y are the pixel coordinate values ​​of the current navigation module in the image data, H is the homography matrix, and By solving the homography matrix, all radar points whose pixel coordinate system coincides with the world coordinate system of the same external scene are obtained.

[0126] It should be noted that the symbolic meaning of the homography matrix is ​​not interchangeable with the other symbolic meanings in this embodiment.

[0127] Preferably, the existing 2D detection model can also be used to locate the region of interest (ROI) on the RGB image, and then a pixel mapping strategy is adopted in the point cloud, and finally the initial 2D bounding box is mapped to the 3D space.

[0128] Step S40, obtaining the symmetry axis of the two-dimensional person detection frame in the vertical direction, and rotating the two-dimensional person detection frame based on the symmetry axis.

[0129] Step S50, obtaining a complete rotation trajectory of the two-dimensional person detection frame, and defining the complete rotation trajectory as a three-dimensional person detection frame.

[0130] Preferably, the actual shape of the three-dimensional person detection frame is a cylinder, and the diameter of the cylinder is the lateral length of the two-dimensional person detection frame.

[0131] Step S60, obtaining the elevation coordinates of the three-dimensional person detection frame based on the relative position of the three-dimensional person detection frame and the construction site.

[0132] Preferably, the elevation coordinates of the navigation module can be directly acquired and then expanded outward into a cylinder, and the degree of expansion depends on the horizontal length of the two-dimensional person detection frame.

[0133] Step S70, obtaining the elevation coordinates of the navigation module and determining whether the elevation coordinates of the navigation module are within a preset range of the elevation coordinates of the three-dimensional person detection frame. If not, executing step S80.

[0134] Step S80, generating a warning of improper wearing of safety gear and sending it to an external decision-making end.

[0135] The design intention of step S10 to step S80 is to prevent construction workers from not wearing safety gear correctly, which may lead to large subsequent calculation errors or inability to perform calculations, and also to urge construction workers to ensure their own personal safety.

[0136] Furthermore, step S20, in response to the entry signal, obtaining a person detection frame matching the entry signal based on a target detection algorithm, includes:

[0137] Step S201, in response to an entry signal, acquiring image data matching the entry signal through an external preset camera terminal.

[0138] Step S202, dividing the image data into a preset number of grids on average.

[0139] Preferably, the size of the original picture of the image data may be adjusted to 448×448, and then the resized picture may be evenly divided into S×S (eg, 7×7) grids, and the size of each grid is 64×64.

[0140] Preferably, each grid is used to predict the coordinates and width and height of N detection boxes, as well as the confidence of each detection box, that is, each grid needs to predict N×(4+1) values.

[0141] It should be noted that the "N" in these N detection boxes is not interoperable with the "N" in the global optimization algorithm.

[0142] Step S203 , predicting a plurality of first-order bounding boxes for the moving target in the image data based on all the grids according to the target detection algorithm, each first-order bounding box including at least one grid.

[0143] Preferably, if the center of an object lies on a certain grid, then that grid is responsible for predicting the bounding box of the object.

[0144] Step S204, defining the construction personnel with the highest confidence.

[0145] Step S205 , respectively obtain the confidence of each first-order bounding box, obtain the bounding box with the maximum confidence and mark it as the second-order bounding box.

[0146] Step S206 , calculating the intersection-over-union ratio between the second-order bounding box and each of the other first-order bounding boxes.

[0147] Preferably, the intersection-over-union ratio is a ratio obtained by dividing the intersection of the optimal detection box and each bounding box by the union of the optimal detection box and each bounding box.

[0148] Step S207 : selecting a bounding box whose intersection-over-union ratio is greater than or equal to a preset threshold as a third-order bounding box.

[0149] Step S208: Obtain a third-order bounding box with the highest confidence and define it as a person detection box.

[0150] It can be understood that each grid needs to predict N (x, y, w, h, confidence); where (x, y) is the offset of the center of the detection box relative to the grid, (w, h) is the ratio of the detection box to the above resized image, and (confidence) is the confidence of the grid, which takes a value of 1 or 0.

[0151] Preferably, the confidence level can be understood as whether there is a target in the current grid and the accuracy of the detection box.

[0152] For example: suppose there is an object in a resized image, and the width and height of the resized image are (w a ,h a )but:

[0153] Divide the image into 7×7 (S×S) grids evenly. There is a grid located at the center of the target. The coordinates of the grid are (x i ,y i ), let the coordinates of the center of the target be (x a ,y a ), the above offset (x b ,y b ):

[0154] Preferably, in actual detection, if the predicted detection box and the actual bounding box overlap perfectly, the intersection-and-union ratio is 1. In actual application, the intersection-and-union ratio can generally be set to 0.5 to determine whether the predicted bounding box is correct, and the more accurate the bounding box is, the more positively correlated it is with the intersection-and-union ratio.

[0155] Preferably, the YOLO algorithm also needs to train the detection frame to improve the accuracy of target detection.

[0156] It should be noted that the training model of the person detection frame is generally implemented directly through code, for example:

[0157]

[0158] Among them, “*” is the target category that needs to be identified, which can be set to words related to construction workers such as “person” and “human” to identify construction workers.

[0159] Next, the training model is trained using a preset training set, and the weights and biases of the training model are iteratively adjusted a first preset number of times using a back propagation algorithm to reduce the value of the loss function of the training model.

[0160] Preferably, the loss function is as shown in formula ②:

[0161]

[0162] in, is the indicator function of whether the j detection box of the i-th grid is responsible for the target, and its value is 1 or 0; x i ,y i 、w i 、h i , C i They correspond to the i-th (x, y, w, h, confidence) prediction value, that is, the N×(4+1) values ​​mentioned above.

[0163] It can be understood that the loss function includes the coordinate value deviation of the detection box, the confidence deviation, and the prediction probability deviation (or category deviation).

[0164] in, is the detection frame midpoint loss in the coordinate value deviation, is the loss of detection box width and height in coordinate value deviation, is the confidence deviation, is the deviation of the predicted probability (or class deviation).

[0165] Among them, λ coord is the positioning error penalty, generally λ coord =5;S 2 That is, the S×S grids mentioned above; B is the number of bounding boxes; and is the estimated value of the horizontal and vertical coordinates of the midpoint of the i-th bounding box; and is the estimated value of the width and height of the i-th bounding box; C i is the confidence of the i-th bounding box; is the estimated value of the confidence of the i-th bounding box; noobj is the confidence prediction loss, usually λ noobj =0.5; p i (c) is the category probability of the i-th bounding box; is the estimated value of the category probability of the i-th bounding box; p i (c) with The c in it corresponds to classes.

[0166] It should be noted that since each grid does not necessarily contain a target, if there is no target in the grid, the value of (confidence) will be 0, making the gradient span in the subsequent back propagation algorithm too large, so λ is introduced coordTo control the loss of the predicted position of the detection box, and introduce λ noobj Controls the loss of objects not existing in a single grid.

[0167] It should be noted that the meanings of all symbols in the extended content of the above YOLO algorithm are not interchangeable with other symbol meanings.

[0168] Furthermore, step S7, calculating the minimum value of the weighted average value by a global optimization algorithm, includes:

[0169] Step S71, define several random solutions for the minimum value according to formula (1), and define the optimization result of all random solutions as the weighted average of all labels reaching the minimum.

[0170]

[0171] Among them, X i is the set of all random solutions, x1,x2,…,x i ,…,x N-1 ,x N are each random solution, i is the number of the random solution, and N is the number of all random solutions; V i is the set of velocities of all random solutions, v1,v2,…,v i ,…,v N-1 ,v N are the speeds of each random solution respectively.

[0172] Step S72, initialize the position of each random solution, and update the current position and current speed respectively based on the same random solution according to formula (2):

[0173]

[0174] Among them, v id is the speed of the ith random solution at step d, ω·v id-1 is the velocity inertia of the ith random solution at step d-1, ω is the inertia coefficient, c1·random()·(p best,i -x i ) is the self-perception representation of the i-th random solution, c2·random()·(g best,i -x i ) is the social cognitive representation of the i-th random solution; c1 and c2 are both learning factors, random() is a random number in the preset value range, p best,i is the individual optimal solution obtained by the i-th random solution, g best,i is the global optimal solution obtained by the i-th random solution, x id is the ith random solution of the dth step, x id-1 is the i-th random solution of step d-1.

[0175] Preferably, the preset value range of random() is [0,1], the value range of c1 is [0,0.5], preferably 0.4; the value range of c2 is [0.5,1], preferably 0.8.

[0176] Step S73, iterate each random solution a preset number of times according to formula (2) to update each p best,i And each g best,i .

[0177] Preferably, the inertia coefficient is linearly decreased once according to formula (3) based on each iteration:

[0178]

[0179] Among them, ω id is the inertia coefficient of the i-th random solution after optimization in the d-th step, ω ini is the initial inertia coefficient, G c is the current iteration number, G max is the maximum number of iteration steps.

[0180] Preferably, the initial inertia coefficient is generally set to 0.9, and the maximum number of iteration steps is generally set according to actual needs, and can be set to 100 times in this embodiment.

[0181] Step S74, determine each p best,i Compare whether the first difference value of the previous iteration is less than or equal to the first preset adaptation threshold value. If all the first difference values ​​are less than or equal to the first preset adaptation threshold value, execute step S75.

[0182] Step S75, determine each g best,i Compared with whether the second difference value of the previous iteration is less than or equal to the second preset adaptation threshold, if all the second difference values ​​are less than or equal to the second preset adaptation threshold, step S76 is executed.

[0183] Preferably, the values ​​of the first preset adaptation threshold and the second preset adaptation threshold need to be adjusted according to the specific problem, and generally need to be adjusted according to the calculation results. If the adaptation threshold is set too small, the algorithm may stop prematurely and fail to obtain the optimal solution; if the adaptation threshold is set too large, the algorithm may be over-iterated, wasting computing resources.

[0184] Preferably, the adaptation threshold may also be evaluated by one of the Griewank function, the Rastrigin function, the Schaffer function, the Ackley function, and the Rosenbrock function.

[0185] Step S76, determining the optimal solution that has obtained the minimum value.

[0186] Further, step S8, obtaining the label sequence corresponding to the minimum value and obtaining the shortest path passing through the label sequence in sequence through a path search algorithm, includes:

[0187] Step S81, dividing the construction site into grids of preset density.

[0188] Step S82: Delete the grids that do not have any construction points and any roads, and define them as candidate grid sets.

[0189] Step S83: define each grid in the candidate grid set as a node.

[0190] Step S84, define the entrance and exit where the entry signal is detected as the starting point, define the corresponding construction points in sequence according to the numbering sequence as the waypoints, and define the construction point at the end of the numbering sequence as the end point.

[0191] Step S85, using the A-star algorithm to calculate the minimum number of grids required for the starting point to pass through each waypoint in sequence according to the numbering sequence and finally reach the end point.

[0192] Preferably, the A-star algorithm is the A* algorithm, which does not need to traverse all grids. The A* algorithm is a "search algorithm", which is essentially an optimization of the breadth-first search algorithm (BFS). Starting from the starting point, first traverse the points adjacent to the starting point, and then traverse the points adjacent to the points that have been traversed, and gradually spread outward until the end point is found. The function of the A* algorithm is to "solve the shortest path", such as moving to the target point on a map with obstacles, and digital problems (the shortest path from one state to another). The idea of ​​the A* algorithm is similar to the Dijkstra algorithm, which adopts a greedy strategy, that is, "if the shortest path from A to C passes through B, then the section from A to B must be the shortest", find the shortest path from the starting point to each possible point and record it. The difference between the A* algorithm and the Dijkstra algorithm is that the A* algorithm is a heuristic algorithm, which has prior knowledge, such as "walking in the direction of the end point is more likely to arrive". The A* algorithm not only pays attention to the path that has been traveled, but also predicts the points or states that have not been traveled. Therefore, compared with Dijkstra, the A* algorithm adjusts the order of BFS, searches fewer "unlikely points", and finds the shortest path to the target point faster.

[0193] Step S86, obtaining grids corresponding to the minimum number of grids, and connecting them in sequence to form the shortest path.

[0194] Furthermore, in step S85, the minimum number of grids required from the starting point to the end point is calculated by the A-star algorithm, including:

[0195] Step S851, creating a grid set to be checked.

[0196] Step S852, adding the starting point to the grid set to be checked, setting the priority of the starting point to the highest, setting the priorities of all the waypoints to gradually decrease according to the calculated label order, and setting the priority of the end point to the lowest.

[0197] Step S853, determining whether the grid set to be checked is empty, if the grid set to be checked is not empty, executing step S854.

[0198] Step S854, selecting the node n with the highest priority from the grid set to be checked.

[0199] Step S855, determine whether node n is the end point, if node n is the end point, execute step S856.

[0200] Step S856, starting from the end point, gradually trace the parent node until reaching the starting point.

[0201] Step S857, obtaining the parent node of each tracking step, which is the minimum number of grids.

[0202] Preferably, the priority involves the heuristic function of the A-star algorithm as F=G+H, where G is the movement cost of moving from the starting point to the specified grid, and the path generated along the grid is derived from the known grid information; H is the estimated cost of moving from the specified grid to the end point, and H is derived from the estimation of the unknown grid information; and F is the basis for selecting the next node to be traversed.

[0203] Preferably, for a grid-like graph, the following heuristic functions can be used:

[0204] If the graph allows only four directions of movement, up, down, left, and right, the Manhattan distance can be used to calculate the number of grids that need to be moved horizontally or vertically from the current grid to the target; if the graph allows eight directions of movement, the diagonal distance can be used. Both horizontal and vertical movement and diagonal movement are legal. To improve efficiency, the horizontal and vertical movement is usually an integer of 10, and the diagonal movement is usually an integer of 14 ( If the graph allows movement in any direction, the Euclidean distance, which is the straight-line distance between two points, can be used.

[0205] Furthermore, step S853 determines whether the grid set to be checked is empty, and then includes:

[0206] Step S100: If the grid set to be checked is empty, execute step S200.

[0207] Step S200, traverse all neighboring nodes m of node n, and add all neighboring nodes m to the grid set to be checked.

[0208] Step S300, obtaining the neighboring node m with the highest priority among all neighboring nodes m as the parent node for the next traversal.

[0209] Step S400, starting from the current parent node, gradually tracing the parent node of the next traversal until reaching the end point.

[0210] Step S500, obtaining the parent node of each tracking step, which is the minimum number of grids.

[0211] Preferably, the set of grids to be checked is the open list. In actual application, the A* algorithm implements the shortest path search through the following steps:

[0212] (1) Start from the starting point and add the starting point to an open list for storing grids. Currently, there is only one item in the open list, namely the starting point. More grids will be gradually added in the subsequent search process. The grids in the open list are all grids that can be reached in the next step and are used as alternative grids. In the final shortest path, the grids in the open list may be passed along the way, or they may not be passed. That is, the open list is a list of grids to be checked.

[0213] (2) Check the grids adjacent to the starting point and add the walkable or reachable grids to the open list. Set the starting point to the parent node (parentnode or parentsquare) of these grids. When tracing the path, these parent nodes record the last node passed on the shortest path from the starting point to the node.

[0214] (3) Remove the starting point from the open list and add it to the close list. Each grid in the close list no longer needs to be paid attention to.

[0215] (4) Select the grid with the smallest F value from the open list and repeat steps (2) to (3).

[0216] In summary, by repeatedly traversing the open list, selecting the grid with the smallest F value, and generating new available grids, until the grid where the end point is found.

[0217] Preferably, for the cost of each grid, the heuristic function of each grid needs to be calculated separately. The calculation idea of ​​is similar to the Dijkstra algorithm, which adopts a greedy strategy, that is, "if the shortest path from A to C passes through B, then the section from A to B must be the shortest", find the shortest path from the starting point to each possible point and record it. If and in this embodiment are used as coefficients, the horizontal or vertical movement cost is 10, and the diagonal movement cost is 14.

[0218] This embodiment obtains the elevation coordinates of all entrances and exits, all construction points, and all roads of the construction site; obtains the ratio of the time progress percentage to the construction progress percentage of each construction point, and defines the ratio of the current construction point as the weight value of the current construction point; responds to the entry signal of the navigation module based on any entrance and exit; obtains the preset construction requirements of the construction personnel matching the navigation module, and marks all the construction points that need to be entered as the construction points to be entered according to the preset construction requirements; numbers all the construction points to be entered in sequence with natural numbers, and all the construction points to be entered are marked once as a group of numbering sequences, and the weighted average of the group of numbering sequences is once weighted by the weight values ​​of all the construction points to be entered, and a weighted average value is obtained based on a group of numbering sequences; the minimum value of the weighted average value is calculated by a global optimization algorithm; the numbering sequence corresponding to the minimum value is obtained and the shortest path that passes through the numbering sequence in sequence is obtained by a path search algorithm; and the shortest path is sent to the navigation module. This embodiment uses the ratio of the time progress percentage to the construction progress percentage of each construction point as the weight value of the current construction point, and is intended to intuitively reflect the completion status of the construction point through the weight value. For example, when the ratio of the time progress percentage to the construction progress percentage is greater than 1, it means that the actual construction progress lags behind the expected construction progress and is in a state of needing to speed up the progress; when the ratio of the time progress percentage to the construction progress percentage is less than 1, it means that the actual construction progress is ahead of the expected construction progress and is in a state of not needing to speed up the progress. At this time, the ratio is used as the weight value of the construction point to reflect the completion status of the construction point. That is, the larger the weight value, the more manpower is needed to further increase the construction speed, which provides a quantifiable basis for the previous personnel arrangement, dispatch, and management. This embodiment also supports the situation where a single construction worker is responsible for multiple tasks. By analyzing the distribution of weight values ​​of multiple tasks, the weight values ​​of multiple tasks are repeatedly weighted averaged based on the random numbers of the construction points and their respective distance correction coefficients, and it is iterated with the minimum weighted average as the target. The purpose is to make the weight values ​​with larger numerical values ​​move closer to the smaller numbers, so that the construction workers can reach the construction points with large weight values ​​as early as possible, and finally find the shortest route in the order of construction points corresponding to the minimum value. This not only allows the construction workers to reach the construction point with the largest weight value earliest, and the second largest construction point second earliest, but also avoids detours, thereby further improving construction efficiency.

[0219] like Figure 2 As shown, this embodiment provides an embodiment of a personnel configuration device based on safety gear. In this embodiment, the personnel configuration device is applied to the personnel configuration method based on safety gear as in the above-mentioned embodiment. The personnel configuration device includes an elevation coordinate acquisition module 1, a construction point weight value acquisition module 2, an entry signal response module 3, a construction point marking module 4, a distance correction coefficient acquisition module 5, a construction point number weighted average module 6, a weighted average minimum value calculation module 7, a shortest path acquisition module 8, and a shortest path sending module 9 which are electrically connected in sequence.

[0220] Among them, the elevation coordinate acquisition module 1 is used to obtain the elevation coordinates of all entrances and exits, all construction points, and all roads of the construction site; the construction point weight value acquisition module 2 is used to obtain the ratio of the time progress percentage to the construction progress percentage of each construction point, and define the ratio of the current construction point as the weight value of the current construction point; the entry signal response module 3 is used to respond to the entry signal of the navigation module based on any entrance and exit; the construction point marking module 4 is used to obtain the preset construction requirements of the construction personnel matching the navigation module, and mark all the construction points that need to be entered as the construction points to be entered according to the preset construction requirements; the distance correction coefficient acquisition module 5 is used to obtain the navigation module based on all roads and each construction point to be entered. The distance of each point, and the value of each distance is used as the distance correction coefficient of each construction point to be entered; the weighted average module 6 for construction point labeling is used to number all construction points to be entered in order with natural numbers, and all construction points to be entered are labeled once as a group of labeling sequences, and the group of labeling sequences are weighted averaged once with the weight values ​​of all construction points to be entered, and a weighted average value is obtained based on a group of labeling sequences; the weighted average minimum value calculation module 7 is used to calculate the minimum value of the weighted average value through a global optimization algorithm; the shortest path acquisition module 8 is used to obtain the labeling sequence corresponding to the minimum value and obtain the shortest path that passes through the labeling sequence in sequence through a path search algorithm; the shortest path sending module 9 is used to send the shortest path to the navigation module.

[0221] Furthermore, the personnel configuration device also includes a world coordinate system definition module, a person detection frame acquisition module, a person detection frame mapping module, a two-dimensional person detection frame rotation module, a three-dimensional person detection frame definition module, a three-dimensional person detection frame elevation coordinate acquisition module, a three-dimensional person detection frame elevation coordinate judgment module, and a safety gear not wearing correctly warning generation module, which are electrically connected in sequence; the world coordinate system definition module is electrically connected to the shortest path sending module.

[0222] Among them, the world coordinate system definition module is used to define the world coordinate system based on any horizontal plane and any vertical plane of the construction site; the person detection frame acquisition module is used to respond to the entry signal and obtain the person detection frame matching the entry signal based on the target detection algorithm; the person detection frame mapping module is used to map the person detection frame to the world coordinate system through the homography matrix to form a two-dimensional person detection frame, and the two-dimensional person detection frame is parallel or coplanar with any vertical plane; the two-dimensional person detection frame rotation module is used to obtain the symmetry axis of the two-dimensional person detection frame in the vertical direction, and rotate the two-dimensional person detection frame based on the symmetry axis; the three-dimensional person detection frame definition module is used to obtain the two-dimensional person The complete rotation trajectory of the detection frame is defined as the three-dimensional person detection frame; the three-dimensional person detection frame elevation coordinate acquisition module is used to obtain the elevation coordinates of the three-dimensional person detection frame based on the relative position of the three-dimensional person detection frame and the construction site; the three-dimensional person detection frame elevation coordinate judgment module is used to obtain the elevation coordinates of the navigation module and judge whether the elevation coordinates of the navigation module are within the preset range of the elevation coordinates of the three-dimensional person detection frame; the improper wearing of safety protective gear warning generation module is used to generate a warning of improper wearing of safety protective gear and send it to the external decision-making end if the elevation coordinates of the navigation module are not within the preset range of the elevation coordinates of the three-dimensional person detection frame.

[0223] Furthermore, the person detection frame acquisition module specifically includes a first person detection frame acquisition sub-module, a second person detection frame acquisition sub-module, a third person detection frame acquisition sub-module, a fourth person detection frame acquisition sub-module, a fifth person detection frame acquisition sub-module, a sixth person detection frame acquisition sub-module, a seventh person detection frame acquisition sub-module, and an eighth person detection frame acquisition sub-module, which are electrically connected in sequence; the first person detection frame acquisition sub-module is electrically connected to the world coordinate system definition module, and the eighth person detection frame acquisition sub-module is electrically connected to the person detection frame mapping module.

[0224] Among them, the first person detection frame acquisition submodule is used to respond to the entry signal and acquire image data matching the entry signal through an external preset camera terminal; the second person detection frame acquisition submodule is used to evenly divide the image data into a preset number of grids; the third person detection frame acquisition submodule is used to predict a number of first-order bounding boxes for moving targets in the image data based on all grids according to the target detection algorithm, and each first-order bounding box includes at least one grid; the fourth person detection frame acquisition submodule is used to define the construction personnel with the highest confidence; the fifth person detection frame acquisition submodule is used to respectively acquire the confidence of each first-order bounding box, and acquire the bounding box with the largest confidence and mark it as a second-order bounding box; the sixth person detection frame acquisition submodule is used to calculate the intersection and union ratio of the second-order bounding box with each other first-order bounding box; the seventh person detection frame acquisition submodule is used to select a bounding box with an intersection and union ratio greater than or equal to a preset threshold as a third-order bounding box; the eighth person detection frame acquisition submodule is used to acquire the third-order bounding box with the highest confidence and define it as a person detection frame.

[0225] Furthermore, the weighted average minimum value calculation module specifically includes a first weighted average minimum value calculation submodule, a second weighted average minimum value calculation submodule, a third weighted average minimum value calculation submodule, a fourth weighted average minimum value calculation submodule, a fifth weighted average minimum value calculation submodule, and a sixth weighted average minimum value calculation submodule, which are electrically connected in sequence; the first weighted average minimum value calculation submodule is electrically connected to the construction point number weighted average module, and the sixth weighted average minimum value calculation submodule is electrically connected to the shortest path acquisition module.

[0226] The first weighted average minimum value calculation submodule is used to define a number of random solutions for the minimum value according to formula (1), and define the optimization result of all random solutions as the minimum weighted average value of all labels.

[0227]

[0228] Among them, X i is the set of all random solutions, x1,x2,…,x i ,…,x N -1,x N are each random solution, i is the number of the random solution, and N is the number of all random solutions; V i is the set of velocities of all random solutions, v1,v2,…,v i ,…,v N-1 ,v N are the speeds of each random solution respectively.

[0229] The second weighted average minimum calculation submodule is used to initialize the position of each random solution, and based on the same random solution, update the current position and current speed according to formula (2):

[0230]

[0231] Among them, v id is the speed of the ith random solution at step d, ω·v id-1 is the velocity inertia of the ith random solution at step d-1, ω is the inertia coefficient, c1·random()·(p best,i -x i ) is the self-perception representation of the i-th random solution, c2·random()·(g best,i -x i ) is the social cognitive representation of the i-th random solution; c1 and c2 are both learning factors, random() is a random number in the preset value range, p best,i is the individual optimal solution obtained by the i-th random solution, g best,i is the global optimal solution obtained by the i-th random solution, x id is the ith random solution of the dth step, x id-1 is the i-th random solution of step d-1.

[0232] The third weighted average minimum value calculation submodule is used to iterate each random solution for a preset number of times according to formula (2) to update each p best,i And each g best,i .

[0233] The fourth weighted average minimum value calculation submodule is used to determine each p best,i Whether the first difference compared to the previous iteration is less than or equal to the first preset adaptation threshold.

[0234] The fifth weighted average minimum value calculation submodule is used to determine if all the first differences are less than or equal to the first preset adaptation threshold, best,i Whether the second difference compared to the previous iteration is less than or equal to the second preset adaptation threshold.

[0235] The sixth weighted average minimum value calculation submodule is used to determine that an optimal solution of the minimum value has been obtained if all the second difference values ​​are less than or equal to the second preset adaptation threshold.

[0236] Furthermore, the shortest path acquisition module specifically includes a first shortest path acquisition submodule, a second shortest path acquisition submodule, a third shortest path acquisition submodule, a fourth shortest path acquisition submodule, a fifth shortest path acquisition submodule, and a sixth shortest path acquisition submodule, which are electrically connected in sequence; the first shortest path acquisition submodule is electrically connected to the sixth weighted average minimum value calculation submodule, and the sixth shortest path acquisition submodule is electrically connected to the shortest path sending module.

[0237] Among them, the first shortest path acquisition submodule is used to divide the construction site by grids of preset density; the second shortest path acquisition submodule is used to delete grids that do not have any construction points and any roads, and define them as alternative grid sets; the third shortest path acquisition submodule is used to define each grid in the alternative grid set as a node; the fourth shortest path acquisition submodule is used to define the entrance and exit where the entry signal is detected as the starting point, define the corresponding construction points in sequence according to the numbering order as waypoints, and define the construction point at the end of the numbering order as the end point; the fifth shortest path acquisition submodule is used to calculate the minimum number of grids required for the starting point to pass through each waypoint in sequence according to the numbering order and finally reach the end point through the A-star algorithm; the sixth shortest path acquisition submodule is used to obtain the grids corresponding to the minimum number of grids, and connect them in sequence to form the shortest path.

[0238] Furthermore, the fifth shortest path acquisition submodule specifically includes a first shortest path acquisition unit, a second shortest path acquisition unit, a third shortest path acquisition unit, a fourth shortest path acquisition unit, a fifth shortest path acquisition unit, a sixth shortest path acquisition unit, and a seventh shortest path acquisition unit, which are electrically connected in sequence; the first shortest path acquisition unit is electrically connected to the fourth shortest path acquisition submodule, and the seventh shortest path acquisition unit is electrically connected to the sixth shortest path acquisition submodule.

[0239] Among them, the first shortest path acquisition unit is used to create a grid set to be checked; the second shortest path acquisition unit is used to add the starting point to the grid set to be checked, and set the priority of the starting point to the highest; the third shortest path acquisition unit is used to determine whether the grid set to be checked is empty; the fourth shortest path acquisition unit is used to select the node n with the highest priority from the grid set to be checked if the grid set to be checked is not empty; the fifth shortest path acquisition unit is used to determine whether the node n is the end point; the sixth shortest path acquisition unit is used to gradually track the parent node from the end point until the starting point is reached if the node n is the end point; the seventh shortest path acquisition unit is used to obtain the parent node tracked at each step, which is the minimum number of grids.

[0240] Furthermore, the fifth shortest path acquisition submodule also includes an eighth shortest path acquisition unit, a ninth shortest path acquisition unit, a tenth shortest path acquisition unit, and an eleventh shortest path acquisition unit that are electrically connected in sequence; the eighth shortest path acquisition unit is electrically connected to the seventh shortest path acquisition unit, and the eleventh shortest path acquisition unit is electrically connected to the sixth shortest path acquisition submodule.

[0241] Among them, the eighth shortest path acquisition unit is used to traverse all neighboring nodes m of node n if the grid set to be checked is empty, and add all neighboring nodes m to the grid set to be checked; the ninth shortest path acquisition unit is used to obtain the neighboring node m with the highest priority among all neighboring nodes m as the parent node for the next traversal; the tenth shortest path acquisition unit is used to gradually track the parent node for the next traversal starting from the current parent node until the end point is reached; the eleventh shortest path acquisition unit is used to obtain the parent node for each step of tracking, which is the minimum number of grids.

[0242] It should be noted that this embodiment is a functional module item embodiment based on the above method embodiment. For additional contents such as the optimization, expansion, and example illustration of this embodiment, please refer to the above method embodiment, and this embodiment will not be repeated.

[0243] This embodiment obtains the elevation coordinates of all entrances and exits, all construction points, and all roads of the construction site; obtains the ratio of the time progress percentage to the construction progress percentage of each construction point, and defines the ratio of the current construction point as the weight value of the current construction point; responds to the entry signal of the navigation module based on any entrance and exit; obtains the preset construction requirements of the construction personnel matching the navigation module, and marks all the construction points that need to be entered as the construction points to be entered according to the preset construction requirements; numbers all the construction points to be entered in sequence with natural numbers, and all the construction points to be entered are marked once as a group of numbering sequences, and the weighted average of the group of numbering sequences is once weighted by the weight values ​​of all the construction points to be entered, and a weighted average value is obtained based on a group of numbering sequences; the minimum value of the weighted average value is calculated by a global optimization algorithm; the numbering sequence corresponding to the minimum value is obtained and the shortest path that passes through the numbering sequence in sequence is obtained by a path search algorithm; and the shortest path is sent to the navigation module. This embodiment uses the ratio of the time progress percentage to the construction progress percentage of each construction point as the weight value of the current construction point, and is intended to intuitively reflect the completion status of the construction point through the weight value. For example, when the ratio of the time progress percentage to the construction progress percentage is greater than 1, it means that the actual construction progress lags behind the expected construction progress and is in a state of needing to speed up the progress; when the ratio of the time progress percentage to the construction progress percentage is less than 1, it means that the actual construction progress is ahead of the expected construction progress and is in a state of not needing to speed up the progress. At this time, the ratio is used as the weight value of the construction point to reflect the completion status of the construction point. That is, the larger the weight value, the more manpower is needed to further increase the construction speed, which provides a quantifiable basis for the previous personnel arrangement, dispatch, and management. This embodiment also supports the situation where a single construction worker is responsible for multiple tasks. By analyzing the distribution of weight values ​​of multiple tasks, the weight values ​​of multiple tasks are repeatedly weighted averaged based on the random numbers of the construction points and their respective distance correction coefficients, and it is iterated with the minimum weighted average as the target. The purpose is to make the weight values ​​with larger numerical values ​​move closer to the smaller numbers, so that the construction workers can reach the construction points with large weight values ​​as early as possible, and finally find the shortest route in the order of construction points corresponding to the minimum value. This not only allows the construction workers to reach the construction point with the largest weight value earliest, and the second largest construction point second earliest, but also avoids detours, thereby further improving construction efficiency.

[0244] Figure 3 An embodiment of an electronic device of the present application is shown. In this embodiment, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0245] The memory 102 stores program instructions for implementing the personnel deployment method based on safety gear according to any of the above embodiments.

[0246] The processor 101 is used to execute program instructions stored in the memory 102 to perform personnel configuration based on safety gear.

[0247] The processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having signal processing capabilities. The processor 101 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0248] Further, Figure 4 The schematic diagram of the structure of the storage medium of an embodiment of the present application is that the storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0249] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0250] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

[0251] The specific implementation methods of the present application are described in detail above, but they are only examples, and the present application is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the present application is also within the scope of the present application, and therefore, the equalization, modification, and improvement made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A personnel configuration method based on safety gear, the personnel configuration method is applied to construction personnel wearing safety gear, the safety gear is equipped with a navigation module, the edge of the construction site has at least one entrance and exit, and the construction site has at least one construction point, characterized in that: The personnel positioning method comprises: Step S1, obtaining the elevation coordinates of all entrances and exits, all construction points, and all roads of the construction site; Step S2, respectively obtaining the ratio of the time progress percentage to the construction progress percentage of each construction point, and defining the ratio of the current construction point as the weight value of the current construction point; Step S3, responding to an entry signal of the navigation module based on any entrance or exit; Step S4, obtaining the preset construction requirements of the construction personnel that match the navigation module, and marking all the construction points that need to be entered as construction points to be entered according to the preset construction requirements; Step S5, obtaining the distance between the navigation module and each construction point to be entered based on all roads, and using the value of each distance as a distance correction coefficient for each construction point to be entered; Step S6, all the construction points to be entered are numbered in sequence with natural numbers, all the construction points to be entered are numbered once as a group of numbering sequences, and the group of numbering sequences is weighted averaged once using the weight values ​​of all the construction points to be entered and the distance correction coefficient, and a weighted average value is obtained based on the group of numbering sequences; Step S7, calculating the minimum value of the weighted average value by a global optimization algorithm; Step S8, obtaining the label sequence corresponding to the minimum value and obtaining the shortest path passing through the label sequence in sequence through a path search algorithm; Step S9: sending the shortest path to the navigation module.

2. The personnel allocation method according to claim 1, characterized in that: Step S9, sending the shortest path to the navigation module, then comprising: Step S10, defining a world coordinate system based on any horizontal plane and any vertical plane of the construction site; Step S20, in response to the entry signal, obtaining a person detection frame matching the entry signal based on a target detection algorithm; Step S30, mapping the person detection frame to the world coordinate system through a homography matrix to form a two-dimensional person detection frame, and the two-dimensional person detection frame is parallel to or coplanar with any vertical plane; Step S40, obtaining a symmetry axis of the two-dimensional person detection frame in a vertical direction, and rotating the two-dimensional person detection frame based on the symmetry axis; Step S50, obtaining a complete rotation trajectory of the two-dimensional person detection frame, and defining the complete rotation trajectory as a three-dimensional person detection frame; Step S60, acquiring the elevation coordinates of the three-dimensional person detection frame based on the relative position of the three-dimensional person detection frame and the construction site; Step S70, obtaining the elevation coordinates of the navigation module and determining whether the elevation coordinates of the navigation module are within a preset range of the elevation coordinates of the three-dimensional person detection frame, if not, executing step S80; Step S80, generating a warning of improper wearing of safety gear and sending it to an external decision-making end.

3. The personnel allocation method according to claim 1, characterized in that: Step S20, in response to the entry signal, obtaining a person detection frame matching the entry signal based on a target detection algorithm, including: Step S201, in response to the entry signal, acquiring image data matching the entry signal through an external preset camera terminal; Step S202, dividing the image data into a preset number of grids on average; Step S203, predicting a plurality of first-order bounding boxes for the moving object in the image data based on all the grids according to the object detection algorithm, each first-order bounding box including at least one grid; Step S204, defining the construction worker as having the highest confidence level; Step S205, respectively obtaining the confidence of each first-order bounding box, and obtaining the bounding box with the largest confidence and marking it as the second-order bounding box; Step S206, calculating the intersection-over-union ratio between the second-order bounding box and each other first-order bounding box; Step S207, selecting a bounding box whose intersection-over-union ratio is greater than or equal to a preset threshold as a third-order bounding box; Step S208: Obtain a third-order bounding box with the highest confidence and define it as the person detection box.

4. The personnel allocation method according to claim 1, characterized in that: Step S7, calculating the minimum value of the weighted average value by a global optimization algorithm, including: Step S71, defining a plurality of random solutions for the minimum value according to formula (1), and defining the optimization result of all random solutions as the weighted average of all labels reaching the minimum; Among them, X i is the set of all random solutions, x1,x2,...,x i ,...,x N-1 ,x N are each random solution, i is the number of the random solution, and N is the number of all random solutions; V i is the set of velocities of all random solutions, v1,v2,...,v i ,…,v N-1 ,v N are the speeds of each random solution respectively; Step S72, initialize the position of each random solution, and update the current position and current speed respectively based on the same random solution according to formula (2): Among them, v id is the speed of the ith random solution at step d, ω·v id-1 is the velocity inertia of the ith random solution at step d-1, ω is the inertia coefficient, c1·random()·(p best,i -x i ) is the self-perception representation of the i-th random solution, c2·random()·(g best,i -x i ) is the social cognitive representation of the i-th random solution; c1 and c2 are both learning factors, random() is a random number in the preset value range, p best,i is the individual optimal solution obtained by the i-th random solution, g best,i is the global optimal solution obtained by the i-th random solution, x id is the ith random solution of the dth step, x id-1 is the i-th random solution of step d-1; Step S73, iterate each random solution a preset number of times according to formula (2) to update each p best,i And each g best,i ; Step S74, determine each p best,i Comparing the first difference values ​​of the previous iteration to see whether they are less than or equal to the first preset adaptation threshold, if all the first difference values ​​are less than or equal to the first preset adaptation threshold, executing step S75; Step S75, determine each g best,i Comparing the second difference values ​​of the previous iteration to see whether they are less than or equal to the second preset adaptation threshold, if all the second difference values ​​are less than or equal to the second preset adaptation threshold, executing step S76; Step S76, determining that the optimal solution for the minimum value has been obtained.

5. The personnel allocation method according to claim 1, characterized in that: Step S8, obtaining the label sequence corresponding to the minimum value and obtaining the shortest path passing through the label sequence in sequence through a path search algorithm, including: Step S81, dividing the construction site into grids of preset density; Step S82, deleting grids without any construction points and any roads, and defining them as candidate grid sets; Step S83, defining each grid in the candidate grid set as a node; Step S84, defining the entrance and exit where the entry signal is detected as the starting point, defining the corresponding construction points in the order of the numbers as waypoints, and defining the construction point at the end of the order of the numbers as the end point; Step S85, calculating the minimum number of grids required for the starting point to pass through each waypoint in sequence according to the numbering sequence and finally reach the end point by using the A-star algorithm; Step S86, obtaining grids corresponding to the minimum number of grids, and connecting them in sequence to form the shortest path.

6. The personnel allocation method according to claim 5, characterized in that: Step S85, calculating the minimum number of grids required from the starting point to the end point by using the A-star algorithm, including: Step S851, creating a grid set to be checked; Step S852, adding the starting point to the grid set to be checked, and setting the priority of the starting point to the highest; Step S853, determining whether the grid set to be checked is empty, if the grid set to be checked is not empty, executing step S854; Step S854, selecting a node n with the highest priority from the grid set to be checked; Step S855, determining whether the node n is the end point, if the node n is the end point, executing step S856; Step S856, starting from the end point, gradually tracing the parent node until reaching the start point; Step S857, obtaining the parent node of each tracking step, which is the minimum number of grids.

7. The personnel allocation method according to claim 6, characterized in that: Step S853, determine whether the grid set to be checked is empty, then, include: Step S100, if the grid set to be checked is empty, execute step S200; Step S200, traversing all neighboring nodes m of the node n, and adding all neighboring nodes m to the grid set to be checked; Step S300, obtaining the neighboring node m with the highest priority among all neighboring nodes m as the parent node for the next traversal; Step S400, starting from the current parent node, gradually tracing the parent node of the next traversal until reaching the end point; Step S500, obtaining the parent node of each tracking step, which is the minimum number of grids.

8. A personnel configuration device based on safety gear, the personnel configuration device based on safety gear being applied to the personnel configuration method based on safety gear as claimed in any one of claims 1 to 7, characterized in that: The personnel configuration device comprises: An elevation coordinate acquisition module is used to acquire the elevation coordinates of all entrances and exits, all construction points, and all roads of the construction site; The construction point weight value acquisition module is used to obtain the ratio of the time progress percentage to the construction progress percentage of each construction point, and define the ratio of the current construction point as the weight value of the current construction point; An entry signal response module, used to respond to the entry signal of the navigation module based on any entrance and exit; A construction point marking module to be entered is used to obtain the preset construction requirements of the construction personnel that match the navigation module, and mark all construction points to be entered as construction points to be entered according to the preset construction requirements; A distance correction coefficient acquisition module is used to acquire the distance between the navigation module and each construction point to be entered based on all roads, and use the value of each distance as the distance correction coefficient of each construction point to be entered; The construction point label weighted average module is used to label all the construction points to be entered in order with natural numbers, and all the construction points to be entered are labeled once as a group of labeling sequences, and the group of labeling sequences is weighted averaged once with the weight values ​​of all the construction points to be entered, and a weighted average value is obtained based on the group of labeling sequences; A weighted average minimum value calculation module, used to calculate the minimum value of the weighted average value by a global optimization algorithm; A shortest path acquisition module, used to acquire the label sequence corresponding to the minimum value and acquire the shortest path passing through the label sequence in sequence through a path search algorithm; The shortest path sending module is used to send the shortest path to the navigation module.

9. An electronic device, characterized in that: It includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the personnel configuration method based on safety gear as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the personnel configuration method based on safety gear as described in any one of claims 1 to 7 can be implemented.

Images