Terminal multi-dimensional parameter intelligent diagnosis method, system, electronic device and storage medium

Abstract

The embodiment of the present application provides a terminal multi-dimensional parameter intelligent diagnosis method, system, electronic device and storage medium, which belongs to the field of Internet of Things technology. The solution obtains the triplet information of the Internet of Things terminal, and the triplet information includes the terminal identification, the current time interval and the current wireless signal level; matches the configuration list of the Internet of Things terminal according to the terminal identification; based on the configuration list, adds three fields of data status, dynamic maximum value and dynamic minimum value to obtain eight-tuple diagnostic data and stores it persistently in the module; collects the current business data of the Internet of Things terminal, based on the current time interval and the current wireless signal level, updates the eight-tuple diagnostic data according to the current business data; diagnoses the fault status of the updated eight-tuple diagnostic data through the multi-dimensional parameter trend fusion algorithm to obtain the diagnosis result. The present application can improve the timeliness and accuracy of diagnosis and reduce the overall power consumption of the terminal.

Description

Technical Field

[0001] The present application relates to the field of Internet of Things technology, and in particular to a terminal multi-dimensional parameter intelligent diagnosis method, system, electronic device and storage medium. Background Art

[0002] When IoT terminals process services in wireless communication networks, they often experience failures due to various reasons. These failures require rapid diagnosis and troubleshooting of these factors. Currently, most IoT terminals rely on a single or limited amount of sensor parameter data, which fails to fully reflect device status and inter-logical relationships. Furthermore, the diagnostic functions in related technologies are simplistic and rigid, resulting in low accuracy and efficiency in terminal diagnosis. Furthermore, most use general-purpose processors with complex instruction set architectures, resulting in low energy efficiency and increased maintenance costs. Summary of the Invention

[0003] The main purpose of the embodiments of the present application is to propose a terminal multi-dimensional parameter intelligent diagnosis method, system, electronic device and storage medium, aiming to improve the timeliness and accuracy of diagnosis and reduce the overall power consumption of the terminal.

[0004] To achieve the above objectives, one aspect of an embodiment of the present application provides a method for intelligent diagnosis of multi-dimensional parameters of a terminal, the method comprising:

[0005] Obtaining triplet information of the IoT terminal, the triplet information including the terminal identifier, the current time interval, and the current wireless signal level;

[0006] Matching a configuration list of the IoT terminal according to the terminal identifier, wherein the configuration list includes multidimensional parameters and threshold boundaries, the multidimensional parameters include a reference time interval, a reference wireless signal level, and a parameter name of reference service data, and the threshold boundaries include a maximum boundary threshold and a minimum boundary threshold of the reference service data;

[0007] Based on the configuration list, three fields, namely data status, dynamic maximum value and dynamic minimum value, are added to obtain eight-tuple diagnostic data and store it persistently in the module;

[0008] Collecting current service data of the IoT terminal, and updating the octet diagnostic data according to the current service data based on the current time interval and the current wireless signal level;

[0009] The updated octet diagnostic data is diagnosed for a fault state using a multi-dimensional parameter trend fusion algorithm to obtain a diagnostic result, wherein the multi-dimensional parameter trend fusion algorithm is obtained through extended instructions based on a reduced instruction set architecture and is preset in the module.

[0010] In some embodiments, the step of adding three fields, data status, dynamic maximum value, and dynamic minimum value, based on the configuration list to obtain eight-tuple diagnostic data and persistently storing it in the module includes the following steps:

[0011] Parsing the configuration list to obtain five-tuple diagnostic data corresponding to each reference service data, the five-tuple diagnostic data including the reference time interval, the reference wireless signal level, the parameter name, the maximum boundary threshold, and the minimum boundary threshold;

[0012] Initialize the fields of data status, dynamic maximum value and dynamic minimum value;

[0013] According to the initialized data state, the dynamic maximum value and the dynamic minimum value, the five-tuple diagnostic data is spliced to obtain eight-tuple diagnostic data and persistently stored in the module.

[0014] In some embodiments, the updating of the octet diagnostic data based on the current service data based on the current time interval and the current wireless signal level comprises the following steps:

[0015] Matching the octet diagnostic data according to the current time interval, the current wireless signal level, and the parameter name of the current service data;

[0016] determining an update strategy according to the data status in the octet diagnostic data;

[0017] Based on the update strategy, the dynamic maximum value and the dynamic minimum value are updated according to the current business data.

[0018] In some embodiments, performing fault status diagnosis on the updated octet diagnostic data using a multi-dimensional parameter trend fusion algorithm to obtain a diagnostic result includes the following steps:

[0019] Perform threshold fault diagnosis on the updated dynamic maximum value and the dynamic minimum value according to the maximum boundary threshold and the minimum boundary threshold, determine whether there is an over-threshold fault, and obtain a threshold result;

[0020] When the threshold result indicates that an over-threshold fault exists, determining that the diagnosis result is an over-threshold fault alarm state;

[0021] Alternatively, when the threshold result indicates that there is no over-threshold fault, a trend prediction is performed based on the current service data and the updated dynamic maximum value and the updated dynamic minimum value to obtain a prediction result, the prediction result including a trend balance value, a trend maximum value, and a trend minimum value;

[0022] Perform risk diagnosis on the prediction result according to the highest boundary threshold and the lowest boundary threshold to determine whether there is potential risk and obtain a risk result;

[0023] When the risk result is that there is a potential risk, the diagnosis result is determined to be in a potential risk trend state; otherwise, the diagnosis result is determined to be in a stable fault-free trend state.

[0024] In some embodiments, performing trend prediction based on the current business data and the updated dynamic maximum value and the updated dynamic minimum value to obtain a prediction result includes the following steps:

[0025] Based on the preset calculation weights, a weighted calculation is performed according to the current business data and the updated dynamic maximum value and the updated dynamic minimum value to obtain a trend balance value;

[0026] Fluctuation quantification processing is performed based on the trend balance value and the updated dynamic minimum value to obtain the trend maximum value and the trend minimum value.

[0027] In some embodiments, performing risk diagnosis on the prediction result based on the highest boundary threshold and the lowest boundary threshold to determine whether there is a potential risk and obtain a risk result includes the following steps:

[0028] Performing an upper limit safety diagnosis on the trend maximum value according to the maximum boundary threshold to obtain an upper limit result;

[0029] Performing a lower limit safety diagnosis on the trend minimum value according to the lowest boundary threshold to obtain a lower limit result;

[0030] Perform risk diagnosis based on the upper limit result and the lower limit result to determine whether there is a potential risk and obtain a risk result;

[0031] The risk diagnosis is performed based on the upper limit result and the lower limit result to determine whether there is a potential risk, and the risk result is obtained, including:

[0032] When the upper limit result is that the highest value of the trend is greater than the highest boundary threshold or the lower limit result is that the lowest value of the trend is less than the lowest boundary threshold, the risk result is determined to be that there is a potential risk;

[0033] Alternatively, when the upper limit result is that the highest value of the trend is less than the highest boundary threshold and the lower limit result is that the lowest value of the trend is greater than the lowest boundary threshold, it is determined that the risk result is that there is no potential risk.

[0034] In some embodiments, the terminal multi-dimensional parameter intelligent diagnosis method further includes the following steps:

[0035] When the diagnosis result is the over-threshold fault alarm state or the potential risk trend state, sending an alarm message;

[0036] Execute troubleshooting operations according to the alarm information;

[0037] After completing the troubleshooting operation, an update instruction is sent to the module to update the data state in the octet diagnostic data to an initial state.

[0038] To achieve the above objectives, another aspect of the present application provides a terminal multi-dimensional parameter intelligent diagnosis system, the system comprising:

[0039] The first module is used to obtain triplet information of the IoT terminal, where the triplet information includes the terminal identifier, the current time interval, and the current wireless signal level;

[0040] A second module is configured to match a configuration list of the IoT terminal according to the terminal identifier, wherein the configuration list includes multidimensional parameters and threshold boundaries, the multidimensional parameters include a reference time interval, a reference wireless signal level, and a parameter name of reference service data, and the threshold boundaries include a maximum boundary threshold and a minimum boundary threshold of the reference service data;

[0041] The third module is used to add three fields, namely, data status, dynamic maximum value, and dynamic minimum value, based on the configuration list, to obtain eight-tuple diagnostic data and store it persistently in the module;

[0042] A fourth module is configured to collect current service data of the IoT terminal, and update the octet diagnostic data according to the current service data based on the current time interval and the current wireless signal level;

[0043] The fifth module performs fault status diagnosis on the updated octet diagnostic data through a multi-dimensional parameter trend fusion algorithm to obtain a diagnostic result, wherein the multi-dimensional parameter trend fusion algorithm is obtained through extended instructions based on a reduced instruction set architecture and is preset in the module.

[0044] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned method when executing the computer program.

[0045] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above-mentioned method when executed by a processor.

[0046] The embodiments of the present application include at least the following beneficial effects: The present application provides a terminal multi-dimensional parameter intelligent diagnosis method, system, electronic device and storage medium. The solution obtains triplet information of the IoT terminal, the triplet information including the terminal identification, the current time interval and the current wireless signal level; matches the configuration list of the IoT terminal according to the terminal identification; based on the configuration list, adds three fields, data status, dynamic maximum value and dynamic minimum value, to obtain eight-tuple diagnostic data and stores it persistently in the module; collects the current business data of the IoT terminal, and based on the current time interval and the current wireless signal level, updates the eight-tuple diagnostic data according to the current business data; performs fault status diagnosis on the updated eight-tuple diagnostic data through a multi-dimensional parameter trend fusion algorithm to obtain a diagnostic result. The present application can improve the timeliness and accuracy of diagnosis and reduce the overall power consumption of the terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flow chart of the terminal multi-dimensional parameter intelligent diagnosis method provided by an embodiment of the present application;

[0048] Figure 2 This embodiment of the present application provides Figure 1 Specific method step flow chart of step S103;

[0049] Figure 3 This embodiment of the present application provides Figure 1 Specific method step flow chart of step S104;

[0050] Figure 4 This embodiment of the present application provides Figure 1 Specific method step flow chart of step S105;

[0051] Figure 5 This embodiment of the present application provides Figure 4 Specific method step flow chart of step S403;

[0052] Figure 6 This embodiment of the present application provides Figure 4 Specific method step flow chart of step S404;

[0053] Figure 7 This is a flowchart of steps S701 to S703 in the terminal multi-dimensional parameter intelligent diagnostic method provided in an embodiment of the present application;

[0054] Figure 8 This is a flow chart of a terminal multi-dimensional parameter intelligent diagnosis method provided by another embodiment of the present application;

[0055] Figure 9 This is a schematic diagram of the structure of the terminal multi-dimensional parameter intelligent diagnosis system provided in an embodiment of the present application;

[0056] Figure 10 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are merely examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0058] It will be understood that the terms "first", "second", etc. used in this application may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0059] The terms "at least one", "plurality", "each", "any", etc. used in this application include "at least one", "two" or more, "plurality" or "each", "any" or "any one", "each" or "any one" as used herein.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0061] Before describing the embodiments of the present application in detail, some related technologies involved in the embodiments of the present application are first described.

[0062] Current mainstream IoT terminal fault diagnosis solutions only monitor single parameters through sensors, ignoring the correlations between multi-dimensional parameters. This makes it difficult to fully reflect device status and their logical relationships. Furthermore, these solutions typically directly compare sensor data against preset fixed thresholds, resulting in simple, rigid diagnostic functionality without multi-dimensional parameter adaptation or fault trend prediction capabilities. Furthermore, related technical solutions often utilize a complex instruction set (CISC) architecture. This increasingly complex instruction set is not only difficult to implement but also degrades terminal performance. This inherent structural complexity increases design time and cost while also leading to design errors and compromising fault diagnosis accuracy. Therefore, a low-power, intelligent terminal diagnosis method that integrates adaptive multi-dimensional parameters is needed to improve terminal diagnostic accuracy and efficiency while reducing operational and maintenance costs.

[0063] In view of this, the embodiments of the present application provide a terminal multi-dimensional parameter intelligent diagnosis method, system, electronic device and storage medium. The solution obtains the triplet information of the Internet of Things terminal, and the triplet information includes the terminal identification, the current time interval and the current wireless signal level; matches the configuration list of the Internet of Things terminal according to the terminal identification; based on the configuration list, adds three fields of data status, dynamic maximum value and dynamic minimum value to obtain eight-tuple diagnostic data and stores it persistently in the module; collects the current business data of the Internet of Things terminal, and based on the current time interval and the current wireless signal level, updates the eight-tuple diagnostic data according to the current business data; performs fault status diagnosis on the updated eight-tuple diagnostic data through a multi-dimensional parameter trend fusion algorithm to obtain a diagnostic result. The present application can improve the timeliness and accuracy of diagnosis and reduce the overall power consumption of the terminal.

[0064] The terminal multi-dimensional parameter intelligent diagnosis method provided in the embodiment of the present application relates to the field of Internet of Things technology. The terminal multi-dimensional parameter intelligent diagnosis method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server, and can also be software running in the terminal or the server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in the blockchain network; the software can be an application that implements the terminal multi-dimensional parameter intelligent diagnosis method, etc., but is not limited to the above forms.

[0065] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0066] Figure 1 This is an optional flowchart of the terminal multi-dimensional parameter intelligent diagnosis method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S105.

[0067] Step S101: Acquire triplet information of an IoT terminal, where the triplet information includes a terminal identifier, a current time interval, and a current wireless signal level.

[0068] Step S102: Match the configuration list of the IoT terminal according to the terminal identifier, wherein the configuration list includes multidimensional parameters and threshold boundaries. The multidimensional parameters include a reference time interval, a reference wireless signal level, and a parameter name of the reference service data. The threshold boundaries include the highest boundary threshold and the lowest boundary threshold of the reference service data.

[0069] Step S103: Based on the configuration list, three fields, namely, data status, dynamic maximum value, and dynamic minimum value, are added to obtain eight-tuple diagnostic data and store them persistently in the module.

[0070] Step S104 , collecting current service data of the IoT terminal, and updating the octet diagnostic data according to the current service data based on the current time interval and the current wireless signal level.

[0071] Step S105 , performing fault status diagnosis on the updated octet diagnostic data through a multi-dimensional parameter trend fusion algorithm to obtain a diagnostic result, wherein the multi-dimensional parameter trend fusion algorithm is obtained through extended instructions based on a reduced instruction set architecture and is preset in the module.

[0072] In this embodiment, the IoT terminal collects triplet information, which includes the terminal identification ID (including the terminal product model, manufacturer identification information, etc.), the current wireless signal level, and the current time interval, and reports it to the platform through the module connection network.

[0073] Specifically, IoT terminals produced by different product models or manufacturers have different requirements for working environments and business needs. For example, the operating temperature threshold of the terminal of model A is 10°C higher than that of model B. To improve the accuracy of diagnosis, the terminal identification ID is used to match the pre-stored configuration of the terminal. At the same time, considering that the terminal's requirements for working environment and business also change dynamically with time (such as day and night / season / date) and network status (such as wireless signal level), this application further obtains the current time interval and the current wireless signal level to form triplet information, so as to accurately screen the threshold rules with the minimum granularity in the subsequent process and avoid sending redundant information. In addition, triplet information is lightweight data. Compared with uploading original business data (such as continuously transmitting temperature curves), it can reduce redundant data transmission and reduce power consumption. Using triplet information for communication can effectively improve energy efficiency.

[0074] After receiving the triplet information reported by the terminal, the platform matches the multi-dimensional parameter and threshold configuration list of the corresponding IoT terminal according to the terminal identification ID.

[0075] It is understood that the platform stores configuration lists corresponding to different terminal types. Each terminal type's configuration list includes reference time intervals representing different time intervals, reference wireless signal levels representing different wireless signal levels, user-defined parameter names for reference service data fields (such as temperature and battery level), and the maximum and minimum fault boundary thresholds (such as the maximum temperature and the minimum remaining battery level) set by the user for the reference service data field values. The configuration list corresponding to the current terminal ID is matched among multiple configuration lists using the terminal ID and delivered to the terminal.

[0076] After receiving the configuration list, the terminal adds three fields after the configuration list: data status, dynamic maximum value, and dynamic minimum value. These fields are combined into an eight-tuple of diagnostic data (reference time interval, reference wireless signal level, parameter name, maximum boundary threshold, minimum boundary threshold, data status, dynamic maximum value, and dynamic minimum value), and then persistently stored in the module.

[0077] It should be noted that the data status is used to identify the stages of the diagnostic process. For example, 0 is the initial state, indicating that the terminal has just received the configuration list and has not started fault diagnosis, and needs to wait for the first data collection. 1 is the diagnostic monitoring state, indicating that fault diagnosis has started and the terminal has recorded real-time data; the dynamic maximum value is used to record the peak value of the parameter during the fault monitoring period in real time; the dynamic minimum value is used to record the valley value of the parameter during the fault monitoring period in real time.

[0078] Next, the IoT terminal starts to collect current business data, associates the current business data with the current time interval and the current wireless signal level, adaptively matches the octet diagnostic data with the same time interval, current wireless signal level and parameter name as the current time interval from the stored octet diagnostic data set, uses the current business data to update the dynamic maximum value and / or dynamic minimum value in the matched octet diagnostic data, and overwrites the old octet diagnostic data with the updated octet diagnostic data, and stores it persistently in the module.

[0079] Finally, the module performs fault status diagnosis using a multi-dimensional parameter trend fusion algorithm. The multi-dimensional parameter trend fusion algorithm is obtained by extending instructions based on the reduced instruction set (RISC) architecture. The reduced instruction set only contains a small number of frequently used instructions and provides some necessary instructions to support operating systems and high-level languages. Among them, the fifth-generation reduced instruction set (RISC-V) can freely view, use, and modify the design of the instruction set. Developers can freely match and expand the instruction set that best suits the project according to actual needs. This embodiment implements the multi-dimensional parameter trend fusion algorithm by expanding the definition of several source data groups and operation calculation logic based on the RISC-V architecture. It is completed by a hardware and software integrated execution unit and is pre-installed in the chip for use by the module integrating this chip.

[0080] Specifically, after completing the update of the octet diagnostic data, the module first compares the collected current business data with the highest boundary threshold and the lowest boundary threshold stored in the octet diagnostic data. If the current business data is within the threshold range, the trend analysis phase is further carried out to determine whether there is a potential risk based on the trend. If the analysis shows that the parameter does not immediately exceed the threshold but shows a trend of change that may cause a fault, then there is a potential risk in the terminal. Finally, based on the threshold comparison and trend analysis, the terminal status is classified to obtain a diagnostic result that characterizes the terminal status, so that the platform can process the terminal according to the diagnostic result.

[0081] The embodiments of the present application improve the original method of diagnosing faults using a single or simple parameter on a high-energy-consuming chip into a low-power RISC-V proprietary instruction for a hardware-software integrated execution unit. This method can timely calculate fault trend data values, greatly improving the timeliness of diagnosis and reducing the overall power consumption of the terminal. At the same time, by persistently storing octet diagnostic data in the terminal module and adaptively matching the data collected by the terminal to the octet diagnostic data, and using an intelligent diagnostic trend calculation algorithm to predict the potential risk status of terminal faults, it can also predict possible faults in advance, greatly improving the accuracy of terminal fault diagnosis and the efficiency of terminal operation and fault handling.

[0082] Reference Figure 2In some embodiments, step S103 may include but is not limited to steps S201 to S203.

[0083] Step S201 , the configuration list is parsed to obtain five-tuple diagnostic data corresponding to each reference service data, where the five-tuple diagnostic data includes a reference time interval, a reference wireless signal level, a parameter name, a maximum boundary threshold, and a minimum boundary threshold.

[0084] Step S202 , initializing the fields of data status, dynamic maximum value, and dynamic minimum value.

[0085] Step S203 , according to the initialized data state, the dynamic maximum value and the dynamic minimum value, the five-tuple diagnostic data is spliced to obtain eight-tuple diagnostic data and persistently stored in the module.

[0086] In this embodiment, the terminal module first parses the configuration list issued by the platform and generates independent five-tuple diagnostic data for each parameter of the reference service data, including the reference time interval, reference wireless signal level, parameter name, maximum boundary threshold and minimum boundary threshold.

[0087] It should be noted that a five-tuple diagnostic data is structured data of a terminal for a certain reference business data in a specific scenario, which represents the monitoring specifications of the terminal in a specific operating environment. The reference time interval represents the specific time period division to which the threshold of this group of parameters is applicable; the reference wireless signal level can be quantified by level, for example, 1-3 levels represent good, general, and poor respectively; the parameter name is used to identify the data type of the reference business data; the highest boundary threshold and the lowest boundary threshold jointly define the safe operating range of the reference business data in a specific scenario.

[0088] Exemplarily, the terminal module reads each record in the configuration list, establishes a data index based on the parameter name field in the record, and then extracts the reference time interval, reference wireless signal level, maximum boundary threshold and minimum boundary threshold fields in the record to form a complete five-tuple diagnostic data.

[0089] It is understood that a terminal can simultaneously maintain multiple five-tuple diagnostic data sets. The five-tuple diagnostic data sets corresponding to service data with different time intervals, different wireless reference signal levels, or different parameter names are different. For example, for temperature, [1,1,Temperature,60,10] can exist simultaneously: it represents the temperature threshold range on the first day of each month when the wireless signal is good, while [1,3,Temperature,50,10] represents the temperature threshold range on the first day of each month when the wireless signal is poor.

[0090] Through a multi-dimensional threshold management mechanism, it can dynamically adapt to changes in the terminal operating environment, avoiding misdiagnosis caused by fixed threshold judgments. At the same time, it provides differentiated monitoring standards for different business scenarios. Through this structured design, flexible diagnosis configuration and high-quality matching are achieved, providing an accurate judgment basis for subsequent real-time diagnostic analysis.

[0091] Furthermore, considering that the five-tuple diagnostic data only contains static threshold rules, it is impossible to distinguish whether monitoring diagnosis has started, and in order to achieve potential risk prediction, three dynamic fields, namely data status, dynamic maximum value and dynamic minimum value, are added and each field is initialized.

[0092] The data status field is used to identify the diagnosis stage. In the initialization stage, 0 is used to identify the initial state of the data status, that is, the monitoring parameter has not yet started data collection and diagnosis. When the terminal collects data for this parameter for the first time, the data status is updated to 1, that is, it enters the diagnostic monitoring state.

[0093] The Dynamic High and Dynamic Low fields are used to record historical data to support trend analysis. By continuously updating these fields to record parameter changes during the monitoring process, they provide input for trend calculations and predict potential risks. During the initialization phase, the Dynamic High and Dynamic Value fields can be initialized to 0 or invalid values. After valid data is first collected, these two fields are updated and the historical extreme values of the parameter are continuously recorded during the subsequent monitoring cycle.

[0094] The terminal module concatenates the three initialized dynamic fields with the five-tuple diagnostic data to form a complete eight-tuple diagnostic data.

[0095] For example, the five-tuple diagnostic data [1,1,Temperature,60,10] is concatenated with the initialized field to obtain the eight-tuple diagnostic data [1,1,Temperature,60,10,0,0,0].

[0096] The generated octet diagnostic data is written to the terminal module to ensure that the historical monitoring status is retained after the terminal device is restarted or disconnected from the network.

[0097] Reference Figure 3 In some embodiments, step S104 may include but is not limited to steps S301 to S303.

[0098] Step S301 : Matching octet diagnostic data according to the current time interval, the current wireless signal level and the parameter name of the current service data.

[0099] Step S302: determining an update strategy according to the data status in the octet diagnostic data.

[0100] Step S303: Based on the update strategy, the dynamic maximum value and the dynamic minimum value are updated according to the current business data.

[0101] In this embodiment, the terminal performs a matching operation based on the collected current business data, and constructs a data matching retrieval condition by obtaining key parameters of the current business environment, such as the current time interval, the current wireless signal level, and the parameter name of the current business data. Based on the retrieval condition, the target data is searched in the set of eight-tuple diagnostic data stored in the module, and a precise matching mechanism is used to ensure that the diagnostic rules are adapted to the current business environment. The target data is a reference time interval that matches the current time interval, a reference wireless signal level that is consistent with the current wireless signal level, and eight-tuple diagnostic data with the same parameter name.

[0102] Parse the data status field in the matched octet diagnostic data and check the value of the data status field. When the data status field shows 0, that is, the initial state, change the state to the diagnostic monitoring state, and determine the update strategy to store the data value of the current business data into the dynamic maximum value and the dynamic minimum value at the same time. Based on the update strategy, update the dynamic maximum value and the dynamic minimum value according to the current business data.

[0103] When the data status field displays 1, which is the diagnostic monitoring state, it indicates that the business parameter has entered the normal monitoring process, and the dynamic maximum value and dynamic minimum value have been stored in the collected data. A judgment mechanism is used to distinguish the fields to be updated, and based on the update strategy, the dynamic maximum value or dynamic minimum value is updated according to the current business data.

[0104] Specifically, if the data value of the current business data is greater than the dynamic maximum value of the octet diagnostic data storage, the update strategy is determined to be to change the dynamic maximum value to the data value of the current business data. If the data value of the current business data is less than the dynamic minimum value of the octet diagnostic data storage, the update strategy is determined to be to change the dynamic minimum value to the data value of the current business data.

[0105] Reference Figure 4 In some embodiments, step S105 may include but is not limited to steps S401 to S405.

[0106] Step S401 , performing threshold fault diagnosis on the updated dynamic maximum value and dynamic minimum value according to the highest boundary threshold and the lowest boundary threshold, determining whether an over-threshold fault exists, and obtaining a threshold result.

[0107] Step S402: When the threshold result indicates that an over-threshold fault exists, the diagnosis result is determined to be an over-threshold fault alarm state.

[0108] Step S403: When the threshold result indicates that there is no over-threshold fault, a trend prediction is performed based on the current business data and the updated dynamic maximum value and dynamic minimum value to obtain a prediction result, which includes a trend balance value, a trend maximum value, and a trend minimum value.

[0109] Step S404: perform risk diagnosis on the prediction result according to the highest boundary threshold and the lowest boundary threshold to determine whether there is a potential risk and obtain a risk result.

[0110] Step S405: When the risk result indicates that there is a potential risk, the diagnosis result is determined to be a potential risk trend state; otherwise, the diagnosis result is determined to be a stable fault-free trend state.

[0111] In this embodiment, the threshold fault diagnosis compares the updated dynamic maximum value and dynamic minimum value according to the highest boundary threshold and the lowest boundary threshold respectively through parallel detection, determines whether the dynamic maximum value is greater than the highest boundary threshold and determines whether the dynamic minimum value is lower than the lowest boundary threshold, and obtains the threshold result.

[0112] When the threshold result of step S401 is an over-threshold fault, it means that any at least one extreme value exceeds the corresponding boundary threshold range. At this time, jump to step S402 and determine the diagnosis result as an over-threshold fault alarm state. The first line of defense for fault diagnosis is formed by direct threshold comparison, and obvious parameter abnormalities are quickly identified.

[0113] If the threshold result of step S401 indicates that there are no faults exceeding the threshold, the process jumps to step S403. Considering that static diagnosis alone can only diagnose faults after they occur, if the data gradually approaches the threshold, potential risks cannot be detected in advance, it is necessary to further perform trend prediction based on the current business data and the updated dynamic maximum and minimum values. By quantifying the trend of data fluctuations, more intelligent fault diagnosis can be achieved.

[0114] Specifically, a dedicated multi-dimensional parameter trend fusion algorithm pre-installed in the RISC-V chip is called upon to calculate a trend balance value, representing the overall distribution trend of the parameters, through weighted average calculation. Using this trend balance value as a benchmark, the algorithm then expands upward and downward based on the quantified fluctuation range to further derive predictive trend maximum and trend minimum values. These trend minimum and trend maximum values can reflect the possible fluctuation range of current business data over a period of time, providing a basis for forward-looking risk assessment.

[0115] Perform risk diagnosis on the prediction results based on the highest boundary threshold and the lowest boundary threshold to determine whether there is potential risk.

[0116] If the data fluctuation range is too large, even if the current business data is still within the threshold range, but the fluctuation exceeds the threshold limit, it will be judged that there is a potential risk. This design enables the terminal to detect abnormal parameter change trends in advance and determine the risk result as a potential risk trend state.

[0117] If the data fluctuation range is within a small interval, it indicates that the terminal is in normal operation, the parameters are running within a safe and stable range, there is no potential risk, and the risk result is determined to be a stable and fault-free trend state.

[0118] Reference Figure 5 In some embodiments, step S403 may include but is not limited to steps S501 to S502.

[0119] Step S501 , based on preset calculation weights, weighted calculation is performed according to current business data and updated dynamic maximum value and dynamic minimum value to obtain a trend balance value.

[0120] Step S502 : performing fluctuation quantification processing according to the trend balance value and the updated dynamic minimum value to obtain the trend maximum value and the trend minimum value.

[0121] Specifically, the RISC-V-based dedicated multi-dimensional parameter trend fusion algorithm customizes the following instruction functions within the chip:

[0122] Tydiag SH, SHW, SL, SLW, SC, SCW, DB, DH, DL.

[0123] Among them, Tydiag is a custom operation code, SH, SHW, SL, SLW, SC, and SCW are source data groups, SH represents the dynamic highest value, SHW represents the calculation weight of SH, SL represents the dynamic lowest value, SLW represents the calculation weight of SL, SC represents the current business data, and SCW represents the calculation weight of SC; DH, DL, and DB are the target trend data groups output after executing the trend prediction operation, DB represents the trend balance value, DH represents the trend highest value, and DL represents the trend lowest value.

[0124] Multiply the current business data and the updated dynamic maximum and minimum values by their corresponding calculation weights respectively. Add the three weighted values and divide them by the sum of the calculation weights to complete the weighted calculation. The weighted formula is as follows:

[0125] DB=(SH*SHW+SL*SLW+SC*SCW) / (SHW+SLW+SCW)(1).

[0126] It is understandable that the calculation weights can be dynamically adjusted according to the actual application scenario. In this embodiment, the default weight is 1 standard deviation.

[0127] By weighted calculation, the dynamic maximum and minimum values recorded in the historical data are balanced with the impact of the current business data on trend analysis. Not only the long-term change trend of the parameters is considered, but also the latest data fluctuations are taken into account to obtain the trend balance value.

[0128] Next, the trend balance value obtained in step S501 is used to quantify the fluctuation range.

[0129] For example, by subtracting the trend average from the updated dynamic minimum value, a benchmark difference value representing the data fluctuation amplitude is obtained. The benchmark difference value is then added to and subtracted from the trend balance value to obtain the predicted trend maximum value and trend minimum value. The calculation formula is as follows:

[0130] DH=DB+(DB-SL) (2);

[0131] DL=DB-(DB-SL) (3);

[0132] The highest trend value DH represents the upper limit that the current business data may reach while maintaining the current change trend, and the lowest trend value DL represents the lower limit that the current business data may reach while maintaining the current change trend.

[0133] After completing the trend prediction, the highest and lowest trend values will be temporarily stored to provide data support for subsequent risk diagnosis.

[0134] Reference Figure 6 In some embodiments, step S404 may include but is not limited to steps S601 to S603.

[0135] Step S601 , performing an upper limit safety diagnosis on the trend maximum value according to the highest boundary threshold to obtain an upper limit result.

[0136] Step S602: Perform a lower limit safety diagnosis on the trend minimum value according to the lowest boundary threshold to obtain a lower limit result.

[0137] Step S603: Perform risk diagnosis based on the upper limit result and the lower limit result to determine whether there is a potential risk and obtain a risk result.

[0138] In this embodiment, first, the trend maximum value obtained in step S502 is compared with the highest boundary threshold in the octet diagnostic data to determine whether the predicted upper limit of the parameter fluctuation in the future period may exceed the safety boundary and obtain the upper limit result.

[0139] At the same time, the trend minimum value obtained in step S502 is compared with the lowest boundary threshold in the octet diagnostic data in parallel to determine whether the predicted fluctuation lower limit of the parameter in the future period may exceed the safety boundary and obtain the lower limit result.

[0140] In step S603 of some embodiments, when the upper limit result is that the highest value of the trend is greater than the highest boundary threshold or the lower limit result is that the lowest value of the trend is less than the lowest boundary threshold, this indicates that although the parameters of the current business data are still within the safe range, their changing trend has shown risk characteristics that may exceed the safety boundary in the future.

[0141] It is understandable that the diagnostic analysis of the current business data of the same monitoring does not require that the maximum trend value and the minimum trend value exceed the safety boundary at the same time. As long as any one of the conditions is met, it can be determined that there is a potential risk. This is because a unilateral deviation of the parameter upward or downward may constitute an independent safety hazard. For example, a continuous increase in temperature may cause the terminal equipment to overheat, while a continuous decrease in voltage may cause an undervoltage fault. Therefore, parallel judgment is adopted and double detection is performed synchronously. As long as any one condition is triggered, the risk result can be determined to be a potential risk.

[0142] In step S603 of other embodiments, when the upper limit result is that the highest trend value is less than the highest boundary threshold and the lower limit result is that the lowest trend value is greater than the lowest boundary threshold, it indicates that even after fluctuations occur, the highest trend value is still less than the highest boundary threshold and the lowest trend value is still greater than the lowest boundary threshold, and the parameters will maintain stable operation in the future period, then the risk result is determined to be that there is no potential risk.

[0143] Reference Figure 7 In some embodiments, the terminal multi-dimensional parameter intelligent diagnosis method may also include but is not limited to steps S701 to S703.

[0144] Step S701: When the diagnosis result is an over-threshold fault alarm state or a potential risk trend state, an alarm message is sent.

[0145] Step S702: perform troubleshooting operations based on the alarm information.

[0146] Step S703: After the troubleshooting operation is completed, an update instruction is sent to the module to update the data status in the octet diagnostic data to the initial state.

[0147] In this embodiment, the terminal sends an alarm message according to the diagnosis result when the fault alarm state or the potential risk trend state exceeds the threshold.

[0148] Specifically, when the diagnosis result is an over-threshold fault alarm state, the eight-tuple diagnostic data corresponding to the diagnosis result is sent to the terminal or platform as alarm information.

[0149] When the diagnosis result is a potential risk trend state, the eight-tuple diagnostic data, the highest trend value or the lowest trend value corresponding to the diagnosis result is sent to the terminal or platform as an alarm signal.

[0150] After receiving the alarm signal, the terminal will invoke the preset fault resolution strategy for routine faults that can be repaired by itself and autonomously perform the fault resolution operation according to the strategy. For complex faults that require manual intervention, the alarm signal is pushed to the operation and maintenance personnel through the platform so that the operation and maintenance personnel can quickly locate the fault based on the alarm information.

[0151] After the fault is processed, an update instruction is sent to the module to update the data state of the octet diagnostic data in the module to the initial state, and at the same time clear the dynamic maximum value and dynamic minimum value in the octet diagnostic data. This state reset mechanism provides an initial environment for the new monitoring cycle, ensuring that subsequent diagnosis will not be interfered with by historical fault data.

[0152] The following describes and explains the solution of the embodiment of the present invention in detail with reference to specific application examples.

[0153] The terminal multi-dimensional parameter intelligent diagnosis method provided in the embodiment of the present application can be applied to the intelligent fault diagnosis of IoT terminals. Based on the present application, the terminal fault diagnosis strategy is optimized, the overall accuracy and timeliness of terminal fault diagnosis are improved, and the terminal power consumption and terminal maintenance costs are reduced.

[0154] At the same time, the network core network or platform is used to place fault diagnosis trend calculations on the terminal module side, which intelligently diagnoses risk trends, improves network and platform performance and operational efficiency, and reduces cloud platform diagnostic pressure and operation and maintenance costs.

[0155] Reference Figure 8 , Figure 8 This is a flowchart of a terminal multi-dimensional parameter intelligent diagnosis method provided by another embodiment of the present application.

[0156] In this embodiment, by proposing a customized RISC-V proprietary multi-dimensional parameter trend fusion instruction, a method for the terminal module to form eight-tuple diagnostic data and adaptively match the eight-tuple diagnostic data, a calculation algorithm for the terminal module intelligent diagnosis calculation trend data, defining the terminal triplet identification information and eight-tuple diagnostic data, and the diagnostic trend analysis data, a terminal multi-dimensional parameter intelligent diagnosis method is implemented, which can timely alarm threshold faults and provide potential risk trend analysis, not only reducing the overall terminal power consumption and improving the alarm response time, but also greatly improving the diagnostic accuracy and efficiency, and reducing operation and maintenance costs.

[0157] This embodiment also provides a diagnostic system, including a proprietary multi-dimensional parameter trend fusion instruction module, a terminal information collection and reporting module, a platform data receiving module, a multi-dimensional parameter and threshold matching module, a sending module, a receiving configuration list module, a persistent eight-tuple diagnostic data module, an intelligent diagnostic calculation module, a fault handling module, and an update data module.

[0158] Specifically, the proprietary multi-dimensional parameter trend fusion instruction module is used to customize RISC-V-based proprietary multi-dimensional parameter trend fusion instructions. Based on the RISC-V architecture, the instructions are expanded through custom opcodes SH, SHW, SL, SLW, SC, SCW, DB, DH, and DL. At the same time, the operation calculation logic is defined as: DB=(SH*SHW+SL*SLW+SC*SCW) / (SHW+SLW+SCW), DH=DB+(DB-SL), DL=DB-(DB-SL), and pre-installed in the module's RISC-V chip.

[0159] The terminal information collection and reporting module is used to collect terminal triplet information (terminal identification ID (including terminal product model / manufacturer identification information), current wireless signal level, current time interval) and report it to the platform through the module.

[0160] The platform data receiving module is used to receive terminal identification information; the multidimensional parameter and threshold matching module is used to match the multidimensional parameter and threshold configuration list of the corresponding terminal according to the terminal identification ID; and the sending module is used to control the platform to send the multidimensional parameter and threshold configuration list to the terminal.

[0161] The configuration list receiving module controls the terminal module's reception of multi-dimensional parameter and threshold configuration lists. The octet diagnostic data persistence module persists the diagnostic data octet within the module. The terminal module receives the configuration list from the platform and combines three fields (data status, dynamic maximum value, and dynamic minimum value) to form a diagnostic data octet (reference time interval, reference wireless signal level, parameter name, maximum boundary threshold, minimum boundary threshold, data status, dynamic maximum value, and dynamic minimum value). This octet is then persistently stored within the module for later diagnostic use.

[0162] The intelligent diagnostic calculation module controls terminal data collection, adaptively matches octet diagnostic data, invokes the module's intelligent diagnostic calculations, and outputs diagnostic status to the terminal and platform. The terminal collects current data values and invokes module instructions to perform diagnostics. The module adaptively matches octet diagnostic data based on the current time interval, current wireless signal level, and parameter names, invokes the intelligent diagnostic calculation module, and obtains diagnostic results (exceeding threshold fault alarm status, potential risk trend status, stable fault-free trend status). This alarm is sent to the terminal and reported to the platform.

[0163] The process of diagnostic calculation and selection is as follows:

[0164] Check the data status field value in the octet diagnostic data. If the data status is the initial state, change the state to the diagnostic monitoring state, and store the current data value in the dynamic maximum value and the dynamic minimum value. If the state is the diagnostic monitoring state and the current data value is higher than the stored dynamic maximum value, change the dynamic maximum value to the current data value. If the current data value is lower than the dynamic minimum value, change the stored dynamic minimum value to the current data value.

[0165] If the current data value is higher than the upper boundary threshold or lower than the lower boundary threshold, the terminal is directly judged to be in the over-threshold fault alarm state;

[0166] If the current data value is between the highest boundary threshold and the lowest boundary threshold, the dynamic highest value, dynamic lowest value, current data value and weight (users can customize weights as needed, the default is 1 standard deviation equal weight) are used as SH, SHW, SL, SLW, SC, SCW parameter data, and the function module that implements the customized proprietary multi-dimensional parameter trend fusion instruction is called to obtain the business data trend balance value DB, business data trend highest value DH, business data trend lowest value DL, and finally compare them with the threshold value according to the following judgment:

[0167] When the highest value DH of the business data trend is higher than the highest threshold value or the lowest value DL of the business data trend is lower than the lowest threshold value, the terminal is judged to be in a potential risk trend state;

[0168] When the above conditions are not met, that is, the service data trend maximum value DH is lower than the threshold maximum value and the service data trend minimum value DL is higher than the threshold minimum value, the terminal is judged to be in a stable fault-free trend state.

[0169] The fault handling module is used to control the platform or terminal to handle faults and update the diagnostic data status. After receiving the fault alarm status information, the terminal or platform performs the fault handling operation and sends instructions to the module after completing the fault handling. The data update module is used to update the data status in the octet diagnostic data in the module to the initial state.

[0170] For example, an IoT terminal contains temperature and battery data, and fault monitoring and diagnosis of both temperature and battery data is required. Using a module pre-installed with proprietary RISC-V-based multi-dimensional parameter trend fusion instructions, the terminal reports its terminal identification (assuming IMEI number, date 1, and wireless signal level). The platform matches the terminal identification to a parameter list and issues the following parameters:

[0171] 1,1,Temperature,60,10;

[0172] 1, 2, Temperature, 55, 10;

[0173] 1, 3, Temperature, 50, 10;

[0174] 1,1,Battery,100,10;

[0175] 1, 2, Battery, 100, 20;

[0176] 1,3,Battery,100,30.

[0177] The first field indicates the date (1 indicates the first day of each month, 2 indicates the second day of each month, and so on), the second field indicates the wireless signal level (1 indicates good, 2 indicates fair, and 3 indicates poor), the third field indicates the parameter name, the fourth field indicates the upper limit threshold, and the fifth field indicates the lower limit threshold.

[0178] After receiving the above parameters, the terminal merges the three fields into an octet of diagnostic data within the module and stores it persistently, as shown below:

[0179] 1, 1, Temperature, 60, 10, 0, 0, 0;

[0180] 1, 2, Temperature, 55, 10, 0, 0, 0;

[0181] 1, 3, Temperature, 50, 10, 0, 0, 0;

[0182] 1, 1, Battery, 100, 10, 0, 0, 0;

[0183] 1, 2, Battery, 100, 20, 0, 0, 0;

[0184] 1, 3, Battery, 100, 30, 0, 0, 0.

[0185] Among them, the sixth field indicates the data state (0 is the initial state, 1 is the diagnostic monitoring state), the seventh field stores the real-time maximum value, and the eighth field stores the real-time minimum value.

[0186] The terminal collects data and performs intelligent diagnosis. Assuming that the data collected for the first time on the 1st is a temperature of 20, a battery level of 80, and a current wireless signal level of 1 (indicating a good wireless signal level), the corresponding octet diagnostic data in the module changes to:

[0187] 1, 1, Temperature, 60, 10, 1, 20, 20;

[0188] 1, 1, Battery, 100, 10, 1, 80, 80.

[0189] According to step S401, the threshold fault diagnosis is performed, and if the threshold result is that there is no over-threshold fault, the process jumps to step S403 for calculation.

[0190] temperature:

[0191] DB=(20*1+20*1+20*2) / (1+1+2)=20;

[0192] DH=20+(20-20)=20;

[0193] DL=20-(20-20)=20.

[0194] Battery life:

[0195] DB=(80*1+80*1+80*2) / (1+1+2)=80;

[0196] DH=80+(80-80)=80;

[0197] DL=80-(80-80)=80.

[0198] Among them, if the temperature DH=20 is not higher than 60 and DL=20 is not lower than 10, and the power DH=80 is not higher than 100 and DL=80 is not lower than 10, the terminal state is a stable fault-free trend state.

[0199] Assuming the second data obtained is a temperature of 50, a battery level of 60, and the current wireless signal level is still 1, the data in the module changes to:

[0200] 1,1,Temperature,60,10,1,50,20;

[0201] 1,1,Battery,100,10,1,80,60.

[0202] According to step S401, the threshold fault diagnosis is performed, and if the threshold result is that there is no over-threshold fault, the process jumps to step S403 for calculation.

[0203] temperature:

[0204] DB=(50*1+20*1+50*2) / (1+1+2)=42.5;

[0205] DH=42.5+(42.5-20)=65;

[0206] DL=42.5-(42.5-20)=20.

[0207] Battery life:

[0208] DB=(80*1+60*1+60*2) / (1+1+2)=65;

[0209] DH=65+(65-60)=70;

[0210] DL=65-(65-60)=55.

[0211] Among them, if the temperature DH=65 is higher than 60, DL=20 is not lower than 10, and the power DH=65 is not higher than 100 and DL=55 is not lower than 10, then the terminal status is a potential risk trend state (because the temperature has the potential to exceed the threshold risk).

[0212] Assume that the third data obtained is the temperature is 70, the battery level is 8, and the current wireless signal level is still 1. The data in the module changes to:

[0213] 1,1,Temperature,60,10,1,70,20;

[0214] 1,1,Battery,100,10,1,80,8.

[0215] At this time, according to step S401, threshold fault diagnosis is performed. The current temperature 70 is higher than 60, and the current power 8 is lower than 10. The threshold result is that there is an over-threshold fault. Then the multi-dimensional parameter intelligent diagnosis obtains that the terminal status is an over-threshold fault alarm state.

[0216] In summary, this application proposes a clear customized RISC-V proprietary multi-dimensional parameter trend fusion instruction, which improves the original method of using a single or simple parameter to diagnose faults on high-energy consumption chips into a low-power RISC-V proprietary instruction of the hardware and software integrated execution unit, which can calculate the fault trend data value in a timely manner, thereby greatly improving the timeliness of diagnosis and reducing the overall power consumption of the terminal.

[0217] The terminal module persistently stores eight-tuple diagnostic data (reference time interval, reference wireless signal level, parameter name, maximum boundary threshold, minimum boundary threshold, data status, dynamic maximum value, dynamic minimum value), and adaptively matches the data collected by the terminal to the eight-tuple diagnostic data. The terminal module intelligently diagnoses and calculates trend data using an algorithm. The method and process of using the intelligent diagnostic trend calculation algorithm to predict the potential risk status of terminal faults greatly improves the accuracy of terminal fault diagnosis and the efficiency of terminal operation and fault handling.

[0218] Reference Figure 9 The present application also provides a terminal multi-dimensional parameter intelligent diagnosis system, which can implement the above-mentioned terminal multi-dimensional parameter intelligent diagnosis method. The system includes:

[0219] The first module is used to obtain the triplet information of the IoT terminal, which includes the terminal identification, the current time interval and the current wireless signal level.

[0220] The second module is used to match the configuration list of the IoT terminal according to the terminal identifier, wherein the configuration list includes multidimensional parameters and threshold boundaries, the multidimensional parameters include the reference time interval, the reference wireless signal level and the parameter name of the reference business data, and the threshold boundaries include the highest boundary threshold and the lowest boundary threshold of the reference business data.

[0221] The third module is used to add three fields, namely data status, dynamic maximum value and dynamic minimum value, based on the configuration list, to obtain eight-tuple diagnostic data and store it persistently in the module.

[0222] The fourth module is used to collect the current business data of the IoT terminal, and based on the current time interval and the current wireless signal level, update the octet diagnostic data according to the current business data.

[0223] The fifth module diagnoses the fault status of the updated octet diagnostic data through a multi-dimensional parameter trend fusion algorithm to obtain a diagnostic result. The multi-dimensional parameter trend fusion algorithm is obtained through extended instructions based on a reduced instruction set architecture and is preset in the module.

[0224] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0225] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-mentioned terminal multi-dimensional parameter intelligent diagnosis method. The electronic device can be any intelligent terminal, including a tablet computer, an in-vehicle computer, or the like.

[0226] It can be understood that the contents of the above method embodiments are applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0227] Reference Figure 10 , Figure 10 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0228] The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0229] Memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). Memory 902 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in memory 902 and is called by processor 901 to execute the terminal multi-dimensional parameter intelligent diagnosis method of the embodiments of this application.

[0230] The input / output interface 903 is used to implement information input and output.

[0231] The communication interface 904 is used to realize communication interaction between this device and other devices. Communication can be realized through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0232] The bus 905 transmits information between various components of the device (eg, the processor 901 , the memory 902 , the input / output interface 903 , and the communication interface 904 ).

[0233] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0234] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned terminal multi-dimensional parameter intelligent diagnosis method.

[0235] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiment, the functions specifically implemented by the present storage medium embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0236] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0237] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0238] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0239] The system embodiment described above is merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0240] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0241] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0242] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A terminal multi-dimensional parameter intelligent diagnosis method, characterized in that: The method comprises the following steps: Obtaining triplet information of the IoT terminal, the triplet information including the terminal identifier, the current time interval, and the current wireless signal level; Matching a configuration list of the IoT terminal according to the terminal identifier, wherein the configuration list includes multidimensional parameters and threshold boundaries, the multidimensional parameters include a reference time interval, a reference wireless signal level, and a parameter name of reference service data, and the threshold boundaries include a maximum boundary threshold and a minimum boundary threshold of the reference service data; Based on the configuration list, three fields, namely data status, dynamic maximum value and dynamic minimum value, are added to obtain eight-tuple diagnostic data and persistently store them in the module. The data status is used to identify the stages of the diagnostic process, including the initial state and the diagnostic monitoring state. The initial state indicates that the terminal has just received the configuration list and has not started fault diagnosis and needs to wait for the first data collection. The diagnostic monitoring state indicates that fault diagnosis has started; the dynamic maximum value is used to record the peak value of the parameter during the fault monitoring period in real time; the dynamic minimum value is used to record the valley value of the parameter during the fault monitoring period in real time. Collecting current service data of the IoT terminal, and updating the octet diagnostic data according to the current service data based on the current time interval and the current wireless signal level; Performing fault status diagnosis on the updated octet diagnostic data using a multi-dimensional parameter trend fusion algorithm to obtain a diagnostic result, wherein the multi-dimensional parameter trend fusion algorithm is obtained through extended instructions based on a reduced instruction set architecture and is preset in the module; The updating process of the octet diagnostic data based on the current time interval and the current wireless signal level and according to the current service data comprises the following steps: Matching the octet diagnostic data according to the current time interval, the current wireless signal level, and the parameter name of the current service data; determining an update strategy according to the data status in the octet diagnostic data; Based on the update strategy, updating the dynamic maximum value and the dynamic minimum value according to the current business data; The method of performing fault status diagnosis on the updated octet diagnostic data by using a multi-dimensional parameter trend fusion algorithm to obtain a diagnosis result includes the following steps: Perform threshold fault diagnosis on the updated dynamic maximum value and the dynamic minimum value according to the maximum boundary threshold and the minimum boundary threshold, determine whether there is an over-threshold fault, and obtain a threshold result; When the threshold result indicates that an over-threshold fault exists, determining that the diagnosis result is an over-threshold fault alarm state; When the threshold result indicates that there is no over-threshold fault, a trend prediction is performed based on the current service data and the updated dynamic maximum value and the updated dynamic minimum value to obtain a prediction result, the prediction result including a trend balance value, a trend maximum value, and a trend minimum value; Perform risk diagnosis on the prediction result according to the highest boundary threshold and the lowest boundary threshold to determine whether there is potential risk and obtain a risk result; When the risk result is that there is a potential risk, the diagnosis result is determined to be in a potential risk trend state; otherwise, the diagnosis result is determined to be in a stable fault-free trend state; The step of performing trend prediction based on the current business data and the updated dynamic maximum value and the updated dynamic minimum value to obtain a prediction result comprises the following steps: Based on the preset calculation weights, a weighted calculation is performed according to the current business data and the updated dynamic maximum value and the updated dynamic minimum value to obtain a trend balance value; Fluctuation quantification processing is performed based on the trend balance value and the updated dynamic minimum value to obtain the trend maximum value and the trend minimum value.

2. The method according to claim 1, characterized in that The method of adding three fields, data status, dynamic maximum value, and dynamic minimum value, based on the configuration list, obtaining eight-tuple diagnostic data and persistently storing it in the module includes the following steps: Parsing the configuration list to obtain five-tuple diagnostic data corresponding to each reference service data, the five-tuple diagnostic data including the reference time interval, the reference wireless signal level, the parameter name, the maximum boundary threshold, and the minimum boundary threshold; Initialize the fields of data status, dynamic maximum value and dynamic minimum value; According to the initialized data state, the dynamic maximum value and the dynamic minimum value, the five-tuple diagnostic data is spliced to obtain eight-tuple diagnostic data and persistently stored in the module.

3. The method according to claim 1, characterized in that The step of performing risk diagnosis on the prediction result according to the highest boundary threshold and the lowest boundary threshold to determine whether there is a potential risk and obtain a risk result includes the following steps: Performing an upper limit safety diagnosis on the trend maximum value according to the maximum boundary threshold to obtain an upper limit result; Performing a lower limit safety diagnosis on the trend minimum value according to the lowest boundary threshold to obtain a lower limit result; Perform risk diagnosis based on the upper limit result and the lower limit result to determine whether there is a potential risk and obtain a risk result; The risk diagnosis is performed based on the upper limit result and the lower limit result to determine whether there is a potential risk, and the risk result is obtained, including: When the upper limit result is that the highest value of the trend is greater than the highest boundary threshold or the lower limit result is that the lowest value of the trend is less than the lowest boundary threshold, the risk result is determined to be that there is a potential risk; When the upper limit result is that the highest value of the trend is less than the highest boundary threshold and the lower limit result is that the lowest value of the trend is greater than the lowest boundary threshold, it is determined that the risk result is that there is no potential risk.

4. The method according to claim 1, wherein The terminal multi-dimensional parameter intelligent diagnosis method further includes the following steps: When the diagnosis result is the over-threshold fault alarm state or the potential risk trend state, sending an alarm message; Execute troubleshooting operations according to the alarm information; After completing the troubleshooting operation, an update instruction is sent to the module to update the data state in the octet diagnostic data to an initial state.

5. A terminal multi-dimensional parameter intelligent diagnosis system, characterized in that: The system comprises: The first module is used to obtain triplet information of the IoT terminal, where the triplet information includes the terminal identifier, the current time interval, and the current wireless signal level; A second module is configured to match a configuration list of the IoT terminal according to the terminal identifier, wherein the configuration list includes multidimensional parameters and threshold boundaries, the multidimensional parameters include a reference time interval, a reference wireless signal level, and a parameter name of reference service data, and the threshold boundaries include a maximum boundary threshold and a minimum boundary threshold of the reference service data; The third module is used to add three fields, namely data status, dynamic maximum value and dynamic minimum value, based on the configuration list, to obtain eight-tuple diagnostic data and store it persistently in the module, wherein the data status is used to identify the stages of the diagnostic process, including the initial state and the diagnostic monitoring state. The initial state indicates that the terminal has just received the configuration list and has not started fault diagnosis and needs to wait for the first data collection. The diagnostic monitoring state indicates the start of fault diagnosis; the dynamic maximum value is used to record the peak value of the parameter during the fault monitoring period in real time; the dynamic minimum value is used to record the valley value of the parameter during the fault monitoring period in real time; A fourth module is configured to collect current service data of the IoT terminal, and update the octet diagnostic data according to the current service data based on the current time interval and the current wireless signal level; a fifth module, performing fault status diagnosis on the updated octet diagnostic data by using a multi-dimensional parameter trend fusion algorithm to obtain a diagnostic result, wherein the multi-dimensional parameter trend fusion algorithm is obtained by extending instructions based on a reduced instruction set architecture and is preset in the module; The updating process of the octet diagnostic data based on the current time interval and the current wireless signal level and according to the current service data comprises the following steps: Matching the octet diagnostic data according to the current time interval, the current wireless signal level, and the parameter name of the current service data; determining an update strategy according to the data status in the octet diagnostic data; Based on the update strategy, updating the dynamic maximum value and the dynamic minimum value according to the current business data; The method of performing fault status diagnosis on the updated octet diagnostic data by using a multi-dimensional parameter trend fusion algorithm to obtain a diagnosis result includes the following steps: Perform threshold fault diagnosis on the updated dynamic maximum value and the dynamic minimum value according to the maximum boundary threshold and the minimum boundary threshold, determine whether there is an over-threshold fault, and obtain a threshold result; When the threshold result indicates that an over-threshold fault exists, determining that the diagnosis result is an over-threshold fault alarm state; When the threshold result indicates that there is no over-threshold fault, a trend prediction is performed based on the current service data and the updated dynamic maximum value and the updated dynamic minimum value to obtain a prediction result, the prediction result including a trend balance value, a trend maximum value, and a trend minimum value; Perform risk diagnosis on the prediction result according to the highest boundary threshold and the lowest boundary threshold to determine whether there is potential risk and obtain a risk result; When the risk result is that there is a potential risk, the diagnosis result is determined to be in a potential risk trend state; otherwise, the diagnosis result is determined to be in a stable fault-free trend state; The step of performing trend prediction based on the current business data and the updated dynamic maximum value and the updated dynamic minimum value to obtain a prediction result comprises the following steps: Based on the preset calculation weights, a weighted calculation is performed according to the current business data and the updated dynamic maximum value and the updated dynamic minimum value to obtain a trend balance value; Fluctuation quantification processing is performed based on the trend balance value and the updated dynamic minimum value to obtain the trend maximum value and the trend minimum value.

6. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images