Intelligent data monitoring method, system, device and equipment and storage medium

Abstract

The invention provides an intelligent data monitoring method, system, device and equipment and a storage medium, and relates to the technical field of computers, the method is applied to a processor in the intelligent data monitoring system, and the method comprises the following steps: analyzing a digital signal corresponding to original data of each chip to obtain first monitoring data of each chip; the digital signal corresponding to the original data is obtained by performing data acquisition on a chip power supply through a sensor to obtain the original data and performing analog-to-digital conversion on an analog voltage signal corresponding to the original data, and the analog-to-digital conversion process is realized by using an analog-to-digital converter; the original data of each chip comprises current, voltage and temperature; determining a target working condition mode of each chip according to the first monitoring data and a preset data mapping table; the target working condition mode is used for the processor to perform optimization control on each chip according to the target working condition mode; and determining a fault position based on the target working condition mode of each chip. According to the invention, the data utilization rate is improved, and intelligent decision making is realized.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and particularly to an intelligent data monitoring method, system, device, equipment and storage medium. Background Art

[0002] Real-time intelligent monitoring of current and voltage refers to using devices such as sensors to monitor the current and voltage data in a circuit. The development of real-time monitoring of current and voltage helps to improve the safety, reliability and efficiency of the power system.

[0003] At present, real-time monitoring systems and methods of current and voltage are mostly used in battery monitoring, and the function is only to display after detection. However, the existing real-time monitoring systems of current and voltage are disconnected from modern application systems, resulting in low utilization rate of data. Summary of the Invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent data monitoring method, system, device, equipment and storage medium to solve the defect of low data utilization rate in the prior art and improve the data utilization rate.

[0005] In a first aspect, the present invention provides an intelligent data monitoring method, which is applied to a processor in an intelligent data monitoring system; the intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each chip, an analog-to-digital converter, and the processor; the method includes the following steps: According to the data format of the target communication protocol, protocol analysis is performed on the digital signals corresponding to the original data of each chip to obtain the first monitoring data of each chip; the digital signals corresponding to the original data of each chip are obtained by using the sensors corresponding to each chip to collect data on the power supply of each chip, obtaining the original data of each chip, and then performing analog-to-digital conversion on the analog voltage signals corresponding to the original data of each chip. The process of analog-to-digital conversion is implemented by using the analog-to-digital converters corresponding to each chip; the original data of each chip includes original current, original voltage, and temperature value; According to the first monitoring data of each chip and a preset data mapping table, determine the target operating mode of each chip; the preset data mapping table includes multiple second monitoring data of each chip and the first operating mode corresponding to each second monitoring data; the first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; the target operating mode of each chip is used for the processor to perform optimized control on each chip according to the target operating mode of each chip; Based on the target operating mode of each chip, determine the fault location.

[0006] An intelligent data monitoring method provided by the present invention, determining the target operating mode of each chip according to the first monitoring data of each chip and a preset data mapping table, includes: According to the first monitoring data of each chip and the preset data mapping table, determining the second monitoring data with the highest similarity in the preset data mapping table; Determining the first operating mode corresponding to the second monitoring data with the highest similarity as the target operating mode of each chip.

[0007] An intelligent data monitoring method provided by the present invention, determining the second monitoring data with the highest similarity in the preset data mapping table according to the first monitoring data of each chip and the preset data mapping table, includes: Performing approximation matching between the first monitoring data of each chip and each second monitoring data in the preset data mapping table to obtain a preset number of second monitoring data that match the first monitoring data of each chip; Performing similarity sorting on the preset number of second monitoring data that match to obtain a similarity sorting result; Determining the second monitoring data corresponding to the maximum similarity in the similarity sorting result as the second monitoring data with the highest similarity.

[0008] An intelligent data monitoring method provided by the present invention, the preset data mapping table is constructed through the following steps, including: Using a target self-organizing mapping network to determine the second operating mode corresponding to the third monitoring data of each chip according to the third monitoring data of each chip; the target self-organizing mapping network is obtained by training an initial self-organizing mapping network according to multiple fourth monitoring data of each chip and the third operating mode of each chip corresponding to each fourth monitoring data; Determining the third monitoring data of each chip, the second chip operating mode corresponding to the third monitoring data of each chip, and the mapping relationship between each third monitoring data and each second chip operating mode as the preset data mapping table.

[0009] An intelligent data monitoring method provided by the present invention, the intelligent data monitoring system further includes a cloud server; the method further includes: Packaging and encapsulating the first monitoring data of each chip, the target operating mode of each chip, and the system fault location to obtain the encapsulated monitoring data of each chip; Sending the encapsulated monitoring data of each chip to the cloud server.

[0010] An intelligent data monitoring method provided by the present invention, the step of sending the monitoring data after encapsulating each chip to the cloud server includes: Sending the monitoring data after encapsulating each chip to the PHY chip of each module where the chip is located; Using the PHY chip to access the cloud server through a first access path; the first access path includes a switching module and a first RJ45 connector; Uploading the monitoring data after encapsulating each chip to the cloud server based on the first access path; Or, Using the PHY chip to access the cloud server through a second access path; the second access path includes a second RJ45 connector; Uploading the monitoring data after encapsulating each chip to the cloud server based on the second access path.

[0011] In a second aspect, the present invention further provides an intelligent data monitoring system, the intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each chip, an analog-to-digital converter, and a processor; wherein, Sensors corresponding to each chip collect data on the power supply of each chip to obtain the original data of each chip; the original data of each chip includes original current, original voltage, and temperature values; The analog-to-digital converter corresponding to each chip performs analog-to-digital conversion on the analog voltage signal corresponding to the original data of each chip to obtain a digital signal corresponding to the original data of each chip; and sends the digital signal corresponding to the original data of each chip to the processor through a target communication protocol; The processor parses the protocol of the digital signal corresponding to the original data of each chip according to the data format of the target communication protocol to obtain the first monitoring data of each chip; determines the target operating mode of each chip according to the first monitoring data of each chip and a preset data mapping table; the preset data mapping table includes multiple second monitoring data of each chip and the first operating mode corresponding to each second monitoring data; the first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; the target operating mode of each chip is used for the processor to perform optimization control on each chip according to the target operating mode of each chip; based on the target operating mode of each chip, the fault location is determined.

[0012] In a third aspect, the present invention further provides an intelligent data monitoring device, which is applied to a processor in an intelligent data monitoring system; the intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each of the chips, an analog-to-digital converter, and the processor; the device includes the following modules: A parsing module, configured to perform protocol parsing on the digital signals corresponding to the original data of each of the chips according to the data format of a target communication protocol, so as to obtain first monitoring data of each of the chips; the digital signals corresponding to the original data of each of the chips are obtained by performing data acquisition on the power supplies of each of the chips through the sensors corresponding to each of the chips to obtain the original data of each of the chips, and then performing analog-to-digital conversion on the analog voltage signals corresponding to the original data of each of the chips, and the process of analog-to-digital conversion is implemented by using the analog-to-digital converters corresponding to each of the chips; the original data of each of the chips includes original current, original voltage, and temperature values; A monitoring module, configured to determine a target operating condition mode of each of the chips according to the first monitoring data of each of the chips and a preset data mapping table; the preset data mapping table includes multiple second monitoring data of each of the chips and a first operating condition mode corresponding to each of the second monitoring data; the first operating condition mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; the target operating condition mode of each of the chips is used for the processor to perform optimized control on each of the chips according to the target operating condition mode of each of the chips; Based on the target operating condition mode of each of the chips, determine the fault location.

[0013] In a fourth aspect, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, it implements the intelligent data monitoring method as described in any one of the above.

[0014] In a fifth aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the intelligent data monitoring method as described in any one of the above.

[0015] In a sixth aspect, the present invention further provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the intelligent data monitoring method as described in any one of the above.

[0016] The intelligent data monitoring method, system, device, equipment and storage medium provided by the present invention. The method is applied to a processor in an intelligent data monitoring system, and the intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each chip, an analog-to-digital converter, and a processor. The method includes: First, according to the data format of the target communication protocol, protocol analysis is performed on the digital signals corresponding to the original data of each chip to obtain the first monitoring data of each chip. Among them, the digital signals corresponding to the original data of each chip are obtained by collecting data on the power supply of each chip through the sensors corresponding to each chip to obtain the original data of each chip, and then performing analog-to-digital conversion on the analog voltage signals corresponding to the original data of each chip by using the analog-to-digital converters corresponding to each chip. The process of analog-to-digital conversion is implemented by using the analog-to-digital converters corresponding to each chip. The original data of each chip includes original current, original voltage, and temperature value. Then, according to the first monitoring data of each chip and a preset data mapping table, the target operating mode of each chip is determined. Among them, the preset data mapping table includes multiple second monitoring data of each chip and the first operating mode corresponding to each second monitoring data. The first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage. The target operating mode of each chip is used for the processor to perform optimized control on each chip according to the target operating mode of each chip. Furthermore, based on the target operating mode of each chip, the fault location is determined.

[0017] The present invention monitors the current and voltage data of multiple chips. After collecting data on the power supply of each chip through the sensors corresponding to each chip to obtain the original data of each chip (including original current, original voltage, and temperature value), the analog-to-digital converter corresponding to each chip performs analog-to-digital conversion on the analog voltage signal corresponding to the original data of each chip to obtain the digital signal corresponding to the original data of each chip. The processor performs protocol analysis on the digital signal corresponding to the original data of each chip. Then, the processor determines the target operating mode of each chip according to the first monitoring data of each chip obtained by the analysis and the preset data mapping table. Furthermore, based on the target operating mode of each chip, the fault location is determined, realizing optimized control of each chip according to the target operating mode of each chip. The present invention improves the data utilization rate of the monitored data and realizes intelligent decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1It is one of the flow schematic diagrams of the intelligent data monitoring method provided by the present invention.

[0020] Figure 2 It is the schematic diagram of the principle of power supply sampling provided by the present invention.

[0021] Figure 3 It is one of the schematic diagrams of the principle of signal processing and uploading provided by the present invention.

[0022] Figure 4 It is the second schematic diagram of the principle of signal processing and uploading provided by the present invention.

[0023] Figure 5 It is the second flow schematic diagram of the intelligent data monitoring method provided by the present invention.

[0024] Figure 6 It is the schematic diagram of the structure of the intelligent data monitoring system provided by the present invention.

[0025] Figure 7 It is the schematic diagram of the structure of the intelligent data monitoring device provided by the present invention.

[0026] Figure 8 It is the schematic diagram of the structure of the electronic device provided by the present invention. Detailed implementation manners

[0027] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope of protection of the present invention.

[0028] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and are not used to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are usually of the same type, and the number of objects is not limited. For example, the first node can be one or more. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally means an "or" relationship between the associated objects before and after.

[0029] The following combines Figures 1 - 8 to describe the intelligent data monitoring method, system, device, equipment and storage medium of the present invention.

[0030] Figure 1It is one of the schematic flowcharts of the intelligent data monitoring method provided by the present invention. This method is applied to the processor in the intelligent data monitoring system. The intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each chip, an analog-to-digital converter, and a processor. As Figure 1 shown, this method includes the following: Step 101: According to the data format of the target communication protocol, parse the digital signals corresponding to the original data of each chip to obtain the first monitoring data of each chip. The digital signals corresponding to the original data of each chip are obtained by using the sensors corresponding to each chip to collect data on the power supply of each chip to obtain the original data of each chip, and then performing analog-to-digital conversion on the analog voltage signals corresponding to the original data of each chip. The process of analog-to-digital conversion is implemented by using the analog-to-digital converters corresponding to each chip. The original data of each chip includes original current, original voltage, and temperature values. Specifically, it should be noted that the execution subject of this embodiment is the processor in the intelligent data monitoring system. For example, the intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each chip, an analog-to-digital converter, and a processor.

[0031] Among them, the chips monitored in this embodiment are not limited to power chips, PHY chips, RS232 chips, RS485 chips, storage chips, eMMC chips, RAM chips, CPU chips, etc. The sensor is, for example, a high-precision sampling resistor such as a negative temperature coefficient (NTC) resistor. This resistor is mainly made of metal oxides such as manganese, cobalt, nickel, and copper and is manufactured by a ceramic process, having semiconductor properties. At lower temperatures, the number of carriers (electrons and holes) in these oxide materials is small, so the resistance value is high; as the temperature rises, the number of carriers increases and the resistance value decreases accordingly. The resistance value of the NTC thermistor decreases with the increase in temperature, and this characteristic makes it widely used in various occasions such as temperature measurement, temperature compensation, and suppression of inrush current. An analog / digital converter (ADC) is a device that converts analog signals in the external world into digital signals that can be processed by a computer or digital circuit. This conversion involves several key steps, including sampling, quantization, and encoding.

[0032] Exemplarily, the intelligent data monitoring method provided in this embodiment is as follows: First, according to the data format of the target communication protocol, protocol analysis is performed on the digital signals corresponding to the original data of each chip to obtain the first monitoring data of each chip. Among them, the target communication protocol is, for example, the SPI (Serial Peripheral Interface) protocol. The SPI protocol is a widely used synchronous serial communication protocol, mainly used for data transmission between microcontrollers and various peripherals (such as sensors, ADCs, DACs, shift registers, SRAMs, etc.). It supports full-duplex communication, that is, data can be transmitted simultaneously in two directions. The basic working principle of SPI includes the following key points: 1. Four-wire communication interface: SPI communication uses four wires, namely: SCLK (Serial Clock): Clock signal line, generated by the master device, used to synchronize data transmission. MOSI (Master Out Slave In): Master device data output line, connected to the data input terminal of the slave device. MISO (Master In Slave Out): Master device data input line, connected to the data output terminal of the slave device. CS (Chip Select): Slave device selection line, used to select the slave device currently communicating with the master device, usually an active-low signal. 2. Data transmission: To start SPI communication, the master device must send a clock signal and select the slave device by enabling the CS signal. SPI is a full-duplex interface, and the master device and the slave device can send data simultaneously through the MOSI and MISO lines respectively. The sending and receiving of data are synchronized by the clock signal edges on the SCLK line. 3. Clock polarity and clock phase: SPI allows users to select the clock polarity (CPOL) and phase (CPHA), which determine the idle state of the clock signal and the clock edge for data sampling. According to different combinations of CPOL and CPHA, SPI has four working modes, and each mode has its specific clock and data sampling timing. 4. Multi-slave device configuration: In the case of multiple slave devices, each slave device requires a separate CS signal, which is controlled by the master device. This allows selection and communication between multiple slave devices. 5. Chain SPI mode: In a chain configuration, multiple slave devices can be connected to a single bus, and data can be transferred between these devices without going back to the master device.

[0033] Here, it should be noted that the method for obtaining the digital signals corresponding to the original data of each chip is as follows: Figure 2 is a schematic diagram of the principle of power sampling provided by the present invention, as Figure 2As shown, data collection is carried out on the power supplies of each chip through the sensors corresponding to each chip (such as NTC thermistors) to obtain the original data of each chip. The original data of each chip includes the original current, the original voltage, and the temperature value. Furthermore, after the original data of each chip is collected, the analog voltage signals corresponding to the original data of each chip can be subjected to analog-to-digital conversion through the analog-to-digital converters corresponding to each chip to obtain the digital signals corresponding to the original data of each chip. Among them, analog / digital conversion involves several key steps, including sampling, quantization, and encoding, where: 1. Sampling: Measure the amplitude of the analog signal at specific time intervals. According to the Nyquist theorem, the sampling rate should be at least twice the highest frequency of the signal to avoid aliasing effects. 2. Quantization: Quantization is the process of mapping the amplitude values of the sampled signal to a finite number of discrete values. The accuracy of quantization is determined by the resolution of the ADC, usually expressed in bits (bit). For example, an 8-bit ADC can produce 2^8 = 256 different quantization levels. 3. Encoding: Convert the quantized values into a digital representation in binary or other encoding forms. The processor, such as the Central Processing Unit (CPU), is responsible for executing the instructions of the computer program and processing data. It is equivalent to the "brain" of the computer, responsible for interpreting and executing program instructions, processing data, controlling other hardware devices, and managing the operation of the computer.

[0034] The process of parsing the original data is also to parse the original data with reference to the data format set by the target communication protocol to obtain a digital representation, that is, the digital signal corresponding to the original data of each chip.

[0035] Step 102: Determine the target operating mode of each chip according to the first monitoring data of each chip and the preset data mapping table; the preset data mapping table includes multiple second monitoring data of each chip and the first operating mode corresponding to each second monitoring data; the first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; the target operating mode of each chip is used for the processor to perform optimized control on each chip according to the target operating mode of each chip. Specifically, after the first monitoring data of each chip is parsed, that is, the actual monitoring data, such as the measured voltage, current, and temperature values, further analysis, processing, and application of the data can be realized to improve the utilization rate of the data.

[0036] For example, determine the target operating mode of each chip according to the first monitoring data of each chip and the preset data mapping table. Among them, the target operating mode of each chip is used for the processor to perform optimized control on each chip according to the target operating mode of each chip, so as to realize the intelligent decision-making of the system.

[0037] It should be noted that the preset data mapping table includes multiple second monitoring data of each chip and the corresponding first operating mode for each second monitoring data. The first operating mode includes any one of the following: chip sleep, chip standby, normal chip operation, and chip damage. That is, the preset data mapping table includes the mapping relationship between the multiple second monitoring data of each chip and the corresponding first operating mode for each second monitoring data. Based on the mapping relationship between the first monitoring data, the multiple second monitoring data of each chip, and the corresponding first operating mode for each second monitoring data, the first operating mode corresponding to each second monitoring data can be determined.

[0038] Step 103: Determine the fault location based on the target operating mode of each chip.

[0039] Specifically, after obtaining the target operating mode of each chip by analyzing the monitoring data, the fault location can be determined based on the target operating mode of each chip. For example, when the target operating mode of a certain chip is chip damage, the fault location of the system is located at the chip, which is convenient for subsequent maintenance personnel to replace according to the fault location.

[0040] Optionally, the processor in this embodiment can also make the following decisions based on the monitoring data: 1) Anomaly detection: Intelligent algorithms can be used to detect anomalies in current and voltage data, such as sudden rises and falls, abnormal fluctuations, etc. By establishing a model based on historical data, the algorithm can automatically identify these anomalies and issue alarms or take corresponding measures; 2) Predictive analysis: Using machine learning and data mining techniques, intelligent algorithms can predict future current and voltage data, helping the real-time monitoring system to detect potential problems in advance and take preventive measures to avoid equipment failures or safety risks; 3) Optimization control: Intelligent algorithms can combine control strategies to optimize the operation of the power system, improving current and voltage stability and efficiency. For example, through real-time monitoring and adjustment, the algorithm can help the system operate in the best state, reducing energy consumption and costs; 4) Fault diagnosis: When anomalies occur in current and voltage data, intelligent algorithms can help diagnose the cause of the fault and locate the specific location of the problem, so that engineers and technicians can quickly take repair measures and shorten the downtime.

[0041] The method provided in this embodiment is applied to a processor in an intelligent data monitoring system. The intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each chip, an analog-to-digital converter, and a processor. The method includes: First, according to the data format of the target communication protocol, protocol analysis is performed on the digital signals corresponding to the original data of each chip to obtain the first monitoring data of each chip. Among them, the digital signals corresponding to the original data of each chip are obtained by collecting data on the power supply of each chip through the sensors corresponding to each chip to obtain the original data of each chip, and then performing analog-to-digital conversion on the analog voltage signals corresponding to the original data of each chip. The analog-to-digital conversion process is implemented using the analog-to-digital converters corresponding to each chip. The original data of each chip includes original current, original voltage, and temperature values. Then, according to the first monitoring data of each chip and a preset data mapping table, the target operating mode of each chip is determined. Among them, the preset data mapping table includes multiple second monitoring data of each chip and the first operating mode corresponding to each second monitoring data. The first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage. The target operating mode of each chip is used for the processor to perform optimized control on each chip according to the target operating mode of each chip. Furthermore, based on the target operating mode of each chip, the fault location is determined.

[0042] The present invention monitors the current and voltage data of multiple chips. After collecting the original data of each chip (including original current, original voltage, and temperature values) through the sensors corresponding to each chip, the analog-to-digital converter corresponding to each chip performs analog-to-digital conversion on the analog voltage signal corresponding to the original data of each chip to obtain the digital signal corresponding to the original data of each chip. The processor performs protocol analysis on the digital signal corresponding to the original data of each chip. Then, the processor determines the target operating mode of each chip according to the first monitoring data of each chip obtained by the analysis and the preset data mapping table. Furthermore, based on the target operating mode of each chip, the fault location is determined, realizing optimized control of each chip according to the target operating mode of each chip. The present invention improves the data utilization rate of the monitored data and realizes intelligent decision-making.

[0043] According to an intelligent data monitoring method provided by the present invention, determining the target operating mode of each chip according to the first monitoring data of each chip and a preset data mapping table includes: Determining the second monitoring data with the highest similarity in the preset data mapping table according to the first monitoring data of each chip and the preset data mapping table; Determining the first operating mode corresponding to the second monitoring data with the highest similarity as the target operating mode of each chip.

[0044] Specifically, in some embodiments, step 102 can be implemented through the following steps, including: First, according to the first monitoring data of each chip and the preset data mapping table, determine the second monitoring data with the highest similarity in the preset data mapping table. For example, use the K-nearest neighbor algorithm to match the first monitoring data of each chip with the second monitoring data in the preset data mapping table, so as to obtain the second monitoring data with the highest similarity.

[0045] Furthermore, according to the second monitoring data with the highest similarity, and the mapping relationship between the multiple second monitoring data of each chip in the preset data mapping table and the first operating mode corresponding to each second monitoring data, determine the first operating mode corresponding to the second monitoring data with the highest similarity. Furthermore, it can be determined as the target operating mode of each chip, realizing the intelligent matching of monitoring data and operating mode.

[0046] The method provided in this embodiment first determines the second monitoring data with the highest similarity in the preset data mapping table according to the first monitoring data of each chip and the preset data mapping table; then, determines the first operating mode corresponding to the second monitoring data with the highest similarity as the target operating mode of each chip, that is, completes the intelligent matching of the monitoring data and operating mode of each chip, improves the data utilization rate of the monitoring data, and thus realizes intelligent decision-making.

[0047] According to an intelligent data monitoring method provided by the present invention, determining the second monitoring data with the highest similarity in the preset data mapping table according to the first monitoring data of each chip and the preset data mapping table includes: Perform approximate matching between the first monitoring data of each chip and each second monitoring data in the preset data mapping table to obtain a preset number of second monitoring data that match the first monitoring data of each chip; Perform similarity sorting on the preset number of second monitoring data that match to obtain a similarity sorting result; Determine the second monitoring data corresponding to the maximum similarity in the similarity sorting result as the second monitoring data with the highest similarity.

[0048] Specifically, in some embodiments, the specific implementation process of determining the second monitoring data with the highest similarity in the preset data mapping table according to the first monitoring data of each chip and the preset data mapping table is as follows, and the steps include: First, perform approximate matching between the first monitoring data of each chip and each second monitoring data in the preset data mapping table to obtain a preset number of second monitoring data that match the first monitoring data of each chip; for example, use the K-nearest neighbor algorithm for approximate matching to obtain a preset number of second monitoring data that match, for example, find the 100 most similar data.

[0049] Further, perform a similarity ranking on the preset number of second monitoring data that match, to obtain a similarity ranking result. For example, rank the similarities from largest to smallest.

[0050] Furthermore, the second monitoring data corresponding to the largest similarity in the similarity ranking result can be determined as the second monitoring data with the highest similarity.

[0051] The method provided in this embodiment first performs an approximation match between the first monitoring data of each chip and each second monitoring data in the preset data mapping table, to obtain the preset number of second monitoring data that match the first monitoring data of each chip; then, perform a similarity ranking on the preset number of second monitoring data that match, to obtain a similarity ranking result; furthermore, the second monitoring data corresponding to the largest similarity in the similarity ranking result is determined as the second monitoring data with the highest similarity, which is convenient for subsequent intelligent matching of the working conditions of each chip.

[0052] According to an intelligent data monitoring method provided by the present invention, the preset data mapping table is constructed through the following steps, including: Using a target self-organizing mapping network, according to the third monitoring data of each chip, determine the second working condition mode corresponding to the third monitoring data of each chip; the target self-organizing mapping network is obtained by training an initial self-organizing mapping network according to multiple fourth monitoring data of each chip and the third working condition mode of each chip corresponding to each fourth monitoring data; Determine the third monitoring data of each chip, the second chip working condition mode corresponding to the third monitoring data of each chip, and the mapping relationship between each third monitoring data and each second chip working condition mode as the preset data mapping table.

[0053] Specifically, in some embodiments, the preset data mapping table is constructed through the following steps, including: First, use a target self-organizing mapping network to determine the second working condition mode corresponding to the third monitoring data of each chip according to the third monitoring data of each chip.

[0054] Among them, the target self-organizing map network (SOM) is an unsupervised learning algorithm that processes data by simulating the self-organization method of neurons in the cerebral cortex. The core idea of SOM is to map high-dimensional data into a low-dimensional (usually two-dimensional) space while maintaining the topological structure of the data, so that similar data points are still adjacent after mapping. The basic structure of the SOM network includes an input layer and a computing layer (competitive layer). The computing layer usually consists of a series of neurons, which can be one-dimensional or two-dimensional structures. The training process of SOM includes three stages: competition, cooperation, and adaptation. During the competition process, each input sample will stimulate a neuron in the network to become the winning neuron (Best Matching Unit, BMU). During the cooperation process, the winning neuron and the neurons within its neighborhood will update their weights to better respond to similar inputs. During the adaptation process, the learning rate will gradually decrease over time to control the amplitude of weight updates.

[0055] Among them, the target self-organizing map network is obtained by training the initial self-organizing map network based on multiple fourth monitoring data of each chip and the third operating mode of each chip corresponding to each fourth monitoring data. The implementation steps of the training process of the SOM algorithm usually include: 1. Initialize the weights. 2. Find the nearest neuron (winning neuron). 3. Update the weights of neighboring neurons. 4. Reduce the neighboring neurons and the learning rate. 5. Repeat the above steps until the stop condition is met.

[0056] Input the third monitoring data of each chip into the trained target self-organizing map network, and the target self-organizing map network can output the second operating mode corresponding to the third monitoring data of each chip.

[0057] Furthermore, the third monitoring data of each chip, the second chip operating mode corresponding to the third monitoring data of each chip, and the mapping relationship between each third monitoring data and each second chip operating mode can be determined as a preset data mapping table. Exemplarily, an instance of the preset data mapping table is as follows in Table 1: Table 1:

[0058] In the method provided in this embodiment, the target self-organizing mapping network is obtained by training the initial self-organizing mapping network based on multiple fourth monitoring data of each chip and the third operating mode of each chip corresponding to each fourth monitoring data. First, using the target self-organizing mapping network, based on the third monitoring data of each chip, determine the second operating mode corresponding to the third monitoring data of each chip. Then, determine the third monitoring data of each chip, the second chip operating mode corresponding to the third monitoring data of each chip, and the mapping relationship between each third monitoring data and each second chip operating mode as a preset data mapping table, which is convenient for subsequently matching the operating mode corresponding to the first monitoring data based on the preset data mapping table, realizing intelligent decision-making, and improving data utilization rate.

[0059] According to an intelligent data monitoring method provided by the present invention, the intelligent data monitoring system further includes a cloud server; the method further includes: Package and encapsulate the first monitoring data of each chip, the target operating mode of each chip, and the system fault location to obtain the encapsulated monitoring data of each chip; Send the encapsulated monitoring data of each chip to the cloud server.

[0060] Specifically, in some embodiments, the intelligent data monitoring system further includes a cloud server. In this embodiment, the method further includes: uploading data to the cloud server, displaying data, voltage and current change diagrams, fault alarms, and fault points. The network upload mode has a simple structure, is stable and efficient, has a rapid response, low latency, and a high fault tolerance rate, making the device more intelligent.

[0061] First, package and encapsulate the first monitoring data of each chip, the target operating mode of each chip, and the system fault location to obtain the encapsulated monitoring data of each chip. Then, send the encapsulated monitoring data of each chip to the cloud server.

[0062] Among them, data encapsulation is a core concept in computer networks and object-oriented programming. It involves combining data and functions that operate on the data to form an organic whole to enhance security and simplify programming. In network programming, data encapsulation refers to the process of encapsulating protocol data units (PDUs) in a set of protocol headers and tails. This process occurs at each layer of the OSI seven-layer reference model. Each layer is mainly responsible for communicating with the peer layer on other machines, and the PDU of each layer is generally composed of the protocol header, protocol tail, and data encapsulation of this layer. During the data transmission process, the process of data encapsulation is generally as follows: 1. Convert user information into data for transmission over the network.

[0063] 2. Convert the data into data segments and establish a reliable connection between the sending and receiving host machines.

[0064] 3. The data segment is converted into a data packet or datagram, and the logical address is placed in the header so that each data packet can be transmitted through the Internetwork.

[0065] 4. The data packet or datagram is converted into a frame for transmission on the local network. On the local network segment, each host is uniquely identified using the hardware address.

[0066] 5. The frame is converted into a bit stream and a digital encoding and clocking scheme is adopted.

[0067] The method provided in this embodiment packs and encapsulates the first monitoring data of each chip, the target operating condition mode of each chip, and the system fault location, and then sends the encapsulated monitoring data of each chip to the cloud server, realizing cloud storage of the data and preventing data loss.

[0068] According to an intelligent data monitoring method provided by the present invention, sending the encapsulated monitoring data of each chip to the cloud server includes: Sending the encapsulated monitoring data of each chip to the PHY chip of the module where each chip is located; Using the PHY chip to access the cloud server through a first access path; the first access path includes a switching module and a first RJ45 connector; Uploading the encapsulated monitoring data of each chip to the cloud server based on the first access path; Or, Using the PHY chip to access the cloud server through a second access path; the second access path includes a second RJ45 connector; Uploading the encapsulated monitoring data of each chip to the cloud server based on the second access path.

[0069] Specifically, in some embodiments, the specific implementation process of sending the encapsulated monitoring data of each chip to the cloud server includes the following steps: Figure 3 is one of the schematic diagrams of the signal processing and uploading principle provided by the present invention, as Figure 3As shown, first, the monitoring data of each chip after packaging is sent to the PHY chip of the module where each chip is located. Among them, the PHY chip, the full name of which is the physical layer interface chip (Physical Layer Interface Devices), is an indispensable component in network communication. It is located in the physical layer of the OSI model and is responsible for realizing the physical connection and signal processing of data transmission, including but not limited to mechanical, electrical, photoelectric conversion and transmission procedures. The main functions of the PHY chip include establishing, maintaining and dismantling physical circuits to realize transparent transmission of physical layer bit streams. In Ethernet, the PHY chip is responsible for converting the logical "1" and "0" bits transmitted from the data link layer into electrical signals or optical signals suitable for transmission on the physical medium, and performing the opposite conversion at the receiving end. These physical media can be twisted pair cables, optical fibers or wireless signals. The PHY chip is also responsible for encoding and decoding signals. For example, under the 10Base-T standard, data is transmitted after Manchester encoding and NRZ encoding.

[0070] Furthermore, method 1 is adopted to access Ethernet: for example, a PHY chip is used to access a cloud server through a first access path, and monitoring data of each chip packaged is uploaded to the cloud server based on the first access path, wherein the first access path includes a switching module and a first RJ45 connector.

[0071] Alternatively, use method 2 to access Ethernet: for example, use a PHY chip to access the cloud server through a second access path, and then upload the packaged monitoring data of each chip to the cloud server based on the second access path, wherein the second access path includes a second RJ45 connector.

[0072] Figure 4 This is the second schematic diagram of the principle of signal processing upload provided by the present invention, which shows the communication process between modules: Among them, the computing module (the computing function is mainly provided by the computing board, which is matched with the intelligent control cloud to realize the edge data center, and needs to support virtualization. At the same time, the board itself must have a certain degree of redundancy to ensure data and power redundancy), the expansion module (mainly provides the logic of expanding DI / DO / serial port / AI / AO), the AI ​​module (the AI ​​function mainly provides artificial intelligence analysis based on video analysis for the edge side, and needs to support 3216-channel camera encoding and decoding. The minimum requirement is to support 3216 channels of cameras, and each camera has one algorithm), and the BMC module (collecting various basic information of other slot boards) all synchronize information through the switching module Ethernet network, but web pages and cloud data access can be on each board. The signal flow is as follows Figure 4 shown.

[0073] The method provided in this embodiment sends the monitored data after packaging and encapsulating each chip to the cloud server, realizing cloud storage of data and preventing data loss.

[0074] Figure 5 It is the second flow schematic diagram of the intelligent data monitoring method provided by the present invention. As Figure 5 shown, the method includes: Step 501, collect a large amount of historical data such as voltage, current, power consumption, temperature, and chip fault status.

[0075] Step 502, use the data to train the self-organizing mapping network to obtain the trained target self-organizing mapping network.

[0076] Step 503, use the target self-organizing mapping network to establish a mapping table between the data and the chip fault modes.

[0077] Step 504, find the 100 most similar data through the K-nearest neighbor algorithm.

[0078] Step 505, process the current monitored data to obtain the most dominant category of similar data.

[0079] Step 506, match the corresponding working condition mode according to the most dominant category of similar data.

[0080] Step 507, predict the current working condition mode and feedback it to the system for system optimization control.

[0081] Figure 6 It is the structural schematic diagram of the intelligent data monitoring system provided by the present invention. The intelligent data monitoring system includes: at least one power chip 610, at least one functional chip 620, sensors 630 corresponding to each of the chips, an analog-to-digital converter 640, and a processor 650; wherein, The sensors corresponding to each of the chips collect data on the power supply of each of the chips to obtain the original data of each of the chips; the original data of each of the chips includes original current, original voltage, and temperature values; The analog-to-digital converters corresponding to each of the chips perform analog-to-digital conversion on the analog voltage signals corresponding to the original data of each of the chips to obtain digital signals corresponding to the original data of each of the chips; and send the digital signals corresponding to the original data of each of the chips to the processor through the target communication protocol; The processor parses the digital signals corresponding to the raw data of each chip according to the data format of the target communication protocol to obtain the first monitoring data of each chip; determines the target operating mode of each chip according to the first monitoring data of each chip and a preset data mapping table; the preset data mapping table includes multiple second monitoring data of each chip and the first operating mode corresponding to each second monitoring data; the first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; the target operating mode of each chip is used for the processor to perform optimization control on each chip according to the target operating mode of each chip; based on the target operating mode of each chip, the fault location is determined.

[0082] The intelligent data monitoring system provided in this embodiment includes: at least one power chip, at least one functional chip, sensors corresponding to each chip, an analog-to-digital converter, and a processor. The sensors corresponding to each chip collect data on the power supply of each chip to obtain the raw data of each chip; wherein, the raw data of each chip includes raw current, raw voltage, and temperature value; then, the analog-to-digital converter corresponding to each chip performs analog-to-digital conversion on the analog voltage signal corresponding to the raw data of each chip to obtain the digital signal corresponding to the raw data of each chip; the digital signal corresponding to the raw data of each chip is sent to the processor through the target communication protocol; furthermore, the processor parses the digital signals corresponding to the raw data of each chip according to the data format of the target communication protocol to obtain the first monitoring data of each chip; determines the target operating mode of each chip according to the first monitoring data of each chip and a preset data mapping table, wherein the preset data mapping table includes multiple second monitoring data of each chip and the first operating mode corresponding to each second monitoring data; the first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; the target operating mode of each chip is used for the processor to perform optimization control on each chip according to the target operating mode of each chip; based on the target operating mode of each chip, the fault location is determined.

[0083] The present invention monitors the current and voltage data of multiple chips. After collecting the original data of each chip's power supply through the sensors corresponding to each chip to obtain the original data of each chip (including the original current, original voltage, and temperature value), the analog voltage signals corresponding to the original data of each chip are converted into digital signals through the analog-to-digital converters corresponding to each chip, and the processor parses the protocol of the digital signals corresponding to the original data of each chip. Then, based on the first monitoring data of each chip obtained by parsing and the preset data mapping table, the processor determines the target operating mode of each chip. Furthermore, based on the target operating mode of each chip, the fault location is determined, realizing the optimized control of each chip according to the target operating mode of each chip. The present invention improves the data utilization rate of the monitoring data and realizes intelligent decision-making.

[0084] The intelligent data monitoring device provided by the present invention will be described below. The intelligent data monitoring device described below can be correspondingly referred to the intelligent data monitoring method described above.

[0085] Figure 7 It is a schematic structural diagram of the intelligent data monitoring device provided by the present invention. The device is applied to the processor in the intelligent data monitoring system. The intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each chip, an analog-to-digital converter, and the processor. The intelligent data monitoring device 700 includes the following modules: The parsing module 710 is configured to parse the protocol of the digital signals corresponding to the original data of each chip according to the data format of the target communication protocol to obtain the first monitoring data of each chip. The digital signals corresponding to the original data of each chip are obtained by collecting the original data of each chip's power supply through the sensors corresponding to each chip, and then converting the analog voltage signals corresponding to the original data of each chip into digital signals through the analog-to-digital converters corresponding to each chip. The process of analog-to-digital conversion is realized by using the analog-to-digital converters corresponding to each chip. The original data of each chip includes the original current, the original voltage, and the temperature value. The monitoring module 720 is configured to determine the target operating mode of each chip according to the first monitoring data of each chip and the preset data mapping table. The preset data mapping table includes multiple second monitoring data of each chip and the first operating mode corresponding to each second monitoring data. The first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage. The target operating mode of each chip is used for the processor to optimize the control of each chip according to the target operating mode of each chip. Based on the target operating mode of each chip, determine the fault location.

[0086] The device provided in this embodiment is applied to a processor in an intelligent data monitoring system. The device includes a parsing module 710 and a monitoring module 720. The intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each chip, an analog-to-digital converter, and a processor. The method includes: First, the parsing module 710 performs protocol parsing on the digital signals corresponding to the raw data of each chip according to the data format of the target communication protocol to obtain the first monitoring data of each chip. Among them, the digital signals corresponding to the raw data of each chip are obtained by collecting data on the power supply of each chip through the sensors corresponding to each chip, obtaining the raw data of each chip, and then performing analog-to-digital conversion on the analog voltage signals corresponding to the raw data of the chip. The process of analog-to-digital conversion is implemented by using the analog-to-digital converters corresponding to each chip. The raw data of each chip includes raw current, raw voltage, and temperature values. Then, the monitoring module 720 determines the target operating mode of each chip according to the first monitoring data of each chip and a preset data mapping table. Among them, the preset data mapping table includes multiple second monitoring data of each chip and the first operating mode corresponding to each second monitoring data. The first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage. The target operating mode of each chip is used for the processor to perform optimized control on each chip according to the target operating mode of each chip. Furthermore, based on the target operating mode of each chip, the fault location is determined.

[0087] The present invention monitors the current and voltage data of multiple chips. After collecting data on the power supply of each chip through the sensors corresponding to each chip to obtain the raw data of each chip (including raw current, raw voltage, and temperature values), the analog-to-digital converter corresponding to each chip performs analog-to-digital conversion on the analog voltage signals corresponding to the raw data of each chip to obtain the digital signals corresponding to the raw data of each chip. The processor performs protocol parsing on the digital signals corresponding to the raw data of each chip. Then, the processor determines the target operating mode of each chip according to the first monitoring data of each chip obtained by parsing and a preset data mapping table. Furthermore, based on the target operating mode of each chip, the fault location is determined, realizing optimized control of each chip according to the target operating mode of each chip. The present invention improves the data utilization rate of the monitored data and realizes intelligent decision-making.

[0088] According to the intelligent data monitoring device 700 provided by the present invention, the monitoring module 720 is specifically used for: Determining the second monitoring data with the highest similarity in the preset data mapping table according to the first monitoring data of each chip and the preset data mapping table; Determining the first operating mode corresponding to the second monitoring data with the highest similarity as the target operating mode of each chip.

[0089] According to the intelligent data monitoring device 700 provided by the present invention, the monitoring module 720 is further configured to: Perform approximate matching between the first monitoring data of each chip and each second monitoring data in the preset data mapping table to obtain a preset number of second monitoring data that match the first monitoring data of each chip; Sort the preset number of matched second monitoring data by similarity to obtain a similarity sorting result; Determine the second monitoring data corresponding to the maximum similarity in the similarity sorting result as the second monitoring data with the highest similarity.

[0090] According to the intelligent data monitoring device 700 provided by the present invention, the preset data mapping table is constructed through the following steps, including: Using the target self-organizing mapping network, determine the second operating mode corresponding to the third monitoring data of each chip according to the third monitoring data of each chip; the target self-organizing mapping network is obtained by training the initial self-organizing mapping network according to multiple fourth monitoring data of each chip and the third operating mode of each chip corresponding to each fourth monitoring data; Determine the third monitoring data of each chip, the second chip operating mode corresponding to the third monitoring data of each chip, and the mapping relationship between each third monitoring data and each second chip operating mode as the preset data mapping table.

[0091] According to the intelligent data monitoring device 700 provided by the present invention, the intelligent data monitoring system further includes a cloud server; the device further includes: a communication module; The communication module is configured to: Package and encapsulate the first monitoring data of each chip, the target operating mode of each chip, and the system fault location to obtain the encapsulated monitoring data of each chip; Send the encapsulated monitoring data of each chip to the cloud server.

[0092] According to the intelligent data monitoring device 700 provided by the present invention, the communication module is further configured to: Send the encapsulated monitoring data of each chip to the PHY chip of each module where the chip is located; Use the PHY chip to access the cloud server through the first access path; the first access path includes a switching module and a first RJ45 connector; Upload the encapsulated monitoring data of each chip to the cloud server based on the first access path; Or, Access the cloud server through the second access path by using the PHY chip; the second access path includes a second RJ45 connector. Upload the monitored data after encapsulating each of the chips to the cloud server based on the second access path.

[0093] Figure 8 Illustrates a schematic diagram of the physical structure of an electronic device, as Figure 8 shown. The electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840. Among them, the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The processor 810 can call the logical instructions in the memory 830 to execute an intelligent data monitoring method, which is applied to the processor in an intelligent data monitoring system; the intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each of the chips, an analog-to-digital converter, and the processor; the method includes: Perform protocol parsing on the digital signals corresponding to the original data of each of the chips according to the data format of the target communication protocol to obtain the first monitored data of each of the chips; the digital signals corresponding to the original data of each of the chips are obtained by collecting data on the power supplies of each of the chips through the sensors corresponding to each of the chips, obtaining the original data of each of the chips, and then performing analog-to-digital conversion on the analog voltage signals corresponding to the original data of each of the chips. The process of analog-to-digital conversion is implemented by using the analog-to-digital converters corresponding to each of the chips; the original data of each of the chips includes original current, original voltage, and temperature values. Determine the target operating mode of each of the chips according to the first monitored data of each of the chips and a preset data mapping table; the preset data mapping table includes multiple second monitored data of each of the chips and the first operating mode corresponding to each of the second monitored data; the first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; the target operating mode of each of the chips is used for the processor to perform optimization control on each of the chips according to the target operating mode of each of the chips. Determine the fault location based on the target operating mode of each of the chips.

[0094] In addition, when the logical instructions in the above-mentioned memory 830 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0095] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the intelligent data monitoring method provided by the above-mentioned various methods. This method is applied to the processor in an intelligent data monitoring system. The intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each of the chips, an analog-to-digital converter, and the processor. The method includes: According to the data format of the target communication protocol, protocol analysis is performed on the digital signals corresponding to the original data of each of the chips to obtain the first monitoring data of each of the chips. The digital signals corresponding to the original data of each of the chips are obtained by performing analog-to-digital conversion on the analog voltage signals corresponding to the original data of each of the chips after data collection of the power supplies of each of the chips through the sensors corresponding to each of the chips to obtain the original data of each of the chips. The process of analog-to-digital conversion is implemented using the analog-to-digital converters corresponding to each of the chips. The original data of each of the chips includes original current, original voltage, and temperature values. According to the first monitoring data of each of the chips and a preset data mapping table, determine the target operating condition mode of each of the chips. The preset data mapping table includes multiple second monitoring data of each of the chips and the first operating condition mode corresponding to each of the second monitoring data. The first operating condition mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage. The target operating condition mode of each of the chips is used for the processor to perform optimized control on each of the chips according to the target operating condition mode of each of the chips. Based on the target operating condition mode of each of the chips, determine the fault location.

[0096] On the other hand, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the intelligent data monitoring method provided by the above-mentioned various methods. This method is applied to the processor in the intelligent data monitoring system; the intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each chip, an analog-to-digital converter, and the processor; the method includes: According to the data format of the target communication protocol, protocol analysis is performed on the digital signals corresponding to the original data of each chip to obtain the first monitoring data of each chip; the digital signals corresponding to the original data of each chip are obtained by collecting data on the power supply of each chip through the sensors corresponding to each chip to obtain the original data of each chip, and then performing analog-to-digital conversion on the analog voltage signals corresponding to the original data of each chip. The process of analog-to-digital conversion is implemented by using the analog-to-digital converters corresponding to each chip; the original data of each chip includes original current, original voltage, and temperature values; According to the first monitoring data of each chip and a preset data mapping table, determine the target operating mode of each chip; the preset data mapping table includes multiple second monitoring data of each chip and the first operating mode corresponding to each second monitoring data; the first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; the target operating mode of each chip is used for the processor to perform optimized control on each chip according to the target operating mode of each chip; Based on the target operating mode of each chip, determine the fault location.

[0097] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0098] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent data monitoring method, characterized in that, A processor applied to an intelligent data monitoring system; The intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each of the chips, an analog-to-digital converter, and the processor; The method includes: According to the data format of the target communication protocol, protocol analysis is performed on the digital signals corresponding to the original data of each of the chips to obtain the first monitoring data of each of the chips; The digital signals corresponding to the original data of each of the chips are obtained by collecting data on the power supplies of each of the chips through the sensors corresponding to each of the chips, obtaining the original data of each of the chips, and then performing analog-to-digital conversion on the analog voltage signals corresponding to the original data of each of the chips. The process of analog-to-digital conversion is implemented using the analog-to-digital converters corresponding to each of the chips; The original data of each of the chips includes original current, original voltage, and temperature values; According to the first monitoring data of each of the chips and a preset data mapping table, determine the target operating mode of each of the chips; The preset data mapping table includes multiple second monitoring data of each of the chips and the first operating mode corresponding to each of the second monitoring data; The first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; The target operating mode of each of the chips is used for the processor to perform optimization control on each of the chips according to the target operating mode of each of the chips; Based on the target operating mode of each of the chips, determine the fault location.

2. The intelligent data monitoring method according to claim 1, wherein The step of determining the target operating mode of each of the chips according to the first monitoring data of each of the chips and the preset data mapping table includes: According to the first monitoring data of each of the chips and the preset data mapping table, determine the second monitoring data with the highest similarity in the preset data mapping table; Determine the first operating mode corresponding to the second monitoring data with the highest similarity as the target operating mode of each of the chips.

3. The intelligent data monitoring method according to claim 2, wherein The step of determining the second monitoring data with the highest similarity in the preset data mapping table according to the first monitoring data of each of the chips and the preset data mapping table includes: Perform approximation matching on the first monitoring data of each of the chips and each of the second monitoring data in the preset data mapping table to obtain a preset number of second monitoring data that match the first monitoring data of each of the chips; Perform similarity sorting on the preset number of second monitoring data that match to obtain a similarity sorting result; Determine the second monitoring data corresponding to the maximum similarity in the similarity sorting result as the second monitoring data with the highest similarity.

4. The intelligent data monitoring method according to claim 1, characterized in that The preset data mapping table is constructed through the following steps, including: Using a target self-organizing mapping network, according to the third monitoring data of each of the chips, determine the second operating mode corresponding to the third monitoring data of each of the chips; The target self-organizing mapping network is obtained by training an initial self-organizing mapping network according to multiple fourth monitoring data of each of the chips and the third operating mode of each of the chips corresponding to each of the fourth monitoring data; Determine the third monitoring data of each of the chips, the second chip operating mode corresponding to the third monitoring data of each of the chips, and the mapping relationship between each of the third monitoring data and each of the second chip operating modes as the preset data mapping table.

5. The intelligent data monitoring method according to any one of claims 1-4, characterized in that The intelligent data monitoring system further includes a cloud server; the method further includes: Package and encapsulate the first monitoring data of each of the chips, the target operating mode of each of the chips, and the system fault location to obtain the encapsulated monitoring data of each of the chips. Send the encapsulated monitoring data of each of the chips to the cloud server.

6. The intelligent data monitoring method according to claim 5, wherein The sending the encapsulated monitoring data of each of the chips to the cloud server includes: Send the encapsulated monitoring data of each of the chips to the PHY chip of each module where the chips are located. Use the PHY chip to access the cloud server through a first access path; the first access path includes a switching module and a first RJ45 connector. Upload the encapsulated monitoring data of each of the chips to the cloud server based on the first access path. Or, Use the PHY chip to access the cloud server through a second access path; the second access path includes a second RJ45 connector. Upload the encapsulated monitoring data of each of the chips to the cloud server based on the second access path.

7. An intelligent data monitoring system, characterized in that, The intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each of the chips, an analog-to-digital converter, and a processor; wherein, The sensors corresponding to each of the chips collect data on the power supply of each of the chips to obtain the original data of each of the chips; the original data of each of the chips includes original current, original voltage, and temperature values. The analog-to-digital converter corresponding to each of the chips performs analog-to-digital conversion on the analog voltage signal corresponding to the original data of each of the chips to obtain the digital signal corresponding to the original data of each of the chips; send the digital signal corresponding to the original data of each of the chips to the processor through a target communication protocol. The processor parses the protocol of the digital signal corresponding to the original data of each of the chips according to the data format of the target communication protocol to obtain the first monitoring data of each of the chips; determine the target operating mode of each of the chips according to the first monitoring data of each of the chips and the preset data mapping table; the preset data mapping table includes multiple second monitoring data of each of the chips and the first operating mode corresponding to each of the second monitoring data; the first operating mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; the target operating mode of each of the chips is used for the processor to perform optimization control on each of the chips according to the target operating mode of each of the chips; determine the fault location based on the target operating mode of each of the chips.

8. An intelligent data monitoring device, characterized in that, A processor applied to an intelligent data monitoring system; The intelligent data monitoring system includes: at least one power chip, at least one functional chip, sensors corresponding to each of the chips, an analog-to-digital converter, and the processor; the device includes: A parsing module, configured to perform protocol parsing on digital signals corresponding to the original data of each chip according to the data format of a target communication protocol, so as to obtain first monitoring data of each chip; the digital signals corresponding to the original data of each chip are obtained by performing data acquisition on the power supplies of each chip through sensors corresponding to each chip to obtain the original data of each chip, and then performing analog-to-digital conversion on the analog voltage signals corresponding to the original data of each chip, and the analog-to-digital conversion process is implemented by using analog-to-digital converters corresponding to each chip; the original data of each chip includes original current, original voltage, and temperature values; A monitoring module, configured to determine a target operating condition mode of each chip according to the first monitoring data of each chip and a preset data mapping table; the preset data mapping table includes a plurality of second monitoring data of each chip and a first operating condition mode corresponding to each second monitoring data; the first operating condition mode includes any one of the following: chip sleep, chip standby, chip normal operation, and chip damage; the target operating condition mode of each chip is used for the processor to perform optimization control on each chip according to the target operating condition mode of each chip; Based on the target operating condition mode of each chip, determine the fault location.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the intelligent data monitoring method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the intelligent data monitoring method according to any one of claims 1 to 7.

Images