Internet of things touch screen controller supporting multiple communication protocols and communication method thereof

Abstract

The application relates to the technical field of communication, and particularly discloses an Internet of Things touch screen controller supporting multiple communication protocols and a communication method thereof. The Internet of Things touch screen controller comprises a protocol identification module, a data analysis module, a data conversion module and a control execution module. The protocol identification module adopts a multi-stage matching algorithm of a weighted decision tree to determine a current communication protocol type. The data analysis module analyzes input data by using a corresponding protocol analysis algorithm, generates a corresponding real-time state transition matrix based on a current analysis state path of the input data, analyzes real-time coincidence degrees between the current analysis state path and an expected analysis state path based on the real-time state transition matrix, judges whether an analysis abnormality processing procedure is triggered based on the real-time coincidence degrees, and extracts payload data until the payload data is extracted. The data conversion module converts the payload data into a unified internal data format to obtain target instruction content. The control execution module executes corresponding device control operations or state feedback operations based on the target instruction content, thereby meeting control requirements in different scenes.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to an Internet of Things (IoT) touchscreen controller that supports multiple communication protocols and its communication method. Background Technology

[0002] With the rapid development of the Internet of Things (IoT), the demand for interconnection and interaction among various devices is increasing daily. Touchscreens, as an intuitive and convenient human-machine interface, are widely used in IoT devices across multiple fields such as smart homes, industrial control, smart healthcare, and intelligent transportation. Different application scenarios and devices often employ different communication protocols for data transmission to meet their respective functional requirements and technical standards. IoT touchscreen controllers that support multiple communication protocols and their communication methods hold an extremely important position in the IoT ecosystem. From the interconnection between devices of different brands in smart home systems to the collaborative operation of various smart devices on industrial production lines, this technology has broad application prospects and helps build a larger, more efficient, and flexible IoT ecosystem.

[0003] However, existing IoT touchscreen controllers cannot use efficient and accurate algorithms to identify their protocols, resulting in the inability to quickly determine the current communication protocol type. This affects the timeliness of data parsing and makes it difficult to determine in a timely manner whether parsing anomaly handling procedures have been triggered. This can easily lead to data parsing errors, which in turn affect the reading and execution of subsequent instruction content and corresponding device control operations or status feedback operations, thus impacting the normal operation of IoT devices and user experience.

[0004] Therefore, this invention proposes an IoT touchscreen controller that supports multiple communication protocols and its communication method. Summary of the Invention

[0005] This invention provides an IoT touchscreen controller and its communication method that support multiple communication protocols. By monitoring input data from the physical interface and employing a multi-level matching algorithm based on a weighted decision tree, the current communication protocol type can be identified quickly and accurately, ensuring targeted processing in subsequent steps. The input data is parsed using the corresponding protocol parsing algorithm, simultaneously generating a real-time state transition matrix and analyzing its real-time consistency with the expected path to determine if an anomaly handling process is triggered, until the payload data is extracted. This ensures the accuracy and stability of the parsing process and allows for timely detection and handling of parsing anomalies. The payload data is converted into a unified internal data format to obtain the target instruction content, achieving standardized processing of data from different protocols and facilitating unified management and operation within the system. Based on the target instruction content, corresponding device control or status feedback operations are executed, achieving precise control and status feedback for the touchscreen device. This improves the operating efficiency and reliability of the IoT touchscreen in various communication protocol environments, meets the control requirements of different scenarios, and enhances the adaptability and flexibility of the entire IoT touchscreen control system.

[0006] This invention provides an IoT touchscreen controller supporting multiple communication protocols, comprising:

[0007] The protocol identification module is used to monitor the input data of the physical interface and uses a multi-level matching algorithm of weighted decision tree to identify the protocol of the input data and determine the current communication protocol type.

[0008] The data parsing module is used to parse the input data using the protocol parsing algorithm corresponding to the current communication protocol type. At the same time, it generates a corresponding real-time state transition matrix based on the current parsing state path of the input data, analyzes the real-time consistency between the current parsing state path and the expected parsing state path based on the real-time state transition matrix, and determines whether to trigger the parsing anomaly handling process based on the real-time consistency, until the effective payload data is extracted.

[0009] The data conversion module is used to convert payload data into a unified internal data format to obtain the target instruction content;

[0010] The control execution module is used to execute corresponding device control operations or status feedback operations based on the target instruction content.

[0011] This invention provides a communication method for an IoT touchscreen controller supporting multiple communication protocols, applicable to the aforementioned IoT touchscreen controller supporting multiple communication protocols, comprising:

[0012] Listen to the input data of the physical interface, and use a multi-level matching algorithm of weighted decision tree to identify the protocol of the input data and determine the current communication protocol type;

[0013] The input data is parsed using the protocol parsing algorithm corresponding to the current communication protocol type. At the same time, a corresponding real-time state transition matrix is ​​generated based on the current parsing state path of the input data. The real-time consistency between the current parsing state path and the expected parsing state path is analyzed based on the real-time state transition matrix. Based on the real-time consistency, it is determined whether to trigger the parsing anomaly handling process until the effective payload data is extracted.

[0014] Convert the payload data into an internal data format to obtain the target instruction content;

[0015] Execute the corresponding device control operation or status feedback operation based on the target instruction content.

[0016] Preferably, a multi-level matching algorithm using weighted decision trees is employed to identify the protocol in the input data and determine the current communication protocol type, including:

[0017] Extract multiple feature vectors from the first N bytes of the input data;

[0018] All extracted feature vectors are input into a pre-trained weighted decision model. The comprehensive matching probability of each communication protocol type is calculated based on the output path of the weighted decision model. The protocol type with the highest probability is selected as the current communication protocol type.

[0019] In this model, different branch nodes correspond to the key features of different protocols, and the node weights are dynamically updated based on the historical recognition confidence of the corresponding key features. At the same time, all link indicators in the protocol recognition process are collected in real time. If any link indicator exceeds the corresponding indicator threshold, the decision tree parameters are dynamically adjusted.

[0020] Preferably, a real-time state transition matrix is ​​generated based on the current parsing state path of the input data, and the real-time consistency between the current parsing state path and the expected parsing state path is analyzed based on the real-time state transition matrix. Based on the real-time consistency, it is determined whether to trigger the parsing anomaly handling process, including:

[0021] Retrieve the expected parsing state path corresponding to the current communication protocol type, and generate the expected state transition matrix based on the expected parsing state path; wherein the expected parsing state path contains the complete expected state sequence of the data packet from start frame identification, packet header parsing, data field extraction to check code verification;

[0022] When parsing the input data, the current state corresponding to each parsing operation is recorded in real time to form the current parsing state path, and a real-time state transition matrix is ​​generated based on the actual jump results of adjacent parsing state nodes in the current parsing state path.

[0023] Calculate the real-time consistency between the real-time state transition matrix and the expected state transition matrix;

[0024] Determine if the real-time matching degree is not less than the set matching degree threshold. If it is, determine that the current parsing status path is normal and continue parsing. Otherwise, determine that there is a status deviation and trigger the parsing exception handling process.

[0025] Preferably, the payload data is converted into an internal data format to obtain the target instruction content, including:

[0026] The semantic mapping rules of the payload data fields to the internal common data model are invoked to convert the specific data names and numerical types of the payload data into unified semantic identifiers and standard data types in the common data model, thereby obtaining the target instruction content.

[0027] Preferred options also include:

[0028] Based on the historical control records of the IoT touch screen controller, the expected transmission resource parameters of the communication link between the IoT touch screen controller and each predicted communication device in each future step are analyzed.

[0029] Based on the expected transmission resource parameters and corresponding communication protocol types of the communication link between the virtual protocol stack, the IoT touch screen controller and each predictive communication device in each future step, a pre-communication link is built.

[0030] When the IoT touchscreen controller receives an actual control command for any predictive communication device at any step, it executes the corresponding device control operation or status feedback operation based on the predictive communication link.

[0031] Preferably, based on the historical control records of the IoT touchscreen controller, the expected transmission resource parameters of the communication link between the IoT touchscreen controller and each predicted communication device for each future step are analyzed, including:

[0032] The system acquires historical control records of the IoT touchscreen controller, and based on these records, it parses out the communication device and multidimensional network environment status parameters of each historical control command, as well as the actual transmission resource parameters of the corresponding communication link. It also calculates the transmission resource ratio of the corresponding communication link under the corresponding multidimensional network environment status parameters.

[0033] Periodic analysis of historical control records identifies all predicted communication devices and their corresponding hit rates for the IoT touchscreen controller at each future step. It also analyzes the critical values ​​of transmission resource parameters for each predicted communication device in the historical control records and the proportion of transmission resources for the corresponding communication link under various multidimensional network environment state parameters.

[0034] The multidimensional network environment state parameters of the IoT touch screen controller are predicted to obtain all predicted values ​​and probability distributions of the multidimensional network environment state parameters in the execution cycle of each future step.

[0035] Based on all predicted communication devices and their corresponding hit rates in each future step of the IoT touch screen controller, the critical value of the transmission resource parameters of each predicted communication device, and the proportion of transmission resources of the corresponding communication link under various multi-dimensional network environment state parameters, a transmission resource expectation inference network tree for each future step is constructed.

[0036] Based on the expected transmission resource inference network tree for each future step and all predicted values ​​and probability distributions of the multidimensional network environment state parameters within the execution cycle of each future step, the expected transmission resource parameters of the communication link between the IoT touchscreen controller and each predicted communication device in each future step are determined.

[0037] Preferably, based on all predicted communication devices and their corresponding hit rates in each future step of the IoT touchscreen controller, the critical values ​​of transmission resource parameters for each predicted communication device, and the proportion of transmission resources of the corresponding communication link under various multi-dimensional network environment state parameters, a transmission resource expectation inference tree for each future step is constructed, including:

[0038] Each future step is treated as a first-layer node, and all predicted communication devices of the IoT touchscreen controller in the corresponding future step are treated as second-layer nodes. The hit rate is used as the weight of the connection edge between the corresponding second-layer node and the first-layer node. Each multi-dimensional network environment state parameter is treated as a third-layer node, and the proportion of transmission resources of the communication link corresponding to each predicted communication device under the corresponding multi-dimensional network environment state parameter is used as the weight of the connection edge between the corresponding second-layer node and the corresponding third-layer node. This yields the transmission resource expectation inference network tree for each future step.

[0039] Preferably, based on the expected transmission resource inference network tree of each future step and all predicted values ​​and probability distributions of the multi-dimensional network environment state parameters within the execution cycle of each future step, the expected transmission resource parameters of the communication link between the IoT touchscreen controller and each predicted communication device in each future step are determined, including:

[0040] In the expected inference network tree of the transport resources in each future step, all inference networks that pass through each multidimensional network environment state parameter are identified as the inference network to which each multidimensional network environment state parameter belongs, where each inference network contains a node of each level.

[0041] Based on all predicted values ​​and probability distributions of the multidimensional network environment state parameters within the execution cycle of each future step, all multidimensional network environment state prediction parameters and corresponding hit rates for each future step are determined.

[0042] Based on the multidimensional network environment state prediction parameter and the corresponding hit rate for each future step, the hit rate of each multidimensional network environment state prediction parameter for all inference networks to which each multidimensional network environment state parameter belongs in the expected inference network tree of transmission resources is calculated.

[0043] In the expected inference network tree of transmission resources, all multidimensional network environment state parameters with a hit rate greater than the hit rate threshold are selected as high-hit-rate multidimensional network environment state parameters.

[0044] Reasoning is performed on all the reasoning networks to which all high-hit-rate multidimensional network environment state parameters belong in the expected reasoning network tree of transmission resources, to obtain the relative proportion of transmission resources and the corresponding absolute hit rate of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters.

[0045] Based on the transmission resource ratio and absolute hit rate of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the expected transmission resource parameters of the communication links between the IoT touch screen controller and each predicted communication device in each future step are determined.

[0046] Preferably, based on the proportion of transmission resources and the corresponding absolute hit rate of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the expected transmission resource parameters of the communication link between the IoT touch screen controller and each predicted communication device in each future step are determined, including:

[0047] Based on the absolute hit rate of the transmission resource ratio of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the relative hit rate of the transmission resource ratio of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters is calculated.

[0048] In each future step, all predictive communication devices whose relative hit rate of the corresponding communication link is not lower than the preset relative hit rate threshold are considered as valid predictive communication devices for the corresponding future step.

[0049] Based on the transmission resource ratio and absolute hit rate of the communication links corresponding to all valid predictive communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the expected transmission resource parameters of the communication links between the IoT touch screen controller and each predictive communication device in each future step are determined.

[0050] The beneficial effects of this invention compared to existing technologies are as follows: By monitoring input data from the physical interface and employing a multi-level matching algorithm based on a weighted decision tree to identify the current communication protocol type, the invention can quickly and accurately determine the data source protocol, ensuring the targeted nature of subsequent processing. The input data is parsed using the corresponding protocol parsing algorithm, simultaneously generating a real-time state transition matrix and analyzing its real-time consistency with the expected path to determine whether an anomaly handling process is triggered, until the payload data is extracted. This ensures the accuracy and stability of the parsing process and allows for timely detection and handling of parsing anomalies. The payload data is converted into a unified internal data format to obtain the target instruction content, achieving standardized processing of different protocol data and facilitating unified management and operation within the system. Based on the target instruction content, corresponding device control or status feedback operations are executed, completing precise control and status feedback for the touchscreen device. This invention enables the touchscreen controller to be compatible with multiple communication protocols, achieving seamless integration and efficient communication with different devices. It improves the operating efficiency and reliability of IoT touchscreens in various communication protocol environments, meeting the control needs of different scenarios. This not only improves the versatility and interoperability of IoT devices and enhances the adaptability and flexibility of the entire IoT touchscreen control system, avoiding the problem of devices being unable to connect due to protocol incompatibility, but also reduces development and deployment costs, promoting the widespread application of IoT technology in more fields.

[0051] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0052] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0053] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0054] Figure 1 This is a schematic diagram of an IoT touchscreen controller supporting multiple communication protocols and its communication method in an embodiment of the present invention;

[0055] Figure 2This is a schematic diagram of the protocol identification process of the weighted decision tree multi-level matching algorithm in an embodiment of the present invention;

[0056] Figure 3 This is a schematic diagram of the judgment process for triggering parsing exception handling in an embodiment of the present invention. Detailed Implementation

[0057] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0058] like Figure 1 As shown, the present invention provides an implementation of an IoT touchscreen controller supporting multiple communication protocols, comprising:

[0059] The protocol identification module is used to monitor the input data of the physical interface and uses a multi-level matching algorithm of weighted decision tree to identify the protocol of the input data and determine the current communication protocol type.

[0060] The data parsing module is used to parse the input data using the protocol parsing algorithm corresponding to the current communication protocol type. At the same time, it generates a corresponding real-time state transition matrix based on the current parsing state path of the input data, analyzes the real-time consistency between the current parsing state path and the expected parsing state path based on the real-time state transition matrix, and determines whether to trigger the parsing anomaly handling process based on the real-time consistency, until the effective payload data is extracted.

[0061] The data conversion module is used to convert payload data into a unified internal data format to obtain the target instruction content;

[0062] The control execution module is used to execute corresponding device control operations or status feedback operations based on the target instruction content.

[0063] In this embodiment, the input data of the physical interface refers to the data transmitted from the outside to the physical connection port of the IoT touch screen controller. This data carries information that follows a specific communication protocol and is the starting input of the entire data processing flow.

[0064] In this embodiment, the current communication protocol type is determined by the protocol identification module after analyzing the physical interface input data during the operation of the IoT touchscreen controller. The IoT touchscreen controller supports multiple communication protocols, such as MQTT (Message Queuing Telemetry Transport), CoAP (Constrained Application Protocol), and Modbus (Industrial Fieldbus Protocol). The specific protocol currently in use, identified through identification, is the current communication protocol type.

[0065] In this embodiment, "multiple communication protocols" means that the IoT touchscreen controller has the ability to handle multiple different communication protocols. Each of these protocols has its own characteristics and applicable scenarios. By supporting multiple communication protocols, the controller can interact and communicate with various devices using different protocol standards. For example, in industrial control scenarios, it can communicate with traditional industrial equipment using the Modbus protocol, and also interact with smart sensors that use the MQTT protocol for data reporting.

[0066] In this embodiment, the IoT touchscreen controller is a device control device that is applied in an IoT environment, integrates a touch operation interface, and can support multiple communication protocols.

[0067] In this embodiment, the protocol parsing algorithm corresponding to the current communication protocol type is a series of rules and steps specifically designed for a particular identified communication protocol to parse input data that conforms to the protocol format. For example, for the MQTT protocol, its protocol parsing algorithm will parse the input data according to the fixed header, variable header, message body, and other structures specified by the MQTT protocol to obtain information such as the topic, message content, and QoS level.

[0068] In this embodiment, the input data is parsed using a protocol parsing algorithm corresponding to the current communication protocol type. This involves applying a parsing algorithm adapted to the currently determined communication protocol to process the input data received from the physical interface. The data is broken down step-by-step according to the specific format and specifications of the protocol, extracting the valid information it contains. For example, when the current communication protocol type is determined to be Modbus, the Modbus protocol parsing algorithm is used to parse the input Modbus data packet, obtaining information such as the function code and device address from the header, and extracting actual data content such as register values ​​from the data field.

[0069] In this embodiment, the current parsing state path of the input data is a sequential path formed by recording the state reached at each parsing step during the parsing process using the corresponding protocol parsing algorithm. Each parsing step corresponds to a specific state, and these states are arranged sequentially to form the current parsing state path as parsing progresses. For example, when parsing a data packet conforming to a specific protocol, starting from the start frame identification state, passing through the header parsing state, the data field extraction state, and finally the checksum verification state, this series of states constitutes the current parsing state path of the input data.

[0070] In this embodiment, the real-time state transition matrix is ​​a matrix representation generated based on the current parsing state path of the input data. The element values ​​of the matrix are updated according to the actual jump result of "current state → next state", with a successful jump recorded as "1" and a failure recorded as "0". It can intuitively reflect the jump situation between various states during the parsing process and help analyze whether the parsing process is normal. For example, when parsing a protocol data packet, if the jump from the initial frame identification state to the packet header parsing state is successful, the corresponding element value in the matrix is ​​recorded as "1"; if the jump from the data field extraction state to the checksum verification state fails, the corresponding element value is recorded as "0".

[0071] In this embodiment, the expected parsing state path is a pre-defined ideal sequence of states conforming to the standard parsing process of each communication protocol. It describes the states that should be reached at each stage from the start of packet parsing to the completion of parsing.

[0072] In this embodiment, payload data refers to the truly valuable and business-relevant data extracted from the input data after protocol parsing. Redundant parts of the protocol itself, such as control information and header information, have been removed. This data is the core content upon which subsequent data conversion and device control operations are based. For example, after parsing a sensor data packet, the payload data might be the actual measured values ​​of temperature, humidity, etc., collected by the sensor.

[0073] In this embodiment, the payload data is converted into a unified internal data format to obtain the target instruction content. This involves extracting the payload data from the input data and converting it into a data format uniformly defined within the IoT touchscreen controller, according to pre-set rules. This results in target instruction content that can be understood and processed by the control execution module. This process involves data type conversion, semantic mapping, and other operations. For example, different data formats and units representing temperature under different protocols are uniformly converted into a floating-point format in degrees Celsius as defined within the controller and mapped to the instruction content of "read temperature".

[0074] In this embodiment, corresponding device control operations or status feedback operations are executed based on the target instruction content: after obtaining the target instruction content, the control execution module performs corresponding control actions on the relevant device according to the type and specific content of the instruction, such as starting or stopping the device, adjusting device parameters, etc.; or performs status feedback operations to feed back the current status information of the device to the relevant system or user.

[0075] like Figure 1 As shown, this invention provides an implementation method for a communication method of an IoT touchscreen controller supporting multiple communication protocols, applied to the IoT touchscreen controller supporting multiple communication protocols in Embodiment 1, comprising:

[0076] Listen to the input data of the physical interface, and use a multi-level matching algorithm of weighted decision tree to identify the protocol of the input data and determine the current communication protocol type;

[0077] The input data is parsed using the protocol parsing algorithm corresponding to the current communication protocol type. At the same time, a corresponding real-time state transition matrix is ​​generated based on the current parsing state path of the input data. The real-time consistency between the current parsing state path and the expected parsing state path is analyzed based on the real-time state transition matrix. Based on the real-time consistency, it is determined whether to trigger the parsing anomaly handling process until the effective payload data is extracted.

[0078] Convert the payload data into an internal data format to obtain the target instruction content;

[0079] Execute the corresponding device control operation or status feedback operation based on the target instruction content.

[0080] like Figure 2 As shown, in order to accurately identify the current communication protocol type, a multi-level matching algorithm using weighted decision trees is proposed to identify the protocol in the input data and determine the current communication protocol type, including:

[0081] Extract multiple feature vectors from the first N bytes of the input data, where N ranges from 16 to 64. From the input data received from the physical interface, select the first N bytes and extract multiple vectors that characterize the data. These feature vectors contain key information related to the communication protocol, such as the start character, function code, and length field value. Different communication protocols often have unique feature patterns in the beginning of the data. For example, for Modbus protocol data packets, the first N bytes may contain specific function codes and device addresses.

[0082] All extracted feature vectors are input into a pre-trained weighted decision model. The model calculates the overall matching probability of each communication protocol type based on its output path, selecting the protocol type with the highest probability as the current communication protocol type. Specifically, all feature vectors extracted from the first N bytes of the input data are input into the pre-trained weighted decision model. The model calculates along different branch nodes based on these feature vectors, with each branch node influencing the calculation result according to its weight. Finally, the model outputs a path, and based on the matching of each node along this path with the key features of different communication protocols, it calculates the overall matching probability of each communication protocol type. For example, if the model calculates a matching probability of 0.7 for the MQTT protocol and 0.3 for the CoAP protocol, then the MQTT protocol with the highest probability is selected as the current communication protocol type. This quantified probability calculation allows for a more accurate identification of the communication protocol followed by the current input data.

[0083] In this weighted decision model, different branch nodes correspond to key features of different protocols, and the node weights are dynamically updated based on the historical recognition confidence of the corresponding key features. Simultaneously, all link metrics during the protocol recognition process are collected in real time. If any link metric exceeds its corresponding threshold, the decision tree parameters are dynamically adjusted. Each branch node of the weighted decision model corresponds to a key feature of a specific communication protocol; for example, a node might correspond to a specific field in the fixed header of the MQTT protocol. Node weights are not fixed but dynamically updated based on the confidence of the key feature in the historical recognition process. If a feature has accurately identified a communication protocol multiple times in the past, its corresponding node weight will increase; conversely, if the recognition effect is poor, the weight will decrease. During protocol recognition, link metrics such as packet matching success rate and recognition latency are collected in real time. If any link metric exceeds a pre-set threshold, such as a recognition latency exceeding 100ms, the parameters of the weighted decision model, typically presented in decision tree form, will be dynamically adjusted. This dynamic adjustment mechanism allows the model to continuously optimize based on actual recognition conditions, improving the accuracy and stability of protocol recognition in complex network environments.

[0084] In this embodiment, the pre-trained weighted decision model is a pre-trained model used to determine the type of communication protocol based on the input feature vector. During training, a large amount of sample data with known communication protocol types is used. A specific algorithm learns the relationship between the feature vectors in this sample data and the protocol type, and assigns corresponding weights to each branch node in the model. These weights reflect the importance of each feature in identifying different communication protocols. For example, if during training it is found that a certain feature has high accuracy in identifying the MQTT protocol, then in the weighted decision model, the node corresponding to this feature will have a relatively high weight.

[0085] like Figure 3 As shown, to ensure accurate and stable data parsing, a real-time state transition matrix is ​​generated based on the current parsing state path of the input data. The real-time consistency between the current parsing state path and the expected parsing state path is analyzed based on the real-time state transition matrix. Finally, based on the real-time consistency, a parsing anomaly handling process is triggered, including:

[0086] The expected parsing state path corresponding to the current communication protocol type is retrieved, and an expected state transition matrix is ​​generated based on the expected parsing state path. The expected parsing state path contains a complete expected state sequence from start frame identification, header parsing, data field extraction to checksum verification. For each communication protocol, the expected parsing state path specifies in detail a series of standard steps and corresponding states for the data packet from start to finish parsing. First, start frame identification confirms the start identifier of the data packet to determine if it belongs to this protocol. Then, header parsing is performed to obtain key information such as the address and function code contained in the packet header. Next, data field extraction is performed to extract the actual data content from the data packet. Finally, checksum verification checks whether any errors occurred during data packet transmission. Taking the Modbus protocol as an example, this series of steps constitutes a complete expected state sequence, ensuring that the data packet is parsed according to the correct process.

[0087] When parsing the input data, the current state corresponding to each parsing operation is recorded in real time to form the current parsing state path, and a real-time state transition matrix is ​​generated based on the actual jump results of adjacent parsing state nodes in the current parsing state path.

[0088] Calculate the real-time consistency between the real-time state transition matrix and the expected state transition matrix;

[0089] The system checks if the real-time matching degree is not less than a set matching degree threshold. If so, the current parsing status path is considered normal, and parsing continues. Otherwise, a status deviation is identified, triggering a parsing anomaly handling process. This process includes various handling methods, such as checking the completeness of the input data and whether there are transmission errors, sending a retransmission request to the data sender, discarding erroneous data packets and recording relevant anomaly information, and displaying alarm information on the touchscreen to notify the user. By triggering the parsing anomaly handling process, problems that occur during parsing are resolved as much as possible, ensuring the accuracy of data parsing and the stability of the system.

[0090] In this embodiment, the expected parsing state path corresponding to the current communication protocol type is retrieved: When parsing input data, based on the determined current communication protocol type, the corresponding standard parsing process, i.e., the expected parsing state path, is obtained from the relevant information pre-stored by the system. This is the order of state changes that the communication protocol data packet should follow under normal parsing conditions. For example, if the current communication protocol type is Modbus, its standard expected parsing state path is retrieved from the stored Modbus protocol-related data.

[0091] In this embodiment, an expected state transition matrix is ​​generated based on the expected parsing state path: the expected parsing state path is transformed into matrix form. The rows and columns of the matrix correspond to the various states in the parsing process, and the matrix element values ​​represent the expected transition from one state to another. If a normal transition from state A to state B is possible in the expected parsing state path, the element value at the corresponding position in the expected state transition matrix may be set to 1 (indicating that the transition is allowed); if the transition is not allowed, it is set to 0.

[0092] In this embodiment, the current state corresponding to each parsing operation is recorded in real time to form the current parsing state path, and a real-time state transition matrix is ​​generated based on the actual jump results of adjacent parsing state nodes in the current parsing state path:

[0093] During the actual parsing of input data, the system records the current parsing state in real time with each parsing operation. These states are connected sequentially to form the current parsing state path. Simultaneously, the system observes the actual transitions between adjacent parsing state nodes in the current parsing state path and assigns a value to the corresponding position in the real-time state transition matrix based on whether the transition is successful or not. If a transition from one state to the next is successful, it is recorded as 1 in the corresponding position of the matrix; if the transition fails, it is recorded as 0.

[0094] In this embodiment, the real-time consistency between the real-time state transition matrix and the expected state transition matrix is ​​calculated: In order to determine the degree of conformity between the actual parsing process and the expected parsing process, algorithms such as cosine similarity and Hamming distance are used to calculate the similarity between the real-time state transition matrix and the expected state transition matrix. This similarity is the real-time consistency.

[0095] In this embodiment, a matching threshold is set: a standard value is predetermined to determine whether the parsing process is normal, i.e., the matching threshold. For example, the matching threshold is set to 80%.

[0096] To achieve standardized data format conversion, a method is proposed to convert payload data into an internal data format to obtain the target instruction content, including:

[0097] The semantic mapping rules of the payload data fields to the internal common data model are invoked to convert the specific data names and numerical types of the payload data into unified semantic identifiers and standard data types in the common data model, thereby obtaining the target instruction content.

[0098] In this embodiment, after successfully extracting payload data from the input data, due to differences in data fields, names, and numerical types under different communication protocols, a specially defined semantic mapping rule is invoked to enable the IoT touchscreen controller to process this data in a unified manner. These rules specify in detail how to convert payload data from various communication protocols, from their specific data names and numerical types, into a unified semantic identifier and standard data type used by the controller's internal common data model. For example, in the Modbus protocol, data might represent temperature using register addresses and specific numerical formats, while another protocol might use different names and data formats. Through the semantic mapping rule, the register data name and specific numerical type representing temperature in the Modbus protocol are transformed into a unified "temperature" semantic identifier in the internal common data model, and the numerical type is standardized to a standard floating-point number.

[0099] After this conversion process, the final result is the target instruction content. The target instruction content is presented in a unified format, which facilitates the subsequent control execution module to accurately execute the corresponding device control operations or status feedback operations based on it.

[0100] To plan communication links in advance and optimize operational processes, the following additional measures are proposed:

[0101] Based on the historical control records of the IoT touch screen controller, the expected transmission resource parameters of the communication link between the IoT touch screen controller and each predicted communication device in each future step are analyzed.

[0102] Based on the expected transmission resource parameters and corresponding communication protocol types of the communication link between the virtual protocol stack, the IoT touch screen controller and each predictive communication device in each future step, a pre-communication link is built.

[0103] When the IoT touchscreen controller receives an actual control command for any predictive communication device at any step, it executes the corresponding device control operation or status feedback operation based on the predictive communication link.

[0104] In this embodiment, the historical control records of the IoT touchscreen controller refer to a series of recorded information generated by the IoT touchscreen controller in the past when performing control operations. These records detail the relevant data of the controller's control over various devices at different points in the past, including but not limited to the specific content of the control commands, the identification of the controlled devices, the network environment status when the control operation occurred, and parameters such as the actual transmission resources consumed by the corresponding communication link. For example, the record may show that at a certain moment, the controller sent a command to read data to a sensor device at a specific address, at which time the network signal strength was -60dBm, and the actual transmission resources consumed by the communication link were: channel occupancy rate of 8%, bandwidth occupancy rate of 1.33%, and channel occupancy time of 1.7 microseconds, etc.

[0105] In this embodiment, future steps refer to the time stages or operation process nodes that are divided when planning or predicting the subsequent operation of the IoT touch screen controller. Each step may involve interactive operations with different predictive communication devices.

[0106] In this embodiment, the predicted communication devices are estimated based on the historical control records and related data analysis of the IoT touchscreen controller. By analyzing factors such as device usage frequency, usage scenarios, and relationships with other devices in historical data, it is determined which devices are highly likely to communicate with the controller in future steps; these devices are the predicted communication devices.

[0107] In this embodiment, the expected transmission resource parameters of the communication link are estimated by combining the historical control records of the IoT touch screen controller, the relevant information of the predicted communication devices, and the prediction of the future multi-dimensional network environment state parameters. This estimate represents the expected transmission resource consumption of the communication link between the controller and each effective predicted communication device in each future step.

[0108] In this embodiment, the virtual protocol stack is a software-defined protocol processing module that supports dynamic loading and switching of multiple protocols. As a key part of the IoT touchscreen controller responsible for protocol processing and communication link management, it pre-constructs communication links based on the expected transmission resource parameters and corresponding communication protocol types of the communication links with each predicted communication device in each future step. First, the required resources and energy consumption are assessed based on the expected transmission resource parameters. For links with high transmission resources, a more efficient communication protocol may be selected or protocol parameters may be adjusted to reduce transmission resources. Then, based on the selected communication protocol type, the virtual protocol stack establishes a logical communication connection between the controller and the predicted communication device, i.e., a pre-construction communication link. For example, if the expected transmission resources for the communication link with a device in the third future step are high, and the device supports both MQTT and CoAP protocols, considering the relatively low transmission resources of the CoAP protocol, the virtual protocol stack pre-constructs a pre-construction communication link for this step based on the CoAP protocol, ensuring fast, efficient, and energy-saving data transmission when actual communication needs occur.

[0109] In this embodiment, during the operation of the IoT touchscreen controller, when it enters a future step and receives an actual control command for a predictive communication device in that step, it will activate the previously established predictive communication link to execute the corresponding operation. If it is a device control operation, the controller will send specific control commands to the predictive communication device through the predictive communication link, such as starting or stopping the device, or adjusting device parameters; if it is a status feedback operation, the predictive communication device will feed back its own status information to the controller through the predictive communication link.

[0110] To accurately predict communication link transmission resources, this paper proposes an approach based on the historical control records of an IoT touchscreen controller. This analysis reveals the expected transmission resource parameters of the communication link between the IoT touchscreen controller and each predicted communication device for each future step, including:

[0111] The process involves acquiring historical control records from the IoT touchscreen controller and parsing them to extract the communication device and multi-dimensional network environment status parameters for each historical control command, as well as the actual transmission resource parameters of the corresponding communication link. The proportion of transmission resources for the corresponding communication link under the given multi-dimensional network environment status parameters is then calculated. Specifically, each historical control command is meticulously reviewed from the existing historical control records of the IoT touchscreen controller. The communication device information associated with each command is extracted to identify which device(s) received and executed the control command. Simultaneously, the multi-dimensional network environment status parameters at the time of the command are acquired. These parameters may encompass multiple dimensions such as network bandwidth, signal strength, latency, and packet loss rate, describing the network state at the time of communication. Additionally, the actual transmission resource parameters consumed by the corresponding communication link are obtained. Based on this information, the proportion of transmission resources of the corresponding communication link within the total system transmission resources under the given multi-dimensional network environment status parameters is calculated. For example, if historical control records show that a control command was sent to device A at a certain moment, when the network bandwidth was 10Mbps, the signal strength was -70dBm, and the actual bandwidth occupied by the communication link was 0.2, then the transmission resource ratio, i.e. the bandwidth ratio, is 2%.

[0112] Periodic analysis of historical control records identifies all predicted communication devices and their corresponding hit rates for the IoT touchscreen controller at each future step. The analysis also determines the critical values ​​of transmission resource parameters for each predicted communication device in the historical control records and the proportion of transmission resources for the corresponding communication link under various multi-dimensional network environment state parameters.

[0113] Historical control records are analyzed in depth according to a certain time period (such as daily, weekly, or monthly). By observing factors such as the frequency, patterns, and scenarios of interactions between communication devices and the IoT touchscreen controller in different time periods, the predicted communication devices are identified as all devices that may communicate with the controller in each future step.

[0114] For each predicted communication device, the probability of it appearing and communicating with the controller in each future step is estimated based on data such as its frequency of appearance in historical control records; this is known as the hit rate. For example, analysis reveals that device B communicated with the controller 8 times around 10 AM each weekday in the past month, and this event communicated with all devices a total of 10 times. Based on this, it is predicted that device B's hit rate in the step at 10 AM each weekday in the future may reach 80%.

[0115] Simultaneously, critical values ​​for transmission resource parameters of each predicted communication device under different conditions are identified from historical control records. These include the minimum transmission resource requirements during normal operation and the maximum transmission resource requirements under full load. Furthermore, for various combinations of multidimensional network environment state parameters, the transmission resource ratio of corresponding communication links under these conditions is analyzed to understand the impact of network environment changes on the transmission resource ratio of communication links.

[0116] The multidimensional network environment state parameters of the IoT touchscreen controller are predicted to obtain all predicted values ​​and probability distributions of the multidimensional network environment state parameters within the execution cycle of each future step:

[0117] Predictive methods such as time series analysis and machine learning algorithms are used to estimate the multi-dimensional network environment parameters that IoT touchscreen controllers will face in the future. These multi-dimensional network environment parameters still include network bandwidth, signal strength, latency, packet loss rate, and other aspects. For the execution cycle of each future step (e.g., if each step is one hour, then the execution cycle is within that one hour), all possible values ​​of these network environment parameters are predicted, along with the probability of each predicted value, forming a probability distribution. For example, predicting the network bandwidth for the third future step (assuming this step spans one hour) might predict that within that one hour, the probability of network bandwidth being 8 Mbps is 30%, 10 Mbps is 50%, and 12 Mbps is 20%, etc. This prediction helps to understand the uncertainties of the future network environment in advance, enabling more accurate calculation of the expected transmission resource parameters of the communication link.

[0118] Based on all predicted communication devices and their corresponding hit rates in each future step of the IoT touch screen controller, the critical value of the transmission resource parameters of each predicted communication device, and the proportion of transmission resources of the corresponding communication link under various multi-dimensional network environment state parameters, a transmission resource expectation inference network tree for each future step is constructed.

[0119] Based on the expected transmission resource inference network tree for each future step and all predicted values ​​and probability distributions of the multidimensional network environment state parameters within the execution cycle of each future step, the expected transmission resource parameters of the communication link between the IoT touchscreen controller and each predicted communication device in each future step are determined.

[0120] In this embodiment, the transmission resource expectation inference tree is a structural model used to organize and display the complex reasoning process from various basic data to the final calculation of the expected transmission resource parameters of the communication link. It is presented in a tree structure, with different branches extending upwards from the root, each branch representing a key reasoning link or data source.

[0121] To provide a clear reasoning structure for determining expected transmission resource parameters, a transmission resource expectation reasoning tree for each future step is constructed based on all predicted communication devices and their corresponding hit rates in each future step of the IoT touchscreen controller, the critical value of the transmission resource parameters for each predicted communication device, and the proportion of transmission resources of the corresponding communication link under various multi-dimensional network environment state parameters. This tree includes:

[0122] Treating each future step as a first-layer node, and all predicted communication devices of the IoT touchscreen controller in the corresponding future step as second-layer nodes, with the corresponding hit rate as the weight of the connection edge between the corresponding second-layer node and the first-layer node, and each multi-dimensional network environment state parameter as a third-layer node, the proportion of transmission resources of the communication link corresponding to each predicted communication device under the corresponding multi-dimensional network environment state parameter is used as the weight of the connection edge between the corresponding second-layer node and the corresponding third-layer node, thus obtaining the transmission resource expectation inference network tree for each future step:

[0123] Determine the first-level nodes: Treat each future step as a first-level node in the expected inference tree of the transmission resources.

[0124] Determine the second-layer nodes and their weights: For each future step (the first-layer node), all predicted communication devices of the IoT touchscreen controller in that future step are designated as second-layer nodes. Devices with a high probability of communicating with the controller in that future step are identified as predicted communication devices. For example, in the step of the third hour in the future, analysis predicts that communication with smart sensor A and smart valve B is possible. Therefore, smart sensor A and smart valve B are designated as second-layer nodes under the corresponding first-layer node of the third hour. Simultaneously, the hit rate of each predicted communication device in that future step is used as the weight of the edge connecting the corresponding second-layer node and the first-layer node. The hit rate is estimated based on factors such as the frequency of device occurrence in historical data, representing the likelihood of the device actually communicating with the controller in that future step. For example, if the hit rate of smart sensor A communicating with the controller in the third hour in the future is 0.7, then the weight of the edge connecting the first-layer node of the third hour and the second-layer node smart sensor A is 0.7.

[0125] Determine the weights of the third-layer nodes and their connections: Treat each multidimensional network environment state parameter as a third-layer node. Multidimensional network environment state parameters include network bandwidth, signal strength, latency, packet loss rate, etc., which affect the transmission resources of the communication link. For example, network bandwidth may have high, medium, and low states, and signal strength may have different numerical ranges. These different states or numerical ranges constitute different multidimensional network environment state parameter nodes. For each predicted communication device (second-layer node), the proportion of transmission resources of its corresponding communication link under the corresponding multidimensional network environment state parameter is used as the weight of the connection edge between the corresponding second-layer node and the corresponding third-layer node. This is derived through analysis of historical control records; different network environments will lead to different proportions of the communication link in the overall system transmission resources. For example, if the communication link of smart sensor A has a transmission resource proportion of 30% under high network bandwidth conditions, then the weight of the edge connecting smart sensor A (second-layer node) and the third-layer node with high network bandwidth is 0.3.

[0126] In this way, a reasoning tree for the expected transmission resources of each future step is constructed. It displays the future steps, predicted communication devices, multi-dimensional network environment state parameters, and the correlation weights between them in an intuitive tree structure.

[0127] To accurately calculate the expected transmission resource parameters, a transmission resource expectation inference network tree based on each future step and the predicted values ​​and probability distributions of multi-dimensional network environment state parameters within the execution cycle of each future step are proposed. This determines the expected transmission resource parameters of the communication link between the IoT touchscreen controller and each predicted communication device in each future step, including:

[0128] In the expected inference network tree of the transport resources in each future step, all inference networks that pass through each multidimensional network environment state parameter are identified as the inference network to which each multidimensional network environment state parameter belongs, where each inference network contains a node of each level.

[0129] Based on all predicted values ​​and probability distributions of the multidimensional network environment state parameters within the execution cycle of each future step, all multidimensional network environment state prediction parameters and corresponding hit rates for each future step are determined.

[0130] Based on the multidimensional network environment state prediction parameter and the corresponding hit rate for each future step, the hit rate of each multidimensional network environment state prediction parameter for all inference networks to which each multidimensional network environment state parameter belongs in the expected inference network tree of transmission resources is calculated.

[0131] In the expected inference network tree of transmission resources, all multidimensional network environment state parameters with a hit rate greater than the hit rate threshold are selected as high-hit-rate multidimensional network environment state parameters.

[0132] Reasoning is performed on all the reasoning networks to which all high-hit-rate multidimensional network environment state parameters belong in the expected reasoning network tree of transmission resources, to obtain the relative proportion of transmission resources and the corresponding absolute hit rate of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters.

[0133] Based on the transmission resource ratio and absolute hit rate of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the expected transmission resource parameters of the communication links between the IoT touch screen controller and each predicted communication device in each future step are determined.

[0134] In this embodiment, the expected inference network tree for transmission resources in each future step determines all inference networks that pass through each multidimensional network environment state parameter as the inference network to which each multidimensional network environment state parameter belongs, wherein each inference network contains one node at each level:

[0135] Within the constructed inference network tree for the expected transmission resources of each future step, for each multidimensional network environment state parameter (third-level node), all paths leading to that parameter node are sought. These paths originate from the first-level future step node, pass through a predicted communication device node in the second level, and ultimately reach the corresponding third-level multidimensional network environment state parameter node. Each such path constitutes an inference network, and each inference network contains one node from each of the three levels. For example, in the network tree of a certain future step, for the multidimensional network environment state parameter "high network bandwidth" (third-level node), there exists a path that originates from "future step 5" (first-level node), passes through the predicted communication device node "smart camera" (second-level node), and reaches the "high network bandwidth" node. This is an inference network belonging to the multidimensional network environment state parameter "high network bandwidth".

[0136] In this embodiment, based on all predicted values ​​and probability distributions of the multidimensional network environment state parameters within the execution cycle of each future step, all multidimensional network environment state prediction parameters and corresponding hit rates for each future step are determined:

[0137] The predicted values ​​of the multidimensional network environment state parameters within the execution cycle of each future step are arbitrarily combined according to the dimensions to obtain a combination of predicted values. This combination of predicted values ​​is a set of multidimensional network environment state prediction parameters, and the product of the probability values ​​of all predicted values ​​in this combination is the corresponding hit rate.

[0138] In this embodiment, based on each multidimensional network environment state prediction parameter and its corresponding hit rate for each future step, the hit rate of each multidimensional network environment state prediction parameter for all its respective inference networks in the expected inference network tree for each multidimensional network environment state parameter is calculated:

[0139] The product of the hit rate corresponding to each multidimensional network environment state prediction parameter in each future step and the similarity between the multidimensional network environment state prediction parameter and each multidimensional network environment state parameter in the transmission resource expected inference network tree is taken as the hit rate of the corresponding multidimensional network environment state prediction parameter to all inference networks to which each multidimensional network environment state parameter belongs in the transmission resource expected inference network tree.

[0140] In this embodiment, all multidimensional network environment state parameters with a hit rate greater than a hit rate threshold are selected from the transmission resource expectation inference network tree and used as high-hit-rate multidimensional network environment state parameters:

[0141] In the transmission resource expectation inference network tree, for each multidimensional network environment state parameter, its hit rate calculated according to the above method is compared with a hit rate threshold. If the hit rate of any multidimensional network environment state parameter is greater than the threshold, it is selected. These selected parameters are the high-hit-rate multidimensional network environment state parameters.

[0142] In this embodiment, the hit rate threshold is a manually set standard value used to determine whether the hit rate of the multi-dimensional network environment state parameters in the transmission resource expectation inference network tree is high enough. It is relatively low. For example, in scenarios where high accuracy is required for transmission resource expectations, the hit rate threshold might be set to 0.5; while in scenarios where the accuracy requirements for transmission resource expectations are relatively relaxed, the threshold could be set to 0.3.

[0143] In this embodiment, reasoning is performed on all the reasoning networks to which all high-hit-rate multidimensional network environment state parameters belong in the expected transmission resource reasoning network tree, to obtain the relative transmission resource ratio and corresponding absolute hit rate of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters:

[0144] The hit rate of all predicted communication devices in the expected inference network tree of transmission resources is taken as the corresponding absolute hit rate.

[0145] Based on the transmission resource expectation inference network tree, the transmission resource ratio of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters is determined. The sum of the products of the transmission resource ratio of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters and their respective absolute hit rates is taken as the total relative transmission resource ratio value. The ratio of the transmission resource ratio of the communication link corresponding to a single predicted communication device to the total relative transmission resource ratio value is taken as the corresponding relative transmission resource ratio.

[0146] To further accurately determine the expected transmission resource parameters of the communication links between the IoT touchscreen controller and each predictive communication device, this paper proposes a method based on the transmission resource ratio and corresponding absolute hit rate of the communication links corresponding to all predictive communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters. This method determines the expected transmission resource parameters of the communication links between the IoT touchscreen controller and each predictive communication device in each future step, including:

[0147] Based on the absolute hit rate of the transmission resource ratio of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the relative hit rate of the transmission resource ratio of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters is calculated.

[0148] In each future step, all predictive communication devices whose relative hit rate of the corresponding communication link is not lower than the preset relative hit rate threshold are considered as valid predictive communication devices for the corresponding future step.

[0149] Based on the transmission resource ratio and absolute hit rate of the communication links corresponding to all valid predictive communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the expected transmission resource parameters of the communication links between the IoT touch screen controller and each predictive communication device in each future step are determined.

[0150] In this embodiment, based on the absolute hit rate of the transmission resource ratio of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the relative hit rate of the transmission resource ratio of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters is calculated:

[0151] The relative hit rate is calculated to compare the relative absolute hit rate of transmission resource proportions of different predictive communication devices under the same high-hit-rate multidimensional network environment state parameters within the same future step. The calculation method includes: for a specific predictive communication device in a future step, dividing the absolute hit rate of its communication link under the same high-hit-rate multidimensional network environment state parameters by the sum of the absolute hit rates of all predictive communication devices under the same high-hit-rate multidimensional network environment state parameters within that future step. The result is the relative hit rate of the transmission resource proportion of that predictive communication device's communication link under these high-hit-rate multidimensional network environment state parameters.

[0152] In this embodiment, a preset relative hit rate threshold is used: this is a standard value pre-set during the system design phase to filter predicted communication devices. For example, if it is desired to focus on predicted communication devices that have a significant impact on transmission resources and a relatively high probability of occurrence in a specific network environment, the preset relative hit rate threshold may be set to 0.3.

[0153] In this embodiment, among all the predictive communication devices for each future step, the predictive communication devices whose relative hit rate for the corresponding communication link is not lower than a preset relative hit rate threshold are considered as valid predictive communication devices for the corresponding future step:

[0154] If the relative hit rate of a predictive communication device's communication link is greater than or equal to a preset relative hit rate threshold under all these high-hit-rate multidimensional network environment state parameters, then the predictive communication device is considered a valid predictive communication device for this future step. For example, if the preset relative hit rate threshold is 0.3, and in the fifth future step, predictive communication device C has a relative hit rate greater than or equal to 0.3 under all high-hit-rate multidimensional network environment state parameters such as "high network bandwidth" and "stable signal strength," while predictive communication device D has a relative hit rate of 0.25 under "high network bandwidth," which is less than the threshold, then predictive communication device C is a valid predictive communication device for the fifth future step, while predictive communication device D is not.

[0155] In this embodiment, based on the proportion of transmission resources and the corresponding absolute hit rate of the communication links corresponding to all valid predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the expected transmission resource parameters of the communication links between the IoT touch screen controller and each predicted communication device in each future step are determined:

[0156] The total transmission resource value corresponding to the standard multidimensional network environment state parameter with the highest similarity to the multidimensional network environment state prediction parameter with the highest hit rate in the multidimensional network environment state parameter-total transmission resource list library is taken as the total transmission resource value for the corresponding future step.

[0157] The ratio of the product of the transmission resource ratio and the corresponding absolute hit rate of the communication link corresponding to each effective predicted communication device in each future step under all kinds of high hit rate multidimensional network environment state parameters to the product of the transmission resource ratio and the corresponding absolute hit rate of the communication link corresponding to all effective predicted communication devices under all kinds of high hit rate multidimensional network environment state parameters is taken as the expected transmission resource ratio of the corresponding effective predicted communication device.

[0158] The product of the total transmission resource value of future steps and the expected transmission resource ratio of each effective predicted communication device is used as the expected transmission resource parameter of the communication link between the IoT touch screen controller and the corresponding predicted communication device of the corresponding future step.

[0159] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. An IoT touchscreen controller supporting multiple communication protocols, characterized in that, include: The protocol identification module is used to monitor the input data of the physical interface and uses a multi-level matching algorithm of weighted decision tree to identify the protocol of the input data and determine the current communication protocol type. The data parsing module is used to parse the input data using the protocol parsing algorithm corresponding to the current communication protocol type. At the same time, it retrieves the expected parsing state path corresponding to the current communication protocol type and generates the expected state transition matrix based on the expected parsing state path. The expected parsing state path contains the complete expected state sequence of the data packet from the start frame identification, packet header parsing, data field extraction to check code verification. When parsing the input data, the current state corresponding to each parsing operation is recorded in real time to form the current parsing state path, and a real-time state transition matrix is ​​generated based on the actual jump results of adjacent parsing state nodes in the current parsing state path. Calculate the real-time consistency between the real-time state transition matrix and the expected state transition matrix; Determine if the real-time matching degree is not less than the set matching degree threshold. If it is, determine that the current parsing state path is normal and continue parsing. Otherwise, determine that there is a state deviation and trigger the parsing anomaly handling process until the effective payload data is extracted. The data conversion module is used to convert payload data into a unified internal data format to obtain the target instruction content; The control execution module is used to execute corresponding device control operations or status feedback operations based on the target instruction content.

2. A communication method for an IoT touchscreen controller supporting multiple communication protocols, characterized in that, The IoT touchscreen controller supporting multiple communication protocols as described in claim 1 includes: Listen to the input data of the physical interface, and use a multi-level matching algorithm of weighted decision tree to identify the protocol of the input data and determine the current communication protocol type; The input data is parsed using the protocol parsing algorithm corresponding to the current communication protocol type. At the same time, the expected parsing state path corresponding to the current communication protocol type is retrieved, and the expected state transition matrix is ​​generated based on the expected parsing state path. The expected parsing state path contains the complete expected state sequence of the data packet from the start frame identification, header parsing, data field extraction to check code verification. When parsing the input data, the current state corresponding to each parsing operation is recorded in real time to form the current parsing state path, and a real-time state transition matrix is ​​generated based on the actual jump results of adjacent parsing state nodes in the current parsing state path. Calculate the real-time consistency between the real-time state transition matrix and the expected state transition matrix; Determine if the real-time matching degree is not less than the set matching degree threshold. If it is, determine that the current parsing state path is normal and continue parsing. Otherwise, determine that there is a state deviation and trigger the parsing anomaly handling process until the effective payload data is extracted. Convert the payload data into an internal data format to obtain the target instruction content; Execute the corresponding device control operation or status feedback operation based on the target instruction content.

3. The communication method for an IoT touchscreen controller supporting multiple communication protocols according to claim 2, characterized in that, A multi-level matching algorithm using weighted decision trees is employed to identify the protocol in the input data, determining the current communication protocol type, including: Extract multiple feature vectors from the first N bytes of the input data; All extracted feature vectors are input into a pre-trained weighted decision model. The comprehensive matching probability of each communication protocol type is calculated based on the output path of the weighted decision model. The protocol type with the highest probability is selected as the current communication protocol type. In this model, different branch nodes correspond to the key features of different protocols, and the node weights are dynamically updated based on the historical recognition confidence of the corresponding key features. At the same time, all link indicators in the protocol recognition process are collected in real time. If any link indicator exceeds the corresponding indicator threshold, the decision tree parameters are dynamically adjusted.

4. The communication method for an IoT touchscreen controller supporting multiple communication protocols according to claim 2, characterized in that, The payload data is converted into an internal data format to obtain the target instruction content, including: The semantic mapping rules of the payload data fields to the internal common data model are invoked to convert the specific data names and numerical types of the payload data into unified semantic identifiers and standard data types in the common data model, thereby obtaining the target instruction content.

5. The communication method for an IoT touchscreen controller supporting multiple communication protocols according to claim 2, characterized in that, Also includes: Based on the historical control records of the IoT touch screen controller, the expected transmission resource parameters of the communication link between the IoT touch screen controller and each predicted communication device in each future step are analyzed. Based on the expected transmission resource parameters and corresponding communication protocol types of the communication link between the virtual protocol stack, the IoT touch screen controller and each predictive communication device in each future step, a pre-communication link is built. When the IoT touchscreen controller receives an actual control command for any predictive communication device at any step, it executes the corresponding device control operation or status feedback operation based on the predictive communication link.

6. The communication method for an IoT touchscreen controller supporting multiple communication protocols according to claim 5, characterized in that, Based on the historical control records of the IoT touchscreen controller, the expected transmission resource parameters of the communication link between the IoT touchscreen controller and each predicted communication device for each future step are analyzed, including: The system acquires historical control records of the IoT touchscreen controller, and based on these records, it parses out the communication device and multidimensional network environment status parameters of each historical control command, as well as the actual transmission resource parameters of the corresponding communication link. It also calculates the transmission resource ratio of the corresponding communication link under the corresponding multidimensional network environment status parameters. Periodic analysis of historical control records identifies all predicted communication devices and their corresponding hit rates for the IoT touchscreen controller at each future step. It also analyzes the critical values ​​of transmission resource parameters for each predicted communication device in the historical control records and the proportion of transmission resources for the corresponding communication link under various multidimensional network environment state parameters. The multidimensional network environment state parameters of the IoT touch screen controller are predicted to obtain all predicted values ​​and probability distributions of the multidimensional network environment state parameters in the execution cycle of each future step. Based on all predicted communication devices and their corresponding hit rates in each future step of the IoT touch screen controller, the critical value of the transmission resource parameters of each predicted communication device, and the proportion of transmission resources of the corresponding communication link under various multi-dimensional network environment state parameters, a transmission resource expectation inference network tree for each future step is constructed. Based on the expected transmission resource inference network tree for each future step and all predicted values ​​and probability distributions of the multidimensional network environment state parameters within the execution cycle of each future step, the expected transmission resource parameters of the communication link between the IoT touchscreen controller and each predicted communication device in each future step are determined.

7. The communication method for an IoT touchscreen controller supporting multiple communication protocols according to claim 6, characterized in that, Based on the IoT touchscreen controller's predictions of all communication devices and their corresponding hit rates for each future step, the critical values ​​of transmission resource parameters for each prediction communication device, and the proportion of transmission resources for the corresponding communication link under various multi-dimensional network environment state parameters, a transmission resource expectation inference tree for each future step is constructed, including: Each future step is treated as a first-layer node, and all predicted communication devices of the IoT touchscreen controller in the corresponding future step are treated as second-layer nodes. The hit rate is used as the weight of the connection edge between the corresponding second-layer node and the first-layer node. Each multi-dimensional network environment state parameter is treated as a third-layer node, and the proportion of transmission resources of the communication link corresponding to each predicted communication device under the corresponding multi-dimensional network environment state parameter is used as the weight of the connection edge between the corresponding second-layer node and the corresponding third-layer node. This yields the transmission resource expectation inference network tree for each future step.

8. The communication method for an IoT touchscreen controller supporting multiple communication protocols according to claim 6, characterized in that, Based on the expected transmission resource inference network tree for each future step and all predicted values ​​and probability distributions of the multi-dimensional network environment state parameters within the execution cycle of each future step, the expected transmission resource parameters of the communication link between the IoT touchscreen controller and each predicted communication device in each future step are determined, including: In the expected inference network tree of the transport resources in each future step, all inference networks that pass through each multidimensional network environment state parameter are identified as the inference network to which each multidimensional network environment state parameter belongs, where each inference network contains a node of each level. Based on all predicted values ​​and probability distributions of the multidimensional network environment state parameters within the execution cycle of each future step, all multidimensional network environment state prediction parameters and corresponding hit rates for each future step are determined. Based on the multidimensional network environment state prediction parameter and the corresponding hit rate for each future step, the hit rate of each multidimensional network environment state prediction parameter for all inference networks to which each multidimensional network environment state parameter belongs in the expected inference network tree of transmission resources is calculated. In the expected inference network tree of transmission resources, all multidimensional network environment state parameters with a hit rate greater than the hit rate threshold are selected as high-hit-rate multidimensional network environment state parameters. Reasoning is performed on all the reasoning networks to which all high-hit-rate multidimensional network environment state parameters belong in the expected reasoning network tree of transmission resources, to obtain the relative proportion of transmission resources and the corresponding absolute hit rate of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters. Based on the transmission resource ratio and absolute hit rate of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the expected transmission resource parameters of the communication links between the IoT touch screen controller and each predicted communication device in each future step are determined.

9. The communication method for an IoT touchscreen controller supporting multiple communication protocols according to claim 8, characterized in that, Based on the transmission resource ratio and corresponding absolute hit rate of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the expected transmission resource parameters of the communication links between the IoT touchscreen controller and each predicted communication device in each future step are determined, including: Based on the absolute hit rate of the transmission resource ratio of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the relative hit rate of the transmission resource ratio of the communication links corresponding to all predicted communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters is calculated. In each future step, all predictive communication devices whose relative hit rate of the corresponding communication link is not lower than the preset relative hit rate threshold are considered as valid predictive communication devices for the corresponding future step. Based on the transmission resource ratio and absolute hit rate of the communication links corresponding to all valid predictive communication devices in each future step under the same high-hit-rate multidimensional network environment state parameters, the expected transmission resource parameters of the communication links between the IoT touch screen controller and each predictive communication device in each future step are determined.

Images