Communication method, device, medium and system for Internet of Things device and intelligent device

Abstract

Provided are a communication method, device, medium and system for an Internet of Things device and an intelligent device, the method comprising: obtaining network state data and context information, the network state data comprising RSSI, delay and packet loss rate, and the context information comprising a user movement trajectory and a service QoS demand; at least processing the network state data and the context information by adopting a deep learning model formed by LSTM and an attention mechanism to obtain adaptability scores and corresponding weights of the plurality of pre-selected communication protocols; and determining a final communication protocol according to the adaptability score and the weight of each preselected communication protocol, and communicating with the intelligent equipment by adopting the final communication protocol. Therefore, the problem that the communication efficiency is relatively low due to the fact that the communication protocol of the Internet of Things equipment and the intelligent equipment needs to be manually selected in the prior art is solved.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) communication technology, and more specifically, to a communication method between IoT devices and smart devices, IoT devices, computer-readable storage media, and communication systems. Background Technology

[0002] IoT devices and smart devices use various communication protocols. However, different protocols may exhibit varying performance under different network environments and device conditions. In existing technologies, users typically need to manually select or configure the communication protocol, which not only increases operational complexity but may also fail to guarantee optimal communication performance.

[0003] In other words, existing technologies have poor communication efficiency because they require manual selection of communication protocols for IoT devices and smart devices. Summary of the Invention

[0004] The main objective of this application is to provide a communication method, IoT device, computer-readable storage medium, and communication system for IoT devices and smart devices, so as to at least solve the problem of poor communication efficiency in the prior art due to the need to manually select the communication protocol of IoT devices and smart devices.

[0005] To achieve the above objectives, according to one aspect of this application, a method for communication between an IoT device and a smart device is provided, applied to an IoT device in a communication system. The method includes: acquiring network status data and context information, wherein the network status data includes RSSI, latency, and packet loss rate, and the context information includes user movement trajectory and service QoS requirements; processing the network status data and the context information using a deep learning model composed of LSTM and attention mechanisms to obtain adaptability scores and corresponding weights for multiple pre-selected communication protocols; determining a final communication protocol based on the adaptability scores of each pre-selected communication protocol and the weights, and using the final communication protocol to communicate with the smart device.

[0006] Optionally, determining the final communication protocol based on the adaptability scores of each of the pre-selected communication protocols and the weights includes: determining a first target communication protocol as the pre-selected communication protocol with a weight greater than or equal to the weight threshold; and determining the final communication protocol based on the adaptability score of the first target communication protocol.

[0007] Optionally, determining the final communication protocol based on the adaptability score of the first target communication protocol includes: determining the final communication protocol as the first target communication protocol corresponding to the maximum value of the adaptability score.

[0008] Optionally, determining the final communication protocol based on the adaptability score of the first target communication protocol includes: determining the weight difference of each of the first target communication protocols, wherein the weight difference is the absolute value of the difference between the weight and the weight threshold; determining the second target communication protocol, wherein the second target communication protocol is the first target communication protocol among all the first target communication protocols whose weight difference is less than or equal to the difference threshold; and determining the final communication protocol as the second target communication protocol corresponding to the maximum value of the adaptability score.

[0009] Optionally, a deep learning model composed of LSTM and attention mechanisms processes at least the network state data and the context information to obtain the adaptability scores and corresponding weights of multiple pre-selected communication protocols, including: obtaining the potential overhead of each communication protocol, wherein the potential overhead includes authentication delay and signaling cost; and processing the potential overhead of each communication protocol, the network state data, and the context information using a deep learning model composed of LSTM and attention mechanisms to obtain the adaptability scores and corresponding weights of the multiple pre-selected communication protocols.

[0010] Optionally, determining the final communication protocol based on the adaptability score and weight of each of the pre-selected communication protocols includes: determining a third target communication protocol when there are multiple pre-selected communication protocols with the same adaptability score and weight among all the pre-selected communication protocols, wherein the third target communication protocol is one of the multiple pre-selected communication protocols with the same adaptability score and weight among all the pre-selected communication protocols; and determining the final communication protocol as the third target communication protocol corresponding to the maximum value of the adaptability score.

[0011] Optionally, after communicating with the smart device using the final communication protocol, the method further includes: in the event of a communication failure between the IoT device and the smart device, determining a fourth target communication protocol based on the adaptability scores of other pre-selected communication protocols besides the final communication protocol and the weights thereof; and communicating with the smart device using the fourth target communication protocol.

[0012] According to another aspect of this application, an Internet of Things (IoT) device is provided, comprising: an acquisition unit, configured to acquire network state data and context information, wherein the network state data includes RSSI, latency, and packet loss rate, and the context information includes user movement trajectory and service QoS requirements; a first processing unit, configured to process at least the network state data and the context information using a deep learning model composed of LSTM and attention mechanisms to obtain adaptability scores and corresponding weights for multiple pre-selected communication protocols; and a second processing unit, configured to determine a final communication protocol based on the adaptability scores of each pre-selected communication protocol and the weights, and to communicate with a smart device using the final communication protocol.

[0013] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0014] According to another aspect of this application, a communication system is provided, comprising: an Internet of Things (IoT) device and a smart device, wherein the IoT device and the smart device communicate with each other, and the IoT device is configured to perform any of the methods described.

[0015] The technical solution of this application allows IoT devices to automatically acquire real-time network status data (such as RSSI, latency, and packet loss rate) and user-related contextual information (such as movement trajectory and service QoS requirements). This automatic perception process avoids dependence on user operation, ensures the real-time nature and accuracy of the data, and provides a solid foundation for subsequent intelligent decision-making. A deep learning model integrating LSTM and attention mechanisms is used to process the collected network status data and contextual information. LSTM can capture long-term dependencies, such as the impact of user movement patterns on network connectivity; the attention mechanism allows the model to focus on key features that significantly affect communication quality, such as poor network conditions represented by high packet loss rates or low RSSI. In this way, the model can not only predict future trends in the network environment but also score the adaptability of various pre-selected communication protocols, thereby quantifying the performance of different protocols under expected network conditions. Based on the prediction results and adaptability scores of the deep learning model, the method of this application can dynamically determine which communication protocol best meets the current service QoS requirements. This decision-making process considers the matching degree between the performance parameters of various protocols (such as latency, throughput, and handover delay) and service types (such as real-time voice, high-definition video, and data transmission). Through a weighted scoring method, it automatically selects the communication protocol most suitable for the current scenario and requirements, thus avoiding the blindness and inefficiency of manual selection. Once the optimal communication protocol is determined, IoT devices immediately adopt this protocol to communicate with smart devices. When a protocol switch is needed, the system can prepare in advance based on prediction and evaluation, such as pre-negotiating parameters and caching data, ensuring service continuity and QoS stability during the switchover process. This avoids communication interruptions and quality degradation caused by protocol mismatch or improper selection, thereby solving the problem of poor communication efficiency in existing technologies that require manual selection of communication protocols for IoT devices and smart devices. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 A schematic flowchart illustrating a communication method between an Internet of Things (IoT) device and a smart device according to an embodiment of this application is shown.

[0018] Figure 2 A structural block diagram of an Internet of Things (IoT) device provided according to an embodiment of this application is shown. Detailed Implementation

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] As described in the background section, IoT devices and smart devices use various communication protocols in their communication. However, different protocols may exhibit different performance under different network environments and device conditions. In the prior art, users usually need to manually select or configure the communication protocol, which not only increases operational complexity but may also fail to guarantee optimal communication performance. To address the problem of poor communication efficiency in the prior art due to the need for manual selection of communication protocols for IoT devices and smart devices, embodiments of this application provide a method for communication between IoT devices and smart devices, an IoT device, a computer-readable storage medium, and a communication system.

[0023] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0024] This embodiment provides a communication method between an IoT device and a smart device, which is applied to an IoT device in a communication system. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here.

[0025] Figure 1This is a flowchart illustrating a communication method between an IoT device and a smart device according to an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0026] Step S101: Obtain network status data and context information. The network status data includes RSSI, latency, and packet loss rate. The context information includes user movement trajectory and service QoS requirements.

[0027] RSSI, or Received Signal Strength Indicator, is a measure of the strength of a received wireless signal. In wireless communication technology, the RSSI value is used to measure the strength of the received wireless signal. It is an important parameter that helps determine the quality of the current wireless network connection. RSSI values ​​are usually represented by negative numbers; the closer the value is to 0, the stronger the signal. For example, in a WiFi network, the RSSI value can help identify when the signal strength becomes too weak, potentially requiring a switch to a stronger access point.

[0028] Service QoS requirements: Quality of Service refers to the required level of service. In data communication and network applications, QoS describes the level of service that a service provider guarantees to its customers, especially in data transmission scenarios. Service QoS requirements specifically specify the network performance metrics required for a particular service or application (such as video calls, online games, data transmission, etc.).

[0029] Step S102: The deep learning model composed of LSTM and attention mechanism is used to process at least the above network state data and the above context information to obtain the adaptability scores and corresponding weights of multiple pre-selected communication protocols.

[0030] LSTM, Long Short-Term Memory, is a special type of artificial neural network, mainly used for processing sequence data and time series analysis.

[0031] Step S103: Based on the adaptability scores and weights of each of the pre-selected communication protocols, determine the final communication protocol and use the final communication protocol to communicate with the smart device.

[0032] The above steps allow IoT devices to automatically acquire real-time network status data (such as RSSI, latency, and packet loss rate) and user-related contextual information (such as movement trajectory and service QoS requirements). This automatic perception process avoids dependence on user operations, ensures the real-time nature and accuracy of the data, and provides a solid foundation for subsequent intelligent decision-making. A deep learning model integrating LSTM and attention mechanisms is used to process the collected network status data and contextual information. LSTM can capture long-term dependencies, such as the impact of user movement patterns on network connectivity; the attention mechanism allows the model to focus on key features that significantly impact communication quality, such as poor network conditions represented by high packet loss rates or low RSSI. In this way, the model can not only predict future trends in the network environment but also score the adaptability of various pre-selected communication protocols, thereby quantifying the performance of different protocols under expected network conditions. Based on the prediction results and adaptability scores of the deep learning model, the method in this application can dynamically determine which communication protocol best meets the current service QoS requirements. This decision-making process considers the matching degree between the performance parameters of various protocols (such as latency, throughput, and handover delay) and service types (such as real-time voice, high-definition video, and data transmission). Through a weighted scoring method, it automatically selects the communication protocol most suitable for the current scenario and requirements, thus avoiding the blindness and inefficiency of manual selection. Once the optimal communication protocol is determined, IoT devices immediately adopt this protocol to communicate with smart devices. When a protocol switch is needed, the system can prepare in advance based on prediction and evaluation, such as pre-negotiating parameters and caching data, ensuring service continuity and QoS stability during the switchover process. This avoids communication interruptions and quality degradation caused by protocol mismatch or improper selection, thereby solving the problem of poor communication efficiency in existing technologies that require manual selection of communication protocols for IoT devices and smart devices.

[0033] In one embodiment of this application, determining the final communication protocol based on the adaptability scores of each of the aforementioned pre-selected communication protocols and the aforementioned weights includes: determining a first target communication protocol as one of the aforementioned pre-selected communication protocols with a weight greater than or equal to a weight threshold; and determining the final communication protocol based on the adaptability score of the aforementioned first target communication protocol.

[0034] Weighted threshold screening: The core idea is to assign a weight to pre-selected communication protocols based on their suitability for business requirements (such as low latency and high throughput). These weights take into account the specific needs of the business type; for example, real-time voice communication might assign a higher weight to latency, while file downloading might focus more on throughput. After weighting, the system sets a weight threshold to filter out protocols with poor suitability. Only pre-selected communication protocols whose weight scores reach or exceed the threshold can be further evaluated. This screening process ensures that subsequent decisions focus more on high-quality candidate protocols.

[0035] Adaptability scoring determines the final protocol: For the first-stage target communication protocols that pass the initial screening, the system then determines the final communication protocol based on their adaptability scores. The adaptability score is a comprehensive evaluation metric that integrates the degree of match between key performance data (such as latency, throughput, and packet loss rate) of each protocol in the predicted network environment and the business requirements. The scoring method takes into account predicted changes in the network environment. For example, if the prediction shows that the currently used WiFi network signal is about to drop to an unacceptable level, then even if another 4G network has a lower average score, if it performs the most stably within the predicted time window, it may become the final choice. The final selected communication protocol should be the one with the highest adaptability score in the predicted environment, thus maximizing business continuity and service quality.

[0036] By setting weighted thresholds and using adaptability scoring, the system can more accurately select the communication protocol best suited to current business needs, avoiding simplistic "one-size-fits-all" decisions. The weighted thresholds filter out communication protocols that are clearly unsuitable for the current scenario or business requirements, reducing unnecessary resource waste and switching attempts. The ultimately selected protocol not only meets basic business needs but also provides optimal performance in the anticipated network environment, significantly improving user experience, especially in scenarios with drastic network changes or diverse requirements. Because the decision-making process considers protocol compatibility and switching costs, the selected primary target communication protocol can establish a connection faster during actual switching, reducing switching latency and avoiding service interruptions.

[0037] In one embodiment of this application, determining the final communication protocol based on the adaptability score of the first target communication protocol includes: determining the final communication protocol as the first target communication protocol corresponding to the maximum value of the adaptability score.

[0038] By quantifying the adaptability scores of different protocols, the system can intuitively identify which protocol will provide the best performance in predicting future network conditions. For example, for real-time voice communication, latency and packet loss rate are the most critical performance indicators, while high-definition video transmission prioritizes high throughput and stability. Assigning weights to these indicators and calculating a comprehensive adaptation score ensures that the ultimately selected protocol maximizes the current service's QoS (Quality of Service). The combination of Long Short-Term Memory (LSTM) networks and attention mechanisms enables deep learning models to accurately predict changes in the future network environment. Based on this prediction, the system can proactively switch to a higher-performing protocol before the current protocol's performance deteriorates to the point of being unacceptable, thereby avoiding service interruptions or performance drops and improving user experience.

[0039] In one embodiment of this application, determining the final communication protocol based on the adaptability score of the first target communication protocol includes: determining the weight difference of each of the first target communication protocols, wherein the weight difference is the absolute value of the difference between the weight and the weight threshold; determining the second target communication protocol, wherein the second target communication protocol is the first target communication protocol among all the first target communication protocols whose weight difference is less than or equal to the difference threshold; and determining the final communication protocol as the second target communication protocol corresponding to the maximum value of the adaptability score.

[0040] For example, the weight threshold can be 20%, and the difference threshold can be 10%. This method allows the system to perform more refined evaluations of network protocols based on service type and QoS requirements. By comparing the weights of protocols with preset weight thresholds, the system can identify which protocols' performance characteristics are closest to current service requirements, thus avoiding the limitations of relying solely on a single performance indicator for decision-making. By introducing the concept of weight difference, the system not only focuses on the protocol's score but also considers the degree of matching between the score and service requirements. This means that even if two protocols have similar scores, if one protocol's performance characteristics are closer to the service requirements, it will be prioritized, thereby improving the accuracy of protocol selection. Secondary target communication protocols with weight differences less than or equal to the difference threshold indicate that these protocols have a high degree of matching with current service requirements in terms of performance. Switching to these protocols can be expected to result in less fluctuation in service experience, helping to reduce service interruptions or user experience degradation caused by frequent switching.

[0041] In one embodiment of this application, a deep learning model composed of LSTM and attention mechanisms processes at least the aforementioned network state data and context information to obtain the adaptability scores and corresponding weights of multiple pre-selected communication protocols, including: obtaining the potential overhead of each communication protocol, wherein the potential overhead includes authentication delay and signaling cost; and processing the potential overhead of each of the aforementioned communication protocols, the aforementioned network state data, and the aforementioned context information using a deep learning model composed of LSTM and attention mechanisms to obtain the aforementioned adaptability scores and corresponding weights of multiple pre-selected communication protocols.

[0042] Data preprocessing: First, we need to preprocess the collected network state data and context information, including but not limited to standardization and normalization, to ensure data quality and the effectiveness of model training. Furthermore, for non-numerical context information (such as business type), one-hot encoding should be used to convert it into numerical data.

[0043] Building an LSTM and attention mechanism model:

[0044] LSTM layer: LSTM (Long Short-Term Memory) networks are well-suited for processing and predicting "time series" patterns in data because they can remember past information. This is crucial for predicting network performance, especially when user mobility (such as speed and direction) affects the current and future state of the network.

[0045] Attention mechanism: The attention mechanism allows the model to focus on the feature segments that are most relevant to the prediction results when processing sequence data. This is especially important in multi-network environments because not all network state data are equally important. For example, in a certain case, a sudden increase in latency may be more critical than a decrease in RSSI.

[0046] Model Training: The LSTM and attention mechanism model is trained using a large amount of historical data (including network state data and contextual information) to learn the patterns of protocol performance under various network conditions. The goal of training is to make the adaptive score predicted by the model as close as possible to the protocol performance under real network conditions.

[0047] Potential overhead and weight calculation:

[0048] Potential overhead calculation: The system calculates potential overhead, including authentication latency and signaling costs, by analyzing the differences between the currently used communication protocol and the pre-selected communication protocol. This overhead data also needs to be included as part of the model input so that the model can fully consider switching costs.

[0049] Deep learning model processing: The model combines potential overhead, network state data, and contextual information, and adjusts internal weights and biases to derive an adaptability score and weight for each pre-selected communication protocol. Here, the weights represent the degree of influence of each performance metric on the overall score in a specific business scenario. For example, for real-time voice services, latency has a much higher weight than throughput.

[0050] Adaptability score generation: The model outputs adaptability scores for multiple pre-selected communication protocols. A higher score indicates that the protocol is better able to meet business needs in the predicted future network environment. The score generation fully considers all input factors, including future predictions of network conditions, potential protocol overhead, and the requirements of specific business types.

[0051] LSTM can capture long-term dependencies, while attention mechanisms can focus on key information; the combination of the two greatly improves the accuracy of predicting future network states. By comprehensively evaluating the performance and potential overhead of protocols, the model can intelligently select the protocol most suitable for the current business needs and network environment, reducing the complexity of manual configuration and improving user experience. The model can automatically adjust the weights of performance indicators according to the type of service, ensuring that the most suitable protocol solution can be found under any circumstances, thereby improving the quality of service (QoS). The predictive capabilities of deep learning models help to identify the best time for handover in advance. Combined with pre-negotiation technology, it can significantly reduce latency and authentication costs during the handover process, achieving seamless handover and avoiding service interruption.

[0052] In one embodiment of this application, determining the final communication protocol based on the adaptability scores and weights of each of the aforementioned pre-selected communication protocols includes: determining a third target communication protocol when there are multiple pre-selected communication protocols with the same adaptability scores and weights among all the aforementioned pre-selected communication protocols; the third target communication protocol being one of the multiple pre-selected communication protocols with the same adaptability scores and weights among all the aforementioned pre-selected communication protocols; and determining the final communication protocol as the third target communication protocol corresponding to the maximum value of the aforementioned adaptability scores.

[0053] When multiple protocols perform similarly, clear decision rules can quickly select a candidate protocol, avoiding delays or service interruptions caused by inability to make a choice. By using pre-defined logic (e.g., prioritizing protocols with lower handover latency), user experience can be further improved while maintaining comparable performance, such as reducing handover wait time and making communication smoother and unaffected by the handover process. The selected third-target communication protocol is the result of system evaluation and comparison. Even with the same scores and weights, it ensures that the selected protocol achieves optimal or near-optimal performance in other aspects (such as handover latency and energy consumption), thereby enhancing the overall stability and reliability of the system. This approach simplifies the network management layer's handling of multi-protocol handover, avoids unnecessary inter-protocol comparisons, facilitates rapid decision-making and execution, and reduces the complexity of network management. By considering multiple factors (such as latency, throughput, and handover latency) in protocol selection, this strategy indirectly promotes the optimization of protocol performance itself, encouraging protocol designers to focus on improving secondary indicators such as handover latency while maintaining basic performance. When faced with complex and ever-changing network environments, this approach allows the system to more flexibly select the communication protocol best suited to the current situation, finding the optimal match whether it's a cellular network in a high-speed mobile scenario or Wi-Fi in a static environment. After selecting the final communication protocol, the system can optimize resource allocation based on the characteristics and requirements of that protocol. For example, when selecting a low-latency protocol, bandwidth resources can be prioritized to ensure service quality and efficiency.

[0054] In one embodiment of this application, after communicating with the smart device using the aforementioned final communication protocol, the method further includes: in the event of a communication failure between the IoT device and the smart device, determining a fourth target communication protocol based on the adaptability score of other pre-selected communication protocols besides the aforementioned final communication protocol and the aforementioned weight; and communicating with the smart device using the aforementioned fourth target communication protocol.

[0055] By monitoring network status in real time, once a performance degradation or communication interruption of the current communication protocol is detected, an alternative protocol is quickly selected based on a pre-assessed protocol adaptability score and business requirement weight. This effectively prevents communication failures caused by single-protocol dependence and improves the system's adaptability to network fluctuations. In the event of a communication failure, a rapid and smooth switch to a fourth target communication protocol reduces user waiting time and perceived network latency during interruptions, ensuring the continuity and high quality of real-time applications such as online conferencing and remote control, thus enhancing the user experience. Intelligent analysis based on a deep learning prediction module can anticipate potential changes in the network environment and quickly adjust communication strategies even in worst-case scenarios, avoiding prolonged business interruptions and resource waste, and achieving efficient utilization of network resources. Dynamic protocol adjustment not only solves the problem of sudden network failures but also continuously optimizes communication performance based on current business types and QoS requirements, ensuring optimal communication results in different scenarios (such as high data rate requirements and low latency requirements).

[0056] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0057] This application also provides an Internet of Things (IoT) device. It should be noted that the IoT device of this application can be used to execute the communication method between IoT devices and smart devices provided in this application. This IoT device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the IoT device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0058] The following describes the Internet of Things (IoT) devices provided in the embodiments of this application.

[0059] Figure 2 This is a schematic diagram of an Internet of Things (IoT) device according to an embodiment of this application. For example... Figure 2As shown, the IoT device includes: an acquisition unit 21, used to acquire network status data and context information, wherein the network status data includes RSSI, latency, and packet loss rate, and the context information includes user movement trajectory and service QoS requirements; a first processing unit 22, used to process at least the network status data and the context information using a deep learning model composed of LSTM and attention mechanisms to obtain the adaptability scores and corresponding weights of multiple pre-selected communication protocols; and a second processing unit 23, used to determine the final communication protocol based on the adaptability scores and weights of each pre-selected communication protocol, and use the final communication protocol to communicate with the smart device.

[0060] In one embodiment of this application, the second processing unit includes: a first determining module for determining a first target communication protocol as the pre-selected communication protocol corresponding to a weight greater than or equal to a weight threshold; and a second determining module for determining the final communication protocol based on the adaptability score of the first target communication protocol.

[0061] In one embodiment of this application, the second determining module includes: a first determining submodule for determining that the final communication protocol is the first target communication protocol corresponding to the maximum value of the fitness score.

[0062] In one embodiment of this application, the second determining module includes: a second determining submodule for determining the weight difference of each of the first target communication protocols, wherein the weight difference is the absolute value of the difference between the weight and the weight threshold; a third determining submodule for determining the second target communication protocol, wherein the second target communication protocol is the first target communication protocol among all the first target communication protocols whose weight difference is less than or equal to the difference threshold; and a fourth determining submodule for determining the final communication protocol as the second target communication protocol corresponding to the maximum value of the fitness score.

[0063] In one embodiment of this application, the first processing unit includes: an acquisition module for acquiring the potential overhead of each communication protocol, wherein the potential overhead includes authentication delay and signaling cost; and the first processing module for processing the potential overhead of each communication protocol, the network state data and the context information using a deep learning model composed of LSTM and attention mechanism to obtain the adaptability scores and corresponding weights of multiple pre-selected communication protocols.

[0064] In one embodiment of this application, the second processing unit includes: a second processing module configured to determine a third target communication protocol when there are multiple pre-selected communication protocols with the same fitness score and weight among all the pre-selected communication protocols, wherein the third target communication protocol is one of the multiple pre-selected communication protocols with the same fitness score and weight among all the pre-selected communication protocols; and a third processing module configured to determine that the final communication protocol is the third target communication protocol corresponding to the maximum value of the fitness score.

[0065] In one embodiment of this application, the IoT device further includes: after the third processing unit communicates with the smart device using the aforementioned final communication protocol, in the event of a communication failure between the IoT device and the smart device, it determines a fourth target communication protocol based on the adaptability scores of other pre-selected communication protocols besides the aforementioned final communication protocol and the aforementioned weights; the fourth processing unit is used to communicate with the aforementioned smart device using the aforementioned fourth target communication protocol.

[0066] The aforementioned IoT device includes a processor and a memory. The acquisition unit, the first processing unit, and the second processing unit, etc., are all stored as program units in the memory. The processor executes the program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0067] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the poor communication efficiency in existing technologies where manual selection of communication protocols for IoT and smart devices is required.

[0068] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0069] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the communication method between the Internet of Things device and the smart device.

[0070] This invention provides a processor for running a program, wherein the program executes the above-mentioned communication method between the Internet of Things (IoT) device and the smart device.

[0071] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps: acquiring network state data and context information, wherein the network state data includes RSSI, latency, and packet loss rate, and the context information includes user movement trajectory and service QoS requirements; processing the network state data and context information using a deep learning model composed of LSTM and attention mechanisms to obtain adaptability scores and corresponding weights for multiple pre-selected communication protocols; determining a final communication protocol based on the adaptability scores and weights of each pre-selected communication protocol, and communicating with the smart device using the final communication protocol. The device in this document can be a server, PC, PAD, mobile phone, etc.

[0072] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps: acquiring network state data and context information, wherein the network state data includes RSSI, latency, and packet loss rate, and the context information includes user movement trajectory and service QoS requirements; processing the network state data and the context information at least using a deep learning model composed of LSTM and attention mechanisms to obtain the adaptability scores and corresponding weights of multiple pre-selected communication protocols; determining the final communication protocol based on the adaptability scores of each of the pre-selected communication protocols and the weights, and using the final communication protocol to communicate with the smart device.

[0073] This application also provides a communication system, including: an Internet of Things (IoT) device and a smart device, wherein the IoT device and the smart device communicate with each other, and the IoT device is used to perform any of the above-described methods.

[0074] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0075] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0077] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0078] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0079] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0080] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0081] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0082] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0083] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0084] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for an Internet of Things device to communicate with a smart device, the method comprising: An Internet of Things device applied to a communication system, comprising: obtaining network state data and context information, wherein the network state data comprises RSSI, delay and packet loss rate, and the context information comprises user movement trajectory and service QoS requirement; adopting a deep learning model composed of LSTM and attention mechanism to process at least the network state data and the context information, to obtain adaptability scores and corresponding weights of a plurality of preselected communication protocols; determining a final communication protocol according to the adaptability scores and the weights of each of the preselected communication protocols, and communicating with an intelligent device by adopting the final communication protocol.

2. The method of claim 1, wherein, The method of determining a final communication protocol according to the adaptability scores and the weights of each of the preselected communication protocols comprises: determining a first target communication protocol as the preselected communication protocol corresponding to the weight greater than or equal to a weight threshold value; determining the final communication protocol according to the adaptability score of the first target communication protocol.

3. The method of claim 2, wherein, The method of determining the final communication protocol according to the adaptability score of the first target communication protocol comprises: determining the final communication protocol as the first target communication protocol corresponding to the maximum value of the adaptability score.

4. The method of claim 2, wherein, The method of determining the final communication protocol according to the adaptability score of the first target communication protocol comprises: determining a weight difference value of each of the first target communication protocols, wherein the weight difference value is the absolute value of the difference between the weight and the weight threshold value; determining a second target communication protocol, wherein the second target communication protocol is the first target communication protocol with a weight difference value less than or equal to a difference threshold value among all the first target communication protocols; determining the final communication protocol as the second target communication protocol corresponding to the maximum value of the adaptability score.

5. The method of claim 1, wherein, The method of adopting a deep learning model composed of LSTM and attention mechanism to process at least the network state data and the context information, to obtain adaptability scores and corresponding weights of a plurality of preselected communication protocols comprises: obtaining potential overheads of each communication protocol, wherein the potential overheads comprise authentication delay and signaling cost; adopting a deep learning model composed of LSTM and attention mechanism to process the potential overheads, the network state data and the context information of each of the communication protocols, to obtain the adaptability scores and the corresponding weights of a plurality of the preselected communication protocols.

6. The method of claim 1, wherein, The method of determining a final communication protocol according to the adaptability scores and the weights of each of the preselected communication protocols comprises: in the case that there are a plurality of preselected communication protocols with the same adaptability score and the same weight among all the preselected communication protocols, determining a third target communication protocol, wherein the third target communication protocol is one of the preselected communication protocols with the same adaptability score and the same weight among all the preselected communication protocols; determining the final communication protocol as the third target communication protocol corresponding to the maximum value of the adaptability score.

7. The method of claim 6, wherein, After communicating with an intelligent device by adopting the final communication protocol, the method further comprises: In the case of communication failure between the Internet of Things device and the smart device, a fourth target communication protocol is determined according to the adaptability scores of the preselected communication protocols other than the final communication protocol and the weights; Communication is performed with the smart device using the fourth target communication protocol.

8. An Internet of Things device, characterized by Comprise: An acquisition unit is configured to acquire network state data and context information, the network state data including RSSI, delay and packet loss rate, and the context information including user movement trajectory and service QoS requirement; A first processing unit is configured to process at least the network state data and the context information using a deep learning model composed of LSTM and attention mechanism, to obtain adaptability scores of a plurality of preselected communication protocols and corresponding weights; A second processing unit is configured to determine a final communication protocol according to the adaptability scores of each of the preselected communication protocols and the weights, and to perform communication with a smart device using the final communication protocol.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein the program controls the device where the computer readable storage medium is located to execute the method of any one of claims 1 to 7 when the program is running.

10. A communication system, characterized by Comprise: An Internet of Things device and a smart device, the Internet of Things device and the smart device performing communication, and the Internet of Things device being configured to execute the method of any one of claims 1 to 7.

Images