A mini computer performance optimization method and system based on dynamic control

Abstract

The present invention discloses a minicomputer performance optimization method and system based on dynamic regulation, which specifically relates to the field of dynamic regulation, including S1: dividing time feature text, S2: obtaining key text, S3: preprocessing key text, S4: analyzing key text, S5: comprehensive analysis, S6: optimizing performance, S7: human-computer interaction. Through the division of time feature text, a first performance key text and a second performance key text are obtained, and the key text is preprocessed to obtain keyword groups corresponding to the key texts, so as to obtain a first performance evaluation value and a second performance evaluation value through a minicomputer performance intelligent analysis model; based on the first performance keyword group and the second performance keyword group, a comprehensive performance text output value is obtained, and a comprehensive performance evaluation analysis model is constructed to obtain a comprehensive performance evaluation value, so that in the minicomputer optimization process, different optimization effects can be achieved according to the comprehensive performance evaluation value.

Description

Technical Field

[0001] The present invention relates to the field of dynamic control technology, and more specifically, to a mini computer performance optimization method and system based on dynamic control. Background Art

[0002] With the advancement of science and technology and the popularization of digital life, computers have become an indispensable part of daily life and work. Mini computers meet users' needs for portability and space utilization due to their small size, light weight, portability and relatively high performance. With the popularization of mini computers and the increase in demand for use, people's requirements for computer performance are also constantly increasing. Therefore, a mini computer performance optimization method is needed to improve the performance of mini computers. This optimization method can improve the operating efficiency of mini computers and improve the user experience.

[0003] The existing mini computer optimization method mainly includes the following steps, including a monitoring step, a system optimization management step and a feedback step. The monitoring step is responsible for real-time monitoring of the running status of the mini computer, including CPU usage, memory usage, hard disk read and write speed, etc.; the system optimization management step adjusts the power plan through the control panel and optimizes unnecessary background tasks; the feedback step feeds back the optimization results to the user, so that the user can understand the performance status and optimization effect of the current system.

[0004] However, there are still some shortcomings in its actual use. For example, although the system optimization management steps of the traditional mini computer optimization method optimize the power plan and background tasks, due to the small size and heat dissipation limitations of the mini computer, the single power and background optimization cannot meet the mini computer performance and user needs. It is necessary to conduct a more dimensional analysis of the mini computer in order to achieve a specific method of mini computer optimization. Therefore, a dynamically controlled optimization method is needed to dynamically adjust the mini computer performance analysis. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a mini computer performance optimization method and system based on dynamic control, and solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] S1: Divide time feature text: set the user's usage time on the user information terminal as the starting time, set the user's computer usage time as the optimization area, and divide the optimization area into various time feature texts by equal time division;

[0008] S2: Obtain key text: Select the first performance key text based on the time feature text, and obtain the second performance key text, where the second performance key text is the key text after the first performance key text is selected;

[0009] S3: Preprocessing key text: preprocessing the selected first performance key text, the preprocessing operation is used to obtain a first performance key word group of the first performance key text; preprocessing the obtained second performance key text, the preprocessing operation is used to obtain a second performance key word group corresponding to the second performance key text;

[0010] S4: analyzing key texts: analyzing the key texts preprocessed in S3, obtaining a mini computer performance intelligent analysis model, and obtaining a first performance evaluation value corresponding to the first performance key text and a second performance evaluation value corresponding to the second performance key text according to the mini computer performance intelligent analysis model through the first performance keyword group and the second performance keyword group;

[0011] S5: Comprehensive analysis: based on the first performance keyword group and the second performance keyword group, obtain a comprehensive performance text output value, and obtain a comprehensive performance evaluation value of the comprehensive performance text output value according to the mini computer performance intelligent analysis model;

[0012] S6: Optimize performance: Determine the performance level of the mini computer based on the comprehensive performance evaluation value, and optimize the determination result in real time;

[0013] S7: Human-computer interaction: Based on the judgment results and optimization of S6, information is output to the user information terminal in a preset summary manner.

[0014] Preferably, the optimization area is composed of a system operation database, a preset analysis database, a system central processing unit and a user information terminal. The system operation database includes all data texts for mini computer performance optimization and collects information texts output in each step in real time. The preset analysis database stores preset data, including the correspondence between analysis points and the mini computer performance intelligent analysis model, preset comprehensive performance evaluation values ​​and preset summary methods. The system central processing module is used to control the information text instructions output by each step. The user information terminal is an information output device for receiving mini computer performance optimization, including a small display window embedded in the host. The equal time division of each time feature text selects an appropriate division time precision according to actual needs, including every hour, every minute, every half minute, every second and every half second.

[0015] Preferably, the step of obtaining the key text includes obtaining the first performance key text and obtaining the second performance key text, and the method for selecting the first performance key text is as follows:

[0016] A1: Based on each time feature text divided into equal time periods, data is collected for each time feature text. The mini computer network data collection unit is used to collect network data of the mini computer, including network bandwidth, end-to-end delay, and transmission packet loss rate;

[0017] A2: The network data collected by the mini computer network data collection unit is integrated by the first performance key text integration unit to obtain the first performance key text;

[0018] A3: transmitting the first performance key text integrated in A2 to the system analysis database through the first performance key text output unit;

[0019] The second performance key text is the key text selected after the first performance key text is selected. The second performance key text is obtained as follows:

[0020] B1: Collect storage data of the mini computer based on the first performance key text, including storage capacity, storage bandwidth, and memory bandwidth;

[0021] B2: Integrate the collected storage data through the second performance key text integration unit to obtain the second performance key text;

[0022] B3: The second performance key text integrated in B2 is transmitted to the system analysis database through the second performance key text output unit.

[0023] Preferably, the mini computer performance intelligent analysis model specifically includes:

[0024] According to the first performance keyword group, a classification operation is performed on the first performance key text to obtain the analysis points corresponding to the first performance key text, and the analysis points corresponding to the first performance key text are the first target knowledge field corresponding to the first performance key text, and the first target knowledge field includes the background resource occupancy analysis field, the transmission response analysis field, and the system transmission volume analysis field; according to the second performance keyword group, a classification operation is performed on the second performance key text to obtain the analysis points corresponding to the second performance key text, and the analysis points corresponding to the second performance key text are the second target knowledge field corresponding to the second performance key text, and the second target knowledge field includes the data storage analysis field, the power load analysis field, and the multi-task processing analysis field; in the preset analysis database, a mini computer performance intelligent analysis model corresponding to the analysis points is obtained, and the preset analysis database is used to save the correspondence between the analysis points and the mini computer performance intelligent analysis model.

[0025] Preferably, the method of obtaining the mini computer performance intelligent analysis model, before obtaining the first performance evaluation value corresponding to the first performance key text through the first performance keyword group, constructing the mini computer performance intelligent analysis model, specifically includes: obtaining an analysis data set corresponding to the first target knowledge field and the second target knowledge field; according to the analysis data set, obtaining the target knowledge graph corresponding to the first target knowledge field and the second target knowledge field; according to the target knowledge graph, constructing the mini computer performance intelligent analysis model.

[0026] Preferably, the acquisition of analysis data sets corresponding to the first target knowledge field and the second target knowledge field specifically includes: based on the division of time feature text, acquiring the analysis data set through data collection methods, the data collection methods include crawler programs, router monitoring, and listening to response messages; the analysis data sets include background resource occupancy analysis data sets, transmission response analysis data sets, system transmission volume analysis data sets, data storage analysis data sets, power load analysis data sets, and multi-task processing analysis data sets.

[0027] Preferably, S5 obtains a comprehensive performance text output value based on the first performance keyword group and the second performance keyword group. The method for obtaining the comprehensive performance text output value is as follows:

[0028] C1: Obtain a first performance keyword in the first performance keyword group, and obtain a second performance keyword in the second performance keyword group, wherein the first performance keyword is any keyword in the first performance keyword group, and the second performance keyword is any keyword in the second performance keyword group;

[0029] C2: Calculate the rationality value of the first performance keyword and the second performance keyword;

[0030] C3: Determine whether the rationality value is greater than the preset rationality value;

[0031] C4: if the rationality value is greater than a preset rationality value, the first performance keyword and the second performance keyword are used as the comprehensive performance text output value in the first performance keyword group and the second performance keyword group;

[0032] The comprehensive performance evaluation value is based on the mini computer performance intelligent analysis model, imports the first performance evaluation value and the second performance evaluation value, and constructs a comprehensive performance evaluation analysis model, and its specific analysis formula is: 1 ×Y 1 +u 2 ×Y 2 , where Y represents the comprehensive performance evaluation value, Y 1 represents the first performance evaluation value, Y 2 represents the second performance evaluation value, u 1 and u 2They respectively represent the proportional coefficients corresponding to different evaluation values.

[0033] Preferably, the judgment result of S6 is graded by comparing the comprehensive performance evaluation value with a preset comprehensive performance evaluation value, and the preset comprehensive performance evaluation value is obtained through a preset analysis database, including a minimum preset comprehensive performance evaluation value and a maximum preset comprehensive performance evaluation value, which are respectively denoted as Y min and Y max , the level determination includes level 1, level 2 and level 3. If Y<Y min , indicating that the comprehensive performance evaluation value is less than the minimum preset comprehensive performance evaluation value, the level is judged as level 3, at this time the performance is low and the power consumption is high, the mini computer will be dynamically adjusted to silent mode; if Y min ≤Y≤Y max , indicating that the comprehensive performance evaluation value is greater than the minimum preset comprehensive performance evaluation value and less than the maximum preset comprehensive performance evaluation value, then the level is determined to be level 2. At this time, the performance and power consumption are moderate, and the mini computer will be dynamically adjusted to the balanced mode; if Y>Y max , indicating that the comprehensive performance evaluation value is greater than the maximum preset comprehensive performance evaluation value, the level is determined to be level 1, at this time the performance is higher and the power consumption is lower, the mini computer will be dynamically adjusted to overclocking mode.

[0034] The present invention also provides a mini computer performance optimization system based on dynamic regulation, which is applied to the above-mentioned mini computer performance optimization method based on dynamic regulation, comprising:

[0035] Time feature text division module: the user's usage time on the user information terminal is set as the starting time, the user's computer usage time is set as the optimization area, and the optimization area is divided into various time feature texts by equal time division;

[0036] Key text acquisition module: selects the first performance key text based on the time feature text, and obtains the second performance key text, where the second performance key text is the key text after the first performance key text is selected;

[0037] Key text preprocessing module: preprocessing the selected first performance key text, the preprocessing operation is used to obtain the first performance key word group of the first performance key text; preprocessing the obtained second performance key text, the preprocessing operation is used to obtain the second performance key word group corresponding to the second performance key text;

[0038] Key text analysis module: obtains a mini computer performance intelligent analysis model, and obtains a first performance evaluation value corresponding to the first performance key text and a second performance evaluation value corresponding to the second performance key text according to the mini computer performance intelligent analysis model through the first performance keyword group and the second performance keyword group;

[0039] Comprehensive analysis module: based on the first performance keyword group and the second performance keyword group, obtain a comprehensive performance text output value, and according to the mini computer performance intelligent analysis model, obtain a comprehensive performance evaluation value of the comprehensive performance text output value;

[0040] Performance optimization module: determines the performance level of the mini computer based on the comprehensive performance evaluation value, and optimizes the determination results in real time;

[0041] Human-computer interaction module: Based on the judgment results and optimization, information is output to the user information terminal in a preset summary method;

[0042] The system operation database includes all data texts for mini computer performance optimization, and collects information texts output from each step in real time. The preset analysis database stores preset data, including the correspondence between analysis points and the mini computer performance intelligent analysis model, preset comprehensive performance evaluation values ​​and preset summary methods. The system central processing module is used to control the information text instructions output from each step.

[0043] Technical effects and advantages of the present invention:

[0044] 1. The present invention divides the time feature text to perform detailed and real-time analysis on the use of the mini computer, thereby improving the accuracy of the mini computer performance analysis; based on the division of the time feature text, the first performance key text and the second performance key text are obtained, and the key text is preprocessed to obtain the keyword group corresponding to the key text, so as to obtain the first performance evaluation value corresponding to the first performance key text and the second performance evaluation value corresponding to the second performance key text through the mini computer performance intelligent analysis model; based on the first performance keyword group and the second performance keyword group, the comprehensive performance text output value is obtained, and the first performance evaluation value and the second performance evaluation value are imported to construct a comprehensive performance evaluation analysis model to obtain a comprehensive performance evaluation value, so that the mini computer performance is more accurate and representative, and then in the mini computer optimization process, different optimization effects can be achieved according to the comprehensive performance evaluation value;

[0045] 2. By judging the performance level of the mini computer, the power consumption mode of the product under different performance conditions is actively adjusted, including three modes: silent, balanced, and overclocked. The silent mode is usually used for low-load tasks such as daily office, web browsing or video playback. The balanced mode is suitable for most daily tasks, including document editing, image processing, light games, etc. The overclocking mode can fully release the product performance and meet the needs of high-end games. The user experience is further improved through the conversion of the three modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flow chart of the system operation of the present invention.

[0047] Figure 2 A flow chart is selected for the first performance key text of the present invention.

[0048] Figure 3 A flow chart for obtaining the comprehensive performance text output value of the present invention.

[0049] Figure 4 It is a schematic diagram of the overall structure of the system of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] As attached Figure 1 A method and system for minicomputer performance optimization based on dynamic regulation is shown, and the flow chart mainly includes the following steps: S1 to S7.

[0052] S1: Divide time feature text: set the user's usage time on the user information terminal as the starting time, set the user's computer usage time as the optimization area, and divide the optimization area into various time feature texts by equal time division.

[0053] In this embodiment, it should be specifically explained that the optimization area is composed of a system operation database, a preset analysis database, a system central processing unit and a user information terminal. The system operation database includes all data texts for mini computer performance optimization, and collects information texts output in each step in real time. The preset analysis database stores preset data, including the correspondence between analysis points and the mini computer performance intelligent analysis model, preset comprehensive performance evaluation values ​​and preset summary methods. The system central processing module is used to control the information text instructions output by each step. The user information terminal is an information output device for receiving mini computer performance optimization, including a small display window embedded in the host. The equal time division of each time feature text selects the appropriate division time accuracy according to actual needs, including every hour, every minute, every half minute, every second and every half second.

[0054] S2: Obtain key text: Select the first performance key text based on the time feature text, and obtain the second performance key text, where the second performance key text is the key text after the first performance key text is selected.

[0055] In this embodiment, it should be specifically explained that the step of obtaining the key text includes obtaining the first performance key text and obtaining the second performance key text. The method for selecting the first performance key text is as follows:

[0056] A1: Based on each time feature text divided into equal time periods, data is collected for each time feature text. The mini computer network data collection unit is used to collect network data of the mini computer, including network bandwidth, end-to-end delay, and transmission packet loss rate;

[0057] A2: The network data collected by the mini computer network data collection unit is integrated by the first performance key text integration unit to obtain the first performance key text;

[0058] A3: transmitting the first performance key text integrated in A2 to the system analysis database through the first performance key text output unit;

[0059] The second performance key text is the key text selected after the first performance key text is selected. The second performance key text is obtained as follows:

[0060] B1: Collect storage data of the mini computer based on the first performance key text, including storage capacity, storage bandwidth, and memory bandwidth;

[0061] B2: Integrate the collected storage data through the second performance key text integration unit to obtain the second performance key text;

[0062] B3: The second performance key text integrated in B2 is transmitted to the system analysis database through the second performance key text output unit.

[0063] S3: Preprocess key text: preprocess the selected first performance key text, the preprocessing operation is used to obtain the first performance key word group of the first performance key text; preprocess the obtained second performance key text, the preprocessing operation is used to obtain the second performance key word group corresponding to the second performance key text.

[0064] S4: Analyze key text: Analyze the key text preprocessed by S3 to obtain a mini computer performance intelligent analysis model, and obtain a first performance evaluation value corresponding to the first performance key text and a second performance evaluation value corresponding to the second performance key text through the first performance keyword group and the second performance keyword group according to the mini computer performance intelligent analysis model.

[0065] In this embodiment, it is necessary to specifically explain the minicomputer performance intelligent analysis model, which specifically includes:

[0066] According to the first performance keyword group, a classification operation is performed on the first performance key text to obtain analysis points corresponding to the first performance key text, where the analysis points corresponding to the first performance key text are first target knowledge fields corresponding to the first performance key text, where the first target knowledge fields include background resource occupancy analysis fields, transmission response analysis fields, and system transmission volume analysis fields;

[0067] According to the second performance keyword phrase, a classification operation is performed on the second performance key text to obtain analysis points corresponding to the second performance key text, the analysis points corresponding to the second performance key text are second target knowledge fields corresponding to the second performance key text, and the second target knowledge fields include data storage analysis fields, power load analysis fields, and multi-task processing analysis fields;

[0068] In the preset analysis database, the mini computer performance intelligent analysis model corresponding to the analysis points is obtained, and the preset analysis database is used to store the corresponding relationship between the analysis points and the mini computer performance intelligent analysis model.

[0069] Furthermore, before obtaining a first performance evaluation value corresponding to a first performance key text through a first performance keyword group, the mini computer performance intelligent analysis model is constructed, specifically including: obtaining an analysis data set corresponding to a first target knowledge field and a second target knowledge field; obtaining a target knowledge graph corresponding to the first target knowledge field and the second target knowledge field based on the analysis data set; and constructing a mini computer performance intelligent analysis model based on the target knowledge graph; obtaining an analysis data set corresponding to the first target knowledge field and the second target knowledge field specifically includes: obtaining an analysis data set through a data collection method based on the division of time feature texts, and the data collection method includes a crawler program, router monitoring, and listening to response messages; the analysis data set includes a background resource occupancy analysis data set, a transmission response analysis data set, a system transmission volume analysis data set, a data storage analysis data set, a power load analysis data set, and a multi-tasking analysis data set.

[0070] S5: Comprehensive analysis: Based on the first performance keyword group and the second performance keyword group, a comprehensive performance text output value is obtained, and according to the mini computer performance intelligent analysis model, a comprehensive performance evaluation value of the comprehensive performance text output value is obtained.

[0071] In this embodiment, it is necessary to specifically explain that based on the first performance keyword group and the second performance keyword group, a comprehensive performance text output value is obtained, and a method for obtaining the comprehensive performance text output value is as follows:

[0072] C1: Obtain a first performance keyword in the first performance keyword group, and obtain a second performance keyword in the second performance keyword group, wherein the first performance keyword is any keyword in the first performance keyword group, and the second performance keyword is any keyword in the second performance keyword group;

[0073] C2: Calculate the rationality value of the first performance keyword and the second performance keyword;

[0074] C3: Determine whether the rationality value is greater than the preset rationality value;

[0075] C4: if the rationality value is greater than a preset rationality value, the first performance keyword and the second performance keyword are used as the comprehensive performance text output value in the first performance keyword group and the second performance keyword group;

[0076] Furthermore, the comprehensive performance evaluation value is based on the mini computer performance intelligent analysis model, and the first performance evaluation value and the second performance evaluation value are imported to construct a comprehensive performance evaluation analysis model, and its specific analysis formula is: Y=u 1 ×Y 1 +u 2 ×Y 2 , where Y represents the comprehensive performance evaluation value, Y 1 represents the first performance evaluation value, Y 2 represents the second performance evaluation value, u 1 and u 2 They respectively represent the proportional coefficients corresponding to different evaluation values.

[0077] S6: Optimize performance: The performance of the mini computer is graded based on the comprehensive performance evaluation value, and the results are optimized in real time.

[0078] In this embodiment, it should be specifically explained that the judgment result is graded by comparing the comprehensive performance evaluation value with the preset comprehensive performance evaluation value, and the preset comprehensive performance evaluation value is obtained through the preset analysis database, including the minimum preset comprehensive performance evaluation value and the maximum preset comprehensive performance evaluation value, which are respectively denoted as Y min and Y max , the level determination includes level 1, level 2 and level 3. If Y<Y min , indicating that the comprehensive performance evaluation value is less than the minimum preset comprehensive performance evaluation value, the level is determined to be level three, and the mini computer will be dynamically adjusted to silent mode. In silent mode, the power consumption wall of the mini computer is set at a lower level to limit the power consumption and heat generation of core components such as the CPU and GPU. This mode is usually used for low-load tasks such as daily office work, web browsing or video playback to reduce noise. At this time, the fan speed will be reduced to reduce noise, and the system performance will be reduced accordingly to maintain low power consumption and temperature; if Y min ≤Y≤Ymax , indicating that the comprehensive performance evaluation value is greater than the minimum preset comprehensive performance evaluation value and less than the maximum preset comprehensive performance evaluation value, the level is determined to be level 2, and the mini computer will be dynamically adjusted to balanced mode. In balanced mode, the power consumption wall is set at a moderate level to balance performance and power consumption. This mode is suitable for most daily tasks, including document editing, image processing, light games, etc. At this time, the system performance is moderate, neither too much power consumption nor too much noise; if Y>Y max , indicating that the comprehensive performance evaluation value is greater than the maximum preset comprehensive performance evaluation value, the level is determined to be level 1, and the mini computer will be dynamically adjusted to overclocking mode. In overclocking mode, the core components such as the CPU and GPU are allowed to run at a higher frequency by increasing the power consumption wall. This mode is usually used for tasks that require high performance, such as high-end games, 3D rendering, video editing, etc. At this time, the system performance will be significantly improved, but the power consumption and heat generation will also increase accordingly.

[0079] S7: Human-computer interaction: Based on the judgment results and optimization of S6, information is output to the user information terminal in a preset summary manner.

[0080] In this embodiment, it should be specifically explained that the preset summary method includes any one of a report summary and a chart summary. When determining the preset summary method, it is necessary to select the actual suitability based on the performance changes and the preset summary method. After using the mini computer, the user determines whether there is any unoptimized situation in the optimization area through the summary content. If there is any unoptimized situation, a warning will be issued and the user will perform maintenance according to his or her own needs. The summary content includes the comprehensive performance evaluation value, grade assessment and dynamic control mode of the optimization area.

[0081] As attached Figure 2 The mini computer performance optimization system based on dynamic control shown in the figure also includes:

[0082] Time feature text division module: the user's usage time on the user information terminal is set as the starting time, the user's computer usage time is set as the optimization area, and the optimization area is divided into various time feature texts by equal time division;

[0083] Key text acquisition module: selects the first performance key text based on the time feature text, and obtains the second performance key text, where the second performance key text is the key text after the first performance key text is selected;

[0084] Key text preprocessing module: preprocessing the selected first performance key text, the preprocessing operation is used to obtain the first performance key word group of the first performance key text; preprocessing the obtained second performance key text, the preprocessing operation is used to obtain the second performance key word group corresponding to the second performance key text;

[0085] Key text analysis module: obtains a mini computer performance intelligent analysis model, and obtains a first performance evaluation value corresponding to the first performance key text and a second performance evaluation value corresponding to the second performance key text according to the mini computer performance intelligent analysis model through the first performance keyword group and the second performance keyword group;

[0086] Comprehensive analysis module: based on the first performance keyword group and the second performance keyword group, obtain a comprehensive performance text output value, and according to the mini computer performance intelligent analysis model, obtain a comprehensive performance evaluation value of the comprehensive performance text output value;

[0087] Performance optimization module: determines the performance level of the mini computer based on the comprehensive performance evaluation value, and optimizes the determination results in real time;

[0088] Human-computer interaction module: outputs information to the user information terminal based on the judgment results and optimization of the performance optimization module;

[0089] The system operation database includes all data texts for mini computer performance optimization, and collects information texts output from each step in real time. The preset analysis database stores preset data, including the correspondence between analysis points and the mini computer performance intelligent analysis model, preset comprehensive performance evaluation values ​​and preset summary methods. The system central processing module is used to control the information text instructions output from each step.

[0090] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0091] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A mini computer performance optimization method based on dynamic control, characterized in that: include: S1: Divide time feature text: set the user's usage time on the user information terminal as the starting time, set the user's computer usage time as the optimization area, and divide the optimization area into various time feature texts by equal time division; S2: Obtain key text: Select the first performance key text based on the time feature text, and obtain the second performance key text, where the second performance key text is the key text after the first performance key text is selected; S2 includes obtaining the first performance key text and the second performance key text. The method for selecting the first performance key text is as follows: A1: Based on each time feature text divided into equal time periods, data is collected for each time feature text. The mini computer network data collection unit is used to collect network data of the mini computer, including network bandwidth, end-to-end delay, and transmission packet loss rate; A2: The network data collected by the mini computer network data collection unit is integrated by the first performance key text integration unit to obtain the first performance key text; A3: transmitting the first performance key text integrated in A2 to the system analysis database through the first performance key text output unit; The second performance key text is the key text selected after the first performance key text is selected. The second performance key text is obtained as follows: B1: Collect storage data of the mini computer based on the first performance key text, including storage capacity, storage bandwidth, and memory bandwidth; B2: Integrate the collected storage data through the second performance key text integration unit to obtain the second performance key text; B3: transmitting the second performance key text integrated in B2 to the system analysis database through the second performance key text output unit; S3: Preprocessing the key text: preprocessing the selected first performance key text, the preprocessing operation is used to obtain a first performance keyword group of the first performance key text; Preprocessing the acquired second performance key text, wherein the preprocessing operation is used to obtain a second performance key word group corresponding to the second performance key text; S4: analyzing key texts: analyzing the key texts preprocessed in S3, obtaining a mini computer performance intelligent analysis model, and obtaining a first performance evaluation value corresponding to the first performance key text and a second performance evaluation value corresponding to the second performance key text according to the mini computer performance intelligent analysis model through the first performance keyword group and the second performance keyword group; The mini computer performance intelligent analysis model specifically includes: According to the first performance keyword group, a classification operation is performed on the first performance key text to obtain analysis points corresponding to the first performance key text, where the analysis points corresponding to the first performance key text are first target knowledge fields corresponding to the first performance key text, where the first target knowledge fields include background resource occupancy analysis fields, transmission response analysis fields, and system transmission volume analysis fields; According to the second performance keyword phrase, a classification operation is performed on the second performance key text to obtain analysis points corresponding to the second performance key text, the analysis points corresponding to the second performance key text are second target knowledge fields corresponding to the second performance key text, and the second target knowledge fields include data storage analysis fields, power load analysis fields, and multi-task processing analysis fields; Obtaining a mini computer performance intelligent analysis model corresponding to the analysis key points in a preset analysis database, wherein the preset analysis database is used to store a corresponding relationship between the analysis key points and the mini computer performance intelligent analysis model; S5: Comprehensive analysis: based on the first performance keyword group and the second performance keyword group, obtain a comprehensive performance text output value, and obtain a comprehensive performance evaluation value of the comprehensive performance text output value according to the mini computer performance intelligent analysis model; S6: Optimize performance: Determine the performance level of the mini computer based on the comprehensive performance evaluation value, and optimize the determination result in real time; S7: Human-computer interaction: Based on the judgment results and optimization of S6, information is output to the user information terminal in a preset summary manner.

2. A method for optimizing minicomputer performance based on dynamic control according to claim 1, characterized in that: The optimization area is composed of a system operation database, a preset analysis database, a system central processing unit and a user information terminal. The system operation database includes all data texts for mini computer performance optimization and collects information texts output in each step in real time. The preset analysis database stores preset data, including the correspondence between analysis points and the mini computer performance intelligent analysis model, preset comprehensive performance evaluation values ​​and preset summary methods. The system central processing module is used to control the information text instructions output by each step. The user information terminal is an information output device for receiving mini computer performance optimization, including a small display window embedded in the host. The equal time division of each time feature text selects the appropriate division time accuracy according to actual needs, including every hour, every minute, every half minute, every second and every half second.

3. The method for optimizing the performance of a minicomputer based on dynamic control according to claim 1, characterized in that: The step of obtaining the mini computer performance intelligent analysis model and constructing the mini computer performance intelligent analysis model before obtaining the first performance evaluation value corresponding to the first performance key text through the first performance keyword group specifically includes: Acquire analysis data sets corresponding to the first target knowledge domain and the second target knowledge domain; According to the analysis data set, obtaining a target knowledge graph corresponding to the first target knowledge field and the second target knowledge field; Based on the target knowledge graph, a mini computer performance intelligent analysis model is constructed.

4. A method for optimizing minicomputer performance based on dynamic control according to claim 3, characterized in that: The step of obtaining the analysis data sets corresponding to the first target knowledge field and the second target knowledge field specifically includes: Based on the division of time feature text, analysis data sets are obtained through data collection methods, which include crawler programs, router monitoring, and listening to response messages; analysis data sets include background resource occupancy analysis data sets, transmission response analysis data sets, system transmission volume analysis data sets, data storage analysis data sets, power load analysis data sets, and multi-task processing analysis data sets.

5. The method for optimizing the performance of a minicomputer based on dynamic control according to claim 1, characterized in that: S5 obtains a comprehensive performance text output value based on the first performance keyword group and the second performance keyword group. The method for obtaining the comprehensive performance text output value is as follows: C1: Obtain a first performance keyword in the first performance keyword group, and obtain a second performance keyword in the second performance keyword group, wherein the first performance keyword is any keyword in the first performance keyword group, and the second performance keyword is any keyword in the second performance keyword group; C2: Calculate the rationality value of the first performance keyword and the second performance keyword; C3: Determine whether the rationality value is greater than the preset rationality value; C4: if the rationality value is greater than a preset rationality value, the first performance keyword and the second performance keyword are used as the comprehensive performance text output value in the first performance keyword group and the second performance keyword group; The comprehensive performance evaluation value is based on the minicomputer performance intelligent analysis model, imports the first performance evaluation value and the second performance evaluation value, and constructs a comprehensive performance evaluation analysis model. The specific analysis formula is: Y=u1×Y1+u2×Y2, where Y represents the comprehensive performance evaluation value, Y1 represents the first performance evaluation value, Y2 represents the second performance evaluation value, and u1 and u2 respectively represent the proportional coefficients corresponding to different evaluation values.

6. The method for optimizing the performance of a minicomputer based on dynamic control according to claim 1, characterized in that: The judgment result of S6 is graded by comparing the comprehensive performance evaluation value with the preset comprehensive performance evaluation value. The preset comprehensive performance evaluation value is obtained through the preset analysis database, including the minimum preset comprehensive performance evaluation value and the maximum preset comprehensive performance evaluation value, which are respectively denoted as Y min and Y max , the level determination includes level 1, level 2 and level 3. If Y<Y min , indicating that the comprehensive performance evaluation value is less than the minimum preset comprehensive performance evaluation value, the level is judged as level 3, at this time the performance is low and the power consumption is high, the mini computer will be dynamically adjusted to silent mode; if Y min ≤Y≤Y max , indicating that the comprehensive performance evaluation value is greater than the minimum preset comprehensive performance evaluation value and less than the maximum preset comprehensive performance evaluation value, then the level is determined to be level 2. At this time, the performance and power consumption are moderate, and the mini computer will be dynamically adjusted to the balanced mode; if Y>Y max , indicating that the comprehensive performance evaluation value is greater than the maximum preset comprehensive performance evaluation value, the level is determined to be level 1, at this time the performance is higher and the power consumption is lower, the mini computer will be dynamically adjusted to overclocking mode.

7. Mini computer performance optimization system, characterized in that: A method for optimizing performance of a mini computer based on dynamic control as described in any one of claims 1 to 6, comprising: Time feature text division module: the user's usage time on the user information terminal is set as the starting time, the user's computer usage time is set as the optimization area, and the optimization area is divided into various time feature texts by equal time division; Key text acquisition module: selects the first performance key text based on the time feature text, and obtains the second performance key text, where the second performance key text is the key text after the first performance key text is selected; Key text preprocessing module: preprocessing the selected first performance key text, the preprocessing operation is used to obtain the first performance key word group of the first performance key text; preprocessing the obtained second performance key text, the preprocessing operation is used to obtain the second performance key word group corresponding to the second performance key text; Key text analysis module: obtains a mini computer performance intelligent analysis model, and obtains a first performance evaluation value corresponding to the first performance key text and a second performance evaluation value corresponding to the second performance key text according to the mini computer performance intelligent analysis model through the first performance keyword group and the second performance keyword group; Comprehensive analysis module: based on the first performance keyword group and the second performance keyword group, obtain a comprehensive performance text output value, and according to the mini computer performance intelligent analysis model, obtain a comprehensive performance evaluation value of the comprehensive performance text output value; Performance optimization module: determines the performance level of the mini computer based on the comprehensive performance evaluation value, and optimizes the determination results in real time; Human-computer interaction module: Based on the judgment results and optimization, information is output to the user information terminal in a preset summary method; The system operation database includes all data texts for mini computer performance optimization, and collects information texts output from each step in real time. The preset analysis database stores preset data, including the correspondence between analysis points and the mini computer performance intelligent analysis model, preset comprehensive performance evaluation values ​​and preset summary methods. The system central processing module is used to control the information text instructions output from each step.

8. The mini computer performance optimization system according to claim 7, characterized in that: The method of obtaining the mini computer performance intelligent analysis model, before obtaining the first performance evaluation value corresponding to the first performance key text through the first performance keyword group, constructing the mini computer performance intelligent analysis model, specifically includes: obtaining an analysis data set corresponding to the first target knowledge field and the second target knowledge field; according to the analysis data set, obtaining the target knowledge graph corresponding to the first target knowledge field and the second target knowledge field; according to the target knowledge graph, constructing the mini computer performance intelligent analysis model.

Images