Voice service optimization method and device, electronic equipment and storage medium

Abstract

The present application relates to the field of communication, and provide a kind of voice service optimization method, device, electronic equipment and storage medium, the method comprises: according to the fluctuation index generated by each target configuration parameter and its adjustment that influences voice service perception, constructs association matrix;According to the first service perception index of each to-be-optimized cell and service perception constraint threshold, determine the target optimization cell in each to-be-optimized cell;According to the current configuration parameter of target optimization cell, the fluctuation index of current configuration parameter is obtained by converting association matrix;According to the second service perception index of target optimization cell, the fluctuation index of current configuration parameter and service perception constraint threshold, output the voice service optimization strategy of target optimization cell.The voice service optimization method provided in the embodiment of the present application realizes that voice service is optimized by voice service optimization strategy automatically, and guarantees the voice service user perception in network.

Description

Technical Field

[0001] This invention relates to the field of communications, and more particularly to a voice service optimization method, apparatus, electronic device, and storage medium. Background Technology

[0002] Currently, 5G voice service (VoNR) is in its early stages of development, and network configuration generally uses baseline parameters without personalized optimization based on cell conditions. Even when adjusting relevant optimization parameters, while improving packet loss rate, it also impacts the perceived speed for users in the cell, making it difficult to balance packet loss rate optimization with cell service speed indicators. Consequently, the user experience of 5G services on the current network cannot be adequately guaranteed.

[0003] In summary, the current baseline 5G voice service packet loss rate parameter configuration cannot meet and adapt to the differentiated parameter configuration requirements between different types of cells, and it is difficult to take into account multiple indicators in a coordinated manner. Summary of the Invention

[0004] This invention provides a voice service optimization method, apparatus, electronic device, and storage medium, aiming to automatically optimize voice services through voice service optimization strategies and ensure user experience of voice services in the network.

[0005] In a first aspect, the present invention provides a voice service optimization method, comprising:

[0006] A correlation matrix is ​​constructed based on the various target configuration parameters that affect the perception of voice services and the fluctuation indicators caused by their adjustments.

[0007] Based on the first service perception index and service perception constraint threshold of each cell to be optimized, the target optimized cell among the cells to be optimized is determined.

[0008] The correlation matrix is ​​transformed based on the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters;

[0009] Based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold, the voice service optimization strategy of the target optimized cell is output.

[0010] In one embodiment, constructing a correlation matrix based on various target configuration parameters affecting voice service perception and the fluctuation indicators resulting from their adjustments includes:

[0011] Determine the target HARQ retransmission count, target CCE aggregation level, target neighbor cell reference signal interference avoidance parameters, and target MCS fast order selection parameters in the target configuration parameters;

[0012] A first matrix is ​​constructed based on each step size adjustment of the target HARQ retransmission count and the resulting packet loss rate and user-perceived rate.

[0013] A second matrix is ​​constructed based on each step size adjustment of the target CCE aggregation level and the resulting packet loss rate and user-perceived rate.

[0014] A third matrix is ​​constructed based on the adjustment of the target neighbor cell reference signal interference avoidance parameters at each step size and the resulting packet loss rate and user perceived rate.

[0015] Based on the adjustment of each step size of the target MCS fast order selection parameters and the resulting packet loss rate and user-perceived speed, a fourth matrix is ​​constructed.

[0016] The first matrix, the second matrix, the third matrix, and the fourth matrix are merged according to the row merging method to construct the correlation matrix.

[0017] The step of transforming the correlation matrix based on the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters includes:

[0018] Determine the current HARQ retransmission count, current CCE aggregation level, current neighbor cell reference signal interference avoidance parameter, and current MCS fast order selection parameter in the current configuration parameters;

[0019] The correlation matrix is ​​transformed based on the current HARQ retransmission count and its traversal parameter adjustment value to obtain the fluctuation index of the current HARQ retransmission count.

[0020] The correlation matrix is ​​transformed based on the current CCE aggregation level and its traversal parameter adjustment value to obtain the volatility index of the current CCE aggregation level;

[0021] The correlation matrix is ​​transformed based on the current neighboring cell reference signal interference avoidance parameters and their traversal parameter adjustment values ​​to obtain the fluctuation index of the current neighboring cell reference signal interference avoidance parameters;

[0022] The correlation matrix is ​​transformed based on the current MCS fast order selection parameters and their traversal parameter adjustment values ​​to obtain the fluctuation index of the current MCS fast order selection parameters.

[0023] The step of outputting the voice service optimization strategy for the target optimized cell based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold includes:

[0024] Based on the fluctuation index of the current HARQ retransmission count and the second service awareness index, a first target service awareness index for the current HARQ retransmission count is determined.

[0025] Based on the fluctuation index of the current CCE aggregation level and the second business perception index, determine the second target business perception index of the current CCE aggregation level;

[0026] Based on the fluctuation index of the current neighbor cell reference signal interference avoidance parameter and the second service perception index, a third target service perception index of the current neighbor cell reference signal interference avoidance parameter is determined.

[0027] Based on the fluctuation index of the current MCS rapid selection parameters and the second service perception index, determine the fourth target service perception index of the current MCS rapid selection parameters.

[0028] Based on the first target service perception index, the second target service perception index, the third target service perception index, the fourth target service perception index, and the service perception constraint threshold, the voice service optimization strategy for the target optimized cell is output.

[0029] The step of outputting the voice service optimization strategy for the target optimized cell based on the first target service perception index, the second target service perception index, the third target service perception index, the fourth target service perception index, and the service perception constraint threshold includes:

[0030] If the first target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is output as follows: adjust the current HARQ retransmission count of the target optimized cell to its traversal parameter adjustment value; or / and

[0031] If the second target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is output as follows: adjust the current CCE aggregation level of the target optimized cell to its traversal parameter adjustment value; or / and

[0032] If the third target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is output as follows: adjust the current neighbor cell reference signal interference avoidance parameter of the target optimized cell to its traversal parameter adjustment value; or / and

[0033] If the fourth target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is to adjust the current MCS fast selection parameter of the target optimized cell to its traversal parameter adjustment value.

[0034] The step of determining the target optimization cell among the cells to be optimized based on the first service perception index and service perception constraint threshold of each cell to be optimized includes:

[0035] Determine the first user perceived rate, cell uplink packet loss rate, and cell downlink packet loss rate among the various service perception indicators;

[0036] The first packet loss rate of each cell to be optimized is calculated based on the cell uplink packet loss rate and cell downlink packet loss rate.

[0037] Cells with a first packet loss rate greater than a packet loss rate constraint threshold and a first user-perceived rate greater than a user-perceived rate constraint threshold are identified as the target optimized cells.

[0038] After outputting the voice service optimization strategy for the target optimized cell based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold, the method further includes:

[0039] The correlation matrix is ​​invoked at regular intervals, and the voice service optimization strategy for the target optimized cell is output in each time interval, in conjunction with the configuration parameters of the target optimized cell.

[0040] In a second aspect, the present invention provides a voice service optimization device comprising:

[0041] The matrix construction module is used to construct an association matrix based on the various target configuration parameters that affect the perception of voice services and the fluctuation indicators caused by their adjustment;

[0042] The determination module is used to determine the target optimization cell among the cells to be optimized based on the first service perception index and service perception constraint threshold of each cell to be optimized.

[0043] The matrix transformation module is used to transform the correlation matrix according to the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters;

[0044] The strategy output module is used to output the voice service optimization strategy of the target optimized cell based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold.

[0045] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the voice service optimization method described in the first aspect.

[0046] Fourthly, the present invention also provides a non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium comprising a computer program, which, when executed by the processor, implements the voice service optimization method described in the first aspect.

[0047] Fifthly, the present invention also provides a computer program product, the computer program product comprising a computer program, which, when executed by the processor, implements the voice service optimization method described in the first aspect.

[0048] The voice service optimization method, apparatus, electronic device, and storage medium provided by this invention construct an association matrix based on various target configuration parameters affecting voice service perception and the fluctuation indicators generated by their adjustment; determine the target optimization cell among the cells to be optimized based on the first service perception indicator and service perception constraint threshold of each cell to be optimized; transform the association matrix according to the current configuration parameters of the target optimization cell to obtain the fluctuation index of the current configuration parameters; and output the voice service optimization strategy of the target optimization cell based on the second service perception indicator of the target optimization cell, the fluctuation index of the current configuration parameters, and the service perception constraint threshold.

[0049] During the voice service optimization process, the fluctuation index of the current configuration parameters is obtained by combining the correlation matrix with the current configuration parameters of the target optimization cell. Furthermore, based on the service perception index of the target optimization cell, the fluctuation index of the current configuration parameters, and the service perception constraint threshold, a voice service optimization strategy for the target optimization cell is automatically output. This achieves automatic optimization of the voice service in the target optimization cell through the voice service optimization strategy, ensuring a good user experience for voice services within the target optimization cell's network. Attached Figure Description

[0050] To more clearly illustrate the technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating the voice service optimization method provided by the present invention;

[0052] Figure 2 This is a schematic diagram of the voice service optimization device provided by the present invention;

[0053] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0055] For the sake of brevity and intuitiveness, the following description uses several representative embodiments to illustrate the solution of the present invention. Numerous details in the embodiments are only used to aid in understanding the solution of the present invention. However, it is obvious that the technical solution of the present invention can be implemented without being limited to these details. To avoid unnecessarily obscuring the solution of the present invention, some embodiments are not described in detail, but only a framework is given. In the following text, "comprising" means "including but not limited to," and "according to..." means "at least according to..., but not limited to only according to...". Due to Chinese language habits, unless the quantity of a component is specifically indicated below, it means that the component can be one or more, or can be understood as at least one.

[0056] Combination Figures 1 to 3 This invention describes the voice service optimization method, apparatus, electronic device, and storage medium provided by the present invention. Figure 1 This is a flowchart illustrating the voice service optimization method provided by the present invention; Figure 2 This is a schematic diagram of the voice service optimization device provided by the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention.

[0057] This invention provides an embodiment of a voice service optimization method. It should be noted that although the logical order is shown in the flowchart, under certain data conditions, the steps shown or described may be completed in a different order than that shown here.

[0058] This invention uses an electronic device as an example of the execution subject, and takes a voice call service system as one of the manifestations of the electronic device, but does not impose any limitations.

[0059] Reference Figure 1 , Figure 1 This is a flowchart illustrating the voice service optimization method provided by the present invention. The voice service optimization method provided in this embodiment of the invention includes:

[0060] S101, construct an association matrix based on the various target configuration parameters that affect the perception of voice services and the fluctuation indicators caused by their adjustment.

[0061] The voice call service system identifies various target configuration parameters affecting the perceived voice service in the pilot cells. These target configuration parameters are also known as packet loss parameters, and the pilot cells are set by technical personnel. Further, the voice call service system iterates through and adjusts each target configuration parameter in the pilot cells to determine the fluctuation indicators generated by each parameter at each adjustment step. These fluctuation indicators include packet loss rate and user-perceived speed. Specifically, the voice call service system determines the packet loss rate and user-perceived speed generated by each target configuration parameter at each adjustment step. Further, the voice call service system constructs a two-dimensional correlation matrix between the configuration parameters and the fluctuation indicators based on the target configuration parameters and the resulting packet loss rate and user-perceived speed.

[0062] S102, determine the target optimization cell among the cells to be optimized based on the first service perception index and service perception constraint threshold of each cell to be optimized;

[0063] S103, the correlation matrix is ​​transformed according to the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters.

[0064] Furthermore, the voice call service system obtains the first service perception index of the cell to be optimized through the network management side. The first service perception index includes packet loss rate and user perceived rate. In other words, the voice call service system obtains the packet loss rate and user perceived rate of the cell to be optimized through the network management side.

[0065] Furthermore, the voice call service system determines whether the packet loss rate and user-perceived rate of each cell to be optimized meet the service perception constraint thresholds, which include a packet loss rate threshold and a user-perceived rate threshold. Finally, the voice call service system identifies the cells to be optimized that meet the service perception constraint thresholds in terms of both packet loss rate and user-perceived rate as target optimization cells.

[0066] Furthermore, the voice call service system determines the current configuration parameters of the target optimized cell, and transforms the correlation matrix using the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters.

[0067] S104, based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold, output the voice service optimization strategy of the target optimized cell.

[0068] Furthermore, the voice call service system determines the target service perception index for the current configuration parameters based on the second service perception index of the target optimized cell and the fluctuation index of the current configuration parameters. Further, the voice call service system determines whether the target service perception index of the current configuration parameters meets the service perception constraint threshold. If it is determined that the target service perception index of the current configuration parameters meets the service perception constraint threshold, the voice call service system outputs the voice service optimization strategy for the target optimized cell based on the current configuration parameters.

[0069] The voice service optimization method provided by this invention constructs an association matrix based on various target configuration parameters that affect voice service perception and the fluctuation indicators generated by their adjustment; determines the target optimization cell among the cells to be optimized based on the first service perception indicator and service perception constraint threshold of each cell to be optimized; transforms the association matrix based on the current configuration parameters of the target optimization cell to obtain the fluctuation index of the current configuration parameters; and outputs the voice service optimization strategy of the target optimization cell based on the second service perception indicator of the target optimization cell, the fluctuation index of the current configuration parameters, and the service perception constraint threshold.

[0070] During the voice service optimization process, the fluctuation index of the current configuration parameters is obtained by combining the correlation matrix with the current configuration parameters of the target optimization cell. Furthermore, based on the service perception index of the target optimization cell, the fluctuation index of the current configuration parameters, and the service perception constraint threshold, a voice service optimization strategy for the target optimization cell is automatically output. This achieves automatic optimization of the voice service in the target optimization cell through the voice service optimization strategy, ensuring a good user experience for voice services within the target optimization cell's network.

[0071] Furthermore, the specific analysis of the correlation matrix constructed based on the various target configuration parameters affecting the perception of voice services and the fluctuation indicators resulting from their adjustment, as described in S101, is as follows:

[0072] Determine the target HARQ retransmission count, target CCE aggregation level, target neighbor cell reference signal interference avoidance parameters, and target MCS fast order selection parameters in the target configuration parameters;

[0073] A first matrix is ​​constructed based on each step size adjustment of the target HARQ retransmission count and the resulting packet loss rate and user-perceived rate.

[0074] A second matrix is ​​constructed based on each step size adjustment of the target CCE aggregation level and the resulting packet loss rate and user-perceived rate.

[0075] A third matrix is ​​constructed based on the adjustment of the target neighbor cell reference signal interference avoidance parameters at each step size and the resulting packet loss rate and user perceived rate.

[0076] Based on the adjustment of each step size of the target MCS fast order selection parameters and the resulting packet loss rate and user-perceived speed, a fourth matrix is ​​constructed.

[0077] The first matrix, the second matrix, the third matrix, and the fourth matrix are merged according to the row merging method to construct the correlation matrix.

[0078] Specifically, the voice call service system randomly selects more than 30 cells based on the law of large numbers and determines various target configuration parameters that affect the perception of voice services in more than 30 cells. The target configuration parameters include, but are not limited to, the number of HARQ (hybrid automatic repeat request) retransmissions, CCE aggregation level, neighbor cell reference signal interference avoidance, and MCS fast level selection.

[0079] Regarding the number of HARQ retransmissions, the gNodeB (5G base station) instructs voice users to perform a maximum of 4 HARQ retransmissions at the MAC layer. However, if the user is at the cell edge, it may not be possible to ensure that the uplink data is transmitted completely and accurately. By further increasing the number of retransmissions, the cell packet loss rate can be reduced. It is supported to adjust the maximum number of HARQ retransmissions to 8 times, that is, the parameter step size of the number of HARQ retransmissions is 4 times.

[0080] For CCE aggregation level, the PDCCH CCE aggregation level is improved by adjusting the SINR value of the voice service PDCCH, the BLER of the PDCCH, and the offset of the retransmitted PDCCH CCE aggregation level, thereby reducing voice packet loss and improving the voice service experience. The parameters of CCE aggregation level can be adjusted to 1 / 2 / 4 / 8 / 16, with a step size of 4 times.

[0081] The neighbor cell reference signal interference avoidance parameter is addressed through the VoNR user neighbor cell CSI-RS for CM interference avoidance function. VoNR users in the serving cell will avoid the time-frequency domain resource locations where CSI-RS for CM (including periodic and aperiodic CSI-RS for CM) transmitted by neighbor cells are located, i.e., PDSCH is not scheduled, thereby avoiding mutual interference between the serving cell's PDSCH and the neighbor cell's CSI-RS for CM. The neighbor cell reference signal interference avoidance parameter can be set to on or off, with a step size of 1.

[0082] For the MCS fast order selection parameter, when the initial HARQ feedback for voice services is NACK, the gNodeB adjusts the downlink MCS order to match the channel quality by reducing the downlink MCS order, thereby improving transmission reliability. The MCS fast order selection parameter ranges from 0 to 28, with a step size of 28.

[0083] The voice call service system iterates through and adjusts various target configuration parameters in the pilot cells to determine the fluctuation index of each target configuration parameter at each adjustment step. The formula for calculating the index is as follows: Where v is the adjusted indicator, v' is the indicator before adjustment, and n is the size and number of pilot communities.

[0084] The voice call service system constructs a first matrix based on the target HARQ retransmission count, the step size adjustment, the resulting packet loss rate, and the user-perceived speed. This first matrix can be represented as matrix M. a*4 In this table, row 'a' represents the number of cells, and the four columns represent the original number of HARQ retransmissions, the step size adjustment after step size adjustment, the packet loss rate caused by step size adjustment, and the user-perceived speed caused by step size adjustment, respectively.

[0085] The voice call service system constructs a second matrix based on the target CCE aggregation level, each step size adjustment, and the resulting packet loss rate and user-perceived speed. This second matrix can be represented as matrix M. a*4 The row number 'a' represents the number of cells, and the four columns respectively represent the original CCE aggregation level, the CCE aggregation level after step size adjustment, the packet loss rate caused by step size adjustment, and the user-perceived rate caused by step size adjustment.

[0086] The voice call service system constructs a third matrix based on the target neighbor cell reference signal interference avoidance parameters at each step size and the resulting packet loss rate and user-perceived speed. This third matrix can be represented as matrix M. a*4 In this table, row 'a' represents the number of cells, and the four columns represent the original neighbor reference signal interference avoidance parameters, the neighbor reference signal interference avoidance parameters after step size adjustment, the packet loss rate caused by step size adjustment, and the user perception rate caused by step size adjustment, respectively.

[0087] The voice call service system constructs a fourth matrix based on the target MCS fast order selection parameters, the step size adjustment, and the resulting packet loss rate and user-perceived speed. This fourth matrix can be represented as matrix M. a*4 In this table, row 'a' represents the number of cells, and the four columns respectively represent the original MCS fast order selection parameters, the MCS fast order selection parameters after step size adjustment, the packet loss rate caused by step size adjustment, and the user-perceived rate caused by step size adjustment.

[0088] Furthermore, the voice call service system merges the first, second, third, and fourth matrices according to the row merging method to construct an association matrix.

[0089] In one embodiment, 50 5G cells are randomly selected from the existing network as a verification set, with HARQ retransmission number optimization as an example.

[0090] The number of HARQ reselections was optimized from 4 to 5, 6, 7 and 8. The packet loss rate and user-perceived speed of 50 cells were statistically analyzed and recorded after the relevant parameter adjustments.

[0091] Regarding the optimization of HARQ reselection count, when the parameter setting value of HARQ reselection count was adjusted from 4 to 5, the packet loss rate of 25 cells decreased by 0.06, and the packet loss rate of 25 cells decreased by 0.04; while the user perceived speed of 25 cells decreased by 18Mbps, and that of the other 25 cells decreased by 22Mbps.

[0092] The average value of the fluctuations in the relevant user metrics was calculated and a matrix was formed. Specifically, the matrix corresponding to the HARQ reselection number optimization from 4 to 5 is [4 5 -0.05 -20], the matrix corresponding to the optimization from 5 to 6 is [5 6 -0.05 -2.0], the matrix corresponding to the optimization from 6 to 7 is [6 7 -0.03 -0.9], and the matrix corresponding to the optimization from 7 to 6 is [7 8 -0.06 -1.6].

[0093] The results of actual testing to optimize the number of HARQ reselections were confirmed, and the results were entered into matrix M. 1 4*4 The matrix consists of two columns, the first two columns representing the parameter settings before and after HARQ reselection number adjustment, and the last two columns representing the packet loss rate and user-perceived speed increase resulting from the adjustment. Therefore, M... 1 4*4 The matrix is ​​represented as:

[0094] M 1 4*4 =[4 5 -0.06 -0.5]

[0095] [5 6 -0.05 -2.0]

[0096] [6 7 -0.03 -0.9]

[0097] [7 8 -0.06 -1.6]

[0098] Similarly, the CCE aggregation level, neighbor cell reference signal interference avoidance, and MCS fast order selection adjustment respectively yield three mapping matrices M. 2 4*4 M 3 4*4 M 4 4*4 Merge M by row 1 4*4 M 2 4*4 M 3 4*4 M 44*4 This yields a multi-dimensional correlation matrix consisting of four parameters.

[0099] It should be noted that since the adjustment step size for HARQ retransmission count is 4, the adjustment step size for CCE aggregation level is 4, the adjustment step size for neighboring cell reference signal interference avoidance is 1, and the adjustment step size for MCS fast order selection is 28, the total adjustment step size is 37, that is, the dimension of the correlation matrix is ​​37, that is, the correlation matrix is ​​a 4*37 dimension correlation matrix composed of four parameters.

[0100] This invention constructs an association matrix using HARQ retransmission count, CCE aggregation level, neighbor cell reference signal interference avoidance parameters, and MCS fast order selection parameters. This matrix provides a foundation for automatically optimizing voice services in the target optimized cell through voice service optimization strategies, ensuring user perception of voice services in the target optimized cell's network.

[0101] Furthermore, the specific analysis described in S102 regarding determining the target optimization cell among the cells to be optimized based on the first service perception index and service perception constraint threshold of each cell to be optimized is as follows:

[0102] Determine the first user perceived rate, cell uplink packet loss rate, and cell downlink packet loss rate among the various service perception indicators;

[0103] The first packet loss rate of each cell to be optimized is calculated based on the cell uplink packet loss rate and cell downlink packet loss rate.

[0104] Cells with a first packet loss rate greater than a packet loss rate constraint threshold and a first user-perceived rate greater than a user-perceived rate constraint threshold are identified as the target optimized cells.

[0105] Specifically, the voice call service system determines the first user-perceived rate, uplink packet loss rate, and downlink packet loss rate for each cell to be optimized. Further, the voice call service system calculates the average packet loss rate based on the uplink and downlink packet loss rates of each cell to be optimized, and determines the average packet loss rate as the first packet loss rate for each cell to be optimized, using the following formula: R lost =(R lost_ul +R lost_dl ) / 2, where R lost_ul R represents the uplink packet loss rate of the cell. lost_dl R represents the downlink packet loss rate of the cell. lost This represents the average packet loss rate.

[0106] Furthermore, the voice call service system identifies cells to be optimized that have a first packet loss rate (average packet loss rate) greater than the packet loss rate constraint threshold and a first user-perceived rate greater than the user-perceived rate constraint threshold as target optimization cells.

[0107] In one embodiment, the packet loss rate constraint threshold is 0.5, and the user-perceived rate constraint threshold is 20 Mbps (megabits per second). Taking three cells A1, A2, and A3 under base station A as an example: Cell A1 has an uplink packet loss rate of 0.55, a downlink packet loss rate of 0.55, and a user-perceived rate of 21 Mbps; Cell A2 has an uplink packet loss rate of 0.65, a downlink packet loss rate of 0.55, and a user-perceived rate of 18 Mbps; Cell A3 has an uplink packet loss rate of 0.69, a downlink packet loss rate of 0.75, and a user-perceived rate of 48 Mbps.

[0108] Averaging the uplink and downlink packet loss rates, we find that: Cell A1 has a packet loss rate of 0.55, which is greater than the packet loss rate constraint threshold of 0.5, and a user-perceived speed of 21 Mbps, which is greater than the user-perceived speed constraint threshold of 20 Mbps; Cell A2 has a packet loss rate of 0.60, which is greater than the packet loss rate constraint threshold of 0.5, and a user-perceived speed of 18 Mbps, which is less than the user-perceived speed constraint threshold of 20 Mbps; Cell A3 has a packet loss rate of 0.72, which is greater than the packet loss rate constraint threshold of 0.5, and a user-perceived speed of 48 Mbps, which is greater than the user-perceived speed constraint threshold of 20 Mbps. Therefore, the target optimized cell among Cells A1, A2, and A3 is Cell A1 and Cell A3.

[0109] The embodiments of the present invention determine the target optimized cell by using a first packet loss rate, a first user-perceived rate, a packet loss rate constraint threshold, and a user-perceived rate constraint threshold, thereby providing a data foundation for ensuring user perception of voice services in the network of the target optimized cell.

[0110] Furthermore, the specific analysis of the fluctuation index of the current configuration parameters obtained by transforming the correlation matrix according to the current configuration parameters of the target optimized cell, as described in S103, is as follows:

[0111] Determine the current HARQ retransmission count, current CCE aggregation level, current neighbor cell reference signal interference avoidance parameter, and current MCS fast order selection parameter in the current configuration parameters;

[0112] The correlation matrix is ​​transformed based on the current HARQ retransmission count and its traversal parameter adjustment value to obtain the fluctuation index of the current HARQ retransmission count.

[0113] The correlation matrix is ​​transformed based on the current CCE aggregation level and its traversal parameter adjustment value to obtain the volatility index of the current CCE aggregation level;

[0114] The correlation matrix is ​​transformed based on the current neighboring cell reference signal interference avoidance parameters and their traversal parameter adjustment values ​​to obtain the fluctuation index of the current neighboring cell reference signal interference avoidance parameters;

[0115] The correlation matrix is ​​transformed based on the current MCS fast order selection parameters and their traversal parameter adjustment values ​​to obtain the fluctuation index of the current MCS fast order selection parameters.

[0116] Specifically, the voice call service system determines the current HARQ retransmission count, current CCE aggregation level, current neighbor cell reference signal interference avoidance parameters, and current MCS fast order selection parameters in the current configuration parameters. Further, the voice call service system transforms the correlation matrix based on the current HARQ retransmission count and its traversal parameter adjustment values ​​to obtain the packet loss rate and user-perceived speed for the current HARQ retransmission count. Further, the voice call service system transforms the correlation matrix based on the current CCE aggregation level and its traversal parameter adjustment values ​​to obtain the packet loss rate and user-perceived speed for the current CCE aggregation level. Further, the voice call service system transforms the correlation matrix based on the current neighbor cell reference signal interference avoidance parameters and its traversal parameter adjustment values ​​to obtain the packet loss rate and user-perceived speed for the current neighbor cell reference signal interference avoidance parameters. Further, the voice call service system transforms the correlation matrix based on the current MCS fast order selection parameters and its traversal parameter adjustment values ​​to obtain the packet loss rate and user-perceived speed for the current MCS fast order selection parameters.

[0117] Taking the optimization of HARQ retransmission count as an example, the original correlation matrix of HARQ retransmission count is M. 1 4*4 M 1 4*4＝ [a i a i+1 R lost _i v_i], where, a i The original parameter setting for the number of HARQ retransmissions, a i+1 The parameter setting value after adjusting the unit step size for the HARQ retransmission count, R lost _i is the packet loss rate after adjusting the number of HARQ retransmissions, v_i is the user-perceived rate after adjusting the number of HARQ retransmissions, i∈(1,n), where n is the total number of steps, i.e. n=37.

[0118] After transforming the incidence matrix, the target matrix obtained is M. 1’ 4*4 M 1’ 4*4＝ [a'a' i R' lost_i v'_i], where a' is the parameter setting value for the current HARQ retransmission count, a' i The current HARQ retransmission count is adjusted by the traversal parameter R'. lost _i is the packet loss rate after adjusting the current HARQ retransmission count, v'_i is the user-perceived rate after adjusting the current HARQ retransmission count, i∈(1,n), where n is the total number of steps, i.e. n=37.

[0119] Taking cell A1 as an example, the HARQ retransmission count is set to 4, the CCE aggregation level is 2, the neighbor reference signal interference avoidance is 0 (off), and the MCS fast selection level is 20.

[0120] Taking HARQ retransmission data as an example, matrix transformation is implemented in cell A1. Specifically, the parameter values ​​for calculating HARQ retransmission data are adjusted from 4 to 5, 6, 7, and 8 respectively, based on packet loss rate and user-perceived rate, to achieve matrix transformation. The transformed matrix is ​​as follows:

[0121] M 1’ 4*4 =[4 5 -0.06 -0.5]

[0122] [4 6 -0.11 -2.5]

[0123] [4 7 -0.14 -3.4]

[0124] [4 8 -0.2 -5.0]

[0125] This invention employs a linear exploration approach to achieve automated optimization of speech metrics with lower complexity, reducing the complexity from O(n^2). 4 The computational cost has been reduced to O(n), thus lowering the resource computational overhead.

[0126] Furthermore, the specific analysis of outputting the voice service optimization strategy for the target optimized cell based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold, as described in S104, is as follows:

[0127] Based on the fluctuation index of the current HARQ retransmission count and the second service awareness index, a first target service awareness index for the current HARQ retransmission count is determined.

[0128] Based on the fluctuation index of the current CCE aggregation level and the second business perception index, determine the second target business perception index of the current CCE aggregation level;

[0129] Based on the fluctuation index of the current neighbor cell reference signal interference avoidance parameter and the second service perception index, a third target service perception index of the current neighbor cell reference signal interference avoidance parameter is determined.

[0130] Based on the fluctuation index of the current MCS rapid selection parameters and the second service perception index, determine the fourth target service perception index of the current MCS rapid selection parameters.

[0131] Based on the first target service perception index, the second target service perception index, the third target service perception index, the fourth target service perception index, and the service perception constraint threshold, the voice service optimization strategy for the target optimized cell is output.

[0132] Specifically, the voice call service system determines a first target service perception indicator for the current HARQ retransmission count based on the fluctuation index of the current HARQ retransmission count and a second service perception indicator. The voice call service system determines a second target service perception indicator for the current CCE aggregation level based on the fluctuation index of the current CCE aggregation level and the second service perception indicator. The voice call service system determines a third target service perception indicator for the current neighbor cell reference signal interference avoidance parameters based on the fluctuation index of the current neighbor cell reference signal interference avoidance parameters and the second service perception indicator. The voice call service system determines a fourth target service perception indicator for the current MCS fast order selection parameters based on the fluctuation index of the current MCS fast order selection parameters and the second service perception indicator.

[0133] In one embodiment, taking the current HARQ retransmission count as an example, the packet loss rate in the fluctuation index of the current HARQ retransmission count is 0.06, the user-perceived rate is 0.5Mbps, the packet loss rate in the second service perception index is 0.55, and the user-perceived rate is 21Mbps. Then, the packet loss rate in the target service perception index of the current HARQ retransmission count is 0.55-0.05=0.49, and the user-perceived rate is 21-0.5=20.5Mbps.

[0134] Furthermore, the voice call service system determines target service perception indicators and service perception constraint thresholds. The target service perception indicators are the packet loss rate and user-perceived speed optimized using an association matrix. The service perception constraint thresholds are the packet loss rate constraint threshold and user-perceived speed constraint threshold set by technical personnel. It should be further noted that the target service perception indicators meet the service perception constraint thresholds if the optimized packet loss rate is less than the optimized packet loss rate constraint threshold and the optimized user-perceived speed is greater than the optimized service perception constraint threshold.

[0135] Furthermore, the voice call service system outputs a voice service optimization strategy for the target optimized cell based on the first target service perception indicator, the second target service perception indicator, the third target service perception indicator, the fourth target service perception indicator, and the service perception constraint threshold. Specifically, this can be understood as follows: if the target service perception indicator meets the service perception constraint threshold, the parameter adjustment strategy is recorded and input. If the target service perception indicator does not meet the service perception constraint threshold, the parameter adjustment for that dimension is canceled, and a second-best parameter dimension that meets the threshold standard and its corresponding adjustment value are selected. This process continues until a suitable parameter adjustment strategy is output.

[0136] Furthermore, if the packet loss rate after adjusting any single-dimensional parameter fails to meet the constraints, the parameter dimension and its corresponding adjustment value that are closest to the threshold standard are selected first. If the user-perceived rate also meets the constraints, the parameter adjustment strategy is recorded. At the same time, the parameter dimension and its corresponding adjustment value that are next closest to the threshold standard are identified. If the user-perceived rate does not meet the constraints, the adjustment of that parameter dimension is canceled. This process continues until a suitable parameter adjustment strategy is output.

[0137] Furthermore, based on the first target service perception index, the second target service perception index, the third target service perception index, the fourth target service perception index, and the service perception constraint threshold, the specific analysis of the voice service optimization strategy for the target optimized cell is as follows:

[0138] If the first target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is output as follows: adjust the current HARQ retransmission count of the target optimized cell to its traversal parameter adjustment value; or / and

[0139] If the second target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is output as follows: adjust the current CCE aggregation level of the target optimized cell to its traversal parameter adjustment value; or / and

[0140] If the third target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is output as follows: adjust the current neighbor cell reference signal interference avoidance parameter of the target optimized cell to its traversal parameter adjustment value; or / and

[0141] If the fourth target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is to adjust the current MCS fast selection parameter of the target optimized cell to its traversal parameter adjustment value.

[0142] Specifically, if the first target service perception indicator meets the service perception constraint threshold, the voice call service system outputs a voice service optimization strategy to adjust the current HARQ retransmission count of the target optimized cell to its traversal parameter adjustment value. If the second target service perception indicator meets the service perception constraint threshold, the voice call service system outputs a voice service optimization strategy to adjust the current CCE aggregation level of the target optimized cell to its traversal parameter adjustment value. If the third target service perception indicator meets the service perception constraint threshold, the voice call service system outputs a voice service optimization strategy to adjust the current neighbor cell reference signal interference avoidance parameter of the target optimized cell to its traversal parameter adjustment value. If the fourth target service perception indicator meets the service perception constraint threshold, the voice call service system outputs a voice service optimization strategy to adjust the current MCS fast selection parameter of the target optimized cell to its traversal parameter adjustment value.

[0143] In one embodiment, the packet loss rate constraint threshold is 0.5, meaning the optimized packet loss rate must be less than 0.5; the user-perceived rate constraint threshold is 20 Mbps, meaning the optimized user-perceived rate must be greater than 20 Mbps. Taking cell A1 as an example, cell A1 has a packet loss rate of 0.55 and a user-perceived rate of 21 Mbps. Parameter optimization ensures that the packet loss rate is below 0.5 and the user-perceived rate is greater than or equal to 20 Mbps. The corresponding parameters are set as follows: HARQ retransmission count is set to 4, CCE aggregation level is 2, neighbor reference signal interference avoidance is 0 (off), and MCS fast selection level is 20.

[0144] In cell A1, the packet loss rate decreased by 0.06% with HARQ retransmission count and CCE aggregation level, meaning the optimized packet loss rate was 0.49%. The packet loss rate decreased by less than 0.05% with neighbor reference signal interference avoidance parameters and MCS fast order selection parameters, meaning the optimized packet loss rate was greater than 0.5%. Therefore, HARQ retransmission count and CCE aggregation level were chosen as the optimization parameters for cell A. Optimizing the HARQ retransmission count from 4 to 5 resulted in a 0.06% decrease in packet loss rate and a 0.5Mbps decrease in user-perceived rate; optimizing the CCE aggregation level from 2 to 4 resulted in a 0.06% decrease in packet loss rate and a 1.5Mbps decrease in user-perceived rate.

[0145] At this point, optimizing the HARQ retransmission count from 4 to 5 results in a 0.5 Mbps decrease in the perceived user rate. This means the perceived user rate after the HARQ retransmission count optimization is 20.5 Mbps, which is greater than the user rate constraint threshold of 20 Mbps, thus satisfying the user rate constraint condition. However, optimizing the CCE aggregation level from 2 to 4 results in a 1.5 Mbps decrease in the perceived user rate. This means the perceived user rate after the CCE aggregation level optimization is 19.5 Mbps, which is less than the user rate constraint threshold of 20 Mbps, thus not satisfying the perceived rate constraint condition. Therefore, the voice service optimization strategy for cell A1 is to optimize the HARQ retransmission count from 4 to 5.

[0146] In another embodiment, the packet loss rate constraint threshold is 0.5, meaning the optimized packet loss rate must be less than 0.5; the user-perceived rate constraint threshold is 20Mbps, meaning the optimized user-perceived rate must be greater than 20Mbps. Taking cell A3 as an example, cell A3 has a packet loss rate of 0.72 and a user-perceived rate of 48Mbps.

[0147] The HARQ retransmission count is set to 4 times, and can be adjusted up to 8 times. The corresponding packet loss rate decreases by 0.4%, and the user-perceived speed decreases by 5Mbps.

[0148] The CCE aggregation level is 8, which can be adjusted up to 16, corresponding to a 0.08% decrease in packet loss rate and a 5Mbps decrease in perceived speed for the user.

[0149] Neighboring cell reference signal interference avoidance is 0 (off), which can be adjusted to 1 (on), resulting in a 0.1% decrease in packet loss rate and a 10Mbps decrease in user perceived speed.

[0150] The MCS fast selection level is 10, which can be adjusted to 0, resulting in a 0.45% decrease in packet loss rate and a 30Mbps decrease in perceived speed for the user.

[0151] Therefore, the priority is to adjust the MCS fast selection level from 10 to 0. Although the packet loss rate can be reduced by 0.72 to 0.27, the user perceived rate decreases by 30Mbps to only 18Mbps, which does not meet the user perceived rate constraint threshold. Therefore, the MCS fast selection level will not be adjusted.

[0152] In the suboptimal parameter dimension scheme, setting the HARQ retransmission count can reduce the packet loss rate by 0.4, which is better than other parameter adjustment dimensions. The user-perceived rate decreases from 48Mbps to 43Mbps, meeting the threshold condition. Therefore, this parameter adjustment strategy is recorded first. Then, based on the expected packet loss rate of 0.32, setting the neighbor cell reference signal interference avoidance under the transformation matrix from 0 to 1 reduces the packet loss rate to 0.22, while the user-perceived rate decreases by 10Mbps to 33Mbps. Therefore, this parameter adjustment strategy is recorded. Continuing to identify the parameter dimensions closest to the threshold standard and their corresponding adjustment values, it is calculated that when the CCE aggregation level is adjusted from 8 to 16, the packet loss rate decreases from 0.08 to 0.14, and the user-perceived rate decreases by 5Mbps to 38Mbps, meeting the threshold condition. Therefore, this parameter adjustment strategy is recorded. Therefore, the voice service optimization strategy for cell A3 needs to be: adjust the HARQ retransmission count from 4 to 8; set the neighbor cell reference signal interference avoidance from 0 to 1; and adjust the CCE aggregation level from 8 to 16.

[0153] This invention, through an association matrix combined with the current configuration parameters of the target optimized cell, obtains the fluctuation index of the current configuration parameters. Furthermore, based on the service perception index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service perception constraint threshold, it automatically outputs a voice service optimization strategy for the target optimized cell. This achieves automatic optimization of the voice service in the target optimized cell through the voice service optimization strategy, ensuring a positive user experience for voice services within the target optimized cell's network.

[0154] Furthermore, after S104 outputs the voice service optimization strategy for the target optimized cell based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold, it also includes:

[0155] The correlation matrix is ​​invoked at regular intervals, and the voice service optimization strategy for the target optimized cell is output in each time interval, in conjunction with the configuration parameters of the target optimized cell.

[0156] Specifically, since packet loss rate and user perceived speed change in real time, the voice call service system needs to call the correlation matrix every time period, and combine it with the configuration parameters of the target optimized cell to output the voice service optimization strategy of the target optimized cell in each time period.

[0157] In this embodiment of the invention, the voice service optimization strategy of the target optimized cell is output at regular intervals, ensuring the real-time performance of packet loss rate and user perception rate, and guaranteeing the user perception of voice services in the network of the target optimized cell.

[0158] Furthermore, the voice service optimization device and the voice service optimization method provided by the present invention correspond to each other.

[0159] Figure 2 As shown, Figure 2 This is a schematic diagram of the voice service optimization device provided by the present invention. The voice service optimization device includes:

[0160] The matrix construction module 201 is used to construct an association matrix based on the various target configuration parameters that affect the perception of voice services and the fluctuation indicators caused by their adjustment.

[0161] The determining module 202 is used to determine the target optimized cell among the cells to be optimized based on the first service perception index and service perception constraint threshold of each cell to be optimized.

[0162] The matrix transformation module 203 is used to transform the correlation matrix according to the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters;

[0163] The strategy output module 204 is used to output the voice service optimization strategy of the target optimized cell based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold.

[0164] Furthermore, the matrix construction module 201 is also used for:

[0165] Determine the target HARQ retransmission count, target CCE aggregation level, target neighbor cell reference signal interference avoidance parameters, and target MCS fast order selection parameters in the target configuration parameters;

[0166] A first matrix is ​​constructed based on each step size adjustment of the target HARQ retransmission count and the resulting packet loss rate and user-perceived rate.

[0167] A second matrix is ​​constructed based on each step size adjustment of the target CCE aggregation level and the resulting packet loss rate and user-perceived rate.

[0168] A third matrix is ​​constructed based on the adjustment of the target neighbor cell reference signal interference avoidance parameters at each step size and the resulting packet loss rate and user perceived rate.

[0169] Based on the adjustment of each step size of the target MCS fast order selection parameters and the resulting packet loss rate and user-perceived speed, a fourth matrix is ​​constructed.

[0170] The first matrix, the second matrix, the third matrix, and the fourth matrix are merged according to the row merging method to construct the correlation matrix.

[0171] Furthermore, module 202 is also used for:

[0172] Determine the first user perceived rate, cell uplink packet loss rate, and cell downlink packet loss rate among the various service perception indicators;

[0173] The first packet loss rate of each cell to be optimized is calculated based on the cell uplink packet loss rate and cell downlink packet loss rate.

[0174] Cells with a first packet loss rate greater than a packet loss rate constraint threshold and a first user-perceived rate greater than a user-perceived rate constraint threshold are identified as the target optimized cells.

[0175] Furthermore, the matrix transformation module 203 is also used for:

[0176] Determine the current HARQ retransmission count, current CCE aggregation level, current neighbor cell reference signal interference avoidance parameter, and current MCS fast order selection parameter in the current configuration parameters;

[0177] The correlation matrix is ​​transformed based on the current HARQ retransmission count and its traversal parameter adjustment value to obtain the fluctuation index of the current HARQ retransmission count.

[0178] The correlation matrix is ​​transformed based on the current CCE aggregation level and its traversal parameter adjustment value to obtain the volatility index of the current CCE aggregation level;

[0179] The correlation matrix is ​​transformed based on the current neighboring cell reference signal interference avoidance parameters and their traversal parameter adjustment values ​​to obtain the fluctuation index of the current neighboring cell reference signal interference avoidance parameters;

[0180] The correlation matrix is ​​transformed based on the current MCS fast order selection parameters and their traversal parameter adjustment values ​​to obtain the fluctuation index of the current MCS fast order selection parameters.

[0181] Furthermore, the strategy output module 204 is also used for:

[0182] Based on the fluctuation index of the current HARQ retransmission count and the second service awareness index, a first target service awareness index for the current HARQ retransmission count is determined.

[0183] Based on the fluctuation index of the current CCE aggregation level and the second business perception index, determine the second target business perception index of the current CCE aggregation level;

[0184] Based on the fluctuation index of the current neighbor cell reference signal interference avoidance parameter and the second service perception index, a third target service perception index of the current neighbor cell reference signal interference avoidance parameter is determined.

[0185] Based on the fluctuation index of the current MCS rapid selection parameters and the second service perception index, determine the fourth target service perception index of the current MCS rapid selection parameters.

[0186] Based on the first target service perception index, the second target service perception index, the third target service perception index, the fourth target service perception index, and the service perception constraint threshold, the voice service optimization strategy for the target optimized cell is output.

[0187] Furthermore, the strategy output module 204 is also used for:

[0188] If the first target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is output as follows: adjust the current HARQ retransmission count of the target optimized cell to its traversal parameter adjustment value; or / and

[0189] If the second target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is output as follows: adjust the current CCE aggregation level of the target optimized cell to its traversal parameter adjustment value; or / and

[0190] If the third target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is output as follows: adjust the current neighbor cell reference signal interference avoidance parameter of the target optimized cell to its traversal parameter adjustment value; or / and

[0191] If the fourth target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is to adjust the current MCS fast selection parameter of the target optimized cell to its traversal parameter adjustment value.

[0192] Furthermore, the strategy output module 204 is also used for:

[0193] The correlation matrix is ​​invoked at regular intervals, and the voice service optimization strategy for the target optimized cell is output in each time interval, in conjunction with the configuration parameters of the target optimized cell.

[0194] The specific embodiments of the voice service optimization device provided by the present invention are basically the same as the embodiments of the above-described voice service optimization method, and will not be described in detail here.

[0195] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a voice service optimization method, which includes:

[0196] A correlation matrix is ​​constructed based on the various target configuration parameters that affect the perception of voice services and the fluctuation indicators caused by their adjustments.

[0197] Based on the first service perception index and service perception constraint threshold of each cell to be optimized, the target optimized cell among the cells to be optimized is determined.

[0198] The correlation matrix is ​​transformed based on the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters;

[0199] Based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold, the voice service optimization strategy of the target optimized cell is output.

[0200] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0201] On the other hand, the present invention also provides a computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, which, when executed by a computer, enable the computer to execute the voice service optimization methods provided by the above methods, the method comprising:

[0202] A correlation matrix is ​​constructed based on the various target configuration parameters that affect the perception of voice services and the fluctuation indicators caused by their adjustments.

[0203] Based on the first service perception index and service perception constraint threshold of each cell to be optimized, the target optimized cell among the cells to be optimized is determined.

[0204] The correlation matrix is ​​transformed based on the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters;

[0205] Based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold, the voice service optimization strategy of the target optimized cell is output.

[0206] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the aforementioned voice service optimization methods, the method comprising:

[0207] A correlation matrix is ​​constructed based on the various target configuration parameters that affect the perception of voice services and the fluctuation indicators caused by their adjustments.

[0208] Based on the first service perception index and service perception constraint threshold of each cell to be optimized, the target optimized cell among the cells to be optimized is determined.

[0209] The correlation matrix is ​​transformed based on the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters;

[0210] Based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold, the voice service optimization strategy of the target optimized cell is output.

[0211] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0212] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0213] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A voice service optimization method, characterized in that, include: A correlation matrix is ​​constructed based on the various target configuration parameters that affect the perception of voice services and the fluctuation indicators caused by their adjustments. Based on the first service perception index and service perception constraint threshold of each cell to be optimized, the target optimized cell among the cells to be optimized is determined. The correlation matrix is ​​transformed based on the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters; Based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold, the voice service optimization strategy of the target optimized cell is output. The step of constructing a correlation matrix based on the various target configuration parameters affecting the perception of voice services and the fluctuation indicators resulting from their adjustments includes: Determine the target HARQ retransmission count, target CCE aggregation level, target neighbor cell reference signal interference avoidance parameters, and target MCS fast order selection parameters in the target configuration parameters; A first matrix is ​​constructed based on each step size adjustment of the target HARQ retransmission count and the resulting packet loss rate and user-perceived rate. A second matrix is ​​constructed based on each step size adjustment of the target CCE aggregation level and the resulting packet loss rate and user-perceived rate. A third matrix is ​​constructed based on the adjustment of the target neighbor cell reference signal interference avoidance parameters at each step size and the resulting packet loss rate and user perceived rate. Based on the adjustment of each step size of the target MCS fast order selection parameters and the resulting packet loss rate and user-perceived speed, a fourth matrix is ​​constructed. The first matrix, the second matrix, the third matrix, and the fourth matrix are merged according to the row merging method to construct the correlation matrix.

2. The voice service optimization method according to claim 1, characterized in that, The step of transforming the correlation matrix based on the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters includes: Determine the current HARQ retransmission count, current CCE aggregation level, current neighbor cell reference signal interference avoidance parameter, and current MCS fast order selection parameter in the current configuration parameters; The correlation matrix is ​​transformed based on the current HARQ retransmission count and its traversal parameter adjustment value to obtain the fluctuation index of the current HARQ retransmission count. The correlation matrix is ​​transformed based on the current CCE aggregation level and its traversal parameter adjustment value to obtain the volatility index of the current CCE aggregation level; The correlation matrix is ​​transformed based on the current neighboring cell reference signal interference avoidance parameters and their traversal parameter adjustment values ​​to obtain the fluctuation index of the current neighboring cell reference signal interference avoidance parameters; The correlation matrix is ​​transformed based on the current MCS fast order selection parameters and their traversal parameter adjustment values ​​to obtain the fluctuation index of the current MCS fast order selection parameters.

3. The voice service optimization method according to claim 2, characterized in that, The step of outputting the voice service optimization strategy for the target optimized cell based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold includes: Based on the fluctuation index of the current HARQ retransmission count and the second service awareness index, a first target service awareness index for the current HARQ retransmission count is determined. Based on the fluctuation index of the current CCE aggregation level and the second business perception index, determine the second target business perception index of the current CCE aggregation level; Based on the fluctuation index of the current neighbor cell reference signal interference avoidance parameter and the second service perception index, a third target service perception index of the current neighbor cell reference signal interference avoidance parameter is determined. Based on the fluctuation index of the current MCS rapid selection parameters and the second service perception index, determine the fourth target service perception index of the current MCS rapid selection parameters. Based on the first target service perception index, the second target service perception index, the third target service perception index, the fourth target service perception index, and the service perception constraint threshold, the voice service optimization strategy for the target optimized cell is output.

4. The voice service optimization method according to claim 3, characterized in that, The step of outputting the voice service optimization strategy for the target optimized cell based on the first target service perception index, the second target service perception index, the third target service perception index, the fourth target service perception index, and the service perception constraint threshold includes: If the first target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is to adjust the current HARQ retransmission count of the target optimized cell to its traversal parameter adjustment value. If the second target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is to adjust the current CCE aggregation level of the target optimized cell to its traversal parameter adjustment value. If the third target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is to adjust the current neighbor cell reference signal interference avoidance parameter of the target optimized cell to its traversal parameter adjustment value. If the fourth target service perception index meets the service perception constraint threshold, then the voice service optimization strategy is to adjust the current MCS fast selection parameter of the target optimized cell to its traversal parameter adjustment value.

5. The voice service optimization method according to claim 1, characterized in that, The step of determining the target optimization cell among the cells to be optimized based on the first service perception index and service perception constraint threshold of each cell to be optimized includes: Determine the first user perceived rate, cell uplink packet loss rate, and cell downlink packet loss rate among the first service perception indicators; The first packet loss rate of each cell to be optimized is calculated based on the cell uplink packet loss rate and cell downlink packet loss rate. Cells with a first packet loss rate greater than a packet loss rate constraint threshold and a first user-perceived rate greater than a user-perceived rate constraint threshold are identified as the target optimized cells.

6. The voice service optimization method according to any one of claims 1 to 5, characterized in that, After outputting the voice service optimization strategy for the target optimized cell based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold, the method further includes: The correlation matrix is ​​invoked at regular intervals, and the voice service optimization strategy for the target optimized cell is output in each time interval, in conjunction with the configuration parameters of the target optimized cell.

7. A voice service optimization device, characterized in that, include: The matrix construction module is used to construct an association matrix based on the various target configuration parameters that affect the perception of voice services and the fluctuation indicators caused by their adjustment; The determination module is used to determine the target optimization cell among the cells to be optimized based on the first service perception index and service perception constraint threshold of each cell to be optimized. The matrix transformation module is used to transform the correlation matrix according to the current configuration parameters of the target optimized cell to obtain the fluctuation index of the current configuration parameters; The strategy output module is used to output the voice service optimization strategy of the target optimized cell based on the second service awareness index of the target optimized cell, the fluctuation index of the current configuration parameters, and the service awareness constraint threshold. The matrix construction module is also used for: Determine the target HARQ retransmission count, target CCE aggregation level, target neighbor cell reference signal interference avoidance parameters, and target MCS fast order selection parameters in the target configuration parameters; A first matrix is ​​constructed based on each step size adjustment of the target HARQ retransmission count and the resulting packet loss rate and user-perceived rate. A second matrix is ​​constructed based on each step size adjustment of the target CCE aggregation level and the resulting packet loss rate and user-perceived rate. A third matrix is ​​constructed based on the adjustment of the target neighbor cell reference signal interference avoidance parameters at each step size and the resulting packet loss rate and user perceived rate. Based on the adjustment of each step size of the target MCS fast order selection parameters and the resulting packet loss rate and user-perceived speed, a fourth matrix is ​​constructed. The first matrix, the second matrix, the third matrix, and the fourth matrix are merged according to the row merging method to construct the correlation matrix.

8. An electronic device, the electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the voice service optimization method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the voice service optimization method according to any one of claims 1 to 6.

Images