Intelligent equipment distribution system based on intelligent Internet of Things

Abstract

The invention discloses an intelligent equipment distribution system based on an intelligent Internet of Things, which belongs to the technical field of Internet of Things and comprises an Internet of Things equipment access module, a data acquisition preprocessing module, a dynamic topology sensing module, a dynamic multi-dimensional decision module, a dynamic equipment resource scheduling module, an equipment collaborative distribution control module and a self-adaptive dynamic adjustment module. According to the invention, the dynamic topology sensing module can monitor the change condition of equipment connection in the Internet of Things environment in real time, update the network topology structure in time, reflect the connection state of equipment and the change of the network structure in real time, provide accurate and timely information, and improve the reliability of the system by monitoring the change condition of equipment connection in real time. According to the invention, abnormal conditions in the network can be found and processed in time, and meanwhile, the network topology structure is updated in time, so that the network change can be quickly adapted, and the flexibility and response speed of equipment allocation are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of Internet of Things, and specifically refers to an intelligent device allocation system based on smart Internet of Things. Background Art

[0002] With the rapid development of IoT technology, more and more devices are connected to the network, forming a huge IoT ecosystem. These devices cover multiple fields from smart homes, industrial automation to smart cities, providing a wealth of application scenarios and services. However, as the number and complexity of devices increase, how to efficiently manage and allocate the resources of these devices has become a problem to be solved;

[0003] However, the existing intelligent allocation of devices in the Internet of Things still has certain defects. The allocation strategy of the existing intelligent allocation system of the device Internet of Things usually only considers a single dimension such as the load or performance of the device, and fails to comprehensively consider multiple factors such as the performance, load, health status and network topology of the device, resulting in the allocation strategy being unreasonable and ineffective. Most of them adopt static resource allocation strategies, which cannot be dynamically adjusted according to changes in real-time data and are difficult to adapt to changing needs and environments. The existing resource scheduling mechanism cannot accurately evaluate the actual needs of the equipment, resulting in resource waste or equipment overload, affecting system performance. There is a lack of effective coordination mechanism. It is easy for some devices to be overloaded while other devices are idle, resulting in frequent bottlenecks and reducing the stability and reliability of the system. It relies on initial configuration or preset rules, lacks the ability to self-adjust, and cannot be continuously optimized according to feedback information and the real-time operating status of the equipment. Therefore, an intelligent allocation system for devices based on the smart Internet of Things is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent device allocation system based on the smart Internet of Things to solve the problems raised in the above background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent device allocation system based on the smart Internet of Things, comprising an Internet of Things device access module, a data acquisition preprocessing module, a dynamic topology perception module, a dynamic multi-dimensional decision module, a dynamic device resource scheduling module, a device collaborative allocation control module and an adaptive dynamic adjustment module;

[0006] The IoT device access module is used to establish a communication connection between each IoT device and the system and perform device authentication;

[0007] The data collection and preprocessing module is used to collect and preprocess raw data from connected IoT devices;

[0008] The dynamic topology perception module is used to monitor the changes in device connections in the IoT environment in real time and update the network topology in a timely manner;

[0009] The dynamic multi-dimensional decision module is used to formulate the optimal device allocation strategy based on the pre-processed device data and network topology information;

[0010] The dynamic device resource scheduling module is used to dynamically adjust device resource allocation according to the optimal device allocation strategy and the network topology state;

[0011] The device collaborative allocation control module is used to execute the device resource allocation task according to the adjustment device resource allocation result, coordinate the task allocation among multiple devices, and provide real-time feedback on the optimization scheduling decision result;

[0012] The adaptive dynamic adjustment module is used to adaptively adjust the allocation strategy according to the feedback information and the real-time operation status of the equipment.

[0013] The Internet of Things device access module is wirelessly connected to the data acquisition preprocessing module, the data acquisition preprocessing module is wirelessly connected to the dynamic topology perception module and the dynamic multidimensional decision-making module, the dynamic topology perception module is wirelessly connected to the dynamic multidimensional decision-making module, the dynamic multidimensional decision-making module and the dynamic topology perception module are wirelessly connected to the dynamic device resource scheduling module, the dynamic device resource scheduling module is wirelessly connected to the device collaborative allocation control module and the adaptive dynamic adjustment module, the device collaborative allocation control module is wirelessly connected to the adaptive dynamic adjustment module and the data acquisition preprocessing module, and the adaptive dynamic adjustment module is wirelessly connected to the data acquisition preprocessing module.

[0014] Among them, the data collection preprocessing module collects and preprocesses the original data from the connected IoT devices; identifies and connects to all authenticated IoT devices according to the IoT device access module, obtains the original device data from the IoT devices, and performs data cleaning and data format conversion preprocessing on the obtained original device data. Data cleaning includes denoising, filling missing values ​​and anomaly detection correction. Data format conversion includes standardized format and timestamp synchronization, and the preprocessed device data is stored in the database.

[0015] The dynamic topology perception module monitors the changes in device connections in the IoT environment in real time and updates the network topology in a timely manner; obtains preprocessed device data, monitors all active devices in the network in real time and records the device status. Let the device be d, the network topology be T, calculate the dynamic weight of each device based on multiple factors, and let the importance score of device d be I d , the workload of device d is W d , the health status score of device d is H d, the connection stability score of device d is S d , the dynamic weight DW of device d d , the device dynamic weight evaluation implementation formula is:

[0016]

[0017] In the formula, DW d represents the dynamic weight of device d, W max It represents the maximum possible workload of the equipment, and α, β, γ, and δ are the importance coefficients of each factor respectively.

[0018] The dynamic topology perception module updates the network topology structure according to the obtained dynamic weight of the device d, and the implementation formula is:

[0019] MF(T)=Σ i,j∈N (DW i +DW j )+C ij -λ·Σ i,j∈N C ij ,

[0020] In the formula, MF(T) represents the updated network topology, C ij represents the connection quality score between device i and device j, DW i and DW j represents the dynamic weight of device i and device j, N represents the set of all devices in the current network, ∈ represents the set of all connections in the current network, and T represents the network topology.

[0021] The dynamic topology awareness module monitors changes in device connections in the IoT environment in real time and updates the network topology in a timely manner. By calculating the dynamic weight of each device, it can comprehensively consider factors such as the device's importance score, workload, health status score, and connection stability score, accurately evaluate the status of each device, and allocate resources more reasonably based on the dynamic weight to avoid overload or waste of resources. In addition, it can also identify bottlenecks and potential failure points in the network, take preventive measures in advance, and improve the stability and reliability of the system.

[0022] The dynamic multi-dimensional decision module formulates the optimal device allocation strategy based on the pre-processed device data and network topology information; obtains the pre-processed device data d and the latest network topology T of the dynamic topology perception module, and assumes that the state data of the device at time point t is d t , to forecast demand, the implementation formula is:

[0023]

[0024] In the formula, P(dt+1 |d t ) represents the current data d t , predict the device data distribution at the future time point t+1, α 0 represents the basic demand, α 1 represents the impact of device data on demand, α 2 It means capturing nonlinear changing trends;

[0025] According to the obtained network topology T, the influencing factors of equipment demand are analyzed and the implementation formula is:

[0026] I(T)=Σ i,j∈N β ij C ij ,

[0027] In the formula, I(T) represents the impact factor of network topology on device demand, β ij represents the connection weight between device i and device j, C ij represents the connection quality score between device i and device j, and N represents the set of all devices;

[0028] By combining the demand forecast results and the network topology influencing factors to perform comprehensive demand scoring, the implementation formula is:

[0029] S(d t+1 ,I(T))=g(P(d t+1 |d t ),I(T),γ),

[0030] In the formula, S(d t+1 ,I(T)) represents the comprehensive demand score, g represents the comprehensive scoring function, and γ represents the weight vector, which adjusts the impact of device demand and network topology on future scoring.

[0031] The dynamic multi-dimensional decision module generates multiple candidate equipment allocation strategies A according to the comprehensive demand score. i , and calculate the expected effect score for each strategy, the implementation formula is:

[0032] R(A i )=h(S(d t+1 ,I(T)),A i ,δ),

[0033] In the formula, R(A i ) represents strategy A i The expected effect score is A i represents the i-th candidate device allocation strategy, h represents the scoring function, S(d t+1 ,I(T)) represents the comprehensive demand score, δ represents the weight vector, which is used to adjust the scoring criteria;

[0034] According to the expected effect scores of all candidate strategies, select the strategy with the highest score as the optimal strategy A * , the implementation formula is:

[0035]

[0036] The dynamic multi-dimensional decision-making module formulates the optimal equipment allocation strategy through pre-processed equipment data and network topology information. Through the demand forecasting model and network topology influencing factor calculation, it can accurately predict future equipment demand and optimize resource allocation in combination with network structure characteristics. The multi-dimensional comprehensive evaluation method not only considers the status of the equipment itself, but also fully considers the impact of network topology on equipment demand, ensuring the comprehensiveness and rationality of resource allocation. In addition, it generates multiple candidate equipment allocation strategies and selects the optimal solution through expected effect scoring, which effectively improves the scientificity and accuracy of decision-making.

[0037] The dynamic device resource scheduling module dynamically adjusts the device resource allocation according to the optimal device allocation strategy and the network topology state; assuming that the optimal device allocation strategy A * The target resource amount of device d is Assume that the bottleneck factor of device d in the network topology T is B d (T), assuming that the current actual resource supply of device d is S d , the device resource scheduling implementation formula is:

[0038]

[0039] In the formula, Q d Indicates the amount of resources that device d needs to adjust, α 1 , α 2 Represents the weight parameter, which adjusts the importance of target resource quantity and bottleneck influencing factors.

[0040] The dynamic device resource scheduling module dynamically adjusts device resource allocation according to the optimal device allocation strategy and network topology status. By calculating the target resource volume and bottleneck impact factor of each device, it can accurately evaluate the actual needs of the device and perform resource scheduling accordingly, which not only avoids resource waste and overload problems, but also improves resource utilization. In addition, it can also make dynamic adjustments based on real-time feedback information. At the same time, by coordinating resource allocation among multiple devices, it effectively balances the workload, reduces bottlenecks, and further improves the stability and reliability of the system.

[0041] Among them, the equipment collaborative allocation control module executes the equipment resource allocation task according to the adjustment of the equipment resource allocation result, coordinates the task allocation among multiple devices, and provides real-time feedback on the optimization scheduling decision results; receives the latest equipment resource allocation plan, sends task allocation instructions to the equipment, starts the resource adjustment and task reallocation process, coordinates the allocation of work tasks among multiple devices, collects various indicators of each device during the execution of the new task in real time, compares the monitoring data with the expected target, evaluates the effect of resource scheduling, and feeds back the monitoring data and analysis results to the data acquisition preprocessing module and the adaptive dynamic adjustment module.

[0042] Among them, the adaptive dynamic adjustment module adaptively adjusts the allocation strategy according to the feedback information and the real-time operation status of the equipment; obtains the real-time equipment data operation status information and feedback information for integration, evaluates the equipment allocation operation status and performance based on the integrated data, generates a new resource allocation strategy based on the real-time status evaluation results, and feeds back to the dynamic equipment resource scheduling module for equipment resource scheduling.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. The present invention can monitor the changes of device connections in the Internet of Things environment in real time through the dynamic topology perception module, and update the network topology structure in time, which can reflect the connection status of the device and the changes of the network structure in real time, and provide accurate and timely information. By monitoring the changes of device connections in real time, it can timely discover and handle abnormal situations in the network. At the same time, timely updating of the network topology structure also helps to quickly adapt to network changes and improve the flexibility and response speed of device allocation;

[0045] 2. The present invention formulates the optimal device allocation strategy according to the pre-processed device data and network topology information through a dynamic multi-dimensional decision module, which can comprehensively consider multiple factors such as device performance, load, health status and network topology to formulate a more reasonable and effective device allocation strategy. By optimizing device allocation, it can ensure the maximum utilization of device resources and improve overall performance and efficiency. At the same time, it can also make dynamic adjustments according to changes in real-time data to adapt to changing needs and environments;

[0046] 3. The present invention uses a dynamic device resource scheduling module to make dynamic adjustments according to changes in real-time data. By calculating the target resource amount and bottleneck impact factor of each device, the actual needs of the device can be accurately evaluated, and resource scheduling can be performed accordingly, which not only avoids resource waste and overload problems, but also improves resource utilization. At the same time, by coordinating resource allocation among multiple devices, the workload is effectively balanced, the bottleneck phenomenon is reduced, and the stability and reliability of the system are further improved;

[0047] 4. The present invention uses an adaptive dynamic adjustment module to perform self-adjustment according to feedback information and the real-time operating status of the equipment, ensuring that the system can continuously optimize resource allocation strategies, evaluate the overall health and performance of the system, identify areas that need improvement, generate new resource allocation strategies or adjust existing strategies, thereby improving the flexibility and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a schematic diagram of the structure of the intelligent device allocation system based on the smart Internet of Things of the present invention;

[0049] Figure 2 This is a flow chart of the operation of the dynamic topology perception module of the device intelligent allocation system based on the smart Internet of Things of the present invention;

[0050] Figure 3 This is a flow chart of the operation of a dynamic multi-dimensional decision-making module of the intelligent device allocation system based on the smart Internet of Things of the present invention;

[0051] Figure 4 This is a flow chart of the operation of the dynamic device resource scheduling module of the device intelligent allocation system based on the smart Internet of Things of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] Example

[0054] See also Figure 1-Figure 4 As shown, the present invention provides a technical solution: including an Internet of Things device access module, a data acquisition preprocessing module, a dynamic topology perception module, a dynamic multi-dimensional decision module, a dynamic device resource scheduling module, a device collaborative allocation control module and an adaptive dynamic adjustment module;

[0055] The IoT device access module is used to establish a communication connection between each IoT device and the system and perform device authentication;

[0056] The data collection and preprocessing module is used to collect and preprocess raw data from connected IoT devices;

[0057] The dynamic topology perception module is used to monitor the changes in device connections in the IoT environment in real time and update the network topology in a timely manner;

[0058] The dynamic multi-dimensional decision module is used to formulate the optimal device allocation strategy based on the pre-processed device data and network topology information;

[0059] The dynamic device resource scheduling module is used to dynamically adjust device resource allocation according to the optimal device allocation strategy and the network topology state;

[0060] The device collaborative allocation control module is used to execute the device resource allocation task according to the adjustment device resource allocation result, coordinate the task allocation among multiple devices, and provide real-time feedback on the optimization scheduling decision result;

[0061] The adaptive dynamic adjustment module is used to adaptively adjust the allocation strategy according to the feedback information and the real-time operation status of the equipment.

[0062] The Internet of Things device access module is wirelessly connected to the data acquisition preprocessing module, the data acquisition preprocessing module is wirelessly connected to the dynamic topology perception module and the dynamic multidimensional decision-making module, the dynamic topology perception module is wirelessly connected to the dynamic multidimensional decision-making module, the dynamic multidimensional decision-making module and the dynamic topology perception module are wirelessly connected to the dynamic device resource scheduling module, the dynamic device resource scheduling module is wirelessly connected to the device collaborative allocation control module and the adaptive dynamic adjustment module, the device collaborative allocation control module is wirelessly connected to the adaptive dynamic adjustment module and the data acquisition preprocessing module, and the adaptive dynamic adjustment module is wirelessly connected to the data acquisition preprocessing module.

[0063] Among them, the data collection preprocessing module collects and preprocesses the original data from the connected IoT devices; identifies and connects to all authenticated IoT devices according to the IoT device access module, obtains the original device data from the IoT devices, and performs data cleaning and data format conversion preprocessing on the obtained original device data. Data cleaning includes denoising, filling missing values ​​and anomaly detection correction. Data format conversion includes standardized format and timestamp synchronization, and the preprocessed device data is stored in the database.

[0064] The dynamic topology perception module monitors the changes in device connections in the IoT environment in real time and updates the network topology in a timely manner; obtains preprocessed device data, monitors all active devices in the network in real time and records the device status. Let the device be d, the network topology be T, calculate the dynamic weight of each device based on multiple factors, and let the importance score of device d be I d , the workload of device d is W d , the health status score of device d is H d , the connection stability score of device d is S d , the dynamic weight DW of device d d , the device dynamic weight evaluation implementation formula is:

[0065]

[0066] In the formula, DW d represents the dynamic weight of device d, W max It represents the maximum possible workload of the equipment, and α, β, γ, and δ are the importance coefficients of each factor respectively.

[0067] The dynamic topology perception module updates the network topology structure according to the obtained dynamic weight of the device d, and the implementation formula is:

[0068] MF(T)=∑ i,j∈N (DW i +DW j )+C ij -λ·v i,j∈N C ij ,

[0069] In the formula, MF(T) represents the updated network topology, C ij represents the connection quality score between device i and device j, DW i and DW j represents the dynamic weight of device i and device j, N represents the set of all devices in the current network, ∈ represents the set of all connections in the current network, and T represents the network topology.

[0070] The dynamic topology awareness module monitors changes in device connections in the IoT environment in real time and updates the network topology in a timely manner. By calculating the dynamic weight of each device, it can comprehensively consider factors such as the device's importance score, workload, health status score, and connection stability score, accurately evaluate the status of each device, and allocate resources more reasonably based on the dynamic weight to avoid overload or waste of resources. In addition, it can also identify bottlenecks and potential failure points in the network, take preventive measures in advance, and improve the stability and reliability of the system.

[0071] The dynamic multi-dimensional decision module formulates the optimal device allocation strategy based on the pre-processed device data and network topology information; obtains the pre-processed device data d and the latest network topology T of the dynamic topology perception module, and assumes that the state data of the device at time point t is d t , to forecast demand, the implementation formula is:

[0072]

[0073] In the formula, P(d t+1 |d t ) represents the current data d t , predict the device data distribution at the future time point t+1, α0 represents the basic demand, α 1 represents the impact of device data on demand, α 2 It means capturing nonlinear changing trends;

[0074] According to the obtained network topology T, the influencing factors of equipment demand are analyzed and the implementation formula is:

[0075] I(T)=∑ i,j∈N β ij C ij ,

[0076] In the formula, I(T) represents the impact factor of network topology on device demand, β ij represents the connection weight between device i and device j, C ij represents the connection quality score between device i and device j, and N represents the set of all devices;

[0077] By combining the demand forecast results and the network topology influencing factors to perform comprehensive demand scoring, the implementation formula is:

[0078] S(d t+1 ,I(T))=g(P(d t+1 |d t ),I(T),γ),

[0079] In the formula, S(d t+1 ,I(T)) represents the comprehensive demand score, g represents the comprehensive scoring function, and γ represents the weight vector, which adjusts the impact of device demand and network topology on future scoring.

[0080] The dynamic multi-dimensional decision module generates multiple candidate equipment allocation strategies A according to the comprehensive demand score. i , and calculate the expected effect score for each strategy, the implementation formula is:

[0081] R(A i )=h(S(d t+1 ,I(T)),A i ,δ),

[0082] In the formula, R(A i ) represents strategy A i The expected effect score is A i represents the i-th candidate device allocation strategy, h represents the scoring function, S(d t+1 ,I(T)) represents the comprehensive demand score, δ represents the weight vector, which is used to adjust the scoring criteria;

[0083] According to the expected effect scores of all candidate strategies, select the strategy with the highest score as the optimal strategy A * , the implementation formula is:

[0084]

[0085] The dynamic multi-dimensional decision-making module formulates the optimal equipment allocation strategy through pre-processed equipment data and network topology information. Through the demand forecasting model and network topology influencing factor calculation, it can accurately predict future equipment demand and optimize resource allocation in combination with network structure characteristics. The multi-dimensional comprehensive evaluation method not only considers the status of the equipment itself, but also fully considers the impact of network topology on equipment demand, ensuring the comprehensiveness and rationality of resource allocation. In addition, it generates multiple candidate equipment allocation strategies and selects the optimal solution through expected effect scoring, which effectively improves the scientificity and accuracy of decision-making.

[0086] The dynamic device resource scheduling module dynamically adjusts the device resource allocation according to the optimal device allocation strategy and the network topology state; assuming that the optimal device allocation strategy A * The target resource amount of device d is Assume that the bottleneck factor of device d in the network topology T is B d (T), assuming that the current actual resource supply of device d is S d , the device resource scheduling implementation formula is:

[0087]

[0088] In the formula, Q d Indicates the amount of resources that device d needs to adjust, α 1 , α 2 Represents the weight parameter, which adjusts the importance of target resource quantity and bottleneck influencing factors.

[0089] The dynamic device resource scheduling module dynamically adjusts device resource allocation according to the optimal device allocation strategy and network topology status. By calculating the target resource volume and bottleneck impact factor of each device, it can accurately evaluate the actual needs of the device and perform resource scheduling accordingly, which not only avoids resource waste and overload problems, but also improves resource utilization. In addition, it can also make dynamic adjustments based on real-time feedback information. At the same time, by coordinating resource allocation among multiple devices, it effectively balances the workload, reduces bottlenecks, and further improves the stability and reliability of the system.

[0090] Among them, the equipment collaborative allocation control module executes the equipment resource allocation task according to the adjustment of the equipment resource allocation result, coordinates the task allocation among multiple devices, and provides real-time feedback on the optimization scheduling decision results; receives the latest equipment resource allocation plan, sends task allocation instructions to the equipment, starts the resource adjustment and task reallocation process, coordinates the allocation of work tasks among multiple devices, collects various indicators of each device during the execution of the new task in real time, compares the monitoring data with the expected target, evaluates the effect of resource scheduling, and feeds back the monitoring data and analysis results to the data acquisition preprocessing module and the adaptive dynamic adjustment module.

[0091] Among them, the adaptive dynamic adjustment module adaptively adjusts the allocation strategy according to the feedback information and the real-time operation status of the equipment; obtains the real-time equipment data operation status information and feedback information for integration, evaluates the equipment allocation operation status and performance based on the integrated data, generates a new resource allocation strategy based on the real-time status evaluation results, and feeds back to the dynamic equipment resource scheduling module for equipment resource scheduling.

[0092] Working principle: Through the IoT device access module, the communication connection and device authentication between each IoT device are first established. The data acquisition preprocessing module collects raw data from the connected IoT devices and preprocesses the raw data, including data cleaning and data format conversion. The preprocessed device data is stored in the database;

[0093] The dynamic topology perception module monitors the changes in device connections in the IoT environment in real time. Based on the pre-processed device data, it monitors all active devices in the network in real time and records the device status. The dynamic weight of each device is calculated through multiple factors, including workload, health status score, and connection stability score. The network topology is updated according to the dynamic weight of the device to reflect the current device connection and network status. The dynamic multi-dimensional decision-making module predicts demand based on the pre-processed device data and network topology information, analyzes the factors affecting device demand, including the impact of network topology on device demand, and performs a comprehensive demand score by combining the demand prediction results and the network topology influencing factors. Based on the comprehensive demand score, multiple candidate device allocation strategies are generated, and the expected effect score is calculated for each strategy. The strategy with the highest score is selected as the optimal strategy. The dynamic device resource scheduling module dynamically adjusts the device resource allocation according to the optimal device allocation strategy and the network topology structure status, considers factors such as the device target resource quantity, bottleneck influencing factors and the current actual resource supply, and calculates the resource quantity that the device needs to adjust. The device collaborative allocation control module executes the device resource allocation task according to the adjustment of the device resource allocation result, coordinates the task allocation among multiple devices, collects various indicators of each device during the execution of the new task in real time, and evaluates the effect of resource scheduling. The adaptive dynamic adjustment module adaptively adjusts the allocation strategy according to the feedback information and the real-time operation status of the device, integrates the real-time device data operation status information and feedback information, evaluates the device allocation operation status and performance, generates a new resource allocation strategy according to the real-time status evaluation results, and feeds it back to the dynamic device resource scheduling module for device resource scheduling.

[0094] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0095] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. The intelligent equipment distribution system based on the smart Internet of Things is characterized by: It includes IoT device access module, data acquisition preprocessing module, dynamic topology perception module, dynamic multi-dimensional decision-making module, dynamic device resource scheduling module, device collaborative allocation control module and adaptive dynamic adjustment module; The IoT device access module is used to establish a communication connection between each IoT device and the system and perform device authentication; The data collection and preprocessing module is used to collect and preprocess raw data from connected IoT devices; The dynamic topology perception module is used to monitor the changes in device connections in the IoT environment in real time and update the network topology in a timely manner; The dynamic multi-dimensional decision module is used to formulate the optimal device allocation strategy based on the pre-processed device data and network topology information; The dynamic device resource scheduling module is used to dynamically adjust device resource allocation according to the optimal device allocation strategy and the network topology state; The device collaborative allocation control module is used to execute the device resource allocation task according to the adjustment device resource allocation result, coordinate the task allocation among multiple devices, and provide real-time feedback on the optimization scheduling decision result; The adaptive dynamic adjustment module is used to adaptively adjust the allocation strategy according to the feedback information and the real-time operation status of the equipment.

2. The intelligent device allocation system based on the smart Internet of Things according to claim 1 is characterized by: The data collection and preprocessing module collects raw data from connected IoT devices and performs preprocessing; According to the IoT device access module, it identifies and connects to all authenticated IoT devices, obtains original device data from IoT devices, and performs data cleaning and data format conversion preprocessing on the obtained original device data. Data cleaning includes denoising, filling missing values ​​and anomaly detection and correction. Data format conversion includes standardized format and timestamp synchronization. The preprocessed device data is stored in the database.

3. The intelligent device allocation system based on the smart Internet of Things according to claim 1 is characterized in that: The dynamic topology perception module monitors the changes in device connections in the IoT environment in real time and updates the network topology in a timely manner; obtains pre-processed device data, monitors all active devices in the network in real time and records the device status. Let the device be d, the network topology be T, calculate the dynamic weight of each device based on multiple factors, and let the importance score of device d be I d , the workload of device d is W d , the health status score of device d is H d , the connection stability score of device d is S d , the dynamic weight DW of device d d , the device dynamic weight evaluation implementation formula is: In the formula, DW d represents the dynamic weight of device d, W max It represents the maximum possible workload of the equipment, and α, β, γ, and δ are the importance coefficients of each factor respectively.

4. The intelligent device allocation system based on the smart Internet of Things according to claim 3 is characterized by: The dynamic topology perception module updates the network topology structure according to the obtained dynamic weight of the device d, and the implementation formula is: MF(T)=Σ i,j∈N (DW i +DW j )+C ij -l·S i,j∈N C ij , In the formula, MF(T) represents the updated network topology, C ij represents the connection quality score between device i and device j, DW i and DW j represents the dynamic weight of device i and device j, N represents the set of all devices in the current network, ∈ represents the set of all connections in the current network, and T represents the network topology.

5. The intelligent device allocation system based on the smart Internet of Things according to claim 1 is characterized in that: The dynamic multi-dimensional decision module formulates the optimal device allocation strategy based on the pre-processed device data and network topology information; obtains the pre-processed device data d and the latest network topology T of the dynamic topology perception module, and assumes that the state data of the device at time point t is d t , to forecast demand, the implementation formula is: In the formula, P(d t+1 |d t ) represents the current data d t , predict the distribution of equipment data at the future time point t+1, α0 represents the basic demand, α1 represents the impact of equipment data on demand, and α2 represents capturing nonlinear change trends; According to the obtained network topology T, the influencing factors of equipment demand are analyzed and the implementation formula is: I(T)=Σ i,j∈N b ij C ij , In the formula, I(T) represents the impact factor of network topology on device demand, β ij represents the connection weight between device i and device j, C ij represents the connection quality score between device i and device j, and N represents the set of all devices; By combining the demand forecast results and the network topology influencing factors to perform comprehensive demand scoring, the implementation formula is: S(d t+1 ,I(T))=g(P(d t+1 |d t ),I(T),γ), In the formula, S(d t+1 ,I(T)) represents the comprehensive demand score, g represents the comprehensive scoring function, and γ represents the weight vector, which adjusts the impact of device demand and network topology on future scoring.

6. The intelligent device allocation system based on the smart Internet of Things according to claim 5 is characterized by: The dynamic multi-dimensional decision module generates multiple candidate equipment allocation strategies A according to the comprehensive demand score. i , and calculate the expected effect score for each strategy, the implementation formula is: R(A i )=h(S(d t+1 ,I(T)),A i ,δ), In the formula, R(A i ) represents strategy A i The expected effect score is A i represents the i-th candidate device allocation strategy, h represents the scoring function, S(d t+1 ,I(T)) represents the comprehensive demand score, δ represents the weight vector, which is used to adjust the scoring criteria; According to the expected effect scores of all candidate strategies, select the strategy with the highest score as the optimal strategy A * , the implementation formula is:

7. The intelligent device allocation system based on the smart Internet of Things according to claim 1 is characterized by: The dynamic device resource scheduling module dynamically adjusts the device resource allocation according to the optimal device allocation strategy and the network topology state; assuming that the optimal device allocation strategy A * The target resource amount of device d is Assume that the bottleneck factor of device d in the network topology T is B d (T), assuming that the current actual resource supply of device d is S d , the device resource scheduling implementation formula is: In the formula, Q d It represents the amount of resources that need to be adjusted for device d, and α1 and α2 represent weight parameters, which adjust the importance of the target resource amount and the bottleneck influencing factor.

8. The intelligent device allocation system based on the smart Internet of Things according to claim 1 is characterized by: The equipment collaborative allocation control module executes equipment resource allocation tasks according to the results of adjusting equipment resource allocation, coordinates task allocation among multiple devices, and provides real-time feedback on the optimization scheduling decision results; receives the latest equipment resource allocation plan, sends task allocation instructions to the equipment, starts the resource adjustment and task reallocation process, coordinates the allocation of work tasks among multiple devices, collects various indicators of each device during the execution of the new task in real time, compares the monitoring data with the expected target, evaluates the effect of resource scheduling, and feeds back the monitoring data and analysis results to the data acquisition preprocessing module and the adaptive dynamic adjustment module.

9. The intelligent device allocation system based on the smart Internet of Things according to claim 1 is characterized by: The adaptive dynamic adjustment module adaptively adjusts the allocation strategy according to the feedback information and the real-time operation status of the equipment; Obtain real-time equipment data operation status information and feedback information for integration. Based on the integrated data, evaluate the equipment allocation operation status and performance. Based on the real-time status evaluation results, generate a new resource allocation strategy and feed it back to the dynamic equipment resource scheduling module for equipment resource scheduling.

Images