Network deployment method and device, computer readable storage medium and product

Abstract

The invention relates to a network deployment method and device, a computer readable storage medium and a product, and relates to the technical field of communication. The network deployment method comprises the following steps: collecting construction site data at a plurality of continuous moments; inputting the construction site data at a plurality of continuous moments into a pre-trained model to predict a communication demand and a communication channel state of the construction site at a target moment; generating a target network deployment scheme based on the plurality of communication modules according to the communication demand and the communication channel state; and deploying a communication network of the construction site according to the target network deployment scheme.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technologies, and particularly to a network deployment method, apparatus, computer-readable storage medium, and product. Background Art

[0002] In recent years, with the rapid development of the intelligent mine, unmanned driving technology, and intelligent construction machinery industries, the number of devices at large-scale engineering construction sites has been increasing day by day, and the demand for a real-time, efficient, and stable communication network has increased sharply. Summary of the Invention

[0003] One technical problem to be solved by the present disclosure is: how to improve the adaptability and efficiency of network deployment.

[0004] According to a first aspect of some embodiments of the present disclosure, there is provided a network deployment method, including: collecting construction site data at a plurality of consecutive moments; inputting the construction site data at a plurality of consecutive moments into a pre-trained model to predict the communication requirements and communication channel states of the construction site at a target moment; generating a target network deployment plan based on a plurality of communication modules according to the communication requirements and communication channel states; and deploying a communication network for the construction site according to the target network deployment plan.

[0005] In some embodiments, network deployment includes multiple stages, and multiple communication modules correspond to the multiple stages of network deployment.

[0006] In some embodiments, for each of the multiple communication modules, the communication module includes one or more communication units. Generating a target network deployment plan based on a plurality of communication modules according to the communication requirements and communication channel states includes: determining a target network deployment plan from a plurality of candidate network deployment plans according to the satisfaction degrees of each candidate network deployment plan in the plurality of candidate network deployment plans with respect to the communication requirements and communication channel states, where each candidate network deployment plan includes a plurality of communication units, and the plurality of units belong to the plurality of communication modules.

[0007] In some embodiments, the communication requirements and communication channel states are represented by a first vector, and each candidate network deployment plan is represented by a second vector. The network deployment method further includes: for each candidate network deployment plan, determining the satisfaction degree of the candidate network deployment plan with respect to the communication requirements and communication channel states according to the similarity between the second vector corresponding to the candidate network deployment plan and the first vector.

[0008] In some embodiments, the multiple stages include at least one of a public network access stage, a network relay stage, a strip network deployment stage, a private network construction stage, a wireless network coverage stage, a sensor network deployment stage, and an equipment information transmission construction stage.

[0009] In some embodiments, the network deployment method further includes: monitoring the performance of the communication network at the construction site of the deployment; determining whether to adjust the communication network at the construction site of the deployment according to the results of the performance monitoring.

[0010] In some embodiments, monitoring the performance of the communication network at the construction site of the deployment includes: monitoring the performance index values of the communication network at the construction site, where the performance index values include at least one of delay, packet loss rate, and throughput; determining the results of the performance monitoring based on the performance index values.

[0011] In some embodiments, determining whether to adjust the communication network at the construction site of the deployment according to the results of the performance monitoring includes: adjusting the communication network at the construction site of the deployment when the results of the performance monitoring are within the specified range; not adjusting the communication network at the construction site of the deployment when the results of the performance monitoring are not within the specified range.

[0012] In some embodiments, adjusting the communication network at the construction site of the deployment includes: re-predicting the communication requirements and communication channel status at the construction site at the target time; regenerating a target network deployment plan based on multiple communication modules according to the re-predicted communication requirements and communication channel status; redeploying the communication network at the construction site according to the regenerated target network deployment plan.

[0013] In some embodiments, deploying the communication network at the construction site according to the target network deployment plan includes: determining network deployment parameters according to the target network deployment plan; sending the network deployment parameters to the devices at the construction site so that the devices at the construction site are configured according to the network deployment parameters.

[0014] In some embodiments, the network deployment parameters include at least one of communication node location, networking structure, data transmission mode, and frequency resource allocation information.

[0015] In some embodiments, deploying the communication network at the construction site according to the target network deployment plan includes: when the communication requirements and communication channel status are met, determining the topology structure that enables the communication link between construction devices to achieve the best communication quality as the topology structure of the communication network.

[0016] In some embodiments, the network deployment method further includes: training the model according to historical construction site data to determine the first parameters of the model; adjusting the first parameters of the model to determine the second parameters of the model; using the model with the second parameters as the pre-trained model.

[0017] In some embodiments, adjusting the first parameter of the model to determine the second parameter of the model includes: inputting historical construction site data into the model with the first parameter to determine the predicted communication demand and the predicted communication channel state at the test moment; and adjusting the first parameter of the model by combining the actual communication demand, the actual communication channel state, the predicted communication demand, and the predicted communication channel state at the test moment to determine the second parameter of the model.

[0018] In some embodiments, the communication demand is represented by at least one of signal-to-noise ratio, packet loss rate, and latency.

[0019] In some embodiments, the construction site data includes at least one of construction equipment data, construction task data, and construction communication data. The construction equipment data includes at least one of construction equipment type, construction equipment quantity, and construction equipment operating state. The construction task data includes the construction task type. The construction communication data includes the communication channel state at the construction site.

[0020] In some embodiments, the model is a Large Language Model (LLM), and the large language model is used to determine the association relationship between the construction equipment quantity, the construction task type, the communication channel state, and the communication demand.

[0021] According to a second aspect of some embodiments of the present disclosure, there is provided a network deployment device, including: an acquisition module configured to acquire construction site data at a plurality of consecutive moments; a prediction module configured to input the construction site data at a plurality of consecutive moments into a pre-trained model to predict the communication demand and the communication channel state of the construction site at the target moment; a generation module configured to generate a target network deployment plan based on a plurality of communication modules according to the communication demand and the communication channel state; and a deployment module configured to deploy the communication network of the construction site according to the target network deployment plan.

[0022] According to a third aspect of some embodiments of the present disclosure, there is provided a network deployment device, including: a processor; and a memory coupled to the processor for storing instructions, which when executed by the processor, cause the processor to execute the network deployment method as described above.

[0023] According to a fourth aspect of some embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program, wherein when the program is executed by a processor, the network deployment method as described above is implemented.

[0024] According to a fifth aspect of some embodiments of the present disclosure, there is provided a computer program product including instructions, which when executed by a processor, cause the processor to execute the network deployment method as described above.

[0025] The present disclosure uses construction site data and a pre-trained model to predict the communication requirements and communication channel status at the construction site, and generates a target network deployment plan using multiple communication modules based on the predicted communication requirements and communication channel status, and deploys the communication network at the construction site. The present disclosure can perform network deployment according to the communication requirements and communication channel status at the construction site, can improve the adaptability of network deployment, and can also enhance the flexibility and efficiency of network deployment by generating a target network deployment plan using multiple communication modules.

[0026] Other features and advantages of the present disclosure will become clear from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0028] Figure 1 A flowchart showing a network deployment method according to some embodiments of the present disclosure is shown.

[0029] Figure 2 A schematic diagram showing multiple communication modules according to some embodiments of the present disclosure is shown.

[0030] Figure 3 A flowchart showing a network deployment method according to some other embodiments of the present disclosure is shown.

[0031] Figure 4 A schematic diagram showing the structure of a network deployment device according to some embodiments of the present disclosure is shown.

[0032] Figure 5 A schematic diagram showing the structure of a network deployment device according to some other embodiments of the present disclosure is shown.

[0033] Figure 6 A schematic diagram showing the structure of a network deployment device according to some further embodiments of the present disclosure is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] Next, the technical solutions in the embodiments of the present disclosure will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and in no way limits the present disclosure and its application or use. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts belong to the scope of protection of the present disclosure.

[0035] The demand for communication networks at the construction site is increasing day by day. For example, in typical scenarios such as smart mines, tunnel construction, and large-scale earthwork construction, dozens or even hundreds of driverless construction vehicles and engineering equipment often need to cooperate simultaneously, and transmit high-bandwidth control, monitoring, and sensing information in real time. Good communication networking is the key guarantee for realizing construction safety, efficient operation, and precise coordination of driverless equipment.

[0036] In the construction machinery industry, the mainstream construction communication solutions usually rely mainly on private network communication (such as 4G / 5G private networks, wireless Mesh networks), supplemented by a small amount of satellite communication or Wi-Fi hotspot coverage. However, such communication solutions are usually fixed and statically deployed at the initial stage of the engineering project, lacking real-time adaptability, and it is difficult to adjust in a timely manner with the dynamic changes of the construction environment, the number of equipment, or the construction tasks, with obvious limitations.

[0037] The current construction communication solution design is mostly in a "one-size-fits-all" mode, that is, according to the communication requirements formulated at the initial stage of the project, little or no dynamic reorganization or adjustment can be carried out during the construction process. Once the construction scenario changes or the demand for construction equipment increases, it is difficult to quickly adapt to the new requirements, which is extremely likely to lead to a decline in communication performance and even the risk of communication interruption, seriously affecting the collaborative work efficiency of on-site equipment.

[0038] At the same time, there is a lack of an efficient and accurate construction communication demand prediction mechanism. The formulation of the current engineering construction communication solution mostly relies on expert experience, lacking intelligent prediction and decision-making tools, and it is impossible to efficiently and accurately predict real-time construction communication demands and on-site channel conditions. Especially in scenarios with complex terrain or rapid progress of the construction process, phenomena such as waste of communication resources, mismatch of communication modules, and even communication paralysis frequently occur due to inaccurate prediction.

[0039] The existing construction communication networking system also lacks a dynamic optimization mechanism. After the communication network for the current large-scale construction scenario is deployed, it is basically in a "static operation" state, and it is very difficult to achieve real-time dynamic optimization based on communication performance feedback. During the construction process, the environment and tasks continue to change, and the existing networking solutions cannot adapt to dynamic adjustments, and the communication performance often shows a gradual downward trend, making it difficult to ensure continuous and stable communication services.

[0040] In summary, there are still prominent problems in the construction communication networking technology of the current construction machinery industry, such as static communication solutions, insufficient accuracy in predicting communication requirements, and lack of real-time dynamic adjustment capabilities. To meet the high real-time, dynamic, and reliable communication requirements of increasingly complex construction scenarios, there is an urgent need to propose a new communication networking method to predict and adapt to the communication requirements and channel conditions at the construction site in a more accurate, efficient, and intelligent manner, realizing the dynamic and adaptive combination of communication networks, thereby greatly improving the overall performance and efficiency of on-site collaborative communication for large-scale construction fleets.

[0041] Based on this, the present disclosure provides a network deployment method. The network deployment method of the present disclosure is an intelligent communication module dynamic combination method based on large model prediction, which can overcome problems such as fixed construction communication solutions, insufficient prediction accuracy, and lack of dynamic optimization mechanisms in related technologies. By adopting a modular solution design, intelligent prediction technology, and an adaptive dynamic combination deployment method, the efficient and flexible adjustment and optimization of the communication networking solution are realized to better meet the communication requirements of construction scenarios such as intelligent mines and large-scale driverless construction fleets.

[0042] Figure 1 A flowchart showing the network deployment method according to some embodiments of the present disclosure is shown. As Figure 1 shown, the method of this embodiment includes steps S11 to S17.

[0043] In step S11, construction site data at a continuous plurality of moments is collected.

[0044] The construction site data includes at least one of construction equipment data, construction task data, and construction communication data. The construction equipment data includes at least one of construction equipment type, construction equipment quantity, and construction equipment operating status. The construction task data includes construction task type, and the construction communication data includes the communication channel status at the construction site.

[0045] Through sensors, communication devices, positioning devices, etc. installed on construction equipment at the construction site, the dynamic data of construction equipment, that is, construction equipment data, is collected in real time.

[0046] The construction equipment operating status includes the real-time position of the construction equipment, whether the construction equipment is operating, the moving speed and trajectory information of the construction equipment, etc.

[0047] The construction task type includes, for example, excavation, transportation, unloading, compaction, etc.

[0048] The communication channel status at the construction site includes the signal interference intensity, communication link quality, etc. at the construction site. The communication channel status at the construction site can be represented by parameters such as signal-to-noise ratio, packet loss rate, and delay.

[0049] In some embodiments, the construction site data can be continuously collected, and the data collected at each moment is aggregated to the central processing unit through the wireless communication module and pre-processed to form a feature dataset. Subsequently, the feature dataset is used as the construction site data for communication demand prediction. For example, at time t, the feature dataset X t can be represented by formula (1).

[0050] X t ={E t ,L t ,M t ,T t ,C t}(1)

[0051] where E t ={e t,i} is the number of construction equipment i at time t, i is the equipment number, i = 1, 2,..., N t , N t is the total number of equipment. L t ={l t,i =(x t,i ,y t,i ,z t,i ,v t,i )} is the position coordinates (x t,i ,y t,i ,z t,i ) and velocity vector v t,i of construction equipment i at time t. M t ={m t,i} is the operating trajectory of construction equipment i at time t. T t is the type of construction task at time t. C t is the communication channel state at time t, including parameters such as signal-to-noise ratio, packet loss rate, and delay. The above feature dataset forms a real-time feature matrix.

[0052] In step S13, the construction site data at multiple consecutive moments is input into a pre-trained model to predict the communication demand and communication channel state of the construction site at the target moment.

[0053] In some embodiments, the model is a large language model, and the large language model is used to determine the correlation relationship between the number of construction equipment, the type of construction task, the communication channel state, and the communication demand. The large language model has strong language ability, friendly interaction, is lightweight, has low deployment cost, and has strong versatility.

[0054] The large language model is pre-trained using the Transformer architecture and is fine-tuned with supervision on a construction scenario dataset, enabling the large language model to learn and master the correlation relationships among the number of construction equipment, the types of construction tasks, the communication channel status, and the communication requirements in different construction scenarios. Thus, the construction site data at multiple consecutive moments can be input into the model to obtain the communication requirements of the construction site at the target moment output by the model.

[0055] In some embodiments, the communication requirements are represented by at least one of signal-to-noise ratio, packet loss rate, and latency. The communication channel status can also be represented by at least one of signal-to-noise ratio, packet loss rate, and latency. That is, the communication requirements represent the signal-to-noise ratio, packet loss rate, and latency conditions required at the target moment, and the communication channel status represents the signal-to-noise ratio, packet loss rate, and latency conditions to be achieved at the target moment.

[0056] Since the construction site data includes various feature data, the large model can learn and master the complex correlation relationships among these various feature data. To balance the accuracy of the model and the training time, the correlation relationships among the four feature data that have a greater impact on the channel environment are selected for the model to master. Those skilled in the art can understand that for different construction scenarios, other feature data can also be selected according to the collected construction site data, and the model can be made to master the correlation relationships among the selected feature data.

[0057] In some embodiments, the prediction process of the communication requirements using the model can be represented by formula (2).

[0058] Y t+Δt =F LLM (X t ,X t-1 ,...,X t-k ;θ) (2)

[0059] Wherein, Y t+Δt is the communication requirements and communication channel status at the predicted moment t + Δt, and the value range of Δt is, for example, 5 to 30 minutes. F LLM (.) is the model function, and X t ,X t-1 ,...,X t-k are the feature data sets at moments t, t - 1,..., t - k respectively, and θ is the set of fine-tuning parameters.

[0060] The fine-tuning parameters are determined by adjusting the model using historical construction site data to improve the accuracy of the model's prediction for the current construction scenario.

[0061] In some embodiments, the network deployment method also includes: training the model based on historical construction site data to determine a first parameter of the model; adjusting the first parameter of the model to determine a second parameter of the model; and using the model with the second parameter as a pre-trained model.

[0062] Adjusting the first parameter of the model to determine the second parameter of the model includes: inputting historical construction site data into the model with the first parameter to determine the predicted communication demand and communication channel status at the test time; combining the actual communication demand, the actual communication channel status, the predicted communication demand, and the predicted communication channel status at the test time, and adjusting the first parameter of the model to determine the second parameter of the model.

[0063] In some embodiments, after the historical construction site data is input into the model having the first parameter, the first parameter of the model is adjusted based on the following optimization objective, ie, formula (3).

[0064]

[0065] Among them, Y T+ΔT , are the predicted communication demand and predicted communication channel state at the test time T+ΔT, and the actual communication demand and actual communication channel state. The above optimization goal is to determine the parameter θ corresponding to minimizing the prediction error, that is, the second parameter.

[0066] After the model is trained using historical construction site data, the model parameters are fine-tuned based on the actual communication needs at the time of testing, making the model more suitable for the current construction scenario and making the model's predicted communication needs and communication channel status more accurate. In other words, for different construction scenarios, such as different construction types and construction times, the fine-tuning parameters corresponding to the current construction scenario can be determined and predictions can be made based on the fine-tuning parameters.

[0067] In step S15, a target network deployment solution is generated based on multiple communication modules according to communication requirements and communication channel status.

[0068] After determining the communication requirements and the communication channel status, the network deployment is carried out in a targeted manner based on the communication requirements and the communication channel status. Since the communication requirements and the communication channel status often change, the corresponding network deployment scheme also needs to be adaptively changed accordingly. In order to improve the flexibility and efficiency of network deployment, the present disclosure generates a target network deployment scheme based on multiple communication modules.

[0069] The network deployment includes multiple phases, and multiple communication modules correspond to the multiple phases of the network deployment. The multiple phases of the network deployment include at least one of a public network access phase, a network relay phase, a strip network deployment phase, a private network construction phase, a wireless network coverage phase, a sensor network deployment phase, and a device information transmission construction phase. The present disclosure divides the network deployment solution into multiple phases, and uses the implementation solution of each phase, that is, the communication unit, to build the target network deployment solution. Those skilled in the art can understand that in addition to these phases listed in the present disclosure, there may be other phases in the network deployment. For example, there are phases where the implementation solutions of various network deployment solutions are the same, so such phases are not modularized anymore.

[0070] The purpose of the public network access phase is for the Internet access project department, which is divided into satellite access, microwave access, and fiber optic access. Satellite access is divided into high-orbit satellite access and low-orbit satellite access, and fiber optic access is divided into directly buried fiber optic, overhead fiber optic, and duct fiber optic.

[0071] The purpose of the network relay phase is to connect the project department and the construction site for communication, which is divided into microwave wireless relay and fiber optic wired relay. Fiber optic relay is divided into directly buried fiber optic, overhead fiber optic, and duct fiber optic.

[0072] The purpose of the strip network deployment phase is to deploy networks in long-strip construction spaces such as tunnels and underground roadways, which is divided into leaky cable solutions, digital fiber optic repeater solutions, and special-shaped antenna solutions.

[0073] The private network construction phase is used to provide 5G network coverage at the construction site, which is divided into virtual 5G private network, hybrid 5G private network, and independent 5G private network.

[0074] The wireless network coverage (WiFiMesh) phase is used to provide WiFi network coverage at the construction site, which is divided into WiFi and WiFiMesh.

[0075] The sensor network deployment phase is used to provide sensor network coverage at the construction site, which is divided into Low Power Wide Area Network (abbreviated as: LoRa Wan) solutions and Low Power Wide Area Network (abbreviated as: LoRa Mesh) solutions.

[0076] The device information transmission construction phase (which can also be called the terminal construction phase) is used to provide information reception and transmission at the device end, which is divided into remote / vehicle-mounted communication modules (Telematics Box, abbreviated as: T-Box) and video modules (Video BOX, abbreviated as: V-Box).

[0077] That is, for each of the multiple communication modules, the communication module includes one or more communication units. For example, for the communication module corresponding to the public network access phase, the communication module includes communication units such as high-orbit satellite access, low-orbit satellite access, microwave access, directly buried optical fiber, aerial optical fiber, and duct optical fiber.

[0078] Figure 2 The schematic diagram of multiple communication modules according to some embodiments of the present disclosure is shown. As Figure 2 shown, the seven stages of network deployment correspond to seven communication modules, and each communication module includes multiple communication units. By combining the communication units in these communication modules, multiple network deployment solutions can be formed.

[0079] Each communication unit included in each of the above stages is the smallest unit of the networking solution. Each communication unit provides applicable scenarios, technical requirements, adapted communication requirements, performance, hardware selection reference, and cost budget for key parts, etc., so as to form a network deployment solution library by combining these communication units. The network deployment solution library M can be represented by formula (4).

[0080] M = {M1, M2,..., M n} (4)

[0081] wherein, M i represents a network deployment solution, including one of the communication units in each of the communication modules corresponding to the above respective stages. i = 1, 2,..., n, and n represents the maximum number of network deployment solutions in the network deployment solution library.

[0082] In some embodiments, generating a target network deployment solution based on multiple communication modules according to communication requirements and communication channel status includes: determining a target network deployment solution from multiple candidate network deployment solutions according to the satisfaction degrees of each candidate network deployment solution in the multiple candidate network deployment solutions with respect to the communication requirements and communication channel status, wherein each candidate network deployment solution includes multiple communication units, and the multiple units belong to multiple communication modules.

[0083] Using the satisfaction degrees of the candidate network deployment solutions with respect to the communication requirements and communication channel status to determine the target network deployment solution. In some embodiments, the communication requirements and communication channel status are represented by a first vector, and each candidate network deployment solution is represented by a second vector. Generating a target network deployment solution based on multiple communication modules according to the communication requirements and communication channel status further includes: for each candidate network deployment solution, determining the satisfaction degree of the candidate network deployment solution with respect to the communication requirements and communication channel status according to the similarity between the second vector corresponding to the candidate network deployment solution and the first vector.

[0084] For example, the communication requirements and communication channel status are represented by vector Y t+ΔtIt is shown that the candidate network deployment plan utilizes M i It is shown that then the target network deployment plan M is determined according to formulas (5) and (6). * .

[0085]

[0086] According to the predicted communication requirements and communication channel status, automatically search and match the communication module or module combination suitable for the current scenario from the network deployment plan library, that is, the target network deployment plan. The matching process adopts the scene requirement similarity calculation and multi-factor decision analysis method, realizing the accurate and rapid matching of communication modules.

[0087] In step S17, according to the target network deployment plan, deploy the communication network at the construction site.

[0088] After determining the target network deployment plan, perform the deployment according to the deployment requirements corresponding to the target network deployment plan.

[0089] In some embodiments, deploying the communication network at the construction site according to the target network deployment plan includes: determining network deployment parameters according to the target network deployment plan; sending the network deployment parameters to the construction equipment so that the construction equipment is configured according to the network deployment parameters. For example, the network deployment parameters can be sent to the construction equipment through the central communication control unit at the construction site, so that the communication units of each construction equipment execute the configuration parameter update according to the instructions of the central communication control unit, complete the real-time dynamic combination of communication modules and network reconstruction, and realize the instant deployment of the communication plan.

[0090] The network deployment parameters include at least one of communication node location, network structure, data transmission mode, and frequency resource allocation information.

[0091] In some embodiments, deploying the communication network at the construction site according to the target network deployment plan includes: when the communication requirements and communication channel status are met, determining the topological structure that enables the communication link between construction equipment to reach the best communication quality (or best communication state) as the topological structure of the communication network. That is, select the topological structure with the best communication quality, and at the same time, the system needs to meet the connectivity constraint and communication rate constraint, and the generation of multi-level communication networking plans follows by analogy.

[0092] For example, the topological structure of the communication network is determined according to formulas (7) and (8).

[0093] G(P,E,W) (7)

[0094] max G ∑ w w i,j (8)

[0095] Among them, P = (p1, p2,..., p1) represents the set of device nodes, E = {(p i , p j ) | p i , p j ∈ P} represents the set of communication links, and W = {w i,j | (p i , p j ) ∈ E} represents the weight of the current communication link, which is determined according to parameters such as communication capacity, link reliability, and link delay.

[0096] In the above embodiments, the present disclosure uses construction site data and a pre-trained model to predict the communication requirements and communication channel status of the construction site, and generates a target network deployment plan using multiple communication modules based on the predicted communication requirements and communication channel status, and deploys the communication network of the construction site. The present disclosure can perform network deployment according to the communication requirements and communication channel status of the construction site, can improve the adaptability of network deployment, and can also improve the flexibility and efficiency of network deployment by generating a target network deployment plan using multiple communication modules.

[0097] In some embodiments, the network deployment method further includes: monitoring the performance of the deployed communication network of the construction site; and determining whether to adjust the deployed communication network of the construction site according to the results of the performance monitoring.

[0098] Monitoring the performance of the deployed communication network of the construction site includes: monitoring the performance index values of the communication network of the construction site, where the performance index values include at least one of delay, packet loss rate, and throughput; and determining the results of the performance monitoring based on the performance index values.

[0099] The results of the performance monitoring are fed back to the control center in real time, and the control center can judge the effectiveness of the current network deployment plan according to the fed-back results.

[0100] In some embodiments, determining whether to adjust the deployed communication network of the construction site according to the results of the performance monitoring includes: adjusting the deployed communication network of the construction site when the results of the performance monitoring are within the specified range; and not adjusting the deployed communication network of the construction site when the results of the performance monitoring are not within the specified range.

[0101] Adjusting the deployed communication network of the construction site includes: re-predicting the communication requirements and communication channel status of the construction site at the target moment; re-generating a target network deployment plan based on the re-predicted communication requirements and communication channel status using multiple communication modules; and re-deploying the communication network of the construction site according to the re-generated target network deployment plan.

[0102] In some embodiments, the result of performance monitoring is represented by the real-time link loss value of the communication system, and the real-time link loss value of the communication system is calculated according to formula (9).

[0103] L t = α·Del t + β·PLR t + γ·(1 - THG t )

[0104] Wherein, Del t ∈ [0, 1] represents the communication delay factor, PLR t ∈ [0, 1] represents the packet loss rate factor, and THG t ∈ [0, 1] represents the network throughput factor. The corresponding relationship between the above three link loss factors and the implemented communication metrics can be determined according to Table 1, for example. α, β, γ ∈ [0, 1] are the weight coefficients corresponding to each factor, and α + β + γ = 1. Their proportional relationship can be adjusted according to the communication requirements of the actual construction scenario.

[0105] Table 1

[0106]

[0107] When L t > L thr , trigger the reorganization of the communication networking scheme, that is, adjust the communication network at the construction site where the deployment is located. L thr is the specified critical value of system link damage. In this way, a closed-loop of dynamic feedback and scheme adjustment is formed to improve the rationality of the deployed communication network.

[0108] Through the above complete closed-loop dynamic adjustment mechanism, the dynamic combined deployment of communication modules driven by real-time data at the construction site is realized, significantly improving the accuracy, real-time performance and stability of the communication networking scheme, and effectively ensuring the unmanned collaborative communication requirements of large-scale construction fleets.

[0109] Figure 3 shows a schematic flowchart of a network deployment method according to other embodiments of the present disclosure. As Figure 3 shown, the network deployment method in this embodiment set includes steps S31 to S36.

[0110] In step S31, the characteristic data such as the device type, location, task, and channel condition at the construction site are collected and processed in real time. This step can serve as a data collection and feature extraction module.

[0111] In step 32, a variety of typical networking schemes are decomposed into basic units for reorganization. This step can serve as a basic unit module for communication networking

[0112] In step 33, the scenario prediction module based on the large model uses the pre-trained large language model to predict the scenario communication requirements and communication channel status (i.e., channel conditions). This step can serve as the prediction module.

[0113] In step 34, the most suitable network deployment plan is selected from the network deployment plan library according to the prediction results. That is, a network deployment plan is selected from the network deployment plan library until the selected network deployment plan meets the standards. This step can serve as the network deployment plan selection module.

[0114] In step 35, the communication modules are dynamically combined in real time, and the configuration and deployment of the construction site communication network are completed. This step can serve as the network deployment module.

[0115] In step 36, the communication performance is monitored in real time, and dynamic feedback and adjustment are performed. In case of need for adjustment, return to step S33 to form a closed-loop optimization. This step can serve as the communication performance monitoring and feedback adjustment module.

[0116] The above modules are interconnected through information interaction interfaces to form a closed-loop structure, realizing an intelligent and dynamic overall solution for construction scenario communication networking. By monitoring and extracting equipment data and channel feature data of the construction scenario in real time, the large language model is used to achieve accurate prediction of communication requirements and channel conditions. Then, based on the prediction results, communication modules are automatically selected and dynamically combined from the preset modular communication plan library to complete the rapid and dynamic deployment of the on-site communication network, and continuously monitor the communication effect, and dynamically adjust the communication plan according to real-time feedback to achieve continuous optimization of the communication network.

[0117] This disclosure predicts construction communication requirements and communication channel status based on a large language model, improving the prediction accuracy and effectively ensuring the adaptability and flexibility of communication networking. And it realizes the modular management and dynamic combination of communication networking modules, greatly reducing the time for plan formulation and adjustment and improving the network deployment efficiency. In addition, a real-time monitoring and feedback adjustment mechanism for communication performance is introduced to achieve continuous optimization of communication network performance and improve the stability and reliability of communication in large-scale construction sites.

[0118] Figure 4 The structural schematic diagram of a network deployment device according to some embodiments of the present disclosure is shown. As Figure 4As shown, the network deployment device 4 in this embodiment includes an acquisition module 41 configured to acquire construction site data at a plurality of consecutive moments; a prediction module 42 configured to input the construction site data at a plurality of consecutive moments into a pre-trained model to predict the communication demand and communication channel state of the construction site at the target moment; a generation module 43 configured to generate a target network deployment plan based on a plurality of communication modules according to the communication demand and communication channel state; and a deployment module 44 configured to deploy the communication network of the construction site according to the target network deployment plan.

[0119] In some embodiments, the network deployment includes multiple stages, and a plurality of communication modules correspond to the multiple stages of the network deployment.

[0120] In some embodiments, for each communication module among the plurality of communication modules, the communication module includes one or more communication units, and the generation module 43 is configured to determine a target network deployment plan from a plurality of candidate network deployment plans according to the satisfaction degrees of the communication demand and communication channel state by each candidate network deployment plan among the plurality of candidate network deployment plans, wherein each candidate network deployment plan includes a plurality of communication units, and the plurality of units belong to the plurality of communication modules.

[0121] In some embodiments, the communication demand is represented by a first vector, each candidate network deployment plan is represented by a second vector, and the generation module 43 is configured to, for each candidate network deployment plan, determine the satisfaction degree of the candidate network deployment plan with respect to the communication demand and communication channel state according to the similarity between the second vector corresponding to the candidate network deployment plan and the first vector.

[0122] In some embodiments, the multiple stages include at least one of a public network access stage, a network relay stage, a strip network deployment stage, a private network construction stage, a wireless network coverage stage, a sensor network deployment stage, and a device information transmission construction stage.

[0123] In some embodiments, the network deployment device 4 is further configured to perform performance monitoring on the deployed communication network of the construction site; and determine whether to adjust the deployed communication network of the construction site according to the result of the performance monitoring.

[0124] In some embodiments, the network deployment device 4 is further configured to monitor the performance index values of the communication network of the construction site, where the performance index values include at least one of delay, packet loss rate, and throughput; and determine the result of the performance monitoring based on the performance index values.

[0125] In some embodiments, the network deployment device 4 is further configured to adjust the communication network at the construction site where the deployment is located when the result of the performance monitoring is within the specified range; and not adjust the communication network at the construction site where the deployment is located when the result of the performance monitoring is not within the specified range.

[0126] In some embodiments, the network deployment device 4 is further configured to re-predict the communication requirements and communication channel status at the construction site at the target time; based on the re-predicted communication requirements and communication channel status, regenerate a target network deployment plan based on multiple communication modules; and re-deploy the communication network at the construction site according to the regenerated target network deployment plan.

[0127] In some embodiments, the deployment module 44 is configured to determine network deployment parameters according to the target network deployment plan; and send the network deployment parameters to the construction equipment so that the construction equipment is configured according to the network deployment parameters.

[0128] In some embodiments, the network deployment parameters include at least one of communication node location, network structure, data transmission mode, and frequency resource allocation information.

[0129] In some embodiments, the deployment module 44 is configured to, when the communication requirements and communication channel status are met, determine the topology structure that enables the communication link between the construction equipment to reach the best communication quality as the topology structure of the communication network.

[0130] In some embodiments, the network deployment device 4 is configured to train a model according to historical construction site data to determine the first parameters of the model; adjust the first parameters of the model to determine the second parameters of the model; and use the model with the second parameters as a pre-trained model.

[0131] In some embodiments, the network deployment device 4 is configured to input historical construction site data into a model with the first parameters to determine the predicted communication requirements and predicted communication channel status at the test time; and combine the real communication requirements, real communication channel status, predicted communication requirements, and predicted communication channel status at the test time to adjust the first parameters of the model to determine the second parameters of the model.

[0132] In some embodiments, the communication requirements are represented by at least one of signal-to-noise ratio, packet loss rate, and latency.

[0133] In some embodiments, the construction site data includes at least one of construction equipment data, construction task data, and construction communication data. The construction equipment data includes at least one of construction equipment type, construction equipment quantity, and construction equipment operating status. The construction task data includes the construction task type. The construction communication data includes the communication channel status at the construction site.

[0134] In some embodiments, the model is a large language model, which is used to determine the correlation relationship between the quantity of construction equipment, the type of construction tasks, the communication channel status, and the communication requirements.

[0135] The present disclosure uses construction site data and a pre-trained model to predict the communication requirements and communication channel status at the construction site, and generates a target network deployment plan using multiple communication modules based on the predicted communication requirements and communication channel status, and deploys the communication network at the construction site. The present disclosure can perform network deployment according to the communication requirements and communication channel status at the construction site, can improve the adaptability of network deployment, and can also improve the flexibility and efficiency of network deployment by generating a target network deployment plan using multiple communication modules.

[0136] The network deployment devices in the embodiments of the present disclosure can each be implemented by various computing devices or computer systems. The following will be described in conjunction with Figure 5 and Figure 6 for description.

[0137] Figure 5 FIG. shows a schematic structural diagram of a network deployment device according to some other embodiments of the present disclosure. As Figure 5 shown, the device 4 of this embodiment includes: a memory 51 and a processor 52 coupled to the memory 51. The processor 52 is configured to execute the network deployment method in any of the embodiments of the present disclosure based on instructions stored in the memory 51.

[0138] Among them, the memory 51 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory stores, for example, an operating system, application programs, a boot loader, a database, and other programs.

[0139] Figure 6 FIG. shows a schematic structural diagram of a network deployment device according to still some other embodiments of the present disclosure. As Figure 6 shown, the device 6 of this embodiment includes: a memory 61 and a processor 62, which are respectively similar to the memory 51 and the processor 52. It may also include an input / output interface 63, a network interface 64, a storage interface 65, etc. These interfaces 63, 64, 65 and the memory 61 and the processor 62 may be connected through a bus 66, for example. Among them, the input / output interface 63 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 64 provides a connection interface for various networking devices, and may be connected to, for example, a database server or a cloud storage server. The storage interface 65 provides a connection interface for external storage devices such as an SD card and a USB flash drive.

[0140] Embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, and characterized in that when the program is executed by a processor, it implements any of the foregoing network deployment methods.

[0141] Embodiments of the present disclosure also provide a computer program product, including instructions that, when executed by a processor, cause the processor to execute according to any of the foregoing network deployment methods.

[0142] Those skilled in the art should understand that embodiments of the present disclosure may be provided as a method, a system, or a computer program product. Therefore, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0143] The present disclosure is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0144] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the specified functions in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0146] The foregoing are only preferred embodiments of the present disclosure, and are not intended to limit the present disclosure. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A network deployment method, comprising: Collecting construction site data at multiple consecutive moments; Inputting the construction site data at the multiple consecutive moments into a pre-trained model to predict the communication demand and communication channel status of the construction site at the target moment; Generating a target network deployment plan based on multiple communication modules according to the communication demand and communication channel status; Deploying the communication network of the construction site according to the target network deployment plan.

2. The network deployment method according to claim 1, wherein, The network deployment includes multiple stages, and the multiple communication modules correspond to the multiple stages of the network deployment.

3. The network deployment method according to claim 2, wherein, For each communication module among the multiple communication modules, the communication module includes one or more communication units, and the generating a target network deployment plan based on multiple communication modules according to the communication demand and communication channel status includes: Determining a target network deployment plan from the multiple candidate network deployment plans according to the satisfaction degrees of each candidate network deployment plan among the multiple candidate network deployment plans with respect to the communication demand and communication channel status, wherein each candidate network deployment plan includes multiple communication units, and the multiple units belong to the multiple communication modules.

4. According to the network deployment method described in claim 3, the communication demand and communication status are represented by a first vector, and each candidate network deployment plan is represented by a second vector. The generating a target network deployment plan based on multiple communication modules according to the communication demand and communication channel status further includes: For each candidate network deployment plan, determining the satisfaction degree of the candidate network deployment plan with respect to the communication demand and communication channel status according to the similarity between the second vector corresponding to the candidate network deployment plan and the first vector.

5. The network deployment method according to claim 2, wherein, The multiple stages include at least one of a public network access stage, a network relay stage, a strip network deployment stage, a private network construction stage, a wireless network coverage stage, a sensor network deployment stage, and a device information transmission construction stage.

6. According to the network deployment method described in claim 1, it further includes: Performing performance monitoring on the deployed communication network of the construction site; Determining whether to adjust the deployed communication network of the construction site according to the result of the performance monitoring.

7. The network deployment method according to claim 6, wherein, The performing performance monitoring on the deployed communication network of the construction site includes: Monitoring the performance index values of the communication network of the construction site, wherein the performance index values include at least one of delay, packet loss rate, and throughput; Determining the result of the performance monitoring based on the performance index values.

8. The network deployment method according to claim 6, wherein, The determining whether to adjust the deployed communication network of the construction site according to the result of the performance monitoring includes: Adjusting the deployed communication network of the construction site when the result of the performance monitoring is within the specified range; Not adjusting the deployed communication network of the construction site when the result of the performance monitoring is not within the specified range.

9. The network deployment method according to claim 8, wherein, The adjusting the deployed communication network of the construction site includes: Re-predicting the communication demand and communication channel status of the construction site at the target moment; Regenerate a target network deployment plan based on the re-predicted communication requirements and communication channel status, based on the multiple communication modules; Redeploy the communication network at the construction site according to the regenerated target network deployment plan.

10. The network deployment method according to claim 1, wherein the deploying the communication network at the construction site according to the target network deployment plan includes: Determine network deployment parameters according to the target network deployment plan; Send the network deployment parameters to the construction equipment so that the construction equipment is configured according to the network deployment parameters.

11. The network deployment method according to claim 10, wherein, The network deployment parameters include at least one of communication node location, networking structure, data transmission mode, and frequency resource allocation information.

12. The network deployment method according to any one of claims 1 to 11, wherein the deploying the communication network at the construction site according to the target network deployment plan includes: When the communication requirements and the communication channel status are met, determine the topology structure that enables the communication link between the construction equipment to achieve the best communication quality as the topology structure of the communication network.

13. The network deployment method according to any one of claims 1 to 11 further includes: Train the model according to historical construction site data to determine the first parameters of the model; Adjust the first parameters of the model to determine the second parameters of the model; Use the model with the second parameters as the pre-trained model.

14. The network deployment method according to claim 13, wherein, The adjusting the first parameters of the model to determine the second parameters of the model includes: Input the historical construction site data into the model with the first parameters to determine the predicted communication requirements and predicted communication channel status at the test time; Combine the real communication requirements, real communication channel status, predicted communication requirements, and predicted communication channel status at the test time to adjust the first parameters of the model to determine the second parameters of the model.

15. The network deployment method according to any one of claims 1 to 11, wherein, The communication requirements are represented by at least one of signal-to-noise ratio, packet loss rate, and latency.

16. The network deployment method according to any one of claims 1 to 11, wherein, The construction site data includes at least one of construction equipment data, construction task data, and construction communication data. The construction equipment data includes at least one of construction equipment type, construction equipment quantity, and construction equipment operating status. The construction task data includes construction task type. The construction communication data includes the communication channel status at the construction site.

17. The network deployment method according to claim 1, wherein, The model is a large language model, and the large language model is used to determine the association relationship between the construction equipment quantity, construction task type, communication channel status, and communication requirements.

18. A network deployment device, comprising: An acquisition module configured to acquire construction site data at a continuous plurality of times; A prediction module configured to input the construction site data at the continuous plurality of times into a pre-trained model to predict the communication requirements and communication channel status of the construction site at the target time; A generation module configured to generate a target network deployment plan based on the communication requirements and the communication channel status, based on a plurality of communication modules; A deployment module, configured to deploy the communication network at the construction site according to the target network deployment plan.

19. A network deployment device, comprising: A processor; And A memory coupled to the processor, for storing instructions, which when executed by the processor, cause the processor to execute the network deployment method according to any one of claims 1 to 17.

20. A computer-readable storage medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the network deployment method according to any one of claims 1 to 17.

21. A computer program product, comprising instructions that when executed by a processor cause the processor to execute the network deployment method according to any one of claims 1 to 17.

Images