Artificial intelligence spectrum sensing port logistics monitoring method

Abstract

The invention relates to an artificial intelligence spectrum sensing port logistics monitoring method, and the method comprises the steps: building a spectrum sensing network based on a plurality of spectrum sensing modules as sensing nodes in advance; if yes, node self-organizing network dynamic adjustment for all sensing nodes in the constructed spectrum sensing network is started, a dynamically adjusted spectrum sensing network is obtained, and idle frequency band resources in the space where the port logistics radiation area is located are detected based on the dynamically adjusted spectrum sensing network; and then, carrying out logistics distribution monitoring on the distribution process of the logistics vehicle in the port logistics radiation area based on the obtained idle frequency band resources. Therefore, not only is the monitoring of the port logistics distribution process realized, but also the idle spectrum resource can be detected based on the constructed spectrum sensing network, so that the wireless data of the monitoring data can be stably and timely completed by using the idle spectrum resource, and the monitoring efficiency and the monitoring timeliness are improved.

Description

Technical Field

[0001] The present invention relates to the field of logistics monitoring, and in particular to an artificial intelligence spectrum sensing port logistics monitoring method. Background Art

[0002] As a special form of modern logistics, port logistics is of great significance to the logistics development and economic activities in the port radiation area. Therefore, it is even more important to realize the monitoring of port logistics.

[0003] In existing port logistics monitoring, the concentration of materials, transportation, and even more logistics vehicles in port logistics requires a significant amount of data transmission between the logistics vehicles and the port logistics monitoring center as they leave the port area and transport goods. This massive amount of data is transmitted wirelessly. However, due to limited spectrum resources within the port's radiation area, the available spectrum for monitoring logistics vehicles is becoming increasingly scarce.

[0004] In port logistics management, all logistics vehicles need to be monitored for transportation, but are limited by the limited idle spectrum resources. As a result, the monitoring process of each logistics vehicle in transit, especially the video monitoring process, is easily unable to complete smooth wireless transmission due to limited spectrum resources, which reduces the efficiency of wireless data transmission and is not conducive to the efficiency and timeliness of port logistics monitoring. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide an artificial intelligence spectrum sensing port logistics monitoring method based on the above-mentioned existing technology.

[0006] The technical solution adopted by the present invention to solve the above technical problems is: an artificial intelligence spectrum sensing port logistics monitoring method, which is characterized by comprising the following steps:

[0007] Step 1: Pre-build a spectrum sensing network based on several spectrum sensing modules as sensing nodes. In this spectrum sensing network, each spectrum sensing module serves as a sensing node for monitoring the availability of spatial spectrum resources in the port logistics radiation area, which includes the port area and the areas already radiated by the port.

[0008] Step 2: Monitor the transportation status of logistics vehicles in the port area;

[0009] Step 3: Make a judgment based on the transport status of the monitored logistics vehicle:

[0010] When the logistics vehicle starts port logistics distribution, go to step 4; otherwise, go to step 2;

[0011] Step 4: start dynamic adjustment of the node self-organizing network for all sensing nodes in the constructed spectrum sensing network to obtain a dynamically adjusted spectrum sensing network;

[0012] Step 5: Based on the dynamically adjusted spectrum sensing network, detect and obtain idle frequency band resources in the space where the port logistics radiation area is located;

[0013] Step 6: Perform logistics distribution monitoring on the distribution process of logistics vehicles within the port logistics radiation area based on the obtained idle frequency band resources.

[0014] Improved, in the artificial intelligence spectrum sensing port logistics monitoring method, in step 6, performing a logistics distribution monitoring process on the distribution process of logistics vehicles within the port logistics radiation area based on the obtained idle frequency band resources includes:

[0015] Assigning corresponding monitoring priorities to each logistics vehicle to be monitored within the port logistics radiation area;

[0016] Logistics distribution monitoring is performed on each logistics vehicle to be monitored in order of monitoring priority and based on the idle frequency band resources.

[0017] As a further improvement, in the artificial intelligence spectrum sensing port logistics monitoring method, the process of assigning corresponding monitoring priorities to each logistics vehicle to be monitored within the port logistics radiation area includes the following steps:

[0018] Step a1, obtaining the real-time curve of the vehicle delivery trajectory corresponding to each logistics vehicle after leaving the port area;

[0019] Step a2: extracting the track station points on the real-time curve of each vehicle's delivery track and the length of time the logistics vehicle stays at the corresponding track station points; wherein the track station points are track points where the length of time the logistics vehicle stays exceeds a preset time threshold;

[0020] Step a3: Calculate the current transportation time required for each logistics vehicle to travel from the port area to the latest track stop;

[0021] Step a4: Calculate the trajectory anomaly index value of each logistics vehicle based on the obtained residence time of each logistics vehicle at each of its trajectory points and the current transportation time;

[0022] Step a5: Arrange all obtained trajectory anomaly index values in ascending order according to the index value size to obtain a trajectory anomaly index value sequence;

[0023] Step a6, assigning corresponding monitoring priorities to the logistics vehicles corresponding to each trajectory abnormality index value in the trajectory abnormality index value sequence; wherein, relative to the logistics vehicles with smaller trajectory abnormality index values, the logistics vehicles with larger trajectory abnormality index values are assigned greater monitoring priorities.

[0024] Furthermore, in the artificial intelligence spectrum sensing port logistics monitoring method, the trajectory anomaly index value of the logistics vehicle is calculated as follows:

[0025]

[0026] in, It represents the trajectory anomaly index value of the mth logistics vehicle after it leaves the port area and drives to the current latest trajectory station point, t n represents the length of time that the mth logistics vehicle stays at the nth track station on its vehicle delivery track real-time curve. N represents the total number of track stations that the mth logistics vehicle appears when it leaves the port area and drives to the latest track station. t N It represents the length of time that the mth logistics vehicle stays at the Nth track point of its vehicle delivery track real-time curve. It represents the current transportation time required for the mth logistics vehicle to leave the port area and travel to the current latest trajectory station.

[0027] As an improvement measure, in the artificial intelligence spectrum sensing port logistics monitoring method, in step 4, the node self-organizing network dynamic adjustment process for all sensing nodes in the constructed spectrum sensing network includes the following steps:

[0028] Step b1, respectively obtaining the real-time energy consumption value of each sensing node in the constructed spectrum sensing network at the current detection time and the average energy consumption value of all sensing nodes at the current detection time;

[0029] Step b2: obtaining the real-time signal-to-noise ratio of each sensing node in the constructed spectrum sensing network at the current detection time and the average signal-to-noise ratio of all sensing nodes at the current detection time;

[0030] Step b3: Obtain the detection probability of each sensing node for detecting an idle frequency band at the current detection time and the average detection probability of all sensing nodes at the current detection time; wherein the average detection probability is the average of the sum of the detection probabilities corresponding to all sensing nodes;

[0031] Step b4, calculating the participation index of each sensing node in the ad hoc network process and the average participation index of all sensing nodes based on the real-time energy consumption value and real-time signal-to-noise ratio of each sensing node at the current detection moment and the average energy consumption value and average signal-to-noise ratio of all sensing nodes;

[0032] Step b5: Select a sensing node whose participation index at the current detection moment is less than the average participation index, and use the selected sensing node as a first-level self-organizing network node;

[0033] Step b6: Select the first-level self-organizing node with a detection probability at the current detection moment that exceeds the obtained average detection probability, and use the selected first-level self-organizing node as the second-level node to be self-organized;

[0034] In step b7, all the secondary nodes to be self-organized perform network self-organization processing.

[0035] As a further improvement, in the artificial intelligence spectrum sensing port logistics monitoring method, the participation index of the sensing node in the self-organizing network process is calculated as follows:

[0036]

[0037] Among them, α u is the participation index of the u-th sensing node in the spectrum sensing network in the self-organizing network process, E u represents the real-time energy consumption value of the u-th sensing node at the current detection moment, U represents the total number of sensing nodes in the spectrum sensing network, μ E represents the average energy consumption value of all sensing nodes in the spectrum sensing network; SNR u represents the real-time signal-to-noise ratio of the u-th sensing node at the current detection moment, μ SNR Represents the average signal-to-noise ratio of all sensing nodes in the spectrum sensing network.

[0038] Improved, in the artificial intelligence spectrum sensing port logistics monitoring method, in step 6, the process of performing logistics distribution monitoring on the distribution process of logistics vehicles within the port logistics radiation area based on the obtained idle frequency band resources includes the following steps:

[0039] Obtain the calculated monitoring priority assigned to each logistics vehicle;

[0040] In descending order of monitoring priority, the instruction uses the idle frequency band resources to perform video data backhaul work on each logistics vehicle in turn; wherein, there is a one-to-one correspondence between logistics vehicles and monitoring priorities.

[0041] Furthermore, in the artificial intelligence spectrum sensing port logistics monitoring method, in step 7, the process of all secondary nodes to be self-organized performing network self-organization processing includes the following steps:

[0042] Step c1: The logistics vehicle corresponding to the highest monitoring priority is regarded as the primary user, and the logistics vehicles corresponding to other monitoring priorities are regarded as secondary users;

[0043] Step c2: determining and processing the switching ratio of the duration of any logistics vehicle using the idle frequency band resources to transmit monitoring data:

[0044] When the duration switching ratio value of any logistics vehicle is less than the preset duration switching ratio threshold, continue to transmit the monitoring data for any logistics vehicle based on the original monitoring priority and use the idle frequency band resources; otherwise, lower the monitoring priority corresponding to any logistics vehicle; wherein the duration switching ratio value of the logistics vehicle is the ratio of the single duration of the logistics vehicle using the idle frequency band resources to the single free duration of the logistics vehicle as the main user using the idle frequency band;

[0045] Step c3: performing monitoring data transmission on each logistics vehicle in sequence according to the monitoring priority from large to small, and utilizing the idle frequency band resources.

[0046] As a further improvement, in the artificial intelligence spectrum sensing port logistics monitoring method, each logistics vehicle is installed with a spectrum sensing module.

[0047] Compared with the existing technology, the advantages of the present invention are: the artificial intelligence spectrum sensing port logistics monitoring method of the invention pre-constructs a spectrum sensing network based on several spectrum sensing modules as sensing nodes, and then when the logistics vehicles in the port area start the port logistics distribution, it starts the node self-organizing network dynamic adjustment for all sensing nodes in the constructed spectrum sensing network, and obtains the dynamically adjusted spectrum sensing network, and detects the idle frequency band resources in the space where the port logistics radiation area is located based on the dynamically adjusted spectrum sensing network; then, based on the obtained idle frequency band resources, the logistics vehicle's distribution process in the port logistics radiation area is performed logistics distribution monitoring. In this way, not only the monitoring of the port logistics distribution process is realized, but also the idle spectrum resources can be detected based on the constructed spectrum sensing network, so as to use the idle spectrum resources to stably and timely complete the wireless data of the monitoring data, thereby improving the monitoring efficiency and monitoring timeliness. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a flow chart of the artificial intelligence spectrum sensing port logistics monitoring method according to an embodiment of the present invention;

[0049] Figure 2 A flow chart showing the process of assigning corresponding monitoring priorities to each logistics vehicle to be monitored within the port logistics radiation area;

[0050] Figure 3 Schematic diagram of a node self-organizing network dynamic adjustment process for all sensing nodes in a constructed spectrum sensing network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The present invention will be described in further detail below with reference to the accompanying drawings and embodiments.

[0052] This embodiment provides an artificial intelligence spectrum sensing port logistics monitoring method. Specifically, the artificial intelligence spectrum sensing port logistics monitoring method in this embodiment includes the following steps 1 to 6:

[0053] Step 1: Pre-build a spectrum sensing network based on a number of spectrum sensing modules as sensing nodes. In this spectrum sensing network, each spectrum sensing module serves as a sensing node for monitoring the availability of spatial spectrum resources within the port logistics radiation area, which includes the port area and areas already radiated by the port. In this embodiment, each logistics vehicle in the port logistics process is equipped with one of the aforementioned spectrum sensing modules.

[0054] It should be noted that, in this embodiment, each spectrum sensing module uses an energy detection method to detect idle spectrum conditions; for example, part of the code section of the energy detection method simulation program is as follows:

[0055] NFFT = 2^nextpow2(L);

[0056] Y=fft(y,NFFT) / L;

[0057] f=fs / 2*linspace(0,1,NFFT / 2);

[0058] subplot(122); plot(f,2*abs(Y(1:NFFT / 2)),'r-*'); title('Energy detection effect');

[0059] Po = sum(abs(Y).^2);

[0060] Step 2: Monitor the transportation status of logistics vehicles in the port area;

[0061] Step 3: Make a judgment based on the transport status of the monitored logistics vehicle:

[0062] When the logistics vehicle starts port logistics distribution, go to step 4; otherwise, go to step 2;

[0063] Step 4: start dynamic adjustment of the node self-organizing network for all sensing nodes in the constructed spectrum sensing network to obtain a dynamically adjusted spectrum sensing network;

[0064] Step 5: Based on the dynamically adjusted spectrum sensing network, detect and obtain idle frequency band resources in the space where the port logistics radiation area is located;

[0065] Step 6: Performing logistics and delivery monitoring on the logistics vehicles' delivery process within the port logistics radiation area based on the obtained idle frequency resources. For example, in this embodiment, performing logistics and delivery monitoring on the logistics vehicles' delivery process within the port logistics radiation area based on the obtained idle frequency resources includes: assigning a corresponding monitoring priority to each logistics vehicle to be monitored within the port logistics radiation area; and then performing logistics and delivery monitoring on each logistics vehicle to be monitored based on the monitoring priority order and the idle frequency resources.

[0066] It should be noted that, in the process of assigning monitoring priorities to Shanshu, the process of assigning corresponding monitoring priorities to each logistics vehicle to be monitored within the port logistics radiation area includes the following steps a1 to a6:

[0067] Step a1, obtaining the real-time curve of the vehicle delivery trajectory corresponding to each logistics vehicle after leaving the port area;

[0068] Step a2: extracting the track station points on the real-time curve of each vehicle's delivery track and the length of time the logistics vehicle stays at the corresponding track station points; wherein the track station points are track points where the length of time the logistics vehicle stays exceeds a preset time threshold;

[0069] Step a3: Calculate the current transportation time required for each logistics vehicle to travel from the port area to the latest track stop;

[0070] Step a4: Calculate the trajectory anomaly index value of each logistics vehicle based on the obtained dwell time of each logistics vehicle at each of its trajectory points and the current transportation time. In this embodiment, the trajectory anomaly index value of the logistics vehicle is calculated as follows:

[0071]

[0072] in, It represents the trajectory anomaly index value of the mth logistics vehicle after it leaves the port area and drives to the current latest trajectory station point, t n represents the length of time that the mth logistics vehicle stays at the nth track station on its vehicle delivery track real-time curve. N represents the total number of track stations that the mth logistics vehicle appears when it leaves the port area and drives to the latest track station. t N It represents the length of time that the mth logistics vehicle stays at the Nth track point of its vehicle delivery track real-time curve. It represents the current transportation time required for the mth logistics vehicle to leave the port area and travel to the latest track station;

[0073] Step a5: Arrange all obtained trajectory anomaly index values in ascending order according to the index value size to obtain a trajectory anomaly index value sequence;

[0074] Step a6, assigning corresponding monitoring priorities to the logistics vehicles corresponding to each trajectory abnormality index value in the trajectory abnormality index value sequence; wherein, relative to the logistics vehicles with smaller trajectory abnormality index values, the logistics vehicles with larger trajectory abnormality index values are assigned greater monitoring priorities.

[0075] In addition, with respect to the aforementioned artificial intelligence spectrum sensing port logistics monitoring method, in step 4, the node self-organizing network dynamic adjustment process for all sensing nodes in the constructed spectrum sensing network includes the following steps b1 to b7:

[0076] Step b1, respectively obtaining the real-time energy consumption value of each sensing node in the constructed spectrum sensing network at the current detection time and the average energy consumption value of all sensing nodes at the current detection time;

[0077] Step b2: obtaining the real-time signal-to-noise ratio of each sensing node in the constructed spectrum sensing network at the current detection time and the average signal-to-noise ratio of all sensing nodes at the current detection time;

[0078] Step b3: Obtain the detection probability of each sensing node for detecting an idle frequency band at the current detection time and the average detection probability of all sensing nodes at the current detection time; wherein the average detection probability is the average of the sum of the detection probabilities corresponding to all sensing nodes;

[0079] Step b4, calculating the participation index of each sensing node in the ad hoc network process and the average participation index of all sensing nodes based on the real-time energy consumption value and real-time signal-to-noise ratio of each sensing node at the current detection moment and the average energy consumption value and average signal-to-noise ratio of all sensing nodes;

[0080] Step b5: Select a sensing node whose participation index at the current detection moment is less than the average participation index, and use the selected sensing node as a first-level self-organizing network node;

[0081] Step b6: Select the first-level self-organizing node with a detection probability at the current detection moment that exceeds the obtained average detection probability, and use the selected first-level self-organizing node as the second-level node to be self-organized;

[0082] In step b7, all the secondary nodes to be self-organized perform network self-organization processing.

[0083] Specifically in this embodiment, in the above step b4, the participation index of the sensing node in the self-organizing network process is calculated as follows:

[0084]

[0085] Among them, α u is the participation index of the u-th sensing node in the spectrum sensing network in the self-organizing network process, E u represents the real-time energy consumption value of the u-th sensing node at the current detection moment, U represents the total number of sensing nodes in the spectrum sensing network, μ E Indicates the average energy consumption of all sensing nodes in the spectrum sensing network; SNR u represents the real-time signal-to-noise ratio of the u-th sensing node at the current detection moment, μ SNR Represents the average signal-to-noise ratio of all sensing nodes in the spectrum sensing network.

[0086] In addition, in the above-mentioned step 6 of this embodiment, the process of performing logistics distribution monitoring on the distribution process of logistics vehicles within the port logistics radiation area based on the obtained idle frequency band resources includes the following steps: obtaining the monitoring priority assigned to each logistics vehicle that has been calculated; and, in order of monitoring priority from large to small, instructing the use of the idle frequency band resources to perform video data backhaul work on each logistics vehicle in turn; wherein, there is a one-to-one correspondence between logistics vehicles and monitoring priorities.

[0087] Regarding the above step 7, in this embodiment, the process of all the secondary nodes to be self-organized performing network self-organization processing includes the following steps c1 to c3:

[0088] Step c1: The logistics vehicle corresponding to the highest monitoring priority is regarded as the primary user, and the logistics vehicles corresponding to other monitoring priorities are regarded as secondary users;

[0089] Step c2: determining and processing the switching ratio of the duration of any logistics vehicle using the idle frequency band resources to transmit monitoring data:

[0090] When the duration switching ratio value of any logistics vehicle is less than the preset duration switching ratio threshold, the monitoring data for any logistics vehicle shall continue to be transmitted based on the original monitoring priority and using the aforementioned idle frequency band resources; otherwise, the monitoring priority corresponding to any logistics vehicle shall be lowered; wherein, the duration switching ratio value of the logistics vehicle is the ratio of the single duration of the logistics vehicle using the aforementioned idle frequency band resources to the single free duration of the logistics vehicle as the main user using the idle frequency band; for example, assuming that the single duration of the logistics vehicle R using the aforementioned idle frequency band resources is marked as T R The logistics vehicle C, as the main user, uses the idle frequency band for a single free time, which is marked as T C , then the duration switching ratio of the logistics vehicle R is marked as β, β = T R / T C ;

[0091] Step c3: perform monitoring data transmission on each logistics vehicle in descending order of monitoring priority using the aforementioned idle frequency band resources.

[0092] Although the preferred embodiments of the present invention have been described in detail above, it should be clearly understood that various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. Artificial intelligence spectrum sensing port logistics monitoring method, characterized by: The steps include: Step 1: Pre-build a spectrum sensing network based on several spectrum sensing modules as sensing nodes. In this spectrum sensing network, each spectrum sensing module serves as a sensing node for monitoring the availability of spatial spectrum resources in the port logistics radiation area, which includes the port area and the areas already radiated by the port. Step 2: Monitor the transportation status of logistics vehicles in the port area; Step 3: Make a judgment based on the transport status of the monitored logistics vehicle: When the logistics vehicle starts port logistics distribution, go to step 4; otherwise, go to step 2; Step 4: start dynamic adjustment of the node self-organizing network for all sensing nodes in the constructed spectrum sensing network to obtain a dynamically adjusted spectrum sensing network; Step 5: Based on the dynamically adjusted spectrum sensing network, detect and obtain idle frequency band resources in the space where the port logistics radiation area is located; Step 6: Perform logistics distribution monitoring on the distribution process of logistics vehicles within the port logistics radiation area based on the obtained idle frequency band resources.

2. The artificial intelligence spectrum sensing port logistics monitoring method according to claim 1 is characterized in that: In step 6, the logistics distribution monitoring process of the logistics vehicles within the port logistics radiation area is performed based on the obtained idle frequency band resources, including: Assigning corresponding monitoring priorities to each logistics vehicle to be monitored within the port logistics radiation area; Logistics distribution monitoring is performed on each logistics vehicle to be monitored in order of monitoring priority and based on the idle frequency band resources.

3. The artificial intelligence spectrum sensing port logistics monitoring method according to claim 2 is characterized in that: The process of assigning corresponding monitoring priorities to each logistics vehicle to be monitored within the port logistics radiation area includes the following steps: Step a1, obtaining the real-time curve of the vehicle delivery trajectory corresponding to each logistics vehicle after leaving the port area; Step a2: extracting the track station points on the real-time curve of each vehicle's delivery track and the length of time the logistics vehicle stays at the corresponding track station points; wherein the track station points are track points where the length of time the logistics vehicle stays exceeds a preset time threshold; Step a3: Calculate the current transportation time required for each logistics vehicle to travel from the port area to the latest track stop; Step a4: Calculate the trajectory anomaly index value of each logistics vehicle based on the obtained residence time of each logistics vehicle at each of its trajectory points and the current transportation time; Step a5: Arrange all obtained trajectory anomaly index values in ascending order according to the index value size to obtain a trajectory anomaly index value sequence; Step a6, assigning corresponding monitoring priorities to the logistics vehicles corresponding to each trajectory abnormality index value in the trajectory abnormality index value sequence; wherein, relative to the logistics vehicles with smaller trajectory abnormality index values, the logistics vehicles with larger trajectory abnormality index values are assigned greater monitoring priorities.

4. The artificial intelligence spectrum sensing port logistics monitoring method according to claim 3 is characterized in that: The calculation method of the trajectory abnormality index value of the logistics vehicle is as follows: in, It represents the trajectory anomaly index value of the mth logistics vehicle after it leaves the port area and drives to the current latest trajectory station point, t n represents the length of time that the mth logistics vehicle stays at the nth track station on its vehicle delivery track real-time curve. N represents the total number of track stations that the mth logistics vehicle appears when it leaves the port area and drives to the latest track station. t N It represents the length of time that the mth logistics vehicle stays at the Nth track point of its vehicle delivery track real-time curve. It represents the current transportation time required for the mth logistics vehicle to leave the port area and travel to the current latest trajectory station.

5. The artificial intelligence spectrum sensing port logistics monitoring method according to claim 4 is characterized in that: In step 4, the node self-organizing network dynamic adjustment process for all sensing nodes in the constructed spectrum sensing network includes the following steps: Step b1, respectively obtaining the real-time energy consumption value of each sensing node in the constructed spectrum sensing network at the current detection time and the average energy consumption value of all sensing nodes at the current detection time; Step b2: obtaining the real-time signal-to-noise ratio of each sensing node in the constructed spectrum sensing network at the current detection time and the average signal-to-noise ratio of all sensing nodes at the current detection time; Step b3: Obtain the detection probability of each sensing node for detecting an idle frequency band at the current detection time and the average detection probability of all sensing nodes at the current detection time; wherein the average detection probability is the average of the sum of the detection probabilities corresponding to all sensing nodes; Step b4, calculating the participation index of each sensing node in the ad hoc network process and the average participation index of all sensing nodes based on the real-time energy consumption value and real-time signal-to-noise ratio of each sensing node at the current detection moment and the average energy consumption value and average signal-to-noise ratio of all sensing nodes; Step b5: Select a sensing node whose participation index at the current detection moment is less than the average participation index, and use the selected sensing node as a first-level self-organizing network node; Step b6: Select the first-level self-organizing node with a detection probability at the current detection moment that exceeds the obtained average detection probability, and use the selected first-level self-organizing node as the second-level node to be self-organized; In step b7, all the secondary nodes to be self-organized perform network self-organization processing.

6. The artificial intelligence spectrum sensing port logistics monitoring method according to claim 5 is characterized in that: The participation index of the sensing node in the self-organizing network process is calculated as follows: Among them, α u is the participation index of the u-th sensing node in the spectrum sensing network in the self-organizing network process, E u represents the real-time energy consumption value of the u-th sensing node at the current detection moment, U represents the total number of sensing nodes in the spectrum sensing network, μ E represents the average energy consumption value of all sensing nodes in the spectrum sensing network; SNR u represents the real-time signal-to-noise ratio of the u-th sensing node at the current detection moment, μ SNR Represents the average signal-to-noise ratio of all sensing nodes in the spectrum sensing network.

7. The artificial intelligence spectrum sensing port logistics monitoring method according to claim 6 is characterized in that: In step 6, the process of performing logistics distribution monitoring on the distribution process of logistics vehicles within the port logistics radiation area based on the obtained idle frequency band resources includes the following steps: Obtain the calculated monitoring priority assigned to each logistics vehicle; In descending order of monitoring priority, the instruction uses the idle frequency band resources to perform video data backhaul work on each logistics vehicle in turn; wherein, there is a one-to-one correspondence between logistics vehicles and monitoring priorities.

Images