Machine quality judgment method and device, equipment and storage medium

Abstract

The invention discloses a machine quality judgment method and device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: determining the score of each machine at a target index according to the quality score of each machine at the target index and the corresponding score scaling factor of the machine under the target index; judging whether the machine has a corresponding quality problem or not according to the score; the quality score is generated based on a standard deviation distance of an index value of a machine under the target index; the score scaling factor is used for aligning score qualified lines under different target indexes and controlling the sparse degree of score distribution. And the quality of each aspect of the machine can be judged by using the same score qualification line.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a machine quality judgment method, device, equipment and storage medium. Background Art

[0002] At present, machine quality judgment is an important part of ensuring the normal operation of the business. For example, SCDN / CDN (Content Delivery Network) services need to be undertaken by different types of machine resources deployed in various places. A single machine has different network characteristics during the service process. In order to identify the deviated machines, it is necessary to score the machines and then quickly lock the corresponding single machines with problematic quality characteristics. In the existing technology, a normalization method is used, but this method will cause the score to be judged as 0 or below 0 points, but the absolute indicators corresponding to these machines are good, and they are not problematic machines, which can easily lead to misjudgment of machine quality. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a machine quality judgment method, device, equipment and storage medium, which can use the same passing score to judge the quality of various aspects of the machine and more intuitively reflect the differences between machines. The specific scheme is as follows:

[0004] In a first aspect, the present application discloses a machine quality judgment method, comprising:

[0005] Determine the score of each machine for the target indicator according to the quality score of each machine for the target indicator and the score scaling factor corresponding to the machine under the target indicator;

[0006] Determine whether the machine has corresponding quality problems based on the ratings;

[0007] The quality score is generated based on the standard deviation distance of the machine's indicator value under the target indicator; the score scaling factor is used to align the score passing lines under different target indicators and control the sparsity of the score distribution.

[0008] Optionally, determining the score of each machine for the target indicator according to the quality score of each machine for the target indicator and the score scaling factor corresponding to the machine under the target indicator includes:

[0009] The score of the machine on the target indicator is obtained according to the ratio of the quality score to the score scaling factor.

[0010] Optionally, the quality score is the difference between the target value and the distance difference;

[0011] The target value represents a full score, and the distance difference represents a gap between the index value of the current machine and the optimal index value, so that when the index value of the machine is the optimal index value, the quality score is the target value.

[0012] Optionally, the target value is a fixed value;

[0013] The distance difference is the difference between the optimal standard deviation distance and the standard deviation distance of the current machine, the optimal standard deviation distance is the standard deviation distance corresponding to the optimal index value, and the optimal index value is the optimal value among all index values.

[0014] Optionally, the fractional scaling factor is used to amplify or reduce the quality score;

[0015] If the score passing line corresponding to the quality score of the target indicator is lower than the preset standard passing line, the score scaling factor is used to amplify the quality score, and the greater the difference between the score passing line and the standard passing line, the stronger the amplification effect of the score scaling factor;

[0016] If the passing score corresponding to the quality score of the target indicator is greater than the preset standard passing score, the score scaling factor is used to reduce the quality score, and the greater the difference between the passing score and the standard passing score, the stronger the reduction effect of the score scaling factor.

[0017] Optionally, the fractional scaling factor is the absolute value of the product of the first factor and the second factor;

[0018] The first factor is obtained based on the target parameter value and the adjustable coefficient, and is used to align the passing score lines under different target indicators;

[0019] The second factor is obtained based on the optimal index value and the index value of the current machine, and is used to control the sparsity of the score distribution.

[0020] Optionally, the first factor is the x-th power of the target parameter value, where x is an adjustable coefficient;

[0021] The second factor is the difference between the optimal index value and the index value of the current machine.

[0022] Optionally, the step of obtaining a score of the target indicator according to the quality score and the score scaling factor is specifically obtained according to the following formula:

[0023] ;

[0024] in, is the quality score, is the fractional scaling factor, 100 is the target value, is the optimal standard deviation distance, is the standard deviation distance of the current machine, is the optimal indicator value, is the index value of the current machine, is an adjustable coefficient.

[0025] In a second aspect, the present application discloses a machine multi-quality judgment method, comprising:

[0026] The above-mentioned machine quality judgment method is used to calculate the scores of each machine under different target indicators, so as to judge whether the machine has corresponding quality problems based on the scores using the same scoring criteria.

[0027] In a third aspect, the present application discloses a machine quality judgment device, comprising:

[0028] A score determination module, used to determine the score of each machine for the target indicator according to the quality score of each machine for the target indicator and the score scaling factor corresponding to the machine under the target indicator;

[0029] A quality judgment module, used to judge whether the machine has corresponding quality problems according to the score;

[0030] The quality score is generated based on the standard deviation distance of the machine's indicator value under the target indicator; the score scaling factor is used to align the score passing lines under different target indicators and control the sparsity of the score distribution.

[0031] In a fourth aspect, the present application discloses an electronic device, including:

[0032] Memory, used to store computer programs;

[0033] The processor is used to execute the computer program to implement the aforementioned machine quality judgment method.

[0034] In a sixth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein the computer program implements the aforementioned machine quality judgment method when executed by a processor.

[0035] In this application, the score of each machine in the target indicator is determined according to the quality score of each machine in the target indicator and the score scaling factor corresponding to the machine under the target indicator; whether the machine has corresponding quality problems is judged according to the score; the quality score is generated based on the standard deviation distance of the indicator value of the machine under the target indicator; the score scaling factor is used to align the score passing lines under different target indicators and control the sparsity of the score distribution. It can be seen that the quality score of the machine is generated according to the standard deviation distance of the indicator value of the machine under the target indicator to avoid the situation where the normalization always has 0 points; in addition, the score scaling factor is used to align the score passing lines under different target indicators so that the quality of the machine in all aspects can be judged by the same score passing line; and the score scaling factor is used to control the sparsity of the score distribution to avoid compact scoring so as to more intuitively reflect the differences between machines. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0037] FIG1 is a flow chart of a machine quality judgment method provided by the present application;

[0038] FIG2 is a flow chart of a specific machine quality judgment method provided by the present application;

[0039] FIG3 is a schematic diagram of the structure of a machine quality judgment device provided by the present application;

[0040] FIG4 is a structural diagram of an electronic device provided in this application. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0042] In the prior art, a normalization method is used, but this method may result in the score being judged as 0 or below 0, but the absolute indicators corresponding to these machines are good and they are not problematic machines, which may easily lead to misjudgment of machine quality. In order to overcome the above technical problems, this application proposes a machine quality judgment method that can use the same score passing line to judge the quality of various aspects of the machine, avoid compact scoring, and more intuitively reflect the differences between machines.

[0043] The present application embodiment discloses a method for determining machine quality. Referring to FIG1 , the method may include the following steps:

[0044] Step S11: Determine the score of each machine for the target indicator according to the quality score of each machine for the target indicator and the score scaling factor corresponding to the machine under the target indicator.

[0045] The quality score is determined based on the standard deviation distance of the machine's indicator value under the target indicator, that is, the indicator value of each machine under the target indicator is obtained, the standard deviation is obtained according to the indicator value of all machines, and the standard deviation distance can be determined according to the indicator value of the machine and the standard deviation and mean under the target indicator, and the standard deviation distance is used as the quality score of the machine. The score of each machine in the target indicator is determined based on the quality score combined with the score scaling factor, where the score scaling factor is used to align the score passing line under different target indicators and control the sparsity of the score distribution; it can be understood that since the quality score calculated based on the standard deviation distance of the indicator value is not based on a fixed value as the passing line, such as some indicators can be considered to be qualified with a quality score of more than 60 points, some indicators need to reach more than 90 points to be qualified, and some indicators may be qualified with more than 50 points. Considering that the different score passing lines corresponding to different indicators will lead to inconvenient analysis, the score scaling factor is used to align the score passing lines under different target indicators; it is also considered that if the machine's score is too concentrated and tight, it is not conducive to intuitive analysis of the difference in machine quality, so the score scaling factor is used to control the sparsity of the score distribution. The above target indicators can be certain parameters during the operation of the machine, such as network delay, retransmission, speed, etc.

[0046] Wherein, the above-mentioned determining the score of each machine for the target indicator according to the quality score of each machine for the target indicator and the score scaling factor corresponding to the machine under the target indicator may include: obtaining the score of the machine for the target indicator according to the ratio of the quality score to the score scaling factor. That is, the machine scoring formula is the ratio of the quality score to the score scaling factor.

[0047] Furthermore, the above-mentioned quality score is the difference between the target value and the distance difference; the target value represents the full score, and the distance difference represents the gap between the index value of the current machine and the optimal index value, so that when the index value of the machine is the optimal index value, the quality score is the target value. The distance difference represents the gap between the index value of the current machine and the optimal index value, that is, the closer the index value is to the optimal index value, the smaller the distance difference is, otherwise the larger the distance difference is, the smaller the distance difference is, the closer the quality score is to the target value, and the target value represents the full score, that is, when the index value is the optimal index value, the quality score is the full score, and the closer the index value is to the optimal index value, the closer the quality score is to the full score.

[0048] The above target value is a fixed value, such as 100. The above distance difference is the difference between the optimal standard deviation distance and the standard deviation distance of the current machine. The optimal standard deviation distance is the standard deviation distance corresponding to the optimal index value, and the optimal index value is the optimal value among all index values. The standard deviation distance is determined based on the mean corresponding to the target index, the standard deviation corresponding to the target index, and the index value corresponding to each machine. Specifically, the standard deviation distance is the ratio of the difference between the index value minus the mean and the standard deviation; the mean corresponding to the target index and the standard deviation corresponding to the target index are determined based on the index values ​​of all machines under the target index. That is, the quality score is calculated based on the gap between the index of the current machine and the optimal index value among all machines; relative indicators are used for quality analysis to avoid misjudgment caused by analysis based on absolute indicators.

[0049] Among them, the above-mentioned score scaling factor is used to enlarge or reduce the quality score. If the score passing line corresponding to the quality score of the target indicator is less than the preset standard passing line, the score scaling factor is used to enlarge the quality score, and the greater the difference between the score passing line and the standard passing line, the stronger the amplification effect of the score scaling factor; for example, the standard passing line is 60, and the quality score of a certain indicator reaches 50, which is a pass, then it is necessary to enlarge the quality score of the indicator through the score scaling factor, so that the calculated 50 points are enlarged to 60 points, so as to achieve the effect of a unified passing line. If the score passing line corresponding to the quality score of the target indicator is greater than the preset standard passing line, the score scaling factor is used to reduce the quality score, and the greater the difference between the score passing line and the standard passing line, the stronger the reduction effect of the score scaling factor; similarly, if the quality score of a certain indicator reaches 90 to pass, it is necessary to reduce the quality score of the indicator through the score scaling factor, so that the calculated 90 points are reduced to 60 points, so as to achieve the effect of a unified passing line.

[0050] In a specific implementation, the score scaling factor is the absolute value of the product of the first factor and the second factor; wherein the first factor is obtained based on the target parameter value and the adjustable coefficient, and is used to align the score pass line under different target indicators; the second factor is obtained based on the optimal indicator value and the indicator value of the current machine, and is used to control the sparsity of the score distribution. It can be understood that if the second factor does not exist, the multiple scores that may be obtained are all concentrated in a certain scoring area, making it difficult to intuitively analyze the differences between different machines.

[0051] In a specific implementation, the first factor can be the x-th power of the target parameter value, where x is an adjustable coefficient; the target parameter can be the optimal standard deviation distance, or other parameters; score scaling is achieved by adjusting x. The second factor is the difference between the optimal index value and the index value of the current machine; that is, the greater the difference between the index value and the optimal index value, the greater the second factor, and the smaller the difference between the index value and the optimal index value, the smaller the second factor, thereby increasing the gap between the scores.

[0052] In a specific implementation, the step of obtaining the score of the target indicator according to the quality score and the score scaling factor is specifically obtained according to the following formula:

[0053] ;

[0054] in, is the quality score; 100 is the target value, is the optimal standard deviation distance, is the standard deviation distance of the current machine, is the fractional scaling factor, is the adjustable coefficient, is the optimal indicator value, is the indicator value of the current machine. abs represents the absolute value. Because the smaller the indicator value is, the better it is for some indicators. For example, if the inspection indicator is retransmission, the optimal indicator value minus the indicator value may be negative. Therefore, it is necessary to take the absolute value of the optimal standard deviation distance.

[0055] The following uses speed as the target indicator to illustrate the method of judging machine quality:

[0056] When the target indicator is speed, assume that there are 100 machines in total, calculate the mean speed of these 100 machines, recorded as t_speed_mean, and the standard deviation of the speed, recorded as t_speed_std.

[0057] Calculate the standard deviation distance between each machine's index and the mean, that is, subtract t_speed_mean from the speed value of each machine and divide it by t_speed_std, and record this value as host_speed_std (standard deviation distance);

[0058] Right now ;

[0059] Among them, the best speed is recorded as speed_best (optimal indicator value), and the standard deviation distance corresponding to speed_best is recorded as best_speed_std (optimal standard deviation distance);

[0060] Right now ;

[0061] The scoring formula for calculating the score of each machine is:

[0062] ;

[0063] Among them, speed is the speed value of each machine, x is a variable coefficient used to adjust the score, and other variables can refer to the above process. In this way, the score of the machine with the best speed performance is kept at 100 points through (best_speed_std-host_speed_std), because the value of (best_speed_std-host_speed_std) is 0 at this time; in addition, the gap between other machines and 100 points is controlled through (abs(best_speed_std)^x * (speed_best-speed); specifically, (best_speed_std)^x is used to determine the qualified line of the quality scores of different indicators, and (speed_best-speed) is used to reflect the difference in absolute values, so that the scores of all machines are not too compact, and the scores can be distributed, so as to more intuitively reflect the differences between machines.

[0064] Take the speed index as an example to illustrate the above solution: the speeds of 10 machines are obtained as follows: 78, 80, 85, 77, 80, 81, 85, 79, 75, 70. Then the speed mean t_speed_mean is: 79; the speed standard deviation t_speed_std is: 4.2; the optimal speed speed_best is: 85; the optimal standard deviation distance best_speed_std is: 1.43. Taking the speed value of 80 as an example, the standard deviation distance host_speed_std corresponding to the speed value of 80 is: 0.24; assuming that under the speed index, the user sets the score of 80 or above to be qualified, therefore, in order to unify the qualified lines of different indicators, the qualified lines of all indicators are adjusted to 60, then the adjustable coefficient x under the speed index is: -3.1;

[0065] A machine with a speed value of 80 would be rated:

[0066] ;

[0067] When the speed value is 70, the standard deviation distance host_speed_std is -2.1, and the corresponding machine score is: 58. When the speed value is 81, the standard deviation distance host_speed_std is 1.4, and the corresponding machine score is: 60.04.

[0068] That is, through the adjustable coefficient, the original 80 points are reduced to 60 points, the original scores below 80 points are scaled below 60 points, and the original scores above 80 points are scaled above 60 points, that is, all scores are uniformly scaled; by setting corresponding adjustable coefficients for different indicators, the qualified lines under different indicators are unified, so that the performance of the machine under each indicator can be analyzed more conveniently. In addition, it should be noted that the above example values ​​are only for the purpose of reflecting the effect of this application and are not real data.

[0069] Step S12: judging whether the machine has corresponding quality problems according to the score.

[0070] Finally, the score is used to determine whether the machine has corresponding quality problems in terms of the target indicators. Compared with the normalization algorithm used for scoring single variables in the prior art, this can avoid the situation where the score is always 0, and is more in line with the actual business situation. After all, not every machine with poor relative indicators means poor absolute indicators.

[0071] As can be seen from the above, in this embodiment, the score of each machine in the target indicator is determined according to the quality score of each machine in the target indicator and the score scaling factor corresponding to the machine under the target indicator; whether the machine has corresponding quality problems is judged according to the score; the quality score is generated based on the standard deviation distance of the indicator value of the machine under the target indicator; the score scaling factor is used to align the score passing lines under different target indicators and control the sparsity of the score distribution. It can be seen that the quality score of the machine is generated according to the standard deviation distance of the indicator value of the machine under the target indicator to avoid the situation where the normalization always has 0 points; in addition, the score scaling factor is used to align the score passing lines under different target indicators so that the quality of the machine in all aspects can be judged using the same score passing line; and the sparsity of the score distribution is controlled to analyze the machine score more intuitively and effectively.

[0072] The present application embodiment discloses a specific machine quality judgment method, as shown in FIG2 , the method may include the following steps:

[0073] Step S21: Determine the score of each machine for different target indicators according to the quality scores of each machine for different target indicators and the score scaling factors corresponding to the machine under different target indicators.

[0074] According to the above machine quality judgment method, the scores of each machine in different target indicators are calculated in turn.

[0075] Step S22: Based on the score, use the same score standard to determine whether the machine has corresponding quality problems.

[0076] The obtained score is scaled by the score scaling factor, so the passing score lines for different indicators are the same. At this time, the same scoring criteria are used to determine whether the machine has corresponding quality problems. That is, the score corresponding to an indicator can represent a quality problem. Of course, the scores of multiple indicators can also be combined for comprehensive analysis.

[0077] The above solution is explained using the speed indicator and throughput as an example:

[0078] The speeds of the 10 machines are: 78, 80, 85, 77, 80, 81, 85, 79, 75, 70. The speed mean t_speed_mean is: 79; the speed standard deviation t_speed_std is: 4.2; the optimal speed speed_best is: 85; the optimal standard deviation distance best_speed_std is: 1.43. Taking the speed value of 80 as an example, the standard deviation distance host_speed_std corresponding to the speed value of 80 is: 0.24; assuming that under the speed index, the user sets the score of 80 or above to be qualified, in order to unify the qualified lines of different indicators, the qualified lines of all indicators are adjusted to 60, then the adjustable coefficient x under the speed index is: -3.1; the score of the machine with a speed value of 80 is:

[0079] ;

[0080] The throughputs of the five machines are 60, 70, 65, 72, and 75 respectively; the throughput mean t_throughput_mean is 68;

[0081] The throughput standard deviation t_throughput_std is: 5.3;

[0082] The optimal throughput throughput_best is: 75;

[0083] The best standard deviation distance best_throughput_std is: 1.3. Taking the throughput of 70 as an example, the standard deviation distance host_throughput_std corresponding to the speed value of 70 is: 0.37; assuming that under the throughput indicator, the user sets the machine with a score of 70 or above to be qualified; in order to unify the qualified lines of different indicators, the qualified lines of all indicators are adjusted to 60, then the adjustable coefficient x under the throughput indicator is: -4.22; the score of the machine with a throughput of 70 is:

[0084] ;

[0085] When the throughput is 65, the standard deviation distance host_speed_std is -0.56, and the corresponding machine score is 59.3. When the throughput is 72, the standard deviation distance host_speed_std is 0.75, and the corresponding machine score is 60.2. That is, through the adjustable coefficient, the original 70 points are reduced to 60 points, the original scores below 70 points are scaled below 60 points, and the original scores above 70 points are scaled above 60 points, that is, all scores are uniformly scaled.

[0086] The above example uses speed and throughput as examples. For the speed with a qualified line of 80 and the throughput with a qualified line of 70, the qualified lines of these two indicators are unified to 60 through adjustable coefficients. Therefore, when the machine quality scores of each machine under each indicator are displayed, the user can filter out machines with unqualified quality at one time based on the same score screening conditions, thereby improving the efficiency of screening, and the user does not need to remember the qualified lines of each indicator, and can more conveniently analyze the performance of the machine under each indicator. In addition, it should be noted that the above example values ​​are only for the purpose of reflecting the effect of this application and are not real data.

[0087] For the specific process of the above step S21, reference may be made to the corresponding contents disclosed in the above embodiment, which will not be described again here.

[0088] As can be seen from the above, in this embodiment, the scores of each machine for different target indicators are determined based on the quality scores of each machine for different target indicators and the score scaling factors corresponding to the machine under different target indicators; based on the scores, the same scoring criteria are used to judge whether the machine has corresponding quality problems. Therefore, the score scaling factors are used to align the score passing lines under different target indicators, so that the same score passing lines can be used to judge the quality of various aspects of the machine, thereby improving the convenience of machine quality judgment.

[0089] Correspondingly, the embodiment of the present application also discloses a machine quality judgment device, as shown in FIG3 , the device includes:

[0090] A score determination module 11 is used to determine the score of each machine under the target indicator according to the quality score of each machine under the target indicator and the score scaling factor corresponding to the machine under the target indicator;

[0091] A quality judgment module 12, used to judge whether the machine has corresponding quality problems according to the score;

[0092] The quality score is generated based on the standard deviation distance of the machine's indicator value under the target indicator; the score scaling factor is used to align the score passing lines under different target indicators and control the sparsity of the score distribution.

[0093] As can be seen from the above, in this embodiment, the score of each machine in the target indicator is determined according to the quality score of each machine in the target indicator and the score scaling factor corresponding to the machine under the target indicator; whether the machine has corresponding quality problems is judged according to the score; the quality score is generated based on the standard deviation distance of the indicator value of the machine under the target indicator; the score scaling factor is used to align the score passing lines under different target indicators and control the sparsity of the score distribution. It can be seen that the quality score of the machine is generated according to the standard deviation distance of the indicator value of the machine under the target indicator to avoid the situation where the normalization always has 0 points; in addition, the score scaling factor is used to align the score passing lines under different target indicators so that the quality of the machine in all aspects can be judged using the same score passing line; and the sparsity of the score distribution is controlled to analyze the machine score more intuitively and effectively.

[0094] In some specific embodiments, the score determination module 11 may specifically include:

[0095] A score determination unit is used to obtain a score of the machine in the target indicator according to the ratio of the quality score to the score scaling factor.

[0096] In some specific embodiments, the quality score is the difference between the target value and the distance difference;

[0097] The target value represents a full score, and the distance difference represents a gap between the index value of the current machine and the optimal index value, so that when the index value of the machine is the optimal index value, the quality score is the target value.

[0098] In some specific embodiments, the target value is a fixed value; the distance difference is the difference between the optimal standard deviation distance and the standard deviation distance of the current machine, the optimal standard deviation distance is the standard deviation distance corresponding to the optimal index value, and the optimal index value is the optimal value among all index values.

[0099] In some specific embodiments, the score scaling factor is used to amplify or reduce the quality score; if the score passing line corresponding to the quality score of the target indicator is less than the preset standard passing line, the score scaling factor is used to amplify the quality score, and the greater the difference between the score passing line and the standard passing line, the stronger the amplification effect of the score scaling factor; if the score passing line corresponding to the quality score of the target indicator is greater than the preset standard passing line, the score scaling factor is used to reduce the quality score, and the greater the difference between the score passing line and the standard passing line, the stronger the reduction effect of the score scaling factor.

[0100] In some specific embodiments, the score scaling factor is the absolute value of the product of the first factor and the second factor; the first factor is obtained based on the target parameter value and the adjustable coefficient, and is used to align the score passing lines under different target indicators; the second factor is obtained based on the optimal indicator value and the indicator value of the current machine, and is used to control the sparsity of the score distribution.

[0101] In some specific embodiments, the first factor is the x-th power of the target parameter value, where x is an adjustable coefficient; and the second factor is the difference between the optimal index value and the index value of the current machine.

[0102] In some specific embodiments, the step of obtaining the score of the target indicator according to the quality score and the score scaling factor is specifically obtained according to the following formula, which is:

[0103] ;

[0104] in, is the quality score, is the fractional scaling factor, 100 is the target value, is the optimal standard deviation distance, is the standard deviation distance of the current machine, is the optimal indicator value, is the index value of the current machine, is an adjustable coefficient.

[0105] Furthermore, an embodiment of the present application also discloses an electronic device, as shown in FIG4 . The content in the figure cannot be regarded as any limitation on the scope of use of the present application.

[0106] FIG4 is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the machine quality judgment method disclosed in any of the aforementioned embodiments.

[0107] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0108] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon include an operating system 221, a computer program 222, and data 223 including scores, etc. The storage method can be temporary storage or permanent storage.

[0109] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, so as to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, and it can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the machine quality judgment method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0110] Furthermore, an embodiment of the present application also discloses a computer storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of the machine quality judgment method disclosed in any of the aforementioned embodiments are implemented.

[0111] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0112] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0113] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0114] The above is a detailed introduction to a machine quality judgment method, device, equipment and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for judging machine quality, characterized in that: include: Determine the score of each machine for the target indicator according to the quality score of each machine for the target indicator and the score scaling factor corresponding to the machine under the target indicator; Determine whether the machine has corresponding quality problems based on the ratings; The quality score is generated based on the standard deviation distance of the machine's indicator value under the target indicator; the score scaling factor is used to align the score passing lines under different target indicators and control the sparsity of the score distribution.

2. The machine quality judgment method according to claim 1, characterized in that: Determining the score of each machine for the target indicator according to the quality score of each machine for the target indicator and the score scaling factor corresponding to the machine under the target indicator includes: The score of the machine on the target indicator is obtained according to the ratio of the quality score to the score scaling factor.

3. The machine quality judgment method according to claim 2, characterized in that: The quality score is the difference between the target value and the distance difference; The target value represents a full score, and the distance difference represents a gap between the index value of the current machine and the optimal index value, so that when the index value of the machine is the optimal index value, the quality score is the target value.

4. The machine quality judgment method according to claim 3, characterized in that: The target value is a fixed value; The distance difference is the difference between the optimal standard deviation distance and the standard deviation distance of the current machine, the optimal standard deviation distance is the standard deviation distance corresponding to the optimal index value, and the optimal index value is the optimal value among all index values.

5. The machine quality judgment method according to claim 2, characterized in that: The fractional scaling factor is used to amplify or reduce the quality score; If the score passing line corresponding to the quality score of the target indicator is lower than the preset standard passing line, the score scaling factor is used to amplify the quality score, and the greater the difference between the score passing line and the standard passing line, the stronger the amplification effect of the score scaling factor; If the passing score corresponding to the quality score of the target indicator is greater than the preset standard passing score, the score scaling factor is used to reduce the quality score, and the greater the difference between the passing score and the standard passing score, the stronger the reduction effect of the score scaling factor.

6. The machine quality judgment method according to claim 2, characterized in that: The fractional scaling factor is the absolute value of the product of the first factor and the second factor; The first factor is obtained based on the target parameter value and the adjustable coefficient, and is used to align the passing score lines under different target indicators; The second factor is obtained based on the optimal index value and the index value of the current machine, and is used to control the sparsity of the score distribution.

7. The machine quality judgment method according to claim 6, characterized in that: The first factor is the x-th power of the target parameter value, and x is an adjustable coefficient; The second factor is the difference between the optimal index value and the index value of the current machine.

8. The machine quality judgment method according to claim 1, characterized in that: The step of obtaining the score of the target indicator according to the quality score and the score scaling factor is specifically obtained according to the following formula: ； in, is the quality score, is the fractional scaling factor, 100 is the target value, is the optimal standard deviation distance, is the standard deviation distance of the current machine, is the optimal indicator value, is the index value of the current machine, is an adjustable coefficient.

9. A machine multi-quality judgment method, characterized in that: include: The machine quality judgment method described in any one of claims 1 to 8 is used to calculate the scores of each machine under different target indicators, so as to judge whether the machine has corresponding quality problems based on the scores using the same scoring criteria.

10. A machine quality judgment device, characterized in that: include: A score determination module, used to determine the score of each machine for the target indicator according to the quality score of each machine for the target indicator and the score scaling factor corresponding to the machine under the target indicator; A quality judgment module, used to judge whether the machine has corresponding quality problems according to the score; The quality score is generated based on the standard deviation distance of the machine's indicator value under the target indicator; the score scaling factor is used to align the score passing lines under different target indicators and control the sparsity of the score distribution.

11. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the machine quality determination method according to any one of claims 1 to 8 or the machine multi-quality determination method according to claim 9.

12. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein when the computer programs are executed by a processor, the machine quality judgment method according to any one of claims 1 to 8 or the machine multi-quality judgment method according to claim 9 is implemented.

Images