Integrated circuit module performance monitoring method and device based on Internet of Things, equipment and medium
By acquiring the performance monitoring parameters of the integrated circuit module through the IoT sensing device, generating a fitting curve and performing a similarity comparison, the efficiency and accuracy issues of integrated circuit performance monitoring are solved, and convenient and efficient detection of the integrated circuit module is achieved.
Patent Information
- Application Number
- CN202510926618.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-07
- Publication Date
- 2025-10-17
AI Technical Summary
Existing integrated circuit performance monitoring technology has deficiencies in efficiency and accuracy, making it difficult to achieve remote, real-time, continuous monitoring and fault prediction of integrated circuits.
Through IoT sensor devices, multiple performance monitoring parameters of the integrated circuit module are obtained. The change characteristics of the performance sub-parameters are determined according to the hardware type, a fitting curve is generated, and the similarity is compared with the set performance reference curve to generate a similarity coefficient. The performance status of the integrated circuit is judged using the similarity threshold.
It improves the convenience and accuracy of integrated circuit module detection, can detect performance failures in a timely manner, and supports equipment optimization and fault prediction.
Smart Images
Figure CN120804731A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure relates to the technical field of Internet of Things, in particular, to an integrated circuit module performance monitoring method, device, equipment and medium based on Internet of Things. BACKGROUND
[0002] The application of Internet of Things in power distribution auxiliary monitoring and early warning is the inevitable result of the development of information communication technology to a certain stage, which can effectively integrate communication infrastructure resources and power system infrastructure resources, make information communication infrastructure resources serve the operation of power system, thereby improving the informatization level of power system, improving the utilization efficiency of existing power system infrastructure. At present, the application of Internet of Things technology in smart grid has involved all aspects of power generation, transmission, transformation, distribution and power utilization, and centralized integrated monitoring has greatly improved the operation and maintenance efficiency. As the core component of electronic equipment, the stability and reliability of integrated circuit performance are crucial to the operation of the entire electronic equipment. Integrated circuit performance monitoring can obtain its running state and performance data in real time, providing an important basis for equipment maintenance, optimization and fault prediction. Internet of Things technology can realize remote, real-time and continuous monitoring of integrated circuits, improve the efficiency and accuracy of monitoring, and through the Internet of Things platform, centralized management and analysis of integrated circuit performance data can be realized, providing strong support for equipment optimization and fault prediction. Internet of Things technology can also realize remote control of integrated circuits, making equipment maintenance and management more convenient and efficient. SUMMARY
[0003] The purpose of the present disclosure is to provide an integrated circuit module performance monitoring method, device, equipment and medium based on Internet of Things.
[0004] In order to achieve the above-mentioned purpose, the first aspect of the present disclosure provides an integrated circuit module performance monitoring method based on Internet of Things, which comprises: obtaining a plurality of performance monitoring parameters obtained by detecting the running state of the integrated circuit module within a set period range by an Internet of Things sensing device, each performance monitoring parameter comprising at least two performance sub-parameters of different dimensions; According to the set hardware type of the integrated circuit module, the parameter variation characteristics of each performance sub-parameter in different dimensions in each performance monitoring parameter are determined, and the values of performance sub-parameters in different dimensions within the set period range are fitted according to the parameter variation characteristics and the plurality of performance monitoring parameters, to generate parameter fitting curves of each performance sub-parameter in different dimensions, and the parameter fitting curves corresponding to each performance sub-parameter are fused to generate target performance monitoring curves corresponding to the plurality of performance monitoring parameters in at least two different dimensions; The target performance monitoring curve is compared with the set performance reference curve corresponding to the integrated circuit module to determine the similarity between the two, and a similarity coefficient is generated; According to the size relationship between the similarity coefficient and the first similarity threshold and the second similarity threshold, a performance monitoring result of the integrated circuit module is generated.
[0005] Optionally, the comparison of the target performance monitoring curve with the set performance reference curve corresponding to the integrated circuit module to determine the similarity between the two and generate a similarity coefficient comprises: The target performance monitoring curve and the set performance reference curve are subjected to discrete cosine transform to represent the image features of the target performance monitoring curve and the performance reference curve in the frequency domain, to obtain a first cosine frequency spectrum coefficient corresponding to the target performance monitoring curve and a second cosine frequency spectrum coefficient corresponding to the set performance reference curve; According to the number of dimensions of each performance sub-parameter in the plurality of performance monitoring parameters, the number of frequency spectrum coefficient points corresponding to the cosine frequency spectrum coefficient in the similarity comparison process is determined; The similarity coefficient is calculated and determined according to the first cosine frequency spectrum coefficient, the second cosine frequency spectrum coefficient and the number of frequency spectrum coefficient points.
[0006] Optionally, the discrete cosine transform of the target performance monitoring curve and the set performance reference curve to represent the image features of the target performance monitoring curve and the performance reference curve in the frequency domain to obtain the first cosine frequency spectrum coefficient corresponding to the target performance monitoring curve comprises: A set curve segmentation window corresponding to the set performance reference curve is obtained; The target performance monitoring curve and the set performance reference curve are subjected to windowed cutting processing according to the set curve segmentation window to generate a plurality of performance monitoring sub-curves corresponding to the target performance monitoring curve and a plurality of set performance monitoring sub-curves corresponding to the set performance reference curve; According to the plurality of performance monitoring sub-curves, a first cosine frequency spectrum sub-coefficient point number and a first cosine frequency spectrum sub-coefficient of a first performance monitoring sub-curve are determined, the first performance monitoring sub-curve being any performance monitoring sub-curve in the plurality of performance monitoring sub-curves; According to the plurality of first cosine frequency spectrum sub-coefficient point numbers and the plurality of first cosine frequency spectrum sub-coefficients corresponding to the plurality of performance monitoring sub-curves respectively, the first cosine frequency spectrum coefficient is determined.
[0007] Optionally, the calculation and determination of the similarity coefficient according to the first cosine frequency spectrum coefficient, the second cosine frequency spectrum coefficient and the number of frequency spectrum coefficient points comprises: According to the spectrum coefficient points, the product of the first cosine spectrum coefficient and the second cosine spectrum coefficient at each spectrum coefficient point is superimposed to obtain a sum value; According to the spectrum coefficient points, the second cosine spectrum coefficient is taken to the second power at each spectrum coefficient point, and the obtained power value is superimposed and then taken to the square root to obtain a second value. According to the spectrum coefficient points, the second cosine spectrum coefficient is taken to the second power at each spectrum coefficient point, and the obtained power value is superimposed and then taken to the square root to obtain a second value. The first value and the second value are multiplied to generate a third value, and the sum value and the third value are divided to obtain the similarity coefficient.
[0008] Optionally, the performance monitoring result of the integrated circuit module is generated according to the size relationship between the similarity coefficient and a first similarity threshold and a second similarity threshold, including: In a case where it is determined that the similarity coefficient is greater than the first similarity threshold, a first performance monitoring result is generated, the first performance monitoring result is used to indicate that the performance state of the integrated circuit module is good, and the first similarity threshold is greater than the second similarity threshold; In a case where it is determined that the similarity coefficient is less than or equal to the first similarity threshold and the similarity coefficient is greater than the second similarity threshold, a second performance monitoring result is generated, the second performance monitoring result is used to indicate degradation of the integrated circuit module; In a case where it is determined that the similarity coefficient is less than or equal to the second similarity threshold, a third performance monitoring result is generated, and the third performance monitoring result is used to indicate that the integrated circuit module has a performance failure.
[0009] Optionally, the method further includes: Obtaining a first reference threshold corresponding to the first similarity threshold and a second reference threshold corresponding to the second similarity threshold; According to the coefficient interval value where the similarity coefficient is located, a first smooth prediction coefficient corresponding to the first similarity threshold and a second smooth prediction coefficient corresponding to the second similarity threshold are determined based on exponential smoothing prediction; The first similarity threshold is generated according to the first smooth prediction coefficient and the first reference threshold; The second similarity threshold is generated according to the second smooth prediction coefficient and the second reference threshold.
[0010] Optionally, the values of the performance sub-parameters in different dimensions within the set period are fitted according to the parameter variation characteristics and the plurality of performance monitoring parameters, and parameter fitting curves of each performance sub-parameter in different dimensions are generated, including: According to the parameter variation characteristics, a reference polynomial function in different dimensions is determined; From the plurality of performance monitoring parameters, a plurality of performance sub-parameters corresponding to each dimension are determined; According to the plurality of performance sub-parameters, the reference polynomial function is solved to generate the parameter fitting curve.
[0011] According to a second aspect of the embodiments of the present disclosure, an integrated circuit module performance monitoring device based on Internet of Things is provided, and the device includes: An acquisition module is configured to acquire a plurality of performance monitoring parameters obtained by detecting the running state of the integrated circuit module within a set period by an Internet of Things sensing device, and each performance monitoring parameter includes performance sub-parameters in at least two different dimensions; A determination module is configured to determine the parameter variation characteristics of each performance sub-parameter in different dimensions in each performance monitoring parameter according to a set hardware type of the integrated circuit module, and fit the values of the performance sub-parameters in different dimensions within the set period according to the parameter variation characteristics and the plurality of performance monitoring parameters, to generate parameter fitting curves of each performance sub-parameter in different dimensions. The parameter fitting curves corresponding to each performance sub-parameter are fused to generate a target performance monitoring curve corresponding to the plurality of performance monitoring parameters in at least two different dimensions; A generation module is configured to compare the target performance monitoring curve with a set performance reference curve corresponding to the integrated circuit module, determine the similarity between the two, and generate a similarity coefficient; An execution module is configured to generate a performance monitoring result of the integrated circuit module according to the size relationship between the similarity coefficient and a first similarity threshold and a second similarity threshold.
[0012] According to a third aspect of the embodiments of the present disclosure, a computer readable storage medium having a computer program stored thereon is provided, and the program is executed by a processor to implement the steps of the method in any one of the first aspect of the present disclosure.
[0013] According to a fourth aspect of the embodiments of the present disclosure, an electronic device is provided, including: A memory having a computer program stored thereon; A processor configured to execute the computer program in the memory to implement the steps of the method in any one of the first aspect of the present disclosure.
[0014] By the technical solution, the multiple performance monitoring parameters obtained by detecting the running state of the integrated circuit module by the Internet of Things sensing device within the set period range are acquired, and each performance monitoring parameter includes at least two performance sub-parameters in different dimensions; according to the set hardware type of the integrated circuit module, the parameter change characteristics of each performance sub-parameter in different dimensions in each performance monitoring parameter are determined, and the values of the performance sub-parameters in different dimensions within the set period range are fitted according to the parameter change characteristics and the multiple performance monitoring parameters, to generate a parameter fitting curve of each performance sub-parameter in different dimensions, the parameter fitting curves corresponding to each performance sub-parameter are fused, and a target performance monitoring curve corresponding to the multiple performance monitoring parameters in at least two different dimensions is generated; the target performance monitoring curve is compared with the set performance reference curve corresponding to the integrated circuit module, the similarity between the two is determined, and a similarity coefficient is generated; according to the size relationship between the similarity coefficient and the first similarity threshold and the second similarity threshold, a performance monitoring result of the integrated circuit module is generated. Thus, whether the current detected integrated circuit module fails is determined based on the comparison of the parameter curves, and the convenience and accuracy of the integrated circuit module detection are improved based on the Internet of Things communication.
[0015] Other features and advantages of the present disclosure will be described in detail in the following detailed description section. BRIEF DESCRIPTION OF DRAWINGS
[0016] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, which together with the following detailed description, serve to explain the present disclosure. In the drawings: Figure 1 FIG. 1 is a flowchart of an integrated circuit module performance monitoring method based on the Internet of Things according to an embodiment of the present disclosure.
[0017] Figure 2 FIG. 2 is an integrated circuit module performance monitoring device based on the Internet of Things according to an embodiment of the present disclosure.
[0018] Figure 3 FIG. 3 is a block diagram of an electronic device 300 according to an exemplary embodiment. DETAILED DESCRIPTION
[0019] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure.
[0020] Figure 1 FIG. 1 is a flowchart of an integrated circuit module performance monitoring method based on the Internet of Things according to an embodiment of the present disclosure. As shown in FIG. 1, the method is performed by a server, and the method comprises: Figure 1 obtaining multiple performance monitoring parameters obtained by detecting the running state of the integrated circuit module by the Internet of Things sensing device within the set period range; In step S11, a plurality of performance monitoring parameters of the integrated circuit module are obtained by the Internet of Things sensor device within a set period, each of the performance monitoring parameters including at least two performance sub-parameters of different dimensions.
[0021] In step S12, according to the set hardware type of the integrated circuit module, parameter variation characteristics of each performance sub-parameter in different dimensions in each performance monitoring parameter are determined, and the values of the performance sub-parameters in different dimensions within the set period are fitted according to the parameter variation characteristics and the plurality of performance monitoring parameters, to generate parameter fitting curves of each performance sub-parameter in different dimensions, and the parameter fitting curves of each performance sub-parameter are fused to generate target performance monitoring curves of the plurality of performance monitoring parameters in at least two different dimensions. In step S13, the target performance monitoring curves are compared with the set performance reference curves corresponding to the integrated circuit module to determine the similarity therebetween, and a similarity coefficient is generated. In step S14, according to the size relationship between the similarity coefficient and the first similarity threshold and the second similarity threshold, a performance monitoring result of the integrated circuit module is generated.
[0022] Optionally, in some embodiments, the step of comparing the target performance monitoring curves with the set performance reference curves corresponding to the integrated circuit module to determine the similarity therebetween, and generating a similarity coefficient, includes: Discrete cosine transform is performed on the target performance monitoring curves and the set performance reference curves to represent the image features of the target performance monitoring curves and the performance reference curves in the frequency domain, to obtain first cosine frequency spectrum coefficients corresponding to the target performance monitoring curves and second cosine frequency spectrum coefficients corresponding to the set performance reference curves. According to the number of dimensions of each performance sub-parameter in the plurality of performance monitoring parameters, the number of frequency spectrum coefficient points corresponding to the cosine frequency spectrum coefficients in the similarity comparison process is determined. According to the first cosine frequency spectrum coefficients, the second cosine frequency spectrum coefficients, and the number of frequency spectrum coefficient points, the similarity coefficient is calculated and determined.
[0023] Optionally, in some embodiments, the step of performing discrete cosine transform on the target performance monitoring curves and the set performance reference curves to represent the image features of the target performance monitoring curves and the performance reference curves in the frequency domain, to obtain first cosine frequency spectrum coefficients corresponding to the target performance monitoring curves, includes: A set curve segmentation window corresponding to the set performance reference curves is obtained. Performing windowing and cutting processing on the target performance monitoring curve and the set performance reference curve according to the set curve cutting window to generate a plurality of performance monitoring sub-curves corresponding to the target performance monitoring curve and a plurality of set performance monitoring sub-curves corresponding to the set performance reference curve; Determining, based on the multiple performance monitoring sub-curves, the number of first cosine spectrum sub-coefficient points and the first cosine spectrum sub-coefficient of a first performance monitoring sub-curve, where the first performance monitoring sub-curve is any one of the multiple performance monitoring sub-curves; The first cosine spectrum coefficient is determined according to the plurality of first cosine spectrum sub-coefficient point numbers and the plurality of first cosine spectrum sub-coefficients respectively corresponding to the plurality of performance monitoring sub-curves.
[0024] Optionally, in some embodiments, the above step of calculating and determining the similarity coefficient based on the first cosine spectrum coefficient, the second cosine spectrum coefficient, and the number of spectrum coefficient points includes: According to the number of spectrum coefficient points, superimposing the products of the first cosine spectrum coefficient and the second cosine spectrum coefficient at each spectrum coefficient point to obtain a sum value; According to the number of spectrum coefficient points, the first cosine spectrum coefficient is taken as the cosine spectrum coefficient at each spectrum coefficient point, raised to the second power, and then the obtained power values are superimposed and the square root is taken to obtain the first value; According to the number of spectrum coefficient points, the second cosine spectrum coefficient is taken as the cosine spectrum coefficient at each spectrum coefficient point, raised to the second power, and then the obtained power values are superimposed and the square root is taken to obtain a second value; The first value is multiplied by the second value to generate a third value, and the sum is divided by the third value to obtain the similarity coefficient.
[0025] Optionally, in some embodiments, the step of generating the performance monitoring result of the integrated circuit module according to the magnitude relationship between the similarity coefficient and the first similarity threshold and the second similarity threshold includes: If it is determined that the similarity coefficient is greater than the first similarity threshold, generating a first performance monitoring result, the first performance monitoring result being used to indicate that the performance status of the integrated circuit module is good, and the first similarity threshold is greater than the second similarity threshold; If it is determined that the similarity coefficient is less than or equal to the first similarity threshold and the similarity coefficient is greater than the second similarity threshold, generating a second performance monitoring result, the second performance monitoring result being used to indicate degradation of the integrated circuit module; If it is determined that the similarity coefficient is less than or equal to the second similarity threshold, a third performance monitoring result is generated, where the third performance monitoring result is used to indicate that a performance fault occurs in the integrated circuit module.
[0026] Optionally, before step S14, the method further comprises: obtaining a first reference threshold corresponding to the first similarity threshold, and a second reference threshold corresponding to the second similarity threshold; determining, according to the coefficient interval value where the similarity coefficient is located, a first smooth prediction coefficient corresponding to the first similarity threshold and a second smooth prediction coefficient corresponding to the second similarity threshold based on exponential smoothing prediction; generating the first similarity threshold according to the first smooth prediction coefficient and the first reference threshold; generating the second similarity threshold according to the second smooth prediction coefficient and the second reference threshold.
[0027] Optionally, in some embodiments, the step of fitting the values of the performance sub-parameters in different dimensions within the set period range according to the parameter variation characteristics and the plurality of performance monitoring parameters to generate the parameter fitting curves of each performance sub-parameter in different dimensions comprises: determining a reference polynomial function in different dimensions according to the parameter variation characteristics; determining a plurality of performance sub-parameters corresponding to each dimension from the plurality of performance monitoring parameters; solving the reference polynomial function according to the plurality of performance sub-parameters to generate the parameter fitting curves.
[0028] Through the above technical solution, a plurality of performance monitoring parameters obtained by detecting the running state of the integrated circuit module within a set period range by the Internet of Things sensing device are obtained, and each performance monitoring parameter includes at least two performance sub-parameters in different dimensions; according to the set hardware type of the integrated circuit module, the parameter variation characteristics of each performance sub-parameter in different dimensions in each performance monitoring parameter are determined, and the values of the performance sub-parameters in different dimensions within the set period range are fitted according to the parameter variation characteristics and the plurality of performance monitoring parameters to generate the parameter fitting curves of each performance sub-parameter in different dimensions. The parameter fitting curves corresponding to each performance sub-parameter are fused to generate the target performance monitoring curve corresponding to the plurality of performance monitoring parameters in at least two different dimensions. The target performance monitoring curve is compared with the set performance reference curve corresponding to the integrated circuit module to determine the similarity therebetween, and a similarity coefficient is generated. According to the size relationship between the similarity coefficient and the first similarity threshold and the second similarity threshold, the performance monitoring result of the integrated circuit module is generated. Thus, whether the current detected integrated circuit module has failed is determined based on parameter curve comparison, and the convenience and accuracy of integrated circuit module detection are improved based on Internet of Things communication.
[0029] Figure 2The device is a kind of integrated circuit module performance monitoring device based on Internet of Things according to the embodiment of the present disclosure. Figure 2 As shown in the figure, the device 100 comprises: The acquisition module 110 is configured to acquire a plurality of performance monitoring parameters obtained by detecting the running state of the integrated circuit module by the Internet of Things sensing device within a set period range, wherein each performance monitoring parameter comprises at least two performance sub-parameters in different dimensions; The determination module 120 is configured to determine the parameter variation characteristics of each performance sub-parameter in different dimensions in each performance monitoring parameter according to the set hardware type of the integrated circuit module, and fit the values of performance sub-parameters in different dimensions within the set period range according to the parameter variation characteristics and the plurality of performance monitoring parameters, to generate the parameter fitting curve of each performance sub-parameter in different dimensions, and fuse the parameter fitting curves corresponding to each performance sub-parameter to generate the target performance monitoring curve corresponding to the plurality of performance monitoring parameters in at least two different dimensions; The generation module 130 is configured to compare the target performance monitoring curve with the set performance reference curve corresponding to the integrated circuit module, determine the similarity between the two, and generate a similarity coefficient; The execution module 140 is configured to generate the performance monitoring result of the integrated circuit module according to the size relationship between the similarity coefficient and the first similarity threshold and the second similarity threshold.
[0030] Optionally, in some embodiments, the generation module 130 comprises: The transformation sub-module is configured to perform discrete cosine transformation on the target performance monitoring curve and the set performance reference curve to represent the image features of the target performance monitoring curve and the performance reference curve in frequency domain, to obtain the first cosine frequency spectrum coefficient corresponding to the target performance monitoring curve and the second cosine frequency spectrum coefficient corresponding to the set performance reference curve; The determination sub-module is configured to determine the number of frequency spectrum coefficient points corresponding to the cosine frequency spectrum coefficient in the similarity comparison process according to the number of dimensions of each performance sub-parameter in the plurality of performance monitoring parameters; The calculation sub-module is configured to calculate the similarity coefficient according to the first cosine frequency spectrum coefficient, the second cosine frequency spectrum coefficient and the number of frequency spectrum coefficient points.
[0031] Optionally, in some embodiments, the transformation sub-module comprises: The acquisition unit is configured to acquire a set curve segmentation window corresponding to the set performance reference curve; The generating unit is configured to perform windowing cutting processing on the target performance monitoring curve and the set performance reference curve according to the set curve to generate a plurality of performance monitoring sub-curves corresponding to the target performance monitoring curve and a plurality of set performance monitoring sub-curves corresponding to the set performance reference curve. The first determining unit is configured to determine a first cosine spectral sub-coefficient point number and a first cosine spectral sub-coefficient of a first performance monitoring sub-curve according to the plurality of performance monitoring sub-curves, the first performance monitoring sub-curve being any one of the plurality of performance monitoring sub-curves. The second determining unit is configured to determine the first cosine spectral coefficient according to a plurality of first cosine spectral sub-coefficient point numbers and a plurality of first cosine spectral sub-coefficients corresponding to the plurality of performance monitoring sub-curves respectively.
[0032] Optionally, in some embodiments, the calculating sub-module is configured to: According to the spectral coefficient point number, the product of the first cosine spectral coefficient and the second cosine spectral coefficient at each spectral coefficient point number is superimposed to obtain a sum value. According to the spectral coefficient point number, the first cosine spectral coefficient is taken to the second power at each spectral coefficient point number, and then the obtained power value is superimposed to take the square root to obtain a first value. According to the spectral coefficient point number, the second cosine spectral coefficient is taken to the second power at each spectral coefficient point number, and then the obtained power value is superimposed to take the square root to obtain a second value. The first value and the second value are multiplied to generate a third value, and then the sum value and the third value are divided to obtain the similarity coefficient.
[0033] Optionally, in some embodiments, the execution module is configured to: In a case where it is determined that the similarity coefficient is greater than the first similarity threshold value, a first performance monitoring result is generated, the first performance monitoring result being used to indicate that the performance state of the integrated circuit module is good, and the first similarity threshold value being greater than the second similarity threshold value. In a case where it is determined that the similarity coefficient is less than or equal to the first similarity threshold value and greater than the second similarity threshold value, a second performance monitoring result is generated, the second performance monitoring result being used to indicate that the integrated circuit module is degraded. In a case where it is determined that the similarity coefficient is less than or equal to the second similarity threshold value, a third performance monitoring result is generated, the third performance monitoring result being used to indicate that the integrated circuit module has a performance fault.
[0034] Optionally, in some embodiments, the apparatus 100 comprises an obtaining module, configured to: obtain a first reference threshold corresponding to the first similarity threshold, and a second reference threshold corresponding to the second similarity threshold; determine, according to the coefficient interval value where the similarity coefficient is located, a first smooth prediction coefficient corresponding to the first similarity threshold and a second smooth prediction coefficient corresponding to the second similarity threshold based on exponential smoothing prediction; generate the first similarity threshold according to the first smooth prediction coefficient and the first reference threshold; generate the second similarity threshold according to the second smooth prediction coefficient and the second reference threshold.
[0035] Optionally, in some embodiments, the determining module is configured to: determine a reference polynomial function under different dimensions according to the parameter variation characteristics; determine a plurality of performance sub-parameters corresponding to each dimension from the plurality of performance monitoring parameters; solve the reference polynomial function according to the plurality of performance sub-parameters to generate the parameter fitting curve.
[0036] Through the above technical solution, a plurality of performance monitoring parameters obtained by detecting the running state of the integrated circuit module within a set period range by the Internet of Things sensing device are obtained, each performance monitoring parameter including at least two performance sub-parameters in different dimensions; according to the set hardware type of the integrated circuit module, the parameter variation characteristics of each performance sub-parameter in different dimensions in each performance monitoring parameter are determined, and the values of the performance sub-parameters in different dimensions within the set period range are fitted according to the parameter variation characteristics and the plurality of performance monitoring parameters to generate a parameter fitting curve of each performance sub-parameter in different dimensions. The parameter fitting curves corresponding to each performance sub-parameter are fused to generate a target performance monitoring curve corresponding to the plurality of performance monitoring parameters in at least two different dimensions. The target performance monitoring curve is compared with the set performance reference curve corresponding to the integrated circuit module to determine the similarity therebetween to generate a similarity coefficient. The performance monitoring result of the integrated circuit module is generated according to the size relationship between the similarity coefficient and the first similarity threshold and the second similarity threshold. Thus, whether the current detected integrated circuit module has failed is determined based on parameter curve comparison, and the convenience and accuracy of integrated circuit module detection are improved based on Internet of Things communication.
[0037] As to the apparatus in the above embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments of the method, and will not be described in detail here.
[0038] Figure 3is a block diagram of an electronic device 300 according to an exemplary embodiment. As shown, the electronic device 300 can include a processor 301, a memory 302. The electronic device 300 can also include one or more of a multimedia component 303, an input / output (I / O) interface 304, and a communication component 305. Figure 3
[0039] The processor 301 is configured to control overall operations of the electronic device 300 to complete all or part of the steps of the above-mentioned method for monitoring performance of an integrated circuit module based on Internet of Things. The memory 302 is configured to store various types of data to support operations of the electronic device 300, which can include, for example, instructions for operating any application or method on the electronic device 300, and application-related data such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 303 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 302 or transmitted through the communication component 305. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 304 provides an interface between the processor 301 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 305 is configured to perform wired or wireless communication between the electronic device 300 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 305 can include a Wi-Fi module, a Bluetooth module, and an NFC module.
[0040] In an exemplary embodiment, the electronic device 300 can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic elements for executing the above-mentioned method for monitoring performance of an integrated circuit module based on Internet of Things.
[0041] In another exemplary embodiment, a computer readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-mentioned method for monitoring performance of an integrated circuit module based on Internet of Things. For example, the computer readable storage medium can be the above-mentioned memory 302 including program instructions, which can be executed by the processor 301 of the electronic device 300 to complete the above-mentioned method for monitoring performance of an integrated circuit module based on Internet of Things.
[0042] In another exemplary embodiment, a computer program product is also provided, which contains a computer program capable of being executed by a processor, and when the computer program is executed by the processor, the steps of the above-mentioned method for monitoring performance of an integrated circuit module based on Internet of Things are implemented.
[0043] In another exemplary embodiment, a computer program product is also provided, which contains a computer program capable of being executed by a processor, and when the computer program is executed by the processor, the steps of the above-mentioned method for monitoring performance of an integrated circuit module based on Internet of Things are implemented.
[0044] The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details in the above-described embodiments. Within the technical concept scope of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
[0045] In addition, it should be noted that each specific technical feature described in the above-described specific embodiments can be combined in any appropriate manner without contradiction.
[0046] Furthermore, the various embodiments of the present disclosure can be arbitrarily combined with each other unless they contradict each other, and it should be understood that the same should be construed as being included in the disclosure of the present disclosure.
Claims
1. A method for monitoring integrated circuit module performance based on the Internet of Things, characterized in that: The method comprises: Acquire multiple performance monitoring parameters obtained by detecting the operating status of the integrated circuit module by an IoT sensor device within a set period, where each performance monitoring parameter includes at least two performance sub-parameters in different dimensions; Determining, based on the set hardware type of the integrated circuit module, parameter change characteristics of each performance sub-parameter in different dimensions of each performance monitoring parameter, and fitting the values of the performance sub-parameters in different dimensions within the set period range based on the parameter change characteristics and the multiple performance monitoring parameters to generate parameter fitting curves for each performance sub-parameter in different dimensions, and fusing the parameter fitting curves corresponding to each performance sub-parameter to generate target performance monitoring curves corresponding to the multiple performance monitoring parameters in at least two different dimensions; Comparing the target performance monitoring curve with a set performance reference curve corresponding to the integrated circuit module, determining a similarity between the two, and generating a similarity coefficient; A performance monitoring result of the integrated circuit module is generated according to a magnitude relationship between the similarity coefficient and the first similarity threshold and the second similarity threshold.
2. The method for monitoring integrated circuit module performance based on the Internet of Things according to claim 1, characterized in that: The comparing the target performance monitoring curve with the set performance reference curve corresponding to the integrated circuit module, determining the similarity between the two, and generating a similarity coefficient includes: Performing a discrete cosine transform on the target performance monitoring curve and the set performance reference curve to represent the image features of the target performance monitoring curve and the performance reference curve in the frequency domain, thereby obtaining a first cosine spectrum coefficient corresponding to the target performance monitoring curve and a second cosine spectrum coefficient corresponding to the set performance reference curve; Determining the number of spectrum coefficient points corresponding to the cosine spectrum coefficient in the similarity comparison process according to the number of dimensions of each performance sub-parameter in the multiple performance monitoring parameters; The similarity coefficient is calculated and determined according to the first cosine spectrum coefficient, the second cosine spectrum coefficient and the number of spectrum coefficient points.
3. The method for monitoring integrated circuit module performance based on the Internet of Things according to claim 2, wherein: The performing of discrete cosine transform on the target performance monitoring curve and the set performance reference curve to represent the image features of the target performance monitoring curve and the performance reference curve in the frequency domain to obtain a first cosine spectrum coefficient corresponding to the target performance monitoring curve includes: Obtaining a set curve segmentation window corresponding to the set performance reference curve; Performing windowing and cutting processing on the target performance monitoring curve and the set performance reference curve according to the set curve segmentation window to generate a plurality of performance monitoring sub-curves corresponding to the target performance monitoring curve and a plurality of set performance monitoring sub-curves corresponding to the set performance reference curve; Determining, according to the multiple performance monitoring sub-curves, the number of first cosine spectrum sub-coefficient points and the first cosine spectrum sub-coefficient of a first performance monitoring sub-curve, where the first performance monitoring sub-curve is any one of the multiple performance monitoring sub-curves; The first cosine spectrum coefficient is determined according to the plurality of first cosine spectrum sub-coefficient point numbers and the plurality of first cosine spectrum sub-coefficients respectively corresponding to the plurality of performance monitoring sub-curves.
4. The method for monitoring integrated circuit module performance based on the Internet of Things according to claim 3, characterized in that: The calculating and determining the similarity coefficient according to the first cosine spectrum coefficient, the second cosine spectrum coefficient, and the number of spectrum coefficient points includes: According to the number of spectrum coefficient points, superimposing products of the first cosine spectrum coefficient and the second cosine spectrum coefficient at each spectrum coefficient point to obtain a sum value; According to the number of spectrum coefficient points, taking the first cosine spectrum coefficient and raising it to the second power of the cosine spectrum coefficient at each spectrum coefficient point, and then superimposing the obtained power values and taking the square root to obtain a first value; According to the number of spectrum coefficient points, taking the second cosine spectrum coefficient at each spectrum coefficient point and raising it to the second power, then superimposing the obtained power values and taking the square root to obtain a second value; The first value is multiplied by the second value to generate a third value, and the sum is divided by the third value to obtain the similarity coefficient.
5. The method for monitoring integrated circuit module performance based on the Internet of Things according to any one of claims 1 to 4, characterized in that: Generating the performance monitoring result of the integrated circuit module according to the magnitude relationship between the similarity coefficient and the first similarity threshold and the second similarity threshold includes: If it is determined that the similarity coefficient is greater than the first similarity threshold, generating a first performance monitoring result, the first performance monitoring result being used to indicate that the performance status of the integrated circuit module is good, and the first similarity threshold is greater than the second similarity threshold; generating a second performance monitoring result when it is determined that the similarity coefficient is less than or equal to the first similarity threshold and the similarity coefficient is greater than the second similarity threshold, wherein the second performance monitoring result is used to indicate degradation of the integrated circuit module; In a case where it is determined that the similarity coefficient is less than or equal to the second similarity threshold, a third performance monitoring result is generated, where the third performance monitoring result is used to indicate that a performance fault occurs in the integrated circuit module.
6. The method for monitoring integrated circuit module performance based on the Internet of Things according to claim 5, characterized in that: The method further comprises: Obtaining a first reference threshold corresponding to the first similarity threshold and a second reference threshold corresponding to the second similarity threshold; Determine, based on exponential smoothing prediction and according to the coefficient interval value of the similarity coefficient, a first smoothed prediction coefficient corresponding to the first similarity threshold and a second smoothed prediction coefficient corresponding to the second similarity threshold; generating the first similarity threshold according to the first smoothed prediction coefficient and the first reference threshold; The second similarity threshold is generated according to the second smoothed prediction coefficient and the second reference threshold.
7. The method for monitoring integrated circuit module performance based on the Internet of Things according to claim 1, wherein: The step of fitting the values of the performance sub-parameters in different dimensions within the set period range according to the parameter change characteristics and the multiple performance monitoring parameters to generate parameter fitting curves of the performance sub-parameters in different dimensions includes: Determining reference polynomial functions in different dimensions according to the parameter variation characteristics; Determining, from the multiple performance monitoring parameters, multiple performance sub-parameters corresponding to each dimension; The reference polynomial function is solved according to the multiple performance sub-parameters to generate the parameter fitting curve.
8. An integrated circuit module performance monitoring device based on the Internet of Things, characterized in that: The device comprises: an acquisition module, configured to acquire a plurality of performance monitoring parameters obtained by detecting the operating status of the integrated circuit module by an IoT sensor device within a set period, wherein each performance monitoring parameter includes at least two performance sub-parameters of different dimensions; a determination module, configured to determine, based on a set hardware type of the integrated circuit module, parameter variation characteristics of each performance sub-parameter in different dimensions of each performance monitoring parameter, and to fit, based on the parameter variation characteristics and the multiple performance monitoring parameters, the values of the performance sub-parameters in different dimensions within the set period range to generate parameter fitting curves for each performance sub-parameter in different dimensions, and to fuse the parameter fitting curves corresponding to the respective performance sub-parameters to generate target performance monitoring curves corresponding to the multiple performance monitoring parameters in at least two different dimensions; a generating module, configured to compare the target performance monitoring curve with a set performance reference curve corresponding to the integrated circuit module, determine a similarity between the two, and generate a similarity coefficient; An execution module is configured to generate a performance monitoring result of the integrated circuit module according to a magnitude relationship between the similarity coefficient and the first similarity threshold and the second similarity threshold.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.