CN112906999B - Method, device and computing equipment for evaluating effect of traffic index optimization - Google Patents

Abstract

The embodiment of the invention relates to the technical field of wireless communication, and discloses a telephone traffic index optimization effect evaluation method, a device and a computing device, wherein the method comprises the following steps: obtaining a plurality of groups of telephone traffic samples, wherein each group of telephone traffic samples comprises a multi-dimensional telephone traffic index and a corresponding evaluation index; normalizing the multidimensional traffic index to obtain a corresponding multidimensional standard traffic index; performing dimension reduction on the multi-dimension standard telephone traffic index to obtain a plurality of characteristic data; establishing a relational expression between the plurality of feature data and the evaluation index; and evaluating the optimization effect of the multidimensional traffic index to be optimized according to the relational expression. Through the mode, the embodiment of the invention realizes the evaluation of the optimization effect of the session index.

Description

Method, device and computing equipment for evaluating effect of traffic index optimization

technical field

The embodiments of the present invention relate to the technical field of wireless communication, and in particular to a method, device and computing device for evaluating the optimization effect of a traffic index.

Background technique

Parameter optimization is an important optimization method to improve the network performance of a cell. For different traffic indicators, the network performance of the community is improved by adjusting the corresponding traffic indicators.

When optimizing the existing traffic indicators, it is necessary to formulate an optimization plan first, and manually judge the traffic indicators to be optimized and the optimization threshold of each traffic indicator.

In the process of implementing the embodiments of the present invention, the inventors found that: the existing parameter optimization methods mainly rely on empiricism, and the accuracy is low.

Contents of the invention

In view of the above problems, embodiments of the present invention provide a traffic index optimization effect evaluation method, device and computing equipment, which can accurately evaluate the traffic index optimization effect.

According to an aspect of an embodiment of the present invention, a method for evaluating the effect of traffic index optimization is provided, and the method includes:

Obtain multiple groups of traffic samples, each group of traffic samples contains multi-dimensional traffic indicators and corresponding evaluation indicators;

Standardizing the multi-dimensional traffic index to obtain a corresponding multi-dimensional standard traffic index;

performing dimensionality reduction on the multi-dimensional standard traffic indicators to obtain a plurality of characteristic data;

Establishing a relational expression between the plurality of characteristic data and the evaluation index;

The optimization effect of the multi-dimensional traffic index to be optimized is evaluated according to the relational expression.

In an optional manner, the evaluating the optimization effect of the multi-dimensional traffic index according to the relational expression includes:

Obtain multi-dimensional traffic indicators to be optimized and target evaluation indicators;

Arranging the multi-dimensional traffic indicators to be optimized in descending order of preset priority;

Combining continuous at least one-dimensional traffic indicators to obtain multiple sets of traffic indicators to be optimized;

Calculating the optimized prediction and evaluation index of the traffic index contained in each traffic index set to be optimized according to the relational expression;

calculating the difference between the predictive evaluation index and the target evaluation index;

The optimization effect of the multi-dimensional traffic index is evaluated according to the difference.

In an optional manner, the evaluating the optimization effect of the multi-dimensional traffic index according to the relational expression includes:

Obtain multi-dimensional traffic indicators to be optimized and target evaluation indicators;

Arranging the multi-dimensional traffic indicators to be optimized in descending order of preset priority;

Combining continuous at least one-dimensional traffic indicators to obtain multiple sets of traffic indicators to be optimized;

Calculating the optimized prediction and evaluation index of the traffic index contained in each traffic index set to be optimized according to the relational expression;

calculating the difference between the predictive evaluation index and the target evaluation index;

The optimization effect of the multi-dimensional traffic index is evaluated according to the difference.

In an optional manner, the evaluating the optimization effect of the multi-dimensional traffic index according to the difference includes:

Determining the optimization amount of each traffic index in the traffic index set to be optimized with the smallest difference;

Optimizing the corresponding traffic index according to the optimization amount;

Obtain optimized actual evaluation indicators;

If the difference between the actual evaluation index and the target evaluation index is within a preset interval, the optimization effect meets the requirements.

In an optional manner, the obtaining the optimized actual evaluation index includes:

determining the first acquisition time of the multi-dimensional traffic index to be optimized;

determining a second acquisition time of the actual evaluation indicator according to the first acquisition time, where the second acquisition time is aligned with the first acquisition time by hour;

The optimized actual evaluation index is acquired according to the second acquisition time.

In an optional manner, the establishment of the relationship between the plurality of feature data and the evaluation index includes:

Divide the plurality of groups of traffic samples into a training set and a verification set;

The training set is trained by a regression algorithm to obtain a relational set of the plurality of characteristic data and the evaluation index;

Calculating output results corresponding to the multidimensional traffic indicators in the verification set according to each relational expression in the set of relational expressions;

calculating the difference between the output result and the evaluation index;

The relational expression with the smallest difference is determined as the relational expression between the plurality of feature data and the evaluation index.

In an optional manner, the training set is performed on the training set by using a regression algorithm to obtain a relational set of the plurality of characteristic data and the evaluation index, including:

The training set is respectively trained by Bayesian regression algorithm, K-neighbor regression algorithm and Ridge regression algorithm to obtain corresponding relational expressions;

Combining the relational expressions to obtain a relational expression set of the plurality of characteristic data and the evaluation index.

In an optional manner, dimensionality reduction is performed on the standard traffic index to obtain multiple feature data, including:

Dimensionality reduction is performed on the standard traffic index by the partial least square method to obtain a plurality of characteristic data.

In an optional manner, the standardizing the plurality of traffic indicators respectively to obtain corresponding standard traffic indicators includes:

The multi-dimensional traffic indicators are respectively standardized according to the standard deviation standardization method to obtain corresponding multi-dimensional standard traffic indicators.

According to another aspect of the embodiments of the present invention, a device for evaluating traffic index optimization effect is provided, and the device includes:

An acquisition module, configured to acquire multiple groups of traffic samples, each group of traffic samples including multi-dimensional traffic indicators and corresponding evaluation indicators;

A standardization module, configured to standardize the multi-dimensional traffic indicators to obtain corresponding multi-dimensional standard traffic indicators;

A dimensionality reduction module, configured to perform dimensionality reduction on the multi-dimensional standard traffic indicators to obtain a plurality of characteristic data;

a modeling module, configured to establish a relational expression between the plurality of characteristic data and the evaluation index;

An evaluation module, configured to evaluate the optimization effect of the multi-dimensional traffic index to be optimized according to the relational expression.

According to yet another aspect of the embodiments of the present invention, there is provided a computing device, which is characterized in that it includes: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface pass through the The communication bus completes the communication with each other;

The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the above-mentioned method for evaluating the optimization effect of traffic indicators.

According to still another aspect of the embodiments of the present invention, a computer storage medium is provided, and at least one executable instruction is stored in the storage medium, and the executable instruction causes the processor to perform the above-mentioned traffic index optimization Effect evaluation method.

The embodiment of the present invention evaluates the optimization effect of the multi-dimensional traffic index to be optimized by establishing a relational expression between the multi-dimensional traffic index and the evaluation index; the relational expression between the multi-dimensional traffic index and the evaluation index is obtained through multiple groups of traffic samples sample obtained, therefore, the relationship can accurately represent the relationship between multi-dimensional traffic indicators and evaluation indicators, through the embodiment of the present invention can accurately evaluate the optimization effect, and save manpower, improve the optimization effect evaluation efficiency.

The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and The advantages can be more obvious and understandable, and the specific embodiments of the present invention are enumerated below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same parts. In the attached picture:

FIG. 1 shows a flow chart of a method for evaluating the effect of traffic index optimization provided by an embodiment of the present invention;

FIG. 2 shows a flowchart of optimization effect evaluation in a traffic index optimization effect evaluation method provided by another embodiment of the present invention;

Fig. 3 shows a functional block diagram of a traffic index optimization effect evaluation device provided by an embodiment of the present invention;

Fig. 4 shows a schematic structural diagram of a computing device provided by an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

Fig. 1 shows a flow chart of a method for evaluating the effect of traffic index optimization according to the first embodiment of the present invention. As shown in Figure 1, the method includes the following steps:

Step 110: Obtain multiple groups of traffic samples.

Wherein, the traffic samples are related service indicators collected from multiple different cells. Each group of traffic samples contains multi-dimensional traffic indicators and corresponding evaluation indicators. There is a correlation between the evaluation index and the multi-dimensional traffic index, that is, the change of the multi-dimensional traffic index affects the change of the evaluation index. When the evaluation indexes are different, the multidimensional traffic indexes may be the same or different. The selection of evaluation indexes and corresponding multi-dimensional traffic indexes is artificially set according to experience in daily community operation. In some embodiments, the evaluation index is the cell edge rate, and the relevant multi-dimensional traffic index includes the average number of users, the number of activated users, downlink PRB utilization, low CQI ratio, average CQI, edge CQI ratio, downlink traffic, and small packet traffic ratio. There are 11 dimensional traffic indicators including ratio, small packet ratio, spectrum efficiency, and average number of calls per user. The embodiment of the present invention evaluates the optimization effect for one optimization index and the corresponding multi-dimensional traffic index.

Step 120: Standardize the multi-dimensional traffic indicators to obtain corresponding multi-dimensional standard traffic indicators.

The magnitudes of multi-dimensional traffic indicators are different. For example, the range of PRB utilization is 0% to 100%; the value range of traffic indicators related to CQI is 0 to 15; the range of downlink traffic can be 10 ^1x , Wherein, x represents any numerical value from 0 to 9. The difference between orders of magnitude makes the relationship between multi-dimensional traffic indicators and evaluation indicators impossible to measure uniformly. Therefore, each dimension of traffic indicators is standardized. The standardized method may be any one in the prior art, and the embodiment of the present invention does not limit the standardized method. In some implementation manners, multiple traffic indicators are respectively standardized by standard deviation normalized z-score, the specific formula of which is: Among them, x' represents the standardized sample, μ represents the mean of all samples, σ represents the standard deviation of all samples, N represents the total amount of all samples, and x _k represents the kth sample. It should be understood that, when performing standardization, the traffic indicators of the same dimension of all samples are respectively standardized using the above formula.

Step 130: Perform dimensionality reduction on the multi-dimensional standard traffic indicators to obtain multiple feature data.

The dimension of the multidimensional standard traffic indicator is the same as that of the multidimensional traffic indicator. The higher the dimension of the multi-dimensional traffic index, the more information related to the evaluation index can be obtained, and the more accurate the relationship formula obtained in the next step of calculation is. Therefore, the dimensions of the multi-dimensional traffic index are generally relatively high. Dimensionality reduction of multi-dimensional standard traffic indicators can simplify the calculation process and improve calculation efficiency. The embodiment of the present invention does not limit the dimensionality reduction method, and the specific dimensionality reduction method may be selected according to the sample quantity of traffic samples and the characteristics of each dimensionality reduction method. For example, dimensionality reduction methods such as PCA dimensionality reduction or partial least squares dimensionality reduction can be selected. In some embodiments, the partial least squares method is selected for dimensionality reduction, so that while dimensionality reduction is achieved, the feature data after dimensionality reduction can include more dimensional standard traffic indicators.

Step 140: Establish a relationship between multiple feature data and evaluation indicators.

In this step, a regression algorithm is used to establish a relationship between multiple feature data and evaluation indicators. The type of the used regression algorithm is not limited by the embodiment of the present invention. For example, the regression algorithm may be Bayesian Ridge regression, K-neighbor regression, or the like. Divide multiple groups of traffic samples into training set and verification set, establish the relationship between multiple feature data and evaluation indicators through the training set, and verify the relationship between the evaluation indicators through the verification set. Through the above method, the training process can be simplified, and the optimal relation can be determined through verification.

In the process of establishing a relational expression, there is only one evaluation index and multiple feature data. Therefore, when modeling the training set, multiple relational expressions are obtained. Taking the linear relational formula as an example, assuming that the relationship model between the evaluation index and the feature data is y=ax ₁ +bx ₂ +...+nx _n , there are more than one set of values for a, b...n, therefore, After modeling, a relational set of multiple feature data and evaluation indicators is obtained. In some embodiments, the training set is respectively trained by Bayesian regression algorithm, K-neighbor regression algorithm, and ridge regression algorithm to obtain corresponding relational expressions, and each regression algorithm obtains multiple relational expressions. Combine the relational expressions obtained by different regression algorithms to obtain a relational set of multiple feature data and evaluation indicators.

Validate each relational set with a validation set. That is, the multidimensional feature data of each sample in the verification set is respectively substituted into each relational expression in the relational expression set to obtain the output result of each relational expression. Determine the relational expression with the smallest error from the set of relational expressions according to each output result and the actual value of the corresponding evaluation index.

Combining the relational expressions to obtain a relational expression set of the plurality of characteristic data and the evaluation index.

For each relational expression in the relational expression set, when the validation set is used for verification, a set of errors is obtained, and the number of errors contained in a set of errors is the same as the number of samples contained in the validation set. When determining the relational expression with the smallest error, it can be determined by the mean value of a group of errors, and the relational expression with the smallest mean value is the relational expression with the smallest error; A relational expression with the least number of thresholds is determined as the relational expression with the smallest error. A specific determination method may be selected according to requirements. For example, if the requirement is that the average error is the smallest, the relational expression with the smallest error can be determined according to the mean value; if the requirement is that each error is lower than a certain threshold, it can be determined by the number of errors exceeding a certain threshold in a group of errors.

Step 150: Evaluate the optimization effect of the multi-dimensional traffic index to be optimized according to the relational expression.

When evaluating, evaluate whether the optimization reaches the optimization goal of the evaluation index. When optimizing, at least one-dimensional traffic index in the multi-dimensional traffic index is adjusted; the adjusted multi-dimensional traffic index is obtained according to the method in the above-mentioned step 120 to step 130 correspondingly adjusted multiple feature data; the adjusted The last multiple characteristic data are input into the relational expression in step 140, and the optimized evaluation index is calculated and obtained. The calculated evaluation index is compared with the optimization target of the evaluation index until the closest evaluation index is obtained. The adjusted traffic index corresponding to the closest evaluation index and the adjustment amount corresponding to each adjusted traffic index are determined, and the traffic index of the target cell is adjusted accordingly according to the traffic index and the corresponding adjustment amount. Wherein, the target cell is the cell where the multi-dimensional traffic index to be optimized is acquired. After the adjustment, the evaluation index of the target cell is acquired again, and if the difference between the evaluation index and the optimization target of the evaluation index is within a preset range, the optimization effect meets the requirements.

The embodiment of the present invention evaluates the optimization effect of the multi-dimensional traffic index to be optimized by establishing a relational expression between the multi-dimensional traffic index and the evaluation index; the relational expression between the multi-dimensional traffic index and the evaluation index is obtained through multiple groups of traffic samples sample obtained, therefore, the relationship can accurately represent the relationship between multi-dimensional traffic indicators and evaluation indicators, through the embodiment of the present invention can accurately evaluate the optimization effect, and save manpower, improve the optimization effect evaluation efficiency.

In some embodiments, step 150 further includes the following steps as shown in FIG. 2:

Step 210: Obtain the multi-dimensional traffic index and target evaluation index to be optimized.

Wherein, the multi-dimensional traffic index to be optimized is a service index in a certain cell. The target evaluation index is the specific value of the evaluation index that is expected to be achieved. Taking the target evaluation index as the cell edge rate as an example, the current cell edge rate is A, and it is expected that the cell edge rate will reach B by optimizing the multi-dimensional traffic index, and B is greater than A. Then the target evaluation index is the cell edge rate whose value is B.

Step 220: Arrange the multi-dimensional traffic indicators to be optimized in descending order of preset priority.

The priorities of the multi-dimensional traffic indicators are set artificially based on experience in cell optimization. For example, during cell optimization, adjusting the traffic index M in the multi-dimensional traffic index can greatly improve the corresponding evaluation index compared with adjusting other traffic indexes in the multi-dimensional traffic index, then the dimensional traffic The priority of the indicator is higher than that of other traffic indicators. After the multi-dimensional traffic indicators are arranged in descending order of priority, the traffic indicators with higher priority are limitedly adjusted.

Step 230: Combine consecutive at least one-dimensional traffic indicators to obtain multiple sets of traffic indicators to be optimized.

In this step, the dimensions of the traffic indicators included in each traffic indicator set to be optimized are different. When combining, the combinations are performed in the order of increasing traffic index dimensions to obtain a plurality of traffic index sets to be optimized. For example, after the three-dimensional traffic indicators X, Y, and Z are arranged according to the priority from high to low, the arrangement order of the obtained traffic indicators is Y, X, and Z. After the combination, three traffic index sets to be optimized are obtained, namely (Y), (Y, X), (Y, X, Z).

Step 240: Calculating the optimized prediction evaluation index of the traffic index included in each traffic index set to be optimized according to the relational expression.

Wherein, the traffic index in each traffic index set to be optimized is adjusted respectively. The adjusted multi-dimensional traffic index is obtained according to the method in the above steps 120 to 130 to obtain corresponding adjusted multiple feature data; the adjusted multiple feature data are input into the relational expression in step 140, and the prediction evaluation index is calculated. .

It is worth noting that the optimization amount of the traffic index in each traffic index set to be optimized is uncertain, and multiple optimization amounts need to be used to optimize the traffic index respectively. Therefore, there are multiple prediction and evaluation indexes corresponding to each set of traffic indexes to be optimized.

Step 250: Calculate the difference between the predicted evaluation index and the target evaluation index.

In this step, all the traffic index sets to be optimized are respectively substituted into the relational expressions, and after the predicted evaluation index is calculated, the difference between the predicted evaluation index and the target evaluation index is calculated. It is also possible to calculate the difference every time a prediction evaluation index is obtained. The embodiments of the present invention are not limited thereto.

Step 260: Evaluate the optimization effect of the multi-dimensional traffic index according to the difference.

In this step, the optimization amount of each traffic index in the traffic index set to be optimized with the smallest difference is determined. According to the optimization amount, the corresponding traffic index is optimized to obtain the actual evaluation index after optimization. If the difference between the actual evaluation index and the target evaluation index is within a preset interval, it is determined that the optimization effect meets the requirements.

Preferably, in some embodiments, the acquisition time of the actual evaluation index and the acquisition time of the multi-dimensional traffic index to be optimized are aligned on an hourly basis. Specifically, first obtain the first acquisition time of the multi-dimensional traffic index to be optimized, determine the second acquisition time of the actual evaluation index according to the first acquisition time, and align the second acquisition time with the first acquisition time by hour. For example, a certain community covers an office building, and the office building has more users in the community during working hours, and fewer users in the community during non-working hours. If the first acquisition time is 10:00-11:00 in the working time period, then the second acquisition time is also 10:00-11:00 in the working time period. The optimized actual evaluation index is acquired according to the second acquisition time. Through the above method, the problem that the corresponding traffic index of the same cell fluctuates greatly in different time periods is avoided.

The embodiment of the present invention optimizes the multi-dimensional traffic index according to the priority of the multi-dimensional traffic index, and it is easier to reach the target evaluation index after optimizing the traffic index with high priority. Therefore, the multi-dimensional traffic index is optimized in order of decreasing priority. Optimization can make the optimized evaluation index reach the target evaluation index faster, which improves the optimization efficiency.

Fig. 3 shows a functional block diagram of a device for evaluating the effect of traffic index optimization according to an embodiment of the present invention. As shown in FIG. 3 , the device includes: an acquisition module 310, configured to acquire multiple groups of traffic samples, each group of traffic samples including multi-dimensional traffic indicators and corresponding evaluation indicators; a standardization module 320, configured to convert the multi-dimensional The traffic index is standardized to obtain a corresponding multi-dimensional standard traffic index; the dimension reduction module 330 is used to reduce the dimension of the multi-dimensional standard traffic index to obtain a plurality of characteristic data; the modeling module 340 is used to establish the described A relational expression between a plurality of feature data and the evaluation index; an evaluation module 350, configured to evaluate the optimization effect of the multi-dimensional traffic index to be optimized according to the relational expression.

In some embodiments, evaluation module 350 is further configured to:

Obtain multi-dimensional traffic indicators to be optimized and target evaluation indicators;

Arranging the multi-dimensional traffic indicators to be optimized in descending order of preset priority;

Combining continuous at least one-dimensional traffic indicators to obtain multiple sets of traffic indicators to be optimized;

Calculating the optimized prediction and evaluation index of the traffic index contained in each traffic index set to be optimized according to the relational expression;

calculating the difference between the predictive evaluation index and the target evaluation index;

The optimization effect of the multi-dimensional traffic index is evaluated according to the difference.

In some embodiments, evaluation module 350 is further configured to:

Determining the optimization amount of each traffic index in the traffic index set to be optimized with the smallest difference;

Optimizing the corresponding traffic index according to the optimization amount;

Obtain optimized actual evaluation indicators;

If the difference between the actual evaluation index and the target evaluation index is within a preset interval, the optimization effect meets the requirements.

In some embodiments, evaluation module 350 is further configured to:

determining the first acquisition time of the multi-dimensional traffic index to be optimized;

determining a second acquisition time of the actual evaluation indicator according to the first acquisition time, where the second acquisition time is aligned with the first acquisition time by hour;

The optimized actual evaluation index is acquired according to the second acquisition time.

In some embodiments, modeling module 340 is further used to:

Divide the plurality of groups of traffic samples into a training set and a verification set;

The training set is trained by a regression algorithm to obtain a relational set of the plurality of characteristic data and the evaluation index;

Calculating output results corresponding to the multidimensional traffic indicators in the verification set according to each relational expression in the set of relational expressions;

calculating the difference between the output result and the evaluation index;

The relational expression with the smallest difference is determined as the relational expression between the plurality of feature data and the evaluation index.

In some embodiments, modeling module 340 is further used to:

The training set is respectively trained by Bayesian regression algorithm, K-neighbor regression algorithm and Ridge regression algorithm to obtain corresponding relational expressions;

Combining the relational expressions to obtain a relational expression set of the plurality of characteristic data and the evaluation index.

In some embodiments, the dimensionality reduction module 330 is further used to:

Dimensionality reduction is performed on the standard traffic index by the partial least square method to obtain a plurality of characteristic data.

In some embodiments, normalization module 320 is further used to:

The multi-dimensional traffic indicators are respectively standardized according to the standard deviation standardization method to obtain corresponding multi-dimensional standard traffic indicators.

The embodiment of the present invention evaluates the optimization effect of the multi-dimensional traffic index to be optimized by establishing a relational expression between the multi-dimensional traffic index and the evaluation index; the relational expression between the multi-dimensional traffic index and the evaluation index is obtained through multiple groups of traffic samples sample obtained, therefore, the relationship can accurately represent the relationship between multi-dimensional traffic indicators and evaluation indicators, through the embodiment of the present invention can accurately evaluate the optimization effect, and save manpower, improve the optimization effect evaluation efficiency.

An embodiment of the present invention provides a non-volatile computer storage medium, the computer storage medium stores at least one executable instruction, and the computer executable instruction can perform a traffic index optimization effect in any of the above method embodiments assessment method.

FIG. 4 shows a schematic structural diagram of an embodiment of a computing device in the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.

As shown in FIG. 4 , the computing device may include: a processor (processor) 402 , a communication interface (Communications Interface) 404 , a memory (memory) 406 , and a communication bus 408 .

Wherein: the processor 402 , the communication interface 404 , and the memory 406 communicate with each other through the communication bus 408 . The communication interface 404 is used to communicate with network elements of other devices such as clients or other servers. The processor 402 is configured to execute the program 410, specifically, may execute the relevant steps in the above embodiment of the method for evaluating the optimization effect of the traffic index.

Specifically, the program 410 may include program codes including computer operation instructions.

The processor 402 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be of the same type, such as one or more CPUs, or may be different types of processors, such as one or more CPUs and one or more ASICs.

The memory 406 is used to store the program 410 . The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 410 can specifically be used to make the processor 402 execute steps 110-150 in FIG. 1, steps 210-260 in FIG. 2, and realize the functions of the modules 310-350 in FIG.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other device. Various generic systems can also be used with the teachings based on this. The structure required to construct such a system is apparent from the above description. Furthermore, embodiments of the present invention are not directed to any particular programming language. It should be understood that various programming languages can be used to implement the content of the present invention described herein, and the above description of specific languages is for disclosing the best mode of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline the present disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the embodiments of the invention are sometimes grouped together into a single implementation examples, figures, or descriptions thereof. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that although some embodiments herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. And form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the execution order.

Claims (8)

1. a traffic index optimization effect evaluation method, is characterized in that, described method comprises: Obtain multiple groups of traffic samples, each group of traffic samples contains multi-dimensional traffic indicators and corresponding evaluation indicators; Standardizing the multi-dimensional traffic index to obtain a corresponding multi-dimensional standard traffic index; performing dimensionality reduction on the multi-dimensional standard traffic indicators to obtain a plurality of feature data; Establishing a relational expression between the plurality of characteristic data and the evaluation index; Evaluating the optimization effect of the multi-dimensional traffic index to be optimized according to the relational expression, including: obtaining the multi-dimensional traffic index to be optimized and the target evaluation index; decrementing the multi-dimensional traffic index to be optimized according to the preset priority Arranging in order; combining continuous at least one-dimensional traffic indicators to obtain a plurality of traffic indicator sets to be optimized; calculating the optimized prediction and evaluation indicators of the traffic indicators included in each traffic indicator set to be optimized according to the relational expression ; Calculate the difference between the forecast evaluation index and the target evaluation index; evaluate the optimization effect of the multi-dimensional traffic index according to the difference; The evaluation of the optimization effect of the multi-dimensional traffic index according to the difference includes: determining the optimization amount of each traffic index in the traffic index set to be optimized with the smallest difference; Optimizing the corresponding traffic index; obtaining an optimized actual evaluation index; if the difference between the actual evaluation index and the target evaluation index is within a preset interval, the optimization effect meets the requirements. 2. The method according to claim 1, wherein said obtaining the optimized actual evaluation index comprises: determining the first acquisition time of the multi-dimensional traffic index to be optimized; determining a second acquisition time of the actual evaluation indicator according to the first acquisition time, where the second acquisition time is aligned with the first acquisition time by hour; The optimized actual evaluation index is acquired according to the second acquisition time. 3. The method according to claim 1, wherein said establishing the relational expression of said plurality of feature data and said evaluation index comprises: Divide the plurality of groups of traffic samples into a training set and a verification set; The training set is trained by a regression algorithm to obtain a relational set of the plurality of characteristic data and the evaluation index; Calculating output results corresponding to the multidimensional traffic indicators in the verification set according to each relational expression in the set of relational expressions; calculating the difference between the output result and the evaluation index; The relational expression with the smallest difference is determined as the relational expression between the plurality of feature data and the evaluation index. 4. method according to claim 3, is characterized in that, described training set is carried out to described training set by regression algorithm, obtains the relational set of described multiple characteristic data and described evaluation index, comprises: The training set is respectively trained by Bayesian regression algorithm, K-neighbor regression algorithm and Ridge regression algorithm to obtain corresponding relational expressions; Combining the relational expressions to obtain a relational expression set of the plurality of characteristic data and the evaluation index. 5. The method according to claim 1, characterized in that, the dimensionality reduction is carried out to the standard traffic index to obtain a plurality of feature data, including: Dimensionality reduction is performed on the standard traffic index by the partial least square method to obtain a plurality of characteristic data. 6. The method according to claim 1, wherein said standardizing said multi-dimensional traffic index to obtain a corresponding multi-dimensional standard traffic index comprises: The multi-dimensional traffic indicators are respectively standardized according to the standard deviation standardization method to obtain corresponding multi-dimensional standard traffic indicators. 7. A traffic index optimization effect evaluation device, characterized in that the device comprises: An acquisition module, configured to acquire multiple groups of traffic samples, each group of traffic samples including multi-dimensional traffic indicators and corresponding evaluation indicators; A standardization module, configured to standardize the multi-dimensional traffic indicators to obtain corresponding multi-dimensional standard traffic indicators; A dimensionality reduction module, configured to perform dimensionality reduction on the multi-dimensional standard traffic indicators to obtain a plurality of characteristic data; a modeling module, configured to establish a relational expression between the plurality of characteristic data and the evaluation index; The evaluation module is used to evaluate the optimization effect of the multi-dimensional traffic index to be optimized according to the relational expression, including: obtaining the multi-dimensional traffic index to be optimized and the target evaluation index; Arranging in descending order of priority; combining continuous at least one-dimensional traffic indicators to obtain a plurality of traffic indicator sets to be optimized; calculating the traffic indicator optimization included in each traffic indicator set to be optimized according to the relational expression The final prediction evaluation index; calculate the difference between the prediction evaluation index and the target evaluation index; evaluate the optimization effect of the multi-dimensional traffic index according to the difference; Evaluating the optimization effect of the multi-dimensional traffic index, including: determining the optimization amount of each traffic index in the traffic index set to be optimized with the smallest difference; optimizing the corresponding traffic index according to the optimization amount; obtaining An optimized actual evaluation index; if the difference between the actual evaluation index and the target evaluation index is within a preset interval, the optimization effect meets the requirements. 8. A computing device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface complete mutual communication through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute a traffic index optimization effect evaluation method according to any one of claims 1-6.