A computing and communication device based on artificial intelligence hardware collaboration

Abstract

The present invention provides a computing and communication device based on artificial intelligence hardware collaboration, which belongs to the technical field of communication devices. The device has a communication module and a computing module, and is applied to a method for identifying risks at construction sites. The method specifically comprises: using a computing and communication device as an analysis device, and determining based on construction risk factors that a monitoring device does not need to be set up as an analysis device separately, using the monitoring device as a general device, and using monitoring positions to divide the general devices into different monitoring device combinations, and determining an optimal setting scheme in a preferred setting scheme based on the construction risk factors of different general devices in the monitoring device combination and the distance from the analysis device, and using the optimal setting scheme to perform local identification processing of the construction risks of the monitoring device combination, thereby ensuring the efficiency of the identification processing of construction safety risks.

Description

Technical Field

[0001] The present invention belongs to the technical field of communication devices, and in particular, relates to a computing and communication device based on artificial intelligence hardware collaboration. Background Art

[0002] In order to achieve safety supervision of construction sites, the existing technical solutions often identify and process safety risks through the setting of Internet of Things monitoring devices. Specifically, in the invention patent application CN202410143900.5 "Smart construction site safety supervision method and system based on the Internet of Things", safety risks are identified through the Internet of Things monitoring device, but there are the following technical problems:

[0003] The identification of safety risks at construction sites requires high real-time performance. If there is no timely intervention, it may develop into a larger safety accident. Therefore, if local collaborative computing devices cannot be used for identification and processing, the efficiency of safety risk identification and processing cannot be guaranteed.

[0004] In response to the above technical problems, the present invention provides a computing and communication device based on artificial intelligence hardware collaboration. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, a computing and communication device based on artificial intelligence hardware collaboration is provided.

[0007] A computing and communication device based on artificial intelligence hardware collaboration, comprising a communication module and a computing module, is applied to a construction site risk identification method, specifically comprising:

[0008] S1 determines the construction risk factors of different monitoring devices based on the distribution data of risk points in the monitoring area of ​​the monitoring device, uses the computing and communication device as the analysis device, and when it is determined based on the construction risk factor that the monitoring device does not need to be set up as a separate analysis device, uses the monitoring device as a general device;

[0009] S2 divides the general devices into different monitoring device combinations according to the monitoring positions, and determines the number of analysis devices to be set for the monitoring device combination based on the distances between the general devices in the monitoring device combination and the construction risk factors of the different general devices;

[0010] S3 generates a setting scheme for the analysis device of the monitoring device combination based on the monitoring position and setting quantity of the general device as constraint conditions, and determines a preferred setting scheme among the schemes based on the distance between the analysis devices;

[0011] S4 determines the optimal setting scheme in the preferred setting schemes based on the construction risk factors of different general devices in the monitoring device combination and the distance from the analysis device, and uses the optimal setting scheme to perform local identification processing of the construction risk of the monitoring device combination.

[0012] The beneficial effects of the present invention are:

[0013] 1. Based on the distance between general devices in the monitoring device combination and the construction risk factors of different general devices, the number of analysis devices to be set in the monitoring device combination is determined, which ensures the difference in communication processing difficulty when the general devices are performing risk identification processing due to the difference in the distance between the general devices. At the same time, by further combining the construction risk factors of the general devices, the risk identification needs of the monitoring device combination with higher construction risks are also guaranteed. On the basis of reducing costs as much as possible, it also meets the needs of identifying and processing construction safety risks of the monitoring device combination.

[0014] 2. The optimal setting scheme in the preferred setting scheme is determined based on the construction risk factors of different general devices in the monitoring device combination and the distance from the analysis device, thereby achieving accurate setting of the analysis device from multiple dimensions and avoiding the technical problem of greater communication difficulty during risk identification due to the long distance from the general device. Without increasing the number of analysis devices to be set, the reliability of identification and processing of construction safety risks of the monitoring device combination is improved by optimizing the layout of the setting positions.

[0015] A further technical solution is that the communication module is responsible for communication processing with the monitoring device, other analysis devices and the unified security monitoring platform.

[0016] A further technical solution is that the computing module is responsible for identifying and processing the construction safety risks of the monitoring data of the monitoring device using a preset artificial intelligence model.

[0017] A further technical solution is that the distribution data of the risk points include the number of risk points of different types and their distribution positions in the monitoring area.

[0018] A further technical solution is that the method for determining the optimal setting scheme in the preferred setting scheme is:

[0019] Determine the risk identification reliability of different general devices based on the distance between different general devices and different analytical devices;

[0020] Using the construction risk factors of different general devices, determine the weight coefficients of risk identification reliability of different general devices;

[0021] The identification reliability of the priority setting scheme is determined by the weight coefficient of the risk identification reliability of different general devices and the risk identification reliability, and the optimal setting scheme among the preferred setting schemes is determined based on the identification reliability.

[0022] A further technical solution is that the optimal setting scheme is a preferred setting scheme with the highest recognition reliability.

[0023] A further technical solution is to perform local identification processing of the construction risk of the monitoring device combination, specifically including:

[0024] Using the optimal setting scheme to perform local identification and processing of the construction safety risks of the monitoring device combination

[0025] The analysis device in the monitoring device combination is set up and processed using the optimal setting scheme, and the monitoring data of the monitoring devices in the monitoring device combination are processed based on the analysis device in the monitoring device combination, and security risks are identified and processed according to a preset artificial intelligence model.

[0026] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings;

[0029] Figure 1 It is a flow chart of a computing and communication device based on the collaboration of artificial intelligence hardware;

[0030] Figure 2 is a flow chart of a method for determining a construction risk factor of a monitoring device;

[0031] Figure 3 is a flow chart of a method for determining the number of analysis devices to be set in a monitoring device combination;

[0032] Figure 4 It is a flow chart of a method for preferably setting a scheme in a scheme. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification. Example

[0034] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a computing and communication device based on artificial intelligence hardware collaboration is provided, which has a communication module and a computing module and is applied to a construction site risk identification method, specifically including:

[0035] S1 determines the construction risk factors of different monitoring devices based on the distribution data of risk points in the monitoring area of ​​the monitoring device, uses the computing and communication device as the analysis device, and when it is determined based on the construction risk factor that the monitoring device does not need to be set up as a separate analysis device, uses the monitoring device as a general device;

[0036] Furthermore, the communication module is responsible for communication processing with the monitoring device, other analysis devices and the unified security monitoring platform.

[0037] Specifically, the computing module is responsible for identifying and processing the construction safety risks of the monitoring data of the monitoring device using a preset artificial intelligence model.

[0038] It can be understood that the distribution data of the risk points include the number of different types of risk points and their distribution positions in the monitoring area.

[0039] Specifically, Figure 2 As shown, the method for determining the construction risk factor of the monitoring device is:

[0040] Based on the distribution data of the risk points, determining the number of different types of risk points of the monitoring device, and determining the basic risk coefficient of the monitoring device in combination with the preset risk coefficients of the different types of risk points;

[0041] Determine the distribution positions of different types of risk points in the monitoring area based on the distribution data of different types of risk points, determine the risk sub-areas with cross-construction risks through the distribution positions, and determine the sub-area risk coefficients of the risk sub-areas based on the number of risk points in different risk sub-areas and the preset risk coefficients of different risk points;

[0042] The cross-risk coefficient of the monitoring device is determined by using the sub-area risk coefficients of different risk sub-areas, and the construction risk factor of the monitoring device is determined by the basic risk coefficient and the cross-risk coefficient of the monitoring device.

[0043] Furthermore, the cross risk coefficient of the monitoring device is determined according to the sum of sub-area risk coefficients of different risk sub-areas.

[0044] It should also be noted that the value range of the construction risk factor of the monitoring device is between 0 and 1. When the construction risk factor of the monitoring device is greater than the preset coefficient threshold, it is determined that the monitoring device corresponding to the monitoring device needs to be set up as an analysis device separately.

[0045] It can also be understood that the method for determining the construction risk factor of the monitoring device is:

[0046] Based on the distribution data of the risk points, determining the number and distribution positions of different types of risk points of the monitoring device;

[0047] Based on the distribution position of the risk points, determine the interval distance between different risk points and other risk points, determine other risk points with cross-construction risks with the risk points through the interval distance, and use them as cross-construction risk points, and determine the risk assessment coefficients of different risk points based on the types of different risk points and the number of cross-construction risk points;

[0048] The construction risk factor of the monitoring location is determined by risk assessment coefficients of different risk points.

[0049] It can also be understood that the method for determining the construction risk factor of the monitoring location is:

[0050] S11 determines the number of different types of risk points at the monitoring location based on the distribution data of the risk points, and judges whether the number of risk points at the monitoring location is greater than the preset number of risk points. If so, proceed to the next step; if not, proceed to step S14;

[0051] S12 determines the preset risk coefficients of different risk points by using the types of risk points, and judges whether the average values ​​of the preset risk coefficients of different risk points are greater than the preset risk coefficient threshold value. If so, it is determined that the monitoring device corresponding to the monitoring device needs to be set up as an analysis device separately. If not, proceed to the next step;

[0052] S13 determines the risk points whose preset risk coefficients are greater than the maximum value of the set risk coefficients based on the preset risk coefficients of different risk points, and judges whether the number of risk points whose preset risk coefficients are greater than the maximum value of the set risk coefficients meets the requirements, if so, proceeds to the next step, if not, determines that the monitoring device corresponding to the monitoring device needs to be set up as an analysis device separately;

[0053] S14 determines the basic risk coefficient of the monitoring device based on the number of different types of risk points of the monitoring device and the preset risk coefficients of different types of risk points, and judges whether the basic risk coefficient of the monitoring device meets the requirements. If so, proceed to the next step; if not, determine that the monitoring device corresponding to the monitoring position needs to be set up as an analysis device separately;

[0054] S15 determines the distribution positions of different types of risk points in the monitoring area based on the distribution data of different types of risk points, determines the risk sub-areas with cross-construction risks through the distribution positions, determines the sub-area risk coefficients of the risk sub-areas based on the number of risk points in different risk sub-areas and the preset risk coefficients of different risk points, and determines whether the number of risk sub-areas whose sub-area risk coefficients do not meet the requirements meets the requirements, if so, proceeds to the next step, if not, determines that the monitoring device corresponding to the monitoring position needs to be set up as an analysis device separately;

[0055] S16 determines the cross risk coefficient of the monitoring device by using the sub-area risk coefficients of different risk sub-areas, and determines the construction risk factor of the monitoring device by using the basic risk coefficient and the cross risk coefficient of the monitoring device.

[0056] S2 divides the general devices into different monitoring device combinations according to the monitoring positions, and determines the number of analysis devices to be set for the monitoring device combination based on the distances between the general devices in the monitoring device combination and the construction risk factors of the different general devices;

[0057] Furthermore, the general device is divided into different monitoring device combinations, specifically including:

[0058] Divide the construction site into multiple areas using a preset area, and determine the areas corresponding to different general devices based on the areas where the monitoring positions of the general devices are located;

[0059] Group common devices in the same area into the same monitoring device group.

[0060] It should be noted that if Figure 3 As shown, the method for determining the number of analysis devices in the monitoring device combination is as follows:

[0061] Determine the average distance between adjacent general devices using the distance between general devices in the monitoring device combination, and determine the distribution dispersion coefficient of the monitoring device combination according to the preset dispersion coefficient corresponding to the average distance;

[0062] Determine the average value of the construction risk factors of different general devices in the monitoring device combination by using the construction risk factors of different general devices in the monitoring device combination, and use it as the combination risk coefficient;

[0063] The number of analysis devices in the monitoring device combination is determined based on the number of the monitoring device combination, the combination risk coefficient, and the distribution dispersion coefficient.

[0064] Further, determining the number of analysis devices in the monitoring device combination based on the number of the monitoring device combination, the combination risk coefficient, and the distribution dispersion coefficient specifically includes:

[0065] Determining the minimum required number of analysis devices in the monitoring device combination based on the number of the monitoring device combination;

[0066] Based on the combined risk coefficient and the distribution dispersion coefficient, determining a preset proportional factor of the demand quantity under the combined risk coefficient and a preset proportional factor of the demand quantity under the distribution dispersion coefficient;

[0067] The product of the preset proportional factor of the required quantity, the preset proportional factor of the required quantity under the distribution dispersion coefficient and the minimum required quantity is used as the setting quantity of the analysis device in the monitoring device combination.

[0068] It can also be understood that the method for determining the number of analysis devices in the monitoring device combination is:

[0069] The average distance between adjacent general devices in the monitoring device combination is determined by using the distance between the general devices, and the distribution dispersion coefficient of the monitoring device combination is determined according to the preset dispersion coefficient corresponding to the average distance, and the required number of analysis devices under the distribution dispersion coefficient is determined by using the preset mapping function through the distribution dispersion coefficient and the number of the monitoring device combinations;

[0070] Determine the average value of the construction risk factors of different general devices in the monitoring device combination through the construction risk factors of different general devices in the monitoring device combination, and use it as the combined risk coefficient, and determine the required number of analysis devices under the combined risk coefficient by using the combined risk coefficient and the number of monitoring device combinations and using a preset mapping function;

[0071] The number of analysis devices to be set in the monitoring device combination is determined based on the number of analysis devices required to be set under the distribution dispersion coefficient and the number of analysis devices required to be set under the combination risk coefficient.

[0072] Further, determining the number of analysis devices in the monitoring device combination based on the number of analysis devices required for setting under the distribution dispersion coefficient and the number of analysis devices required for setting under the combination risk coefficient specifically includes:

[0073] The maximum value of the required number of analysis devices under the distribution dispersion coefficient and the required number of analysis devices under the combination risk coefficient is used as the number of analysis devices in the monitoring device combination.

[0074] It should also be noted that the method for determining the number of analysis devices in the monitoring device combination is:

[0075] S21: obtaining the number of general devices in the monitoring device combination, determining whether the number of general devices is less than the preset number of devices, if so, determining the number of analysis devices in the monitoring device combination by using the preset number, if not, proceeding to the next step;

[0076] S22 determines whether the number of the general devices is greater than the device limit number, if so, proceeds to the next step, if not, proceeds to step S25;

[0077] S23: using the distance between the general devices in the monitoring device combination to determine the average distance between the adjacent general devices, and determining the distribution dispersion coefficient of the monitoring device combination according to the preset dispersion coefficient corresponding to the average distance, and judging whether the distribution dispersion coefficient of the monitoring device combination meets the requirements, if so, proceeding to the next step, if not, determining the number of analysis devices in the monitoring device combination according to the preset upper limit;

[0078] S24 uses the construction risk factors of different general devices in the monitoring device combination to determine the average value of the construction risk factors of different general devices in the monitoring device combination, and uses it as the combined risk coefficient to determine whether the combined risk coefficient of the monitoring device combination meets the requirements. If so, proceed to the next step; if not, determine the number of analysis devices in the monitoring device combination according to a preset upper limit;

[0079] S25 determines the number of analysis devices in the monitoring device combination based on the number of the monitoring device combination, the combination risk coefficient, and the distribution dispersion coefficient.

[0080] S3 generates a setting scheme for the analysis device of the monitoring device combination based on the monitoring position and setting quantity of the general device as constraint conditions, and determines a preferred setting scheme among the schemes based on the distance between the analysis devices;

[0081] Further, a setting scheme of the analysis device in the monitoring device combination is generated, specifically including:

[0082] Generate a setup plan for the analysis device of the monitoring device combination based on the monitoring location and number of settings of the general device as constraints

[0083] Using the monitoring position of the general device as an alternative setting position;

[0084] Based on the candidate setting positions and setting quantities, a setting scheme of the analysis device in the monitoring device combination is determined.

[0085] Specifically, Figure 4 As shown, the preferred method of setting the scheme in the scheme is:

[0086] Determine the distances between different analysis devices according to the arrangement positions of different analysis devices in the scheme;

[0087] Determining the setting dispersion coefficients of different analysis devices by using the distances between different analysis devices and other analysis devices in the monitoring device combination;

[0088] The comprehensive setting dispersion coefficient of the analysis device in the scheme is determined based on the average value of the setting dispersion coefficients of different analysis devices, and the preferred setting scheme in the scheme is determined based on the comprehensive setting dispersion coefficient.

[0089] Furthermore, the optimal setting scheme in the preferred setting scheme is a priority setting scheme in which the discrete coefficient is comprehensively set to meet the requirements.

[0090] It should also be noted that the preferred method of setting the scheme in the scheme is:

[0091] S31 determines the distances between different analysis devices according to the setting positions of different analysis devices in the scheme, and judges whether there is an analysis device whose distance to other analysis devices is less than a preset distance threshold. If yes, proceed to the next step; if no, determine that the scheme is a priority setting scheme;

[0092] S32: the analysis devices whose distances to other analysis devices are less than a preset distance threshold are regarded as clustered analysis devices, and it is determined whether the number of the clustered analysis devices is greater than the preset number of analysis devices. If so, the process proceeds to the next step; if not, the process proceeds to step S35;

[0093] S33 determines whether the ratio of the number of analysis devices of the clustered setting analysis device in the monitoring device combination meets the requirement, if yes, proceeds to the next step, if no, determines that the scheme does not belong to the priority setting scheme;

[0094] S34 obtains the number of the clustered analysis devices and the proportion of the number of analysis devices in the monitoring device combination, and determines the setting clustering coefficient of the clustered analysis devices in combination with the distances between different clustered analysis devices and other analysis devices, and judges whether the setting clustering coefficient of the clustered analysis devices meets the requirements. If so, proceeds to the next step; if not, determines that the scheme does not belong to the priority setting scheme;

[0095] S35 determines the setting discrete coefficients of different analysis devices by using the distances between different analysis devices and other analysis devices in the monitoring device combination, and determines whether the proportion of the number of analysis devices that do not meet the setting discrete coefficients is greater than the proportion of the number of preset devices. If not, proceed to the next step. If yes, determine that the scheme does not belong to the priority setting scheme.

[0096] S36 determines a comprehensive setting dispersion coefficient of the analysis device in the scheme based on the average value of the setting dispersion coefficients of different analysis devices, and determines a preferred setting scheme in the scheme based on the comprehensive setting dispersion coefficient.

[0097] S4 determines the optimal setting scheme in the preferred setting schemes based on the construction risk factors of different general devices in the monitoring device combination and the distance from the analysis device, and uses the optimal setting scheme to perform local identification processing of the construction risk of the monitoring device combination.

[0098] Specifically, the method for determining the optimal setting scheme in the preferred setting scheme is:

[0099] Determine the risk identification reliability of different general devices based on the distance between different general devices and different analytical devices;

[0100] Using the construction risk factors of different general devices, determine the weight coefficients of risk identification reliability of different general devices;

[0101] The identification reliability of the priority setting scheme is determined by the weight coefficient of the risk identification reliability of different general devices and the risk identification reliability, and the optimal setting scheme among the preferred setting schemes is determined based on the identification reliability.

[0102] Furthermore, the optimal setting scheme is a preferred setting scheme with the highest recognition reliability.

[0103] It can be understood that the local identification process of the construction risk of the monitoring device combination specifically includes:

[0104] Using the optimal setting scheme to perform local identification and processing of the construction safety risks of the monitoring device combination

[0105] The analysis device in the monitoring device combination is set up and processed using the optimal setting scheme, and the monitoring data of the monitoring devices in the monitoring device combination are processed based on the analysis device in the monitoring device combination, and security risks are identified and processed according to a preset artificial intelligence model.

[0106] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0107] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0108] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A computing and communication device based on artificial intelligence hardware collaboration, comprising a communication module and a computing module, applied to a construction site risk identification method, characterized in that: Specifically include: Based on the distribution data of the risk points in the monitoring area of ​​the monitoring device, the construction risk factors of different monitoring devices are determined, and the computing and communication devices are used as analysis devices. When it is determined based on the construction risk factors that the monitoring device does not need to be set up with a separate analysis device, the monitoring device is used as a general device; The general devices are divided into different monitoring device combinations by using monitoring positions, and the number of analysis devices of the monitoring device combinations is determined based on the distances between the general devices in the monitoring device combinations and the construction risk factors of the different general devices; Taking the monitoring position and the number of settings of the general device as constraints, generating a setting scheme of the analysis device of the monitoring device combination, and determining a preferred setting scheme among the schemes based on the distance between the analysis devices; Determine the optimal setting scheme in the preferred setting schemes based on the construction risk factors of different general devices in the monitoring device combination and the distances from the analysis device, and use the optimal setting scheme to perform local identification processing of the construction risk of the monitoring device combination; The method for determining the number of analysis devices in the monitoring device combination is as follows: Determine the average distance between adjacent general devices using the distance between general devices in the monitoring device combination, and determine the distribution dispersion coefficient of the monitoring device combination according to the preset dispersion coefficient corresponding to the average distance; Determine an average value of the construction risk factors of different general devices in the monitoring device combination by using the construction risk factors of different general devices in the monitoring device combination, and use it as a combined risk coefficient; Determining the number of analysis devices in the monitoring device combination based on the number of the monitoring device combination, the combination risk coefficient, and the distribution dispersion coefficient; Determining the number of analysis devices in the monitoring device combination based on the number of the monitoring device combination, the combination risk coefficient, and the distribution dispersion coefficient specifically includes: Determining the minimum required number of analysis devices in the monitoring device combination based on the number of the monitoring device combination; Based on the combined risk coefficient and the distribution dispersion coefficient, determining a preset proportional factor of the demand quantity under the combined risk coefficient and a preset proportional factor of the demand quantity under the distribution dispersion coefficient; The product of the preset proportional factor of the required quantity, the preset proportional factor of the required quantity under the distribution dispersion coefficient and the minimum required quantity is used as the setting quantity of the analysis devices in the monitoring device combination; The method for determining the optimal setting scheme in the preferred setting scheme is: Determine the risk identification reliability of different general devices based on the distance between different general devices and different analytical devices; Using the construction risk factors of different general devices, determine the weight coefficients of risk identification reliability of different general devices; The identification reliability of the preferred setting scheme is determined by the weight coefficient of the risk identification reliability of different general devices and the risk identification reliability, and the optimal setting scheme in the preferred setting scheme is determined based on the identification reliability.

2. The computing and communication device based on artificial intelligence hardware collaboration as claimed in claim 1, characterized in that: The communication module is responsible for communication processing with the monitoring device, other analysis devices and the unified security monitoring platform.

3. The computing and communication device based on artificial intelligence hardware collaboration as claimed in claim 1, characterized in that: The computing module is responsible for identifying and processing the construction safety risks of the monitoring data of the monitoring device using a preset artificial intelligence model.

4. The computing and communication device based on artificial intelligence hardware collaboration as claimed in claim 1, characterized in that: The method for determining the construction risk factor of the monitoring device is: Based on the distribution data of the risk points, determining the number of different types of risk points of the monitoring device, and determining the basic risk coefficient of the monitoring device in combination with the preset risk coefficients of the different types of risk points; Determine the distribution positions of different types of risk points in the monitoring area based on the distribution data of different types of risk points, determine the risk sub-areas with cross-construction risks through the distribution positions, and determine the sub-area risk coefficients of the risk sub-areas based on the number of risk points in different risk sub-areas and the preset risk coefficients of different risk points; The cross-risk coefficient of the monitoring device is determined by using the sub-area risk coefficients of different risk sub-areas, and the construction risk factor of the monitoring device is determined by the basic risk coefficient and the cross-risk coefficient of the monitoring device.

5. The computing and communication device based on artificial intelligence hardware collaboration as claimed in claim 4, characterized in that: The cross-risk coefficient of the monitoring device is determined according to the sum of sub-area risk coefficients of different risk sub-areas.

6. The computing and communication device based on artificial intelligence hardware collaboration as claimed in claim 1, characterized in that: The general device is divided into different monitoring device combinations, specifically including: Divide the construction site into multiple areas using a preset area, and determine the areas corresponding to different general devices based on the areas where the monitoring positions of the general devices are located; Group common devices in the same area into the same monitoring device group.

7. The computing and communication device based on artificial intelligence hardware collaboration as claimed in claim 1, characterized in that: The optimal setting scheme is the preferred setting scheme with the highest recognition reliability.

Images