High performance embedded information processing method and system

Abstract

The application relates to the technical field of information processing, and discloses a high-efficiency embedded information processing method and system, which comprises the following steps: analyzing key indexes of to-be-processed information, constructing index weights of the key indexes, determining information priorities of the to-be-processed information by using the key indexes and the index weights, calculating information processing efficiency of the information priorities and interrupt frequencies, selecting target priorities and target frequencies from the information priorities and the interrupt frequencies respectively, judging whether real-time priorities exist in the target priorities, performing first information processing on the to-be-processed information by using the target priorities, collecting information processing time lengths corresponding to first information processing results, analyzing next round processing time lengths in an embedded platform by using the information processing time lengths, respectively resetting the target priorities and the target frequencies, and completing second information processing of the embedded platform by using the reset priorities and the reset frequencies. The judgment process of whether to adjust the frequencies and the priorities can be interrupted.

Description

Technical Field

[0001] This invention relates to a high-performance embedded information processing method and system, belonging to the field of information processing technology. Background Technology

[0002] Today, embedded information mainly refers to information processed by embedded systems. An embedded system is a dedicated computer system that combines advanced computer technology, semiconductor technology, and electronic technology with specific applications to provide computing and control functions for specific tasks. These systems are usually embedded in target devices and have a series of characteristics that make them widely used in various industries and fields. When using embedded systems for data processing, the system can often enter an energy-saving mode by reducing the main frequency, thereby reducing the power consumption of data processing. In addition, embedded systems can also improve data processing efficiency, for example, by assigning high priority to critical data and increasing the frequency of interrupts, so that the embedded system can switch back and forth between data of different priorities at a high frequency, thereby performing high-frequency switching data processing between different data. The interrupt frequency refers to the number of times the embedded system interrupts per second. An interrupt means interrupting the currently running process and switching to process other processes.

[0003] Currently, frequency adjustment is mainly related to the CPU. When the CPU is detected to be idle, the frequency is reduced to put the system into power-saving mode, thereby reducing the power consumption of data processing. Existing technology proposes a scheme to predict the CPU's idle time, that is, to predict whether the CPU will be idle in the future, and to prepare for the frequency reduction based on the prediction result. However, this approach still has drawbacks. It requires continuous prediction and analysis of whether the CPU will be idle. This prediction process also causes some power consumption, and if the prediction algorithm used is complex, the power consumption will be even higher. In other words, during the dynamic frequency adjustment process, it is impossible to continuously judge whether to adjust the frequency. Secondly, existing technologies generally pre-set the priority division method. When the received data is detected to meet the corresponding characteristics, different priorities are assigned to the data. This priority generally cannot be dynamically adjusted. Even if dynamic priority adjustment can be achieved, it still requires continuous data analysis to decide whether to adjust the priority.

[0004] Therefore, the existing technology cannot interrupt the process of determining whether to adjust the frequency and priority. Summary of the Invention

[0005] This invention provides a high-performance embedded information processing method and system, the main purpose of which is to allow the process of determining whether to adjust frequency and priority to be interrupted.

[0006] To achieve the above objectives, the present invention provides a high-performance embedded information processing method, comprising:

[0007] The system receives information to be processed in an embedded platform, analyzes the key indicators of the information to be processed, constructs the indicator weights of the key indicators, uses the key indicators and indicator weights to determine the information priority of the information to be processed, and sets the interruption frequency of the information to be processed.

[0008] Calculate the information processing efficiency corresponding to the information priority and the interruption frequency, and use the information processing efficiency to select target priority and target frequency from the information priority and the interruption frequency respectively, and determine whether there is a real-time priority among the target priorities;

[0009] When there is no real-time priority in the target priority, the current frequency in the embedded platform is switched to the target frequency, and the information to be processed is processed by the target priority to obtain the first information processing result.

[0010] After performing first information processing on the information to be processed according to the target priority, the information processing time corresponding to the first information processing result is collected, the information processing time is used to analyze the next round of processing time in the embedded platform, and the next round of information is received in the embedded platform.

[0011] Collect the actual processing time of the next round of information under the target priority and the target frequency, and determine whether the actual processing time exceeds the processing time of the next round.

[0012] When the actual processing time exceeds the processing time of the next round, the target priority and the target frequency are reset respectively to obtain the reset priority and the reset frequency. The second information processing of the embedded platform is completed through the reset priority and the reset frequency to obtain the second information processing result.

[0013] The first information processing result and the second information processing result are used as the final information processing result in the embedded platform.

[0014] Optionally, the key indicators for analyzing the information to be processed include:

[0015] The importance level of the information to be processed is analyzed using priority markers in the information to be processed.

[0016] The time complexity of identifying the information to be processed;

[0017] The number of tools required to query the information to be processed;

[0018] The importance level, time complexity, and number of required tools are used as key indicators.

[0019] Optionally, the weights for constructing the key indicators include:

[0020] Query the number of indicators for the aforementioned key indicators;

[0021] Based on the number of indicators, the indicator weights of the key indicators are constructed using the following formula.

[0022] Optionally, determining the information priority of the information to be processed using the key indicators and the indicator weights includes:

[0023] The key indicators are dimensionless to obtain dimensionless indicators.

[0024] The dimensionless indicators are weighted and summed using the aforementioned indicator weights to obtain the weighted summation result.

[0025] Set the priority level of the information to be processed;

[0026] Match the weighted summation result with the priority level to query the information priority corresponding to the weighted summation result in the priority level.

[0027] Optionally, calculating the information processing performance corresponding to the information priority and the interruption frequency includes:

[0028] Calculate the information throughput corresponding to the information priority and the interruption frequency;

[0029] The information throughput is used as information processing efficiency.

[0030] Optionally, the step of performing first information processing on the information to be processed based on the target priority to obtain a first information processing result includes:

[0031] The target priority is used to determine the information processing order of the information to be processed;

[0032] According to the information processing sequence, the information to be processed is transmitted to the information processor in the embedded platform;

[0033] In the information processor, the information to be processed is subjected to first information processing to obtain a first information processing result.

[0034] Optionally, the information processing time corresponding to collecting the first information processing result includes:

[0035] Get the timer in the embedded platform;

[0036] When the first information processing of the information to be processed begins, the timer is controlled to start counting.

[0037] The timer is stopped when the first information processing of the information to be processed is completed.

[0038] The information processing time is collected from the start of the timer to the end of the timer.

[0039] Optionally, the step of using the information processing time to analyze the next round of processing time in the embedded platform includes:

[0040] Calculate the current round processing time corresponding to the information processing time;

[0041] Based on the information processing time and the current round processing time, the next round processing time in the embedded platform is calculated using the following formula:

[0042] T dp2 (k+1)=αT dp1 (k)+(1-α)T dp2 (k)

[0043] Among them, T dp2 (k+1) represents the processing time for the next round, T dp1 (k) represents the information processing time, T dp2 (k) represents the processing time of the current round, α represents the weight, and k represents the round in which the embedded platform processes information.

[0044] Optionally, resetting the target priority and the target frequency respectively to obtain the reset priority and reset frequency includes:

[0045] Receive follow-up information from the next round of information;

[0046] Analyze the information indicators of the subsequent information;

[0047] The target priority and the target frequency are reset by using the throughput corresponding to the information indicators and the subsequent information, respectively, to obtain the reset priority and the reset frequency.

[0048] To address the above problems, the present invention also provides a high-performance embedded information processing system, the system comprising:

[0049] The frequency setting module is used to receive information to be processed in the embedded platform, analyze the key indicators of the information to be processed, construct the indicator weights of the key indicators, determine the information priority of the information to be processed using the key indicators and the indicator weights, and set the interruption frequency of the information to be processed.

[0050] The priority determination module is used to calculate the information processing efficiency corresponding to the information priority and the interruption frequency, select target priority and target frequency from the information priority and the interruption frequency respectively using the information processing efficiency, and determine whether there is a real-time priority among the target priorities.

[0051] The first processing module is configured to, when there is no real-time priority in the target priority, switch the current frequency in the embedded platform to the target frequency, and then perform first information processing on the information to be processed through the target priority to obtain a first information processing result.

[0052] The information receiving module is used to collect the information processing time corresponding to the first information processing result after performing first information processing on the information to be processed according to the target priority, analyze the next round of processing time in the embedded platform using the information processing time, and receive the next round of information in the embedded platform.

[0053] The duration judgment module is used to collect the actual processing time of the next round of information under the target priority and the target frequency, and to determine whether the actual processing time exceeds the processing time of the next round.

[0054] The second processing module is used to reset the target priority and the target frequency respectively when the actual processing time exceeds the next round of processing time, to obtain the reset priority and the reset frequency, and to complete the second information processing of the embedded platform through the reset priority and the reset frequency to obtain the second information processing result.

[0055] An information processing module is used to take the first information processing result and the second information processing result as the final information processing result in the embedded platform.

[0056] Compared to the problems described in the background art, this embodiment of the invention analyzes the key indicators of the information to be processed to evaluate the processing priority of the information. Furthermore, this embodiment constructs indicator weights for the key indicators, assigning different weights to different key indicators to give them different levels of attention. This embodiment calculates the information processing efficiency corresponding to the information priority and the interruption frequency to analyze whether the embedded system can efficiently process the information to be processed in the following time period. It should be noted that at this time, the embedded system is not processing the information to be processed, but rather processing the necessary steps to process the information to be processed. To predict the cost, this embodiment of the invention further analyzes the next round of processing time in the embedded platform using the information processing time, and uses an algorithm to analyze the data processing time required for the data in the next fixed time period. Furthermore, this embodiment of the invention determines whether the actual processing time exceeds the next round of processing time. After initially calculating the next round of processing time using the algorithm, after processing each fixed time period of information, it only needs to compare the difference between the actual time and the analyzed time, without continuously calculating the next round of processing time using the algorithm. Only when the actual processing time exceeds the next round of processing time will the algorithm T be reused. dp2 (k+1)=αT dp1 (k)+(1-α)T dp2 (k) performs data calculation. Since calculating the processing time of the next round can facilitate the subsequent judgment on whether to adjust the frequency and priority, this step can be interrupted in the algorithm calculation process required to determine whether to adjust the frequency and priority, and instead use the comparison between the lengths to determine whether to adjust the frequency and priority. Attached Figure Description

[0057] Figure 1 This is a flowchart illustrating a high-performance embedded information processing method provided in an embodiment of the present invention.

[0058] Figure 2 This is a schematic diagram of a module for implementing the high-performance embedded information processing method according to an embodiment of the present invention.

[0059] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0060] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0061] This application provides a high-performance embedded information processing method. The executing entity of the high-performance embedded information processing method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the high-performance embedded information processing method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0062] Example 1:

[0063] Reference Figure 1 The diagram shown is a flowchart illustrating a high-performance embedded information processing method according to an embodiment of the present invention. In this embodiment, the high-performance embedded information processing method includes:

[0064] S1. Receive information to be processed in the embedded platform, analyze the key indicators of the information to be processed, construct the indicator weights of the key indicators, determine the information priority of the information to be processed using the key indicators and the indicator weights, and set the interruption frequency of the information to be processed.

[0065] In this embodiment of the invention, the embedded platform refers to a computer processor with an embedded system installed, and the information to be processed refers to data that needs to be processed by the embedded system. It should be noted that the information to be processed is data within a fixed time period.

[0066] Furthermore, embodiments of the present invention analyze key indicators of the information to be processed to evaluate the processing priority of the information to be processed based on the key indicators.

[0067] In one embodiment of the present invention, the analysis of key indicators of the information to be processed includes: analyzing the importance level of the information to be processed using priority markers in the information to be processed; identifying the time complexity of the information to be processed; querying the number of required tools for the information to be processed; and using the importance level, the time complexity, and the number of required tools as key indicators.

[0068] The priority flag refers to the flag information carried in the information to be processed that the computer processor hardware recognizes when setting data priorities in a conventional manner. For example, a bit identifier in a data frame specifically indicating priority. The importance level refers to the priority of the information to be processed that the computer processor hardware recognizes when setting data priorities in a conventional manner. The time complexity is a standard for measuring the running time of an algorithm. It describes the relationship between the algorithm's running time and the input data. Time complexity is usually represented using Big O notation, ignoring constant terms and lower-order terms in the function and retaining only the highest-order term. It should be noted that the information to be processed is represented by a code language on the user end, while it is represented by binary 0s and 1s on the computer processor end. Therefore, the time complexity corresponding to the information to be processed can be identified by obtaining the code (which is also the algorithm) corresponding to the information to be processed. The number of required tools refers to the number of hardware tools required by the embedded system to process the information to be processed, such as the number of times the CPU is used.

[0069] Furthermore, in this embodiment of the invention, by constructing the indicator weights of the key indicators, different weights are set for different key indicators, thereby assigning different levels of attention to different key indicators.

[0070] In one embodiment of the present invention, constructing the indicator weights of the key indicators includes: querying the number of key indicators; and constructing the indicator weights of the key indicators based on the number of indicators using the following formula:

[0071]

[0072] r i =random.choice(sequence),r i ≠r j

[0073] Where, r i This represents the weight of the i-th key metric, and `random.choice(sequence)` means randomly selecting an element from the sequence `sequence`. j This represents the indicator weight of the j-th key indicator, where j represents the index that is inconsistent with i, and n represents the number of indicators.

[0074] The number of indicators refers to the number of the three categories: importance level, time complexity, and number of required tools, i.e., the number of indicators is 3.

[0075] In one embodiment of the present invention, determining the information priority of the information to be processed using the key indicators and the indicator weights includes: performing dimensionless transformation on the key indicators to obtain dimensionless indicators; performing weighted summation on the dimensionless indicators using the indicator weights to obtain a weighted summation result; setting a priority level for the information to be processed; and matching the weighted summation result with the priority level to query the information priority corresponding to the weighted summation result within the priority level.

[0076] The priority level refers to the level corresponding to the pre-set weighted summation value. For example, the value corresponding to high priority is set to 80-100, the value corresponding to medium priority is set to 50-80, and the value corresponding to low priority is set to 0-50. High priority, medium priority, and low priority are priority levels, while 80-100, 50-80, and 0-50 are weighted summation values ​​of different sizes.

[0077] Optionally, the process of making the key indicators dimensionless to obtain dimensionless indicators refers to the process of normalizing the key indicators. It should be noted that the time complexity is usually represented by O(), such as O(1) or O(n). Therefore, when making the time complexity dimensionless, only the value inside the parentheses of O() is taken for normalization.

[0078] Furthermore, in this embodiment of the invention, the interrupt frequency refers to a frequency value randomly generated within the frequency range allowed by the embedded system.

[0079] S2. Calculate the information processing performance corresponding to the information priority and the interruption frequency, and use the information processing performance to select target priority and target frequency from the information priority and the interruption frequency respectively, and determine whether there is a real-time priority among the target priorities.

[0080] This invention analyzes whether the embedded system can efficiently process the information to be processed in the following time period by calculating the information processing efficiency corresponding to the information priority and the interruption frequency. It should be noted that the embedded system does not process the information to be processed at this time, but rather makes a prediction of the cost required to process the information to be processed.

[0081] In one embodiment of the present invention, calculating the information processing performance corresponding to the information priority and the interruption frequency includes: calculating the information throughput corresponding to the information priority and the interruption frequency using the following formula:

[0082]

[0083] Where B represents information throughput, and B1 represents the condition as follows: Information throughput at time, B2 represents the condition. Information throughput at time, T u T represents the information processing time for the u-th piece of information to be processed. v This represents the processing time for the v-th message (excluding the u-th message), f represents the interrupt frequency, u and v represent the message priority numbers from high to low, Z represents the set of integers, and Q represents the information processing time for the v-th message. u+v This represents the total number of data bits in the information to be processed, and floor() represents the floor function;

[0084] The information throughput is used as information processing efficiency.

[0085] Among them, T u T represents the information processing time for the u-th piece of information to be processed. v T represents the processing time of the v-th information (excluding the u-th information). u T v The time complexity of the information can be determined. For example, the value within the parentheses of O() mentioned above can be used as the information processing time. The u-th pending information refers to a continuous pending information initiated by the same user. It should be noted that the reciprocal of f is the time required for one interruption, and the time required for one interruption is the time from receiving the interruption request to responding to the request and processing the request. In this embodiment of the invention, receiving the interruption request is simplified to receiving the request for pending information. Secondly, the time contained in the reciprocal of f is simplified to the time for processing the data in the buffer. Since the u-th pending information is too large, the u-th pending information may be divided into multiple parts and passed into the buffer in sequence to wait for interruption processing. Therefore, the u-th pending information may require multiple reciprocals of f to complete the processing.

[0086] Optionally, the process of selecting the target priority and target frequency from the information priority and the interruption frequency using the information processing efficiency means that: among the large number of information priorities with different values ​​obtained by randomly generating index weights and the large number of interruption frequencies with different values ​​obtained by random generation, the information priority and interruption frequency with the highest information processing efficiency are selected as the target priority and target frequency. That is, the process of calculating the information processing efficiency is not calculated only once, but the corresponding information processing efficiency is calculated for different information priorities and interruption frequencies.

[0087] Furthermore, in this embodiment of the invention, the real-time priority refers to the highest priority that the embedded system needs to set aside all currently pending information to process in order to process the newly arrived information, such as aircraft control data.

[0088] S3. When there is no real-time priority in the target priority, the current frequency in the embedded platform is switched to the target frequency, and the information to be processed is processed by the target priority to obtain the first information processing result.

[0089] If there is no real-time priority in the target priority, the data corresponding to the real-time priority does not need to be considered. If there is a real-time priority in the target priority, the pending information corresponding to the real-time priority needs to be executed immediately. After processing, the current S3 step is entered.

[0090] In one embodiment of the present invention, the step of performing first information processing on the information to be processed by the target priority to obtain a first information processing result includes: determining the information processing order of the information to be processed using the target priority; transmitting the information to be processed to an information processor in an embedded platform according to the information processing order; and performing first information processing on the information to be processed in the information processor to obtain a first information processing result.

[0091] The information processor is not a single piece of hardware, but rather a collection of multiple hardware components that coordinate to perform information processing.

[0092] Optionally, the process of performing first information processing on the information to be processed in the information processor to obtain a first information processing result refers to the process of parsing, data operation, and process execution of the information to be processed.

[0093] S4. After performing first information processing on the information to be processed through the target priority, collect the information processing time corresponding to the first information processing result, use the information processing time to analyze the next round of processing time in the embedded platform, and receive the next round of information in the embedded platform.

[0094] In one embodiment of the present invention, the step of collecting the information processing duration corresponding to the first information processing result includes: acquiring a timer in an embedded platform; controlling the timer to start timing when the first information processing of the information to be processed begins; controlling the timer to stop timing when the first information processing of the information to be processed ends; and collecting the information processing duration from the start of timing to the end of timing.

[0095] Furthermore, in this embodiment of the invention, the processing time of the information is used to analyze the processing time of the next round in the embedded platform, so as to use an algorithm to analyze the data processing time required for the data in the next fixed period of time, wherein the duration of the next fixed period of time is consistent with the fixed duration of the aforementioned information to be processed.

[0096] In one embodiment of the present invention, the step of analyzing the next round of processing time in the embedded platform using the information processing time includes: calculating the current round of processing time corresponding to the information processing time using the following formula:

[0097] T dp2 (k)=αT dp1 (k-1)+(1-α)T dp2 (k-1), a∈(0.5,1)

[0098] Among them, T dp2 (k) represents the processing time of the current round, T dp1 (k-1) represents the actual duration of the previous round of processing of the information to be processed, T dp2 (k-1) represents the duration of the previous analysis of the information to be processed, α represents the weight, and k represents the number of rounds of information processing by the embedded platform;

[0099] Based on the information processing time and the current round processing time, the next round processing time in the embedded platform is calculated using the following formula:

[0100] T dp2 (k+1)=αT dp1 (k)+(1-α)T dp2 (k)

[0101] Among them, T dp2 (k+1) represents the processing time for the next round, T dp1 (k) represents the information processing time, T dp2 (k) represents the processing time of the current round, α represents the weight, and k represents the round in which the embedded platform processes information.

[0102] Furthermore, in this embodiment of the invention, the next round of information refers to a user request received by the embedded platform. This user request is similar to the aforementioned pending information, but it is located after the aforementioned pending information in terms of time. The next round of information is also information within a fixed duration, which is consistent with the fixed duration of the aforementioned pending information.

[0103] S5. Collect the actual processing time of the next round of information under the target priority and the target frequency, and determine whether the actual processing time exceeds the processing time of the next round.

[0104] In this embodiment of the invention, the actual processing time refers to the actual time required to process the next round of information, obtained by using a timer.

[0105] Furthermore, in this embodiment of the invention, by determining whether the actual processing time exceeds the processing time of the next round, after initially calculating the processing time of the next round using the algorithm, only the difference between the actual processing time and the analyzed processing time needs to be compared after processing each fixed-duration segment of information. This eliminates the need for continuously calculating the processing time of the next round using the algorithm. Only when the actual processing time exceeds the processing time of the next round will the algorithm T be reused. dp2 (k+1)=αT dp1 (k)+(1-α)T dp2 (k) performs data calculation. Since calculating the processing time of the next round can facilitate the subsequent judgment on whether to adjust the frequency and priority, this step can be interrupted in the algorithm calculation process required to determine whether to adjust the frequency and priority, and instead use the comparison between the lengths to determine whether to adjust the frequency and priority.

[0106] S6. When the actual processing time exceeds the processing time of the next round, the target priority and the target frequency are reset respectively to obtain the reset priority and the reset frequency. The second information processing of the embedded platform is completed through the reset priority and the reset frequency to obtain the second information processing result.

[0107] When the actual processing time exceeds the processing time of the next round, it indicates that the actual information processing speed of the embedded system has decreased, resulting in a decrease in information processing efficiency. At this time, it is necessary to adjust the target priority and target frequency.

[0108] In one embodiment of the present invention, resetting the target priority and the target frequency respectively to obtain a reset priority and a reset frequency includes: receiving subsequent information of the next round of information; analyzing the information indicators of the subsequent information; and resetting the target priority and the target frequency respectively through the information indicators and the throughput corresponding to the subsequent information to obtain a reset priority and a reset frequency.

[0109] It should be noted that the process of resetting the target priority and the target frequency to obtain the reset priority and reset frequency is similar to the principle of selecting the target priority and target frequency from S1 to S2 described above, and will not be elaborated further here.

[0110] S7. The first information processing result and the second information processing result are used as the final information processing result in the embedded platform.

[0111] Compared to the problems described in the background art, this embodiment of the invention analyzes the key indicators of the information to be processed to evaluate the processing priority of the information. Furthermore, this embodiment constructs indicator weights for the key indicators, assigning different weights to different key indicators to give them different levels of attention. This embodiment calculates the information processing efficiency corresponding to the information priority and the interruption frequency to analyze whether the embedded system can efficiently process the information to be processed in the following time period. It should be noted that at this time, the embedded system is not processing the information to be processed, but rather processing the necessary steps to process the information to be processed. To predict the cost, this embodiment of the invention further analyzes the next round of processing time in the embedded platform using the information processing time, and uses an algorithm to analyze the data processing time required for the data in the next fixed time period. Furthermore, this embodiment of the invention determines whether the actual processing time exceeds the next round of processing time. After initially calculating the next round of processing time using the algorithm, after processing each fixed time period of information, it only needs to compare the difference between the actual time and the analyzed time, without continuously calculating the next round of processing time using the algorithm. Only when the actual processing time exceeds the next round of processing time will the algorithm T be reused. dp2 (k+1)=αT dp1 (k)+(1-α)T dp2 (k) performs data calculation. Since calculating the processing time of the next round can facilitate the subsequent judgment on whether to adjust the frequency and priority, this step can be interrupted in the algorithm calculation process required to determine whether to adjust the frequency and priority, and instead use the comparison between the lengths to determine whether to adjust the frequency and priority.

[0112] Example 2:

[0113] like Figure 2 The diagram shown is a functional block diagram of a high-performance embedded information processing system according to the present invention.

[0114] The high-performance embedded information processing system 200 described in this invention can be installed in an electronic device. Depending on the functions implemented, the high-performance embedded information processing system may include a frequency setting module 201, a priority judgment module 202, a first processing module 203, an information receiving module 204, a duration judgment module 205, a second processing module 206, and an information processing module 207. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0115] In this embodiment of the invention, the functions of each module / unit are as follows:

[0116] The frequency setting module 201 is used to receive information to be processed in the embedded platform, analyze the key indicators of the information to be processed, construct the indicator weights of the key indicators, determine the information priority of the information to be processed using the key indicators and the indicator weights, and set the interruption frequency of the information to be processed.

[0117] The priority determination module 202 is used to calculate the information processing efficiency corresponding to the information priority and the interruption frequency, and use the information processing efficiency to select target priority and target frequency from the information priority and the interruption frequency respectively, and determine whether there is a real-time priority among the target priorities;

[0118] The first processing module 203 is used to, when there is no real-time priority in the target priority, switch the current frequency in the embedded platform to the target frequency, and then perform first information processing on the information to be processed through the target priority to obtain a first information processing result.

[0119] The information receiving module 204 is used to collect the information processing time corresponding to the first information processing result after performing first information processing on the information to be processed through the target priority, analyze the next round of processing time in the embedded platform using the information processing time, and receive the next round of information in the embedded platform.

[0120] The duration judgment module 205 is used to collect the actual processing time of the next round of information under the target priority and the target frequency, and to determine whether the actual processing time exceeds the processing time of the next round.

[0121] The second processing module 206 is used to reset the target priority and the target frequency respectively when the actual processing time exceeds the next round processing time, to obtain the reset priority and the reset frequency, and to complete the second information processing of the embedded platform through the reset priority and the reset frequency to obtain the second information processing result.

[0122] The information processing module 207 is used to take the first information processing result and the second information processing result as the final information processing result in the embedded platform.

[0123] In detail, the modules in the high-performance embedded information processing system 200 described in this embodiment of the invention employ the same methods as described above. Figure 1 The high-performance embedded information processing method described herein uses the same technical means and can produce the same technical effects, so it will not be elaborated here.

[0124] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0125] 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 it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A high-performance embedded information processing method, characterized in that, The method includes: The system receives information to be processed in an embedded platform, analyzes the key indicators of the information to be processed, constructs the indicator weights of the key indicators, uses the key indicators and indicator weights to determine the information priority of the information to be processed, and sets the interruption frequency of the information to be processed. Calculate the information processing efficiency corresponding to the information priority and the interruption frequency, and use the information processing efficiency to select target priority and target frequency from the information priority and the interruption frequency respectively, and determine whether there is a real-time priority among the target priorities; When there is no real-time priority in the target priority, the current frequency in the embedded platform is switched to the target frequency, and the information to be processed is processed by the target priority to obtain the first information processing result. After performing first information processing on the information to be processed according to the target priority, the information processing time corresponding to the first information processing result is collected, the information processing time is used to analyze the next round of processing time in the embedded platform, and the next round of information is received in the embedded platform. Collect the actual processing time of the next round of information under the target priority and the target frequency, and determine whether the actual processing time exceeds the processing time of the next round. When the actual processing time exceeds the processing time of the next round, the target priority and the target frequency are reset respectively to obtain the reset priority and the reset frequency. The second information processing of the embedded platform is completed through the reset priority and the reset frequency to obtain the second information processing result. The first information processing result and the second information processing result are used as the final information processing result in the embedded platform.

2. The high-performance embedded information processing method as described in claim 1, characterized in that, The key indicators for analyzing the information to be processed include: The importance level of the information to be processed is analyzed using priority markers in the information to be processed. The time complexity of identifying the information to be processed; The number of tools required to query the information to be processed; The importance level, time complexity, and number of required tools are used as key indicators.

3. The high-performance embedded information processing method as described in claim 1, characterized in that, The indicator weights for constructing the key indicators include: Query the number of indicators for the aforementioned key indicators; Based on the number of indicators, the indicator weights of the key indicators are constructed.

4. The high-performance embedded information processing method as described in claim 1, characterized in that, The step of determining the information priority of the information to be processed using the key indicators and the indicator weights includes: The key indicators are dimensionless to obtain dimensionless indicators. The dimensionless indicators are weighted and summed using the aforementioned indicator weights to obtain the weighted summation result. Set the priority level of the information to be processed; Match the weighted summation result with the priority level to query the information priority corresponding to the weighted summation result in the priority level.

5. The high-performance embedded information processing method as described in claim 1, characterized in that, The calculation of the information processing efficiency corresponding to the information priority and the interruption frequency includes: Calculate the information throughput corresponding to the information priority and the interruption frequency; The information throughput is used as information processing efficiency.

6. The high-performance embedded information processing method as described in claim 1, characterized in that, The step of performing first information processing on the information to be processed based on the target priority to obtain a first information processing result includes: The target priority is used to determine the information processing order of the information to be processed; According to the information processing sequence, the information to be processed is transmitted to the information processor in the embedded platform; In the information processor, the information to be processed is subjected to first information processing to obtain a first information processing result.

7. The high-performance embedded information processing method as described in claim 1, characterized in that, The information processing time corresponding to the collection of the first information processing result includes: Get the timer in the embedded platform; When the first information processing of the information to be processed begins, the timer is controlled to start counting. The timer is stopped when the first information processing of the information to be processed is completed. The information processing time is collected from the start of the timer to the end of the timer.

8. The high-performance embedded information processing method as described in claim 1, characterized in that, The step of analyzing the next round of processing time in the embedded platform using the information processing time includes: Calculate the current round processing time corresponding to the information processing time; Based on the information processing time and the current round processing time, the next round processing time in the embedded platform is calculated using the following formula: T dp2 (k+1)=αT dp1 (k)+(1-α)T dp2 (k) Among them, T dp2 (k+1) represents the processing time for the next round, T dp1 (k) represents the information processing time, T dp2 (k) represents the processing time of the current round, α represents the weight, and k represents the round in which the embedded platform processes information.

9. The high-performance embedded information processing method as described in claim 1, characterized in that, The step of resetting the target priority and the target frequency respectively to obtain the reset priority and reset frequency includes: Receive follow-up information from the next round of information; Analyze the information indicators of the subsequent information; The target priority and the target frequency are reset by using the throughput corresponding to the information indicators and the subsequent information, respectively, to obtain the reset priority and the reset frequency.

10. A high-performance embedded information processing system, characterized in that, The system includes: The frequency setting module is used to receive information to be processed in the embedded platform, analyze the key indicators of the information to be processed, construct the indicator weights of the key indicators, determine the information priority of the information to be processed using the key indicators and the indicator weights, and set the interruption frequency of the information to be processed. The priority determination module is used to calculate the information processing efficiency corresponding to the information priority and the interruption frequency, select target priority and target frequency from the information priority and the interruption frequency respectively using the information processing efficiency, and determine whether there is a real-time priority among the target priorities. The first processing module is configured to, when there is no real-time priority in the target priority, switch the current frequency in the embedded platform to the target frequency, and then perform first information processing on the information to be processed through the target priority to obtain a first information processing result. The information receiving module is used to collect the information processing time corresponding to the first information processing result after performing first information processing on the information to be processed according to the target priority, analyze the next round of processing time in the embedded platform using the information processing time, and receive the next round of information in the embedded platform. The duration judgment module is used to collect the actual processing time of the next round of information under the target priority and the target frequency, and to determine whether the actual processing time exceeds the processing time of the next round. The second processing module is used to reset the target priority and the target frequency respectively when the actual processing time exceeds the next round of processing time, to obtain the reset priority and the reset frequency, and to complete the second information processing of the embedded platform through the reset priority and the reset frequency to obtain the second information processing result. An information processing module is used to take the first information processing result and the second information processing result as the final information processing result in the embedded platform.

Images