CN113301585B

CN113301585B - Information processing method, device, electronic equipment and storage medium

Info

Publication number: CN113301585B
Application number: CN202010112439.9A
Authority: CN
Inventors: 梁双春; 纪春芳; 张帅; 刘童桐
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Communications Ltd Research Institute
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Communications Ltd Research Institute
Priority date: 2020-02-24
Filing date: 2020-02-24
Publication date: 2022-07-15
Anticipated expiration: 2040-02-24
Also published as: CN113301585A

Abstract

The application discloses an information processing method, an information processing device, electronic equipment and a storage medium. The method comprises the following steps: acquiring data corresponding to a plurality of network performance indexes; the obtained multiple network performance indexes can form a network performance summary index; for each network performance index in the obtained multiple network performance indexes, determining a first parameter and a second parameter corresponding to each dimension index in the multiple dimension indexes of the corresponding network index by using the obtained data; the first parameter represents the contribution degree of the corresponding dimension index to the network performance summary index; the second parameter characterizes the dispersion of the corresponding dimension index relative to the plurality of dimension indexes; and positioning the problem cell and/or the problem terminal corresponding to the corresponding network index by using the first parameter and the second parameter corresponding to the multiple dimension indexes.

Description

Information processing method, device, electronic equipment and storage medium

Technical Field

The present application relates to the field of wireless communications, and in particular, to an information processing method and apparatus, an electronic device, and a storage medium.

Background

The fifth generation mobile communication technology (5G) has the advantages that the number of network cells is large, the service types are multiple, and the wireless beam coverage scenes are multiple, so that the multidimensional performance index positioning analysis is required, and the method is very helpful for network fault positioning and optimization analysis.

In the multidimensional performance index positioning analysis technology of the related technology, when the performance of a multidimensional summary index is reduced, the first N (top N) data are mainly selected from each dimension, then manual comparison is carried out, and a final result is given by combining with expert experience, so that the positioning analysis efficiency is low and the accuracy is not high.

Disclosure of Invention

In order to solve the related technical problems, embodiments of the present application provide an information processing method, an information processing apparatus, an electronic device, and a storage medium.

The technical scheme of the embodiment of the application is realized as follows:

an embodiment of the present application provides an information processing method, including:

acquiring data corresponding to a plurality of network performance indexes; the obtained multiple network performance indexes can form a network performance summary index;

for each of the obtained multiple network performance indexes, determining a first parameter and a second parameter corresponding to each of the multiple dimension indexes of the corresponding network index by using the obtained data; the first parameter represents the contribution degree of the corresponding dimension index to the network performance summary index; the second parameter characterizes the dispersion of the corresponding dimension index relative to the plurality of dimension indexes;

and positioning the problem cell and/or the problem terminal corresponding to the corresponding network index by using the first parameter and the second parameter corresponding to the multiple dimension indexes.

In the foregoing solution, the positioning the problem cell and/or the problem terminal corresponding to the corresponding network indicator by using the first parameter and the second parameter corresponding to the multiple dimension indicators includes:

forming a data sample by utilizing a first parameter and a second parameter corresponding to a plurality of dimensions;

and positioning the problem cell and/or the problem terminal corresponding to the corresponding network index by using the formed data sample and combining a hierarchical clustering algorithm.

In the above scheme, the positioning the problem cell and/or the problem terminal corresponding to the corresponding network indicator by using the formed data sample in combination with a hierarchical clustering algorithm includes:

extracting a portion of the data samples from the formed data samples, the extracted data samples forming a first set; forming a second set of data samples other than the extracted data samples from the formed data samples;

clustering the data samples in the first set to obtain at least one clustering result;

determining, for each of the at least one clustering results, a corresponding clustering centroid vector;

for each data sample in the second set, determining a cluster of the corresponding data sample by using a cluster centroid vector of each clustering result;

and positioning the problem cell and/or the problem terminal corresponding to the corresponding network index by using the clustering result of the contribution degree and the dispersion degree.

In the above scheme, the method further comprises:

acquiring a plurality of measured values reported by a plurality of terminals;

counting a plurality of measured values of a corresponding terminal aiming at each terminal in a plurality of terminals to obtain a first statistical result;

when positioning the problem terminal, the method further comprises:

and utilizing the first statistical result to position whether the corresponding terminal is a problem terminal.

In the above scheme, the measurement value includes a measurement value of a signal to interference plus noise ratio (SINR) and/or a Reference Signal Received Power (RSRP); the counting of the plurality of measured values of the corresponding terminal includes:

and setting the reported value corresponding to the measured value of the SINR and/or the RSRP in the statistical item of the reported value of the SINR and/or the statistical item of the reported value of the RSRP.

In the above solution, the setting the reported value corresponding to the measured value of SINR and/or RSRP in the statistics item of SINR reported value and/or RSRP reported value includes:

and performing statistical accumulation on the numerical values of the corresponding statistical intervals of the reported values corresponding to the acquired at least one SINR and/or RSRP measurement values in the statistical items of the SINR reported values and/or the statistical items of the RSRP reported values.

In the above scheme, the method further comprises:

the statistical result of each terminal is utilized, the cell is taken as the granularity, the obtained statistical results of the plurality of terminals are subjected to statistical accumulation, and a statistical accumulation result is obtained;

when locating the problem cell, the method further comprises:

and positioning whether the corresponding cell is the problem cell or not by utilizing the statistical accumulation result.

In the above scheme, the performing statistics and accumulation on the obtained statistics results of the multiple terminals includes:

and performing statistical accumulation on the obtained statistical results of the plurality of terminals in the corresponding statistical intervals in the statistical items of the SINR reported values and/or the statistical items of the RSRP reported values.

In the above scheme, the number of SINR statistics items is X; and the value of X is less than or equal to the number of the measurement value intervals corresponding to the SINR reported value.

In the scheme, the number of the statistical items of the RSRP is Y; and the value of Y is less than or equal to the number of the measurement value intervals corresponding to the RSRP reporting value.

In the above solution, when the measurement value includes measurement values of SINR and RSRP, the report value corresponding to the measurement values of SINR and RSRP is set in a two-dimensional statistical term using the report values of SINR and RSRP.

An embodiment of the present application further provides an information processing apparatus, including:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring data corresponding to a plurality of network performance indexes; the obtained multiple network performance indexes can form a network performance summary index;

the determining unit is used for determining a first parameter and a second parameter corresponding to each of a plurality of dimension indexes of the corresponding network indexes by using the acquired data aiming at each of the plurality of acquired network performance indexes; the first parameter represents the contribution degree of the corresponding dimension index to the network performance summary index; the second parameter characterizes the dispersion of the corresponding dimension index relative to the plurality of dimension indexes;

and the positioning unit is used for positioning the problem cell and/or the problem terminal corresponding to the corresponding network index by using the first parameter and the second parameter corresponding to the multiple dimension indexes.

An embodiment of the present application further provides an electronic device, including: a processor and a memory for storing a computer program capable of running on the processor, wherein,

the processor is configured to execute the steps of any one of the above methods when the computer program is executed.

Embodiments of the present application also provide a storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the steps of any one of the above methods.

The information processing method, the information processing device, the electronic equipment and the storage medium provided by the embodiment of the application acquire data corresponding to a plurality of network performance indexes; the obtained multiple network performance indexes can form a network performance summary index; for each of the obtained multiple network performance indexes, determining a first parameter and a second parameter corresponding to each of the multiple dimension indexes of the corresponding network index by using the obtained data; the first parameter represents the contribution degree of the corresponding dimension index to the network performance summary index; the second parameter characterizes the dispersion of the corresponding dimension index relative to the plurality of dimension indexes; the problem cell and/or the problem terminal corresponding to the corresponding network index are/is located by utilizing the first parameter and the second parameter corresponding to the multiple dimension indexes, for the multi-dimensional multi-level summary performance index, the contribution degree and the dispersion degree of each dimension are analyzed, and then the problem cell and/or the problem terminal are determined by utilizing the contribution degree and the dispersion degree, so that the problem cell and/or the problem terminal can be automatically, accurately and quickly located.

Drawings

FIG. 1 is a schematic flow chart of a method for processing information according to an embodiment of the present disclosure;

FIG. 2a is a schematic view of a dimensional multi-level summary relationship according to an embodiment of the present disclosure;

FIG. 2b is a schematic diagram of a multi-level summary relationship in another dimension according to the present application;

FIG. 3 is a schematic view of a measurement model in the related art;

FIG. 4 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples.

And the multidimensional performance index positioning analysis is carried out through manual judgment, so that the efficiency is low and the accuracy is not high. The accuracy is not high because: during analysis, single-dimension sequencing is performed and then comparison is performed by combining other dimensions, so that under the condition of multiple dimensions and multi-level summarization, an accurate result of multi-dimension index correlation drilling analysis is difficult to obtain. For example, a specific performance index generally includes a time dimension (day, hour, and minute granularity), a region (national, province, city, district/county granularity), a network resource (core network element, base station, and cell granularity), a service (slice, internet of things, group client, home client, and individual dimensionality), and the total number of the dimensionalities is 3 × 4 × 3 × 5 — 180 according to the above definition; for regional dimensions, 31 provinces, 10 cities per province, and 10 districts/counties per city need to be considered, so that the total number of analysis reaches up to ten thousand by only taking the value of regional dimensions as much as 31 × 10 × 10 ═ 3100, and by adding the values of time and business dimensions. The manual multidimensional performance index positioning analysis means in the related technology is difficult to accurately and quickly position to the cell and the UE granularity.

Based on this, in various embodiments of the present application, the multi-dimensional multi-level summary performance index is analyzed for the contribution and dispersion of each dimension, and hierarchical clustering analysis is performed, so as to quickly realize multi-dimensional deep-level drilling until the problem cell and the problem UE are located.

An embodiment of the present application provides an information processing method applied to an electronic device, and as shown in fig. 1, the method includes:

step 101: acquiring data corresponding to a plurality of network performance indexes;

here, the plurality of acquired network performance indicators can form a network performance summary indicator.

Step 102: for each network performance index in the obtained multiple network performance indexes, determining a first parameter and a second parameter corresponding to each dimension index in the multiple dimension indexes of the corresponding network index by using the obtained data;

here, the first parameter characterizes the contribution degree of the corresponding dimension index to the network performance summary index; the second parameter characterizes a dispersion of the respective dimension indicator with respect to the plurality of dimension indicators.

Step 103: and positioning the problem cell and/or the problem terminal corresponding to the corresponding network index by using the first parameter and the second parameter corresponding to the multiple dimension indexes.

In practical application, the electronic device may be a network management device.

In actual application, data corresponding to a plurality of network performance indexes is in the network management system.

The obtained multiple network performance indexes can form a network performance summary index, that is, data corresponding to the multiple network performance indexes included in a certain network performance summary index is obtained. Illustratively, a certain network performance summary indicator is a 5G network radio access rate Key Performance Indicator (KPI), and the definition of the 5G network radio access rate KPI is as follows:

the radio access rate of the 5G network is (the number of times of successful RRC connection establishment/the number of times of request for RRC connection establishment) × (number of successful Flow establishment/number of request for Flow establishment) × (the number of times of successful establishment of logic signaling connection related to NG interface UE/the number of times of request for establishment of logic signaling connection related to NG interface UE) × 100%; wherein, the definition of each performance measurement parameter is as follows:

number of successful RRC connection establishment: the gNB receives a message of 'Radio Resource Control (RRC) connection setup complete' (RRCConnectionSetupComplex) sent by the UE, and each EstablisterCause corresponds to one sub-measurement item;

number of RRC connection establishment requests: the gNB receives an RRC connection request (RRCConnectionRequest) message sent by the UE, and each Establshmentiuse corresponds to one sub-measurement item;

flow (Flow) establishment success number: the gNB sends an INITIAL CONTEXT SETUP RESPONSE (INITIAL CONTEXT SETUP RESPONSE) message or a protocol data unit SESSION (PDSESSION) SETUP RESPONSE (PDU SESSION RESOURCE SETUP RESPONSE) message or a PDSESSION modified RESPONSE (PDU SESSION RESOURCE MODIFY RESPONSE) message, and the number of successfully established flows is determined; and includes Flow collisions that do not directly cause call failures resulting in Flow setup interruptions. Each service type corresponds to one sub-measurement item;

number of Flow establishment requests: the gNB receives an INITIAL CONTEXT SETUP REQUEST message (INITIAL CONTEXT SETUP REQUEST) or a pdussion SETUP REQUEST (PDU SETUP REQUEST) or a pdussion modification REQUEST (PDU SETUP modification REQUEST) from the access and mobility management function (AMF), which includes the number of flows. Each service type corresponds to one sub-measurement item;

the successful times of the establishment of the logic signaling connection related to the NG interface UE are as follows: after sending an INITIAL UE MESSAGE (INITIAL UE MESSAGE) MESSAGE, the gNB receives a first MESSAGE returned by the AMF on the same UE-related logic signaling connection, and when counting the connection establishment success times, the gNB indicates the establishment success as long as receiving the first MESSAGE returned by the AFM, and the connection establishment success times is added by 1;

the number of times of the request for establishing the connection of the logic signaling related to the NG interface UE is as follows: and the gNB sends an INITIAL UE MESSAGE MESSAGE to the AMF, and when counting the connection establishment request times, the GNB only needs to send the INITIAL UE MESSAGE MESSAGE to the AMF once, and the connection establishment request times are added by 1.

Therefore, when determining the wireless access rate KPI of the 5G network, the obtained plurality of network performance indicators include: the number of times of successful RRC connection establishment, the number of times of request for RRC connection establishment, the number of successful Flow establishment, the number of request for Flow establishment, the number of times of successful establishment of NG interface UE related logic signaling connection, and the number of times of request for connection establishment of NG interface UE related logic signaling.

In actual applications, a specific performance index generally includes a time dimension (day, hour, and minute granularity), a region (national, provincial, city, district/county granularity), network resources (core network elements, base stations, and cells), and services (slice, internet of things, group customers, home customers, and individuals), and the total number of dimensions is 180 as defined above, and the data format is shown in table 1, for example.

Time

Region(s)

Network resource

Business

Index

1

Index 2

Index 3

Index 4

…

TABLE 1

As shown in fig. 2a and fig. 2b, in a certain dimension, the dimension includes a multi-level summary relationship.

When a certain summary index fluctuates, especially when the certain summary index is lower than a threshold value (according to a scene, a user defines), the reason causing the index fluctuation needs to be quickly positioned. In the embodiment of the application, the contribution and the dispersion of each fractional expression are analyzed, so that which dimensions influence the most finally can be determined.

In step 102, taking the wireless access rate of the 5G network as an example, the wireless access rate is formed by the product of three fractional expressions: (number of times of success of RRC connection establishment/number of times of request for RRC connection establishment) ((number of success of Flow establishment/number of request for Flow establishment) ((number of success of establishment of logical signaling connection related to NG interface UE/number of request for establishment of logical signaling connection related to NG interface UE) × 100%. Wherein, the three fractional expressions are respectively:

number of times of success of RRC connection establishment/number of times of request for RRC connection establishment;

flow establishment success number/Flow establishment request number;

NG interface UE related logic signaling connection establishment success times/NG interface UE related logic signaling connection establishment request times.

One of the fractional expressions may be PI1/PI2, where PI1 is obtained by summing up several dimension indicators, for example, the number of times of successful RRC connection establishment is summarized from all dimensions to obtain a statistical value of the time period (day or hour) of the whole network, and PI2 is also obtained by summing up several dimension indicators, for example, the number of times of request for RRC connection establishment is summarized from all dimensions to obtain a statistical value of the time period (day or hour) of the whole network.

When the contribution degree is calculated, assuming that each network performance index has I dimensions (such as time, area, network and service), each dimension has J values (such as 31 provincial and municipal autonomous regions if the provincial region is selected), and determining the contribution degree of each dimension relative to the change of the mean value; in particular, the amount of the solvent to be used,

calculating partial derivatives of PI1/PI2, and obtaining the following by adopting a differential form:

G_ij＝(△PI1_ij*PI2ij-△PI2_ij*PI1_ij)/(PI2_ij*(PI2_ij+△PI2_ij)) (1)

when the difference is expressed by the difference between the actual value and the predicted value, the following results can be obtained:

G_ij＝((PI1_ij-FPI1_i)*PI2_ij-(PI2ij-FPI2_i)*PI1_ij)/(PI2_ij*(PI2_ij+PI2_ij-FPI2_i)) (2)

wherein, PI1_ijDenotes PI₁The ith dimension of (1), the jth value of (8), FPI1_iRepresenting the ith dimension of PI1Predicting a value; PI2_ijRepresents the j value of the ith dimension of PI2, FPI2_iRepresenting the predicted value of the ith dimension of PI 2. The predicted value is a value (e.g., days or hours) of the current time granularity obtained by linear regression over the analysis time (month, week, etc.).

In practical application, since the difference result has positive and negative values, in order to measure the contribution degree of effectively measuring the fluctuation change, the absolute value of the result obtained by the formula (2) is taken, and the obtained absolute value result is used as the determined contribution degree.

In actual application, the dispersion can be calculated by adopting a Jensen-Shannon (JS) divergence method; in particular, the amount of the solvent to be used,

first, the dispersion is calculated for PI1 using the following formula:

S1_ij＝0.5(p1_ij*log(2*p1_ij/(p1_ij+q1_ij))+q1_ij*log(2*q1_ij/(p1_ij+q1_ij))) (3)

wherein, p1_ij＝PI1_ij/PI1_i，PI1_i＝∑p1_ij，PI1_iThe indexes representing the j values of the ith dimension are summed; q1_ij＝FPI1_ij/FPI1_i，FPI1_i＝∑FPI1_ij，FPI1_iThe index prediction values representing the j values are summed in the ith dimension.

Then, the dispersion is calculated for PI2 by the same method, that is, the dispersion is calculated for P2 by the following formula:

S2_ij＝0.5(p2_ij*log(2*p2_ij/(p2_ij+q2_ij))+q2_ij*log(2*q2_ij/(p2_ij+q2_ij))) (4)

wherein, p2_ij＝PI2_ij/PI2_i，PI2_i＝∑p2_ij，PI2_iThe index time series of j values is summed in the ith dimension; q2_ij＝FPI2_ij/FPI2_i，FPI2_i＝∑FPI2_ij，FPI2_iThe index prediction values representing the j values are summed in the ith dimension.

Here, the predicted value is a value (for example, day or hour) of the current time granularity obtained by linear regression within the analysis time (month, week, etc.).

Finally, the dispersion of PI1/PI2 is S1ij + S2 ij.

And after the contribution and the dispersion of each dimension are obtained, a hierarchical clustering method is adopted for analyzing the contribution and the dispersion of each dimension. And taking the contribution and dispersion of each dimension as sample data to form a row of a matrix, and analyzing by adopting a hierarchical clustering method, wherein the matrix is formed by different dimensions and different values.

Based on this, in step 103, in an embodiment, the positioning the problem cell and/or the problem terminal corresponding to the corresponding network indicator by using the first parameter and the second parameter corresponding to the multiple dimension indicators includes:

In an embodiment, the locating the problem cell and/or the problem terminal corresponding to the corresponding network indicator by using the formed data sample and combining with a hierarchical clustering algorithm includes:

More specifically, the process of clustering includes:

step 1: a matrix of input samples. Randomly sampling according to the proportion p to obtain a set D1, taking samples which are not sampled as a set D2, and setting a clustering distance threshold beta;

here, in actual application, the value of β can be customized according to the scene.

Step 2: clustering the set D1 by Euclidean distance to obtain K clusters, and calculating the mean vector of each cluster as the centroid vector of the cluster

And 3, step 3: for the samples in the set D2, the distance between each sample and the centroid vector of each cluster is calculated in turn, and the samples are considered to belong to the cluster when the distance is less than beta. If the distances from the samples to the known clustering center-of-mass vectors are all larger than beta, the samples are considered to belong to new clusters, the number of the clusters is changed into K +1, and the steps are sequentially circulated until all the samples in D2 are calculated.

And after all the samples are processed, outputting the cluster to which each sample belongs to perform subsequent operation, namely taking the cluster with large contribution and dispersion as an analysis result to perform positioning analysis on the problems of the cell and/or the terminal.

It should be noted that: for the wireless access rate KPI of the 5G network, three fractional expressions are provided, so that the three fractional expressions are respectively processed in the above mode to respectively reach corresponding cells and/or users with poor quality, all the obtained cells and/or users with poor quality are combined, and finally, a multi-dimensional drilling analysis result when the wireless access rate KPI of the 5G network is abnormal is obtained.

From the above description, it can be seen that the method provided in the embodiment of the present application is an analysis method for quickly realizing multidimensional deep drilling to a cell and a UE through analysis of contribution and dispersion of each dimension and hierarchical clustering analysis on a multidimensional multi-level summary performance index.

In practical application, a method of counting and summarizing measurement reports reported by the UE may be adopted to further locate users with poor quality in each 5G cell with poor quality.

Based on this, in an embodiment, the method may further include:

acquiring a plurality of measured values reported by a plurality of terminals;

counting a plurality of measured values of a corresponding terminal aiming at each terminal in a plurality of terminals to obtain a first counting result;

correspondingly, when the problem terminal is located, the method further comprises the following steps:

After the first statistical result is obtained, the first statistical result may be stored.

In practical application, the electronic device may obtain a plurality of measurement values reported by a plurality of terminals from the base station side. And in the statistical period, the terminal reports a plurality of measured values.

In practical application, as shown in the measurement model shown in fig. 3, when the terminal is in a Radio Resource Control (RRC) connected state, the terminal reports a measurement report of the configured beam according to configuration parameters of the RRC.

Here, in this embodiment of the present application, the network requests the terminal to periodically report the measurement report in the RRC connected state through the RRC configuration parameter. The content of the measurement report includes SINR and/or RSRP measurement values. And after receiving the measurement report reported by each terminal, the base station side stores all the terminals for a long time (the time length is defined according to the requirements).

That is, in one embodiment, the measurements comprise measurements of SINR and/or RSRP; and setting the reported value corresponding to the measured value of the SINR and/or the RSRP in the statistical item of the reported value of the SINR and/or the statistical item of the reported value of the RSRP.

Specifically, the numerical values of the report values corresponding to the obtained at least one SINR and/or RSRP measurement value in the corresponding statistical intervals in the statistical items of the SINR report values and/or the statistical items of the RSRP report values are statistically accumulated.

Here, it should be noted that: when the corresponding terminal reports a plurality of SINR measurement values, namely the electronic device acquires a report value corresponding to each SINR measurement value in the plurality of SINR measurement values, performing statistical accumulation on the value of a corresponding statistical interval in a statistical item of the SINR report value corresponding to the corresponding SINR measurement value; when the corresponding terminal reports the plurality of RSRP measurement values, namely the electronic equipment acquires the report value corresponding to each RSRP measurement value in the plurality of RSRP measurement values, performing statistical accumulation on the numerical value of the corresponding statistical interval of the report value corresponding to the corresponding RSRP measurement value in the statistical item of the RSRP report value.

In practical application, SINR and RSRP measurement values can be reported according to the definition of the related technology; specifically, the SINR measurement value may be reported using the mapping relationship (mapping relationship between the measurement value and the reported value) of the SINR measurement report shown in table 2; and the RSRP measurement value can be reported by using the RSRP measurement report mapping relationship shown in table 3.

Reported value	Measured quantity value	Unit
			SS-SINR_0	SS-SINR<-23	dB
SS-SINR_1	-23≤SS-SINR<-22.5	dB
			SS-SINR_2	-22.5≤SS-SINR<-22	dB
SS-SINR_3	-22≤SS-SINR<-21.5	dB
			SS-SINR_4	-21.5≤SS-SINR<-21	dB
..	..	…
			SS-SINR_123	38≤SS-SINR<38.5	dB
SS-SINR_124	38.5≤SS-SINR<39	dB
			SS-SINR_125	39≤SS-SINR<39.5	dB
SS-SINR_126	39.5≤SS-SINR<40	dB
			SS-SINR_127	40≤SS-SINR	dB

Table 2 shows that the SINR includes SINR of the synchronization signal (SS-SINR).

TABLE 3

Wherein the RSRP includes RSRP of synchronization signals (SS-RSRP) and RSRP of channel state information (CSI-RSRP). Table 3 shows a measurement report mapping relationship between SS-RSRP and CSI-RSRP.

In actual application, statistics can be performed mainly by using CSI-RSRP; of course, SS-RSRP may also be counted simultaneously.

For convenience of analysis, in the embodiment of the present application, an SINR performance measurement statistic is defined, the number of SINR statistic intervals is X, that is, the number of SINR statistic items is X, a value of X is defined according to data storage capacity and processing capacity, and a maximum value of X is 128, which is identical to the number of intervals for measuring reported values at this time, that is, the value of X is less than or equal to the number of measurement value intervals corresponding to SINR reported values. Certainly, under the condition that the memory space can be reduced and the processing efficiency can be improved without affecting the application effect, X may also take a value smaller than 128, for example, the interval-23 ≦ SS-SINR < -22.5 and-22.5 ≦ SS-SINR < -22 defined by SINR may be combined to obtain the interval-23 ≦ SS-SINR < -22, then the total number (number) X of SINR statistical intervals equals 127, and the specific calculation process of the SINR measurement statistics includes counting the number in the statistical interval of the measurement items corresponding to SINR according to the SINR values reported by the UE within the same time granularity. Here, in the embodiment of the present application, since a specific value is reported, the statistical interval may also be understood as a statistical point.

In an embodiment, the values of the report value corresponding to the obtained at least one SINR measurement value in the corresponding statistical interval in the statistical term of the SINR report value are statistically accumulated.

Exemplarily, assuming that the count of Sinrx, X ∈ [0, X) is taken as an example, in a measurement report reporting period T0 of a certain UE, the measured value of SS-SINR is m, and m corresponds to a Sinrx interval in a statistical term according to the definition of the statistical term, so that the count of Sinrx is added by 1, that is, the numerical value of Sinrx is added by 1, for example, the reported value corresponding to m is 0, the count of SINR0 is added by 1, and when m reports T times in the statistical period of the statistical term in total, the count of SINR0 is added by T. In practical applications, the statistical period of the statistical item is T, and generally T ≧ T0. In practical applications, the statistical term may be in the format shown in table 4.

Sinrx	Statistic value (one)
		Sinr0	t0
Sinr1	t1
		…	…
SinrX	tX

TABLE 4

In table 3, t0, t1, and tX represent the number of Sinr0, Sinr1, and SinrX statistics, respectively.

Similarly, for convenience of statistics, in the embodiment of the present application, an RSRP performance measurement statistical value is defined, the number of statistical intervals of RSRP is Y, that is, the number of statistical items of RSRP is Y, the value of Y is defined according to data storage capacity and processing capacity, the maximum value of Y is 128, and at this time, the maximum value of Y is consistent with the number of intervals for measuring reported values, that is, the value of Y is less than or equal to the number of measurement value intervals corresponding to the RSRP reported values. Of course, Y may also be a value smaller than 128 under the condition that the application effect is not affected and the storage space can be reduced and the processing efficiency can be improved, for example, the interval defined by the interval RSRP defined by RSRP-38 ≦ SS-RSRP < -37 and the interval defined by-37 ≦ SS-RSRP < -36 may be combined to obtain the interval-38 ≦ SS-RSRP < -36, the total number (number) X of RSRP statistical intervals is equal to 127, and the specific calculation process of the RSRP measurement statistical value includes counting the number in the statistical interval of the measurement items corresponding to RSRP according to the RSRP value reported by the UE in the same time granularity. Here, in the embodiment of the present application, since a specific value is reported, the statistical interval may also be understood as a statistical point.

For example, assuming that the RSRP, Y e [0, Y) statistic item is taken as an example, in a measurement report reporting period T0 of a certain UE, the measurement value of RSRP is n, and n corresponds to an RSRP interval in the statistic item according to the definition of the statistic item, so that the count of RSRP is increased by 1, that is, the numerical value of RSRP is increased by 1, for example, if the reported value corresponding to n is 0, the count of RSRP0 is increased by 1, and if n reports T times in the statistic period of the statistic item in total, the count of RSRP0 is increased by T. In practical applications, the statistical period of the statistical item is T, and generally T ≧ T0. In actual application, the statistical term may be in the format shown in table 5.

Rsrp	Statistic value (one)
		Rsrp0	z0
Rsrp1	z1
		…	…
RsrpX	zX

TABLE 5

In actual application, when the measurement value includes measurement values of SINR and RSRP, statistics may be performed in a two-dimensional statistical term manner, specifically, a report value corresponding to the measurement values of SINR and RSRP is set in a statistical term taking the report values of SINR and RSRP as two dimensions.

For example, assume that the measurement report reporting period T0 of a certain UE has the SINR measurement value m and the RSRP measurement value n, according to the two-dimensional statistical term definition, m corresponds to the Sinrx interval in the two-dimensional statistical term, and n corresponds to the Rsrpy interval in the two-dimensional statistical term, so that the count of SinrxRsrpy is added by 1, that is, the value of SinrxRsrpy is added by 1, for example, if the reported value corresponding to m is 0 and the reported value corresponding to n is 1, the count of SINR0RSRP1 is added by 1, and if m and n are reported T times in total in the statistical period of the statistical term, the count of SINR0RSRP1 is added by T. In practical applications, the statistical period of the two-dimensional statistical item is T, and T ≧ T0 in general. In practical applications, the two-dimensional statistic item may be in the format shown in table 6.

SinrxRsrpy	Rsrp0	Rsrp1	…	RsrpY
					Sinr0	Sinr0Rsrp0	Sinr0Rsrp1	…	Sinr0 RsrpY
Sinr1	Sinr1Rsrp0	Sinr1Rsrp1	…	Sinr1RsrpY
					…	…	…	…	…
SinrX	Sinr XRsrp0	SinrXRsrp1	…	SinrXRsrpY

TABLE 6

After the statistical result of each terminal is obtained according to the statistical mode, the statistical results of a plurality of terminals in a cell are summarized again by taking the cell as the granularity according to the cell where the terminal is located, that is, the statistical items of each terminal are accumulated again, so that the statistical value of the measured value of the cell granularity is obtained.

Based on this, in an embodiment, the method may further include:

when locating the problem cell, the method further comprises:

Specifically, the obtained statistical results of the multiple terminals are statistically accumulated in the corresponding statistical intervals in the statistical terms of the SINR reported values and/or the statistical terms of the RSRP reported values.

In general, the larger the fraction of the measured value less than a certain value, the worse the cell performance index. In the embodiment of the present application, a regression model is used to analyze the relationship between the service performance index and SINR and RSPR, that is, the correlation between the service performance index and SINR and RSPR, specifically, the following formula is used to analyze the correlation between the service performance index and SINR:

PI＝a×exp(c₁×SINR)+b×exp(c₂×RSRP)+ε；

wherein, a and c₁、b、c₂Epsilon is a coefficient, and SINR represents a reported value corresponding to the SINR measured value; and the RSRP represents a report value corresponding to the RSRP measurement value.

In practical application, when the threshold value is given by the PI index according to a service scene, the corresponding threshold values of SINR and RSRP can be determined through the formula, namely through the correlation model; and the UE which is lower than the SINR and/or RSRP threshold value in the cell can be counted by utilizing the determined threshold value, and finally, the specific user with poor service quality is given.

As can be seen from the above description, the whole analysis process includes:

step 1: inputting: a multi-dimensional network performance index;

and 2, step: analyzing the contribution and dispersion of each dimension and hierarchical clustering analysis of the multi-dimensional multi-level summary performance indexes;

in particular, the amount of the solvent to be used,

for i 1to N # N indicates the total number of levels summarized

Analysis of contribution and dispersion of i-th-level dimension index

Hierarchical clustering of i-th dimension index

Outputting the ith-level dimension clustering result

End

And step 3: analyzing the correlation between the network performance index and the UE measurement report;

and 4, step 4: and outputting an analysis result.

Specifically, the lowest dimension results are output, such as poor quality cells and UEs.

The information processing method provided by the embodiment of the application acquires data corresponding to a plurality of network performance indexes; the obtained multiple network performance indexes can form a network performance summary index; for each of the obtained multiple network performance indexes, determining a first parameter and a second parameter corresponding to each of the multiple dimension indexes of the corresponding network index by using the obtained data; the first parameter represents the contribution degree of the corresponding dimension index to the network performance summary index; the second parameter characterizes the dispersion of the corresponding dimension index relative to the plurality of dimension indexes; the problem cell and/or the problem terminal corresponding to the corresponding network index are/is positioned by utilizing the first parameter and the second parameter corresponding to the multiple dimension indexes, for the multi-dimensional multi-level summary performance indexes, the contribution degree and the dispersion degree of each dimension are analyzed, and then the problem cell and/or the problem terminal are determined by utilizing the contribution degree and the dispersion degree, so that the problem cell and/or the problem terminal can be automatically, accurately and quickly positioned.

In addition, after the contribution and the dispersion of each dimension are analyzed, the contribution and the dispersion are subjected to hierarchical clustering analysis, so that the analysis can be quickly and accurately performed.

For the method for implementing the embodiment of the present application, an embodiment of the present application further provides an information processing apparatus, which is disposed on an electronic device, and as shown in fig. 4, the apparatus includes:

an obtaining unit 41, configured to obtain data corresponding to multiple network performance indexes; the obtained multiple network performance indexes can form a network performance summary index;

a determining unit 42, configured to determine, for each of the obtained multiple network performance indicators, a first parameter and a second parameter corresponding to each of multiple dimension indicators of the corresponding network indicator by using the obtained data; the first parameter represents the contribution degree of the corresponding dimension index to the network performance summary index; the second parameter characterizes the dispersion of the corresponding dimension index relative to the plurality of dimension indexes;

a positioning unit 43, configured to position a problem cell and/or a problem terminal corresponding to the corresponding network indicator by using the first parameter and the second parameter corresponding to the multiple dimension indicators.

In an embodiment, the positioning unit 43 is specifically configured to:

extracting a portion of the data samples from the formed data samples, the extracted data samples forming a first set; forming a second set of data samples of the formed data samples other than the extracted data samples;

In an embodiment, the obtaining unit 41 is further configured to obtain a plurality of measurement values reported by a plurality of terminals;

the apparatus may further include: the statistical unit is used for counting a plurality of measured values of a corresponding terminal aiming at each terminal in a plurality of terminals to obtain a first statistical result;

the positioning unit 43 is further configured to, when positioning the problem terminal, position whether the corresponding terminal is the problem terminal by using the first statistical result.

Wherein, in an embodiment, the measurement value comprises a measurement value of SINR and/or RSRP; the statistical unit is specifically configured to:

In an embodiment, the statistical unit is specifically configured to:

and performing statistical accumulation on the numerical values of the corresponding statistical intervals of the report values corresponding to the acquired at least one SINR and/or RSRP measurement values in the statistical items of the SINR report values and/or the statistical items of the RSRP report values.

In an embodiment, the statistical unit is further configured to:

accordingly, the positioning unit 43 is further configured to, when positioning the problem cell, utilize the statistical accumulation result to position whether the corresponding cell is the problem cell.

In an embodiment, the statistical unit is specifically configured to:

In an embodiment, when the measurement value includes measurement values of SINR and RSRP, the statistical unit is configured to set a report value corresponding to the measurement values of SINR and RSRP in a statistical term taking the report values of SINR and RSRP as two dimensions.

In practical application, the obtaining unit 41 may be implemented by a processor in the information processing apparatus in combination with a communication interface; the determination unit 42, the positioning unit 43 and the statistical unit may be realized by a processor in an information processing device.

It should be noted that: in the information processing apparatus provided in the above embodiment, when performing service recommendation, only the division of each program module is illustrated, and in practical applications, the processing allocation may be completed by different program modules according to needs, that is, the internal structure of the apparatus may be divided into different program modules to complete all or part of the processing described above. In addition, the information processing apparatus and the information processing method provided in the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments, and are not described herein again.

Based on the hardware implementation of the program module, and in order to implement the method according to the embodiment of the present application, an embodiment of the present application further provides an electronic device, as shown in fig. 5, where the electronic device 50 includes:

the communication interface 51 is used for performing information interaction with other equipment to acquire relevant information;

and the processor 52 is connected with the communication interface 51 to realize information interaction with other devices, and is used for executing the method provided by one or more technical schemes on the electronic device side when running the computer program. And the computer program is stored on the memory 53.

Specifically, the processor 52 is configured to obtain data corresponding to a plurality of network performance indicators through the communication interface 51; the obtained multiple network performance indexes can form a network performance summary index;

the processor 52 is further configured to, for each of the obtained plurality of network performance indicators, determine, by using the obtained data, a first parameter and a second parameter corresponding to each of a plurality of dimension indicators of the corresponding network indicator; the first parameter represents the contribution degree of the corresponding dimension index to the network performance summary index; the second parameter characterizes the dispersion of the corresponding dimension index relative to the plurality of dimension indexes; and positioning the problem cell and/or the problem terminal corresponding to the corresponding network index by using the first parameter and the second parameter corresponding to the multiple dimension indexes.

In an embodiment, the processor 52 is specifically configured to:

for each data sample in the second set, determining a cluster of the corresponding data sample by using the cluster centroid vector of each clustering result;

In an embodiment, the processor 52 is further configured to obtain, through the communication interface 51, a plurality of measurement values reported by a plurality of terminals;

the processor 52 is configured to count, for each terminal of the multiple terminals, multiple measurement values of the corresponding terminal to obtain a first statistical result;

the processor 52 is further configured to, when locating the problem terminal, use the first statistical result to locate whether the corresponding terminal is the problem terminal.

Wherein, in an embodiment, the measurement value comprises a measurement value of SINR and/or RSRP; the processor 52 is specifically configured to:

and setting the reported value corresponding to the measured value of the SINR and/or the RSRP in the statistic item of the SINR reported value and/or the statistic item of the RSRP reported value.

In an embodiment, the processor 52 is specifically configured to:

In an embodiment, the processor 52 is further configured to:

accordingly, the processor 52 is further configured to, when locating the problem cell, utilize the statistical accumulation result to locate whether the corresponding cell is the problem cell.

In an embodiment, the processor 52 is specifically configured to:

and performing statistical accumulation on the numerical values of corresponding statistical intervals in the statistical items of the SINR reported values and/or the statistical items of the RSRP reported values according to the acquired statistical results of the plurality of terminals.

In an embodiment, when the measurement value includes measurement values of SINR and RSRP, the processor 52 is configured to set a report value corresponding to the measurement values of SINR and RSRP in a two-dimensional statistical term with the report values of SINR and RSRP.

It should be noted that: the specific processing procedure of the processor 52 is detailed in the method embodiment, and is not described here again.

Of course, in practice, the various components in the electronic device 50 are coupled together by a system bus 54. It is understood that the system bus 54 is used to enable communications among the components. The system bus 54 includes a power bus, a control bus, and a status signal bus in addition to a data bus. But for clarity of illustration the various buses are labeled as system bus 54 in figure 4.

The memory 53 in the embodiment of the present application is used to store various types of data to support the operation of the electronic apparatus 50. Examples of such data include: any computer program for operating on the electronic device 50.

The method disclosed in the above embodiments of the present application may be applied to the processor 52, or implemented by the processor 52. The processor 52 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by instructions in the form of hardware integrated logic circuits or software in the processor 52. The Processor 52 may be a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. The processor 52 may implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present application. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed in the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium located in the memory 53, and the processor 52 reads the information in the memory 53 and performs the steps of the method in combination with its hardware.

In an exemplary embodiment, the electronic Device 50 may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, Micro Controllers (MCUs), microprocessors (microprocessors), or other electronic components for performing the aforementioned methods.

It will be appreciated that the memory 53 of embodiments of the present application may be either volatile memory or nonvolatile memory, and may include both volatile and nonvolatile memory. Among them, the nonvolatile Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a magnetic random access Memory (FRAM), a magnetic random access Memory (Flash Memory), a magnetic surface Memory, an optical Disc, or a Compact Disc Read-Only Memory (CD-ROM); the magnetic surface storage may be disk storage or tape storage. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Enhanced Synchronous Dynamic Random Access Memory (Enhanced DRAM), Synchronous Dynamic Random Access Memory (SLDRAM), Direct Memory (DRmb Access), and Random Access Memory (DRAM). The memories described in the embodiments of the present application are intended to comprise, without being limited to, these and any other suitable types of memory.

In an exemplary embodiment, the present application further provides a storage medium, specifically a computer-readable storage medium, for example, a memory 53 storing a computer program, which can be executed by a processor 52 of the electronic device 50 to complete the steps of the foregoing electronic device side method. The computer readable storage medium may be Memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface Memory, optical disk, or CD-ROM.

It should be noted that: "first," "second," and the like are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.

The technical means described in the embodiments of the present application may be arbitrarily combined without conflict.

The above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application.

Claims

1. An information processing method, characterized by comprising:

for each network performance index in the obtained multiple network performance indexes, determining a first parameter and a second parameter corresponding to each dimension index in the multiple dimension indexes of the corresponding network performance index by using the obtained data; the first parameter represents the contribution degree of the corresponding dimension index to the network performance summary index; the second parameter characterizes the dispersion of the corresponding dimension index relative to the plurality of dimension indexes;

positioning a problem cell and/or a problem terminal corresponding to the corresponding network performance index by using a first parameter and a second parameter corresponding to a plurality of dimension indexes; wherein the content of the first and second substances,

the positioning the problem cell and/or the problem terminal corresponding to the corresponding network performance index by using the first parameter and the second parameter corresponding to the multiple dimension indexes comprises:

forming a data sample by utilizing a first parameter and a second parameter corresponding to a plurality of dimension indexes;

and positioning the problem cell and/or the problem terminal corresponding to the corresponding network performance index by using the formed data sample and combining a hierarchical clustering algorithm.

2. The method according to claim 1, wherein the locating the problem cell and/or the problem terminal corresponding to the corresponding network performance indicator by using the formed data sample in combination with a hierarchical clustering algorithm comprises:

and positioning the problem cell and/or the problem terminal corresponding to the corresponding network performance index by using the clustering result of the contribution degree and the dispersion degree.

3. The method of any of claims 1to 2, further comprising:

acquiring a plurality of measured values reported by a plurality of terminals;

when positioning the problem terminal, the method further comprises:

and positioning whether the corresponding terminal is a problem terminal or not by using the first statistical result.

4. The method according to claim 3, characterized in that said measurement values comprise measurement values of signal to interference plus noise ratio, SINR, and/or reference signal received power, RSRP; the counting a plurality of measured values of the corresponding terminal includes:

5. The method of claim 4, wherein the setting the reported value corresponding to the measured value of SINR and/or RSRP in the statistical item of the reported value of SINR and/or the statistical item of the reported value of RSRP comprises:

6. The method of claim 5, further comprising:

the statistical result of each terminal is utilized, the cell is taken as the granularity, the statistical results of the plurality of acquired terminals are subjected to statistical accumulation, and a statistical accumulation result is obtained;

when locating the problem cell, the method further comprises:

7. The method according to claim 6, wherein the statistically accumulating the obtained statistical results of the plurality of terminals comprises:

8. The method of claim 4, wherein the number of the statistic terms of SINR is X; and the value of X is less than or equal to the number of the measurement value intervals corresponding to the SINR reported value.

9. The method of claim 4, wherein the number of statistical items of RSRP is Y; and the value of Y is less than or equal to the number of the measurement value intervals corresponding to the RSRP reporting value.

10. The method according to claim 4, wherein when the measurement values include SINR and RSRP measurement values, the reported values corresponding to the SINR and RSRP measurement values are set in a two-dimensional statistical term based on the SINR and RSRP reported values.

11. An information processing apparatus characterized by comprising:

the determining unit is used for determining a first parameter and a second parameter corresponding to each of a plurality of dimension indexes of the corresponding network performance indexes by using the acquired data aiming at each of the plurality of acquired network performance indexes; the first parameter represents the contribution degree of the corresponding dimension index to the network performance summary index; the second parameter characterizes the dispersion of the corresponding dimension index relative to the plurality of dimension indexes;

the positioning unit is used for positioning the problem cell and/or the problem terminal corresponding to the corresponding network performance index by utilizing the first parameter and the second parameter corresponding to the multiple dimension indexes; wherein, the first and the second end of the pipe are connected with each other,

the positioning unit is specifically configured to:

12. An electronic device, comprising: a processor and a memory for storing a computer program capable of running on the processor, wherein,

the processor, when executing the computer program, performing the steps of the method of any of claims 1to 10.

13. A storage medium having a computer program stored thereon, the computer program, when being executed by a processor, realizing the steps of the method according to any of the claims 1to 10.