Method, device, equipment and storage medium for determining voice fallback cell

Abstract

The embodiments of the present application disclose a method, apparatus, device and storage medium for determining a voice fallback cell. The method includes: determining the RSRP threshold information corresponding to each RSRP category according to the RSRP values of multiple candidate cells, the initial RSRP threshold information corresponding to multiple RSRP categories and the historical fallback information; determining the SINR threshold information corresponding to each SINR category according to the SINR values of multiple candidate cells, the initial SINR threshold information corresponding to multiple SINR categories and the historical fallback information; determining the number of candidate cells belonging to each RSRP category and each SINR category; calculating the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category; determining the target candidate cell belonging to the target RSRP category with the smallest Gini coefficient in the RSRP category and the target SINR category with the smallest Gini coefficient in the SINR category, and the target candidate cell with the largest RSRP value or the largest SINR value among the target candidate cells is the voice fallback cell. The method provided in the embodiments of the present application can determine that a cell with high signal strength and good quality is a voice fallback cell.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to a method, apparatus, device, and storage medium for determining a voice fallback cell. Background Art

[0002] Currently, the fifth generation mobile communication technology (5G) network does not support voice services. If a user terminal uses the 5G network, when a call is initiated or a call request is received, the user terminal will fall back to the fourth generation mobile communication technology (4G) network, and the 4G network will provide voice services for the user terminal.

[0003] In the existing fallback method, under the premise that the networks of all 4G cells received by the user terminal have the same frequency priority, the Reference Signal Receiving Power (RSRP) of the 4G cells received by the user terminal are sorted from high to low, and the 4G cell with the highest RSRP value is preferentially selected as the voice fallback cell. If the level value meets an absolute threshold condition, the user terminal will finally select this cell for fallback and perform voice services on this cell.

[0004] In the existing fallback method, a fallback cell is selected based on the RSRP value, which tends to select a cell with poor signal quality as the fallback cell. Summary of the Invention

[0005] The embodiments of the present application provide a method, apparatus, device, and storage medium for determining a voice fallback cell, which can determine a cell with high signal strength and good quality as a voice fallback cell, thereby improving user perception.

[0006] In a first aspect, an embodiment of the present application provides a method for determining a voice fallback cell, the method comprising:

[0007] Obtain RSRP values, Signal to Interference plus Noise Ratio (SINR) values, and historical fallback information of multiple candidate cells, including fallback success or fallback failure;

[0008] Determining RSRP threshold information corresponding to each RSRP category based on RSRP values of multiple candidate cells, initial RSRP threshold information corresponding to multiple RSRP categories, and historical fallback information; and determining SINR threshold information corresponding to each SINR category based on SINR values of multiple candidate cells, initial SINR threshold information corresponding to multiple SINR categories, and historical fallback information; wherein the RSRP category with the largest threshold among the multiple RSRP threshold information is the target RSRP category, and the SINR category with the largest threshold among the multiple SINR threshold information is the target SINR category;

[0009] Determining the number of candidate cells belonging to each RSRP category and each SINR category according to multiple RSRP threshold information and multiple SINR threshold information, RSRP values, SINR values, and historical fallback information of multiple candidate cells;

[0010] Calculate the Gini coefficient for each RSRP category and the Gini coefficient for each SINR category based on the number of candidate cells belonging to each category;

[0011] Determine, based on the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category, a target candidate cell belonging to a target RSRP category with the smallest Gini coefficient among the RSRP categories and a target candidate cell belonging to a target SINR category with the smallest Gini coefficient among the SINR categories;

[0012] The target candidate cell with the largest RSRP value or the largest SINR value among the target candidate cells is determined as the voice fallback cell.

[0013] In one possible implementation, determining RSRP threshold information corresponding to each RSRP category based on RSRP values of multiple candidate cells, initial RSRP threshold information corresponding to multiple RSRP categories, and historical fallback information includes:

[0014] Determine, based on the RSRP values of the multiple candidate cells and the initial RSRP threshold information corresponding to the multiple RSRP categories, the first RSRP threshold information corresponding to each RSRP category, and the RSRP category with the largest threshold among the multiple first RSRP threshold information as the target RSRP category;

[0015] Determining the number of candidate cells belonging to each RSRP category according to the first RSRP threshold information corresponding to each RSRP category;

[0016] Determine, based on the number of candidate cells belonging to each RSRP category and historical fallback information, the number of first candidate cells in each RSRP category that have successfully fallen back, and the number of second candidate cells in each RSRP category that have failed fallback;

[0017] Calculate the Gini coefficient of each RSRP category based on the number of first candidate cells and the number of second candidate cells in each RSRP category;

[0018] When the Gini coefficient of the target RSRP category is the smallest, the first RSRP threshold information corresponding to each RSRP category is determined to be the RSRP threshold information corresponding to each RSRP category.

[0019] In one possible implementation, determining SINR threshold information corresponding to each SINR category based on SINR values of multiple candidate cells, initial SINR threshold information corresponding to multiple SINR categories, and historical fallback information includes:

[0020] Determine, according to the SINR values of the multiple candidate cells and the initial SINR threshold information corresponding to the multiple SINR categories, the first SINR threshold information corresponding to each SINR category, and the SINR category with the largest threshold among the multiple first SINR threshold information is the target SINR category;

[0021] Determining the number of candidate cells belonging to each SINR category according to the first SINR threshold information corresponding to each SINR category;

[0022] Determine, based on the number of candidate cells belonging to each SINR category and historical fallback information, the number of third candidate cells that successfully fall back in each first SINR category, and the number of fourth candidate cells that failed fallback in each SINR category;

[0023] Calculate the Gini coefficient of each SINR category according to the number of third candidate cells and the number of fourth candidate cells in each SINR category;

[0024] When the Gini coefficient of the target SINR category is the smallest, the first SINR threshold information corresponding to each SINR category is determined to be the SINR threshold information corresponding to each SINR category.

[0025] In a possible implementation, determining, based on the Gini coefficient, a target candidate cell belonging to a target RSRP category with the smallest Gini coefficient among RSRP categories and a target SINR category with the smallest Gini coefficient among SINR categories includes:

[0026] Calculating an RSRP Gini coefficient based on the Gini coefficients of the multiple RSRP categories and a ratio of the number of candidate cells belonging to each RSRP category to the number of the multiple candidate cells;

[0027] Calculating an SINR Gini coefficient according to the Gini coefficients of the multiple SINR categories and a ratio of the number of candidate cells belonging to each SINR category to the number of the multiple candidate cells;

[0028] Determine the first candidate cell based on the RSRP Gini coefficient and the SINR Gini coefficient;

[0029] The target candidate cell is determined according to the Gini coefficient of each category in the first candidate cell.

[0030] In a possible implementation, determining the first candidate cell according to the RSRP Gini coefficient and the SINR Gini coefficient includes:

[0031] When the RSRP Gini coefficient is less than the SINR Gini coefficient, the candidate cell belonging to the target RSRP category is determined as the first candidate cell;

[0032] When the SINR Gini coefficient is less than the RSRP Gini coefficient, the candidate cell belonging to the target SINR category is determined as the first candidate cell.

[0033] In a possible implementation, when a candidate cell belonging to a target RSRP category is determined to be a first candidate cell, determining a target candidate cell according to a Gini coefficient of each category in the first candidate cell includes:

[0034] According to the Gini coefficient of each SINR category in the first candidate cell, a candidate cell of the target SINR category is determined as the target candidate cell.

[0035] In a possible implementation, when a candidate cell belonging to a target SINR category is determined to be a first candidate cell, determining a target candidate cell according to a Gini coefficient of each category in the first candidate cell includes:

[0036] According to the Gini coefficient of each RSRP category in the first candidate cell, a candidate cell of the target RSRP category is determined as the target candidate cell.

[0037] In a second aspect, an embodiment of the present application provides a device for determining a voice fallback cell, the device comprising:

[0038] An acquisition module is used to obtain RSRP values, SINR values and historical fallback information of multiple candidate cells, where the historical fallback information includes fallback success or fallback failure;

[0039] A determination module is configured to determine RSRP threshold information corresponding to each RSRP category based on RSRP values of multiple candidate cells, initial RSRP threshold information corresponding to multiple RSRP categories, and historical fallback information, and to determine SINR threshold information corresponding to each SINR category based on SINR values of multiple candidate cells, initial SINR threshold information corresponding to multiple SINR categories, and historical fallback information; wherein the RSRP category with the largest threshold value among the multiple RSRP threshold information is the target RSRP category, and the SINR category with the largest threshold value among the multiple SINR threshold information is the target SINR category; and further configured to determine the number of candidate cells belonging to each RSRP category and each SINR category based on the multiple RSRP threshold information and the multiple SINR threshold information, the RSRP values, SINR values, and historical fallback information of the multiple candidate cells;

[0040] a calculation module, configured to calculate a Gini coefficient for each RSRP category and a Gini coefficient for each SINR category based on the number of candidate cells belonging to each category;

[0041] The determination module is used to determine, based on the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category, a target RSRP category with the smallest Gini coefficient among the RSRP categories and a target SINR category with the smallest Gini coefficient among the SINR categories; and is also used to determine that the target candidate cell with the largest RSRP value or the largest SINR value among the target candidate cells is a voice fallback cell.

[0042] In a third aspect, an embodiment of the present application provides an electronic device comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the method in the first aspect or any possible implementation of the first aspect.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the method in the first aspect or any possible implementation of the first aspect is implemented.

[0044] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0045] The present application first obtains RSRP values, SINR values and historical fallback information of multiple candidate cells, determines the RSRP threshold information corresponding to each RSRP category according to the RSRP values of the multiple candidate cells, the initial RSRP threshold information corresponding to the multiple RSRP categories and the historical fallback information, and determines the SINR threshold information corresponding to each SINR category according to the SINR values of the multiple candidate cells, the initial SINR threshold information corresponding to the multiple SINR categories and the historical fallback information, the RSRP category with the largest threshold in the multiple RSRP threshold information is the target RSRP category, and the SINR category with the largest threshold in the multiple SINR threshold information is the target SINR category; then, according to the multiple RSRP threshold information and the multiple SINR threshold information, the RSRP values, SINR values and historical fallback information of the multiple candidate cells, the candidate cells belonging to each RSRP category and belonging to each SINR category are determined. The number of candidate cells is calculated, and thus the classification of multiple candidate cells is completed; then, based on the number of candidate cells belonging to each category, the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category are calculated, and the candidate cell belonging to the target RSRP category with the smallest Gini coefficient in the RSRP category and the target SINR category with the smallest Gini coefficient in the SINR category are determined as target candidate cells. Since the candidate cells in the target candidate cells belong to the RSRP category with the largest RSRP threshold and the SINR category with the largest SINR threshold, the candidate cells in the target candidate cells are RSRP-quality cells and SINR-quality cells; the target candidate cell with the largest RSRP value or the largest SINR value among the target candidate cells is determined as the voice fallback cell, and the voice fallback cell has high RSRP and high SINR. In this way, the cell with high signal strength and good quality is determined as the voice fallback cell, thereby improving user perception. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] Figure 1 This is a flow chart of a method for determining a voice fallback cell provided in an embodiment of the present application;

[0048] Figure 2 1 is a schematic diagram of the structure of a device for determining a voice fallback cell provided in an embodiment of the present application;

[0049] Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present application and are not configured to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0051] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0052] In existing fallback methods, the RSRP levels of all 4G cells received by the user terminal are ranked from high to low, assuming that all 4G cell networks have the same frequency priority. The 4G cell with the highest RSRP value is preferentially selected as the voice fallback cell. If this level meets an absolute threshold, the user terminal will ultimately select that cell for fallback and conduct voice services on that cell. This method only considers the signal strength of the fallback cell, not its signal quality. As a result, the mobile terminal may fall back to a cell with poor signal quality, resulting in poor call quality and a negative impact on user experience.

[0053] Based on the above problems, this application improves the fallback method. By determining the candidate cells with high RSRP and SINR values as voice fallback cells based on the RSRP values and SINR values of multiple candidate cells, the cell with high signal strength and good quality is determined as the voice fallback cell, thereby improving user perception.

[0054] The following will be combined Figure 1 A method for determining a voice fallback cell provided by the present application is described in detail.

[0055] The execution subject of the method provided in this application includes a mobile terminal that can make voice calls, such as a mobile phone, tablet or smart watch.

[0056] like Figure 1 As shown, the method for determining a voice fallback cell provided in an embodiment of the present application may include S110 to S160.

[0057] S110: Obtain RSRP values, SINR values, and historical fallback information of multiple candidate cells.

[0058] A candidate cell refers to a cell from which a mobile terminal can receive cell signals.

[0059] The historical fallback information refers to the voice fallback status of the mobile terminal to the candidate cell in the past, including fallback success or fallback failure.

[0060] When a mobile terminal uses a 5G network and initiates a call or receives a call request, the mobile terminal obtains the RSRP values, SINR values, and historical fallback information of multiple candidate cells that can receive candidate cell signals.

[0061] In an example, RSRP values and SINR values of multiple candidate cells are as shown in Table 1, and the cell frequency priorities of these multiple candidate cells are the same.

[0062] Table 1 RSRP values, SINR values and historical fallback information of multiple candidate cells

[0063]

[0064]

[0065] S120, determining the RSRP threshold information corresponding to each RSRP category based on the RSRP values of multiple candidate cells, the initial RSRP threshold information corresponding to multiple RSRP categories, and the historical fallback information, and determining the SINR threshold information corresponding to each SINR category based on the SINR values of multiple candidate cells, the initial SINR threshold information corresponding to multiple SINR categories, and the historical fallback information.

[0066] Among them, the RSRP category with the largest threshold value among the multiple RSRP threshold information is the target RSRP category, and the SINR category with the largest threshold value among the multiple SINR threshold information is the target SINR category.

[0067] The multiple RSRP categories refer to pre-set categories, for example, the multiple RSRP categories include good, medium, and poor categories.

[0068] The initial RSRP threshold information corresponding to the multiple RSRP categories is preset. For example, a technician sets the threshold information for each RSRP category based on experience.

[0069] However, when classifying candidate cells according to the initial RSRP threshold information, the number of candidate cells in each category obtained may not meet the preset conditions. Therefore, it is necessary to verify the initial RSRP threshold information and modify the initial RSRP threshold information when the preset conditions are not met to obtain the RSRP threshold information corresponding to each RSRP category that meets the requirements.

[0070] The larger the RSRP value of a candidate cell, the higher the signal strength of the candidate cell. The target RSRP category is the category with the largest threshold among multiple RSRP categories, so the candidate cell belonging to the target RSRP category is an RSRP-quality cell.

[0071] The mobile terminal determines RSRP threshold information corresponding to each RSRP category that meets preset conditions based on the RSRP values of multiple candidate cells, pre-set initial RSRP threshold information corresponding to multiple RSRP categories, and historical fallback information.

[0072] In an example, the preset condition may be that the Gini coefficient of each category is calculated based on the number of candidate cells in each category and historical fallback information, and the Gini coefficient of the target RSRP category is the smallest.

[0073] The calculation formula of the Gini coefficient is: Where Gini(D) represents the Gini coefficient, and k represents the decision classification of the feature.

[0074] In the embodiment of the present application, the decision classification is divided into two categories: fallback success and fallback failure, so k=2; P k Represents the probability of each classification, that is, the number of samples classified as fallback success or fallback failure in the sample divided by the total number of samples.

[0075] The multiple SINR categories refer to pre-set categories, for example, the multiple SINR categories include good, medium, and poor.

[0076] The initial SINR threshold information corresponding to the multiple SINR categories is preset. For example, a technician sets the threshold information for each SINR category based on experience.

[0077] However, the number of candidate cells in each category obtained by classifying the candidate cells according to the initial SINR threshold information may not meet the preset conditions. Therefore, it is necessary to verify the initial SINR threshold information, modify the initial SINR threshold information when the preset conditions are not met, and obtain the SINR threshold information corresponding to each SINR category that meets the requirements.

[0078] The larger the SINR value of the candidate cell, the better the signal quality of the candidate cell. The target SINR category is the category with the largest threshold among multiple SINR categories, so the candidate cell belonging to the target SINR category is an SINR-high-quality cell.

[0079] The mobile terminal determines the SINR threshold information corresponding to each SINR category that meets the preset conditions according to the SINR values of the multiple candidate cells, the pre-set initial SINR threshold information corresponding to the multiple SINR categories, and the historical fallback information.

[0080] In an example, the preset condition may be that the Gini coefficient of each category is calculated based on the number of candidate cells in each category and historical fallback information, and the Gini coefficient of the target SINR category is the smallest.

[0081] The calculation formula of the Gini coefficient is: Where Gini(D) represents the Gini coefficient, and k represents the decision classification of the feature.

[0082] In the embodiment of the present application, the decision classification is divided into two categories: fallback success and fallback failure, so k=2; P k Represents the probability of each classification, that is, the number of samples classified as fallback success or fallback failure in the sample divided by the total number of samples.

[0083] After determining the RSRP threshold information corresponding to each RSRP category and determining the SINR threshold information corresponding to each SINR category, step 130 is performed.

[0084] S130 : Determine the number of candidate cells belonging to each RSRP category and each SINR category according to the multiple RSRP threshold information and the multiple SINR threshold information, the RSRP values, SINR values, and historical fallback information of the multiple candidate cells.

[0085] The mobile terminal classifies the multiple candidate cells according to the multiple RSRP threshold information and the multiple SINR threshold information, the RSRP values, SINR values and historical fallback information of the multiple candidate cells, and determines the number of candidate cells belonging to each RSRP category and each SINR category.

[0086] In one example, the number of candidate cells belonging to each RSRP category and each SINR category is shown in Table 2.

[0087] Table 2 Number of candidate cells belonging to each RSRP category and each SINR category

[0088] RSRP Category Fallback success Fallback failure total good 7 2 9 middle 1 1 2 Difference 1 3 4 SINR Category Fallback success Fallback failure total good 7 1 8 middle 1 3 4 Difference 1 2 3

[0089] S140 , calculating the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category according to the number of candidate cells belonging to each category.

[0090] The mobile terminal calculates the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category using the calculation formula of the Gini coefficient according to the number of candidate cells belonging to each category.

[0091] In one example, the Gini coefficient for each RSRP category and the Gini coefficient for each SINR category are calculated as follows:

[0092] Here, Gini(RSRP=good) represents the Gini coefficient when the RSRP category is “good”.

[0093] Here, Gini(RSRP=medium) represents the Gini coefficient when the RSRP category is “good”.

[0094] Here, Gini(RSRP=bad) represents the Gini coefficient when the RSRP category is “good”.

[0095] Here, Gini(SINR=good) represents the Gini coefficient when the SINR category is "good".

[0096] Here, Gini(SINR=medium) represents the Gini coefficient for the SINR category of “medium”.

[0097] Here, Gini(SINR=poor) represents the Gini coefficient when the SINR category is "poor".

[0098] S150 , determining, based on the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category, a target candidate cell belonging to a target RSRP category with the smallest Gini coefficient among the RSRP categories and a target SINR category with the smallest Gini coefficient among the SINR categories.

[0099] The mobile terminal compares the Gini coefficients of each RSRP category and determines a candidate cell belonging to a target RSRP category with the smallest Gini coefficient among the RSRP categories; the mobile terminal compares the Gini coefficients of each SINR category and determines a candidate cell belonging to a target RSRP category with the smallest Gini coefficient among the SINR categories; and then determines that the candidate cell belonging to the target RSRP category with the smallest Gini coefficient among the RSRP categories and the target SINR category with the smallest Gini coefficient among the SINR categories is the target candidate cell.

[0100] The candidate cells in the target candidate cells determined in this step belong to the RSRP category with the largest RSRP threshold and the SINR category with the largest SINR threshold. Therefore, the candidate cells in the target candidate cells are RSRP-quality cells and SINR-quality cells. Therefore, the signal strength of any cell of the target candidate cells is high and the quality is good. By using any cell in the target candidate cells as a voice fallback cell, the cell with high signal strength and good quality can be determined as the voice fallback cell.

[0101] After the target candidate cell is determined, step S160 is executed.

[0102] S160: Determine the target candidate cell with the largest RSRP value or the largest SINR value among the target candidate cells as the voice fallback cell.

[0103] The mobile terminal compares the RSRP values of the target candidate cells and determines the target candidate cell with the largest RSRP value as the voice fallback cell.

[0104] Or the mobile terminal compares the SINR values of the target candidate cells and determines the target candidate cell with the largest SINR value as the voice fallback cell.

[0105] The method provided in the embodiment of the present application first obtains RSRP values, SINR values and historical fallback information of multiple candidate cells, and determines the RSRP threshold information corresponding to each RSRP category according to the RSRP values of the multiple candidate cells, the initial RSRP threshold information corresponding to the multiple RSRP categories and the historical fallback information, and determines the SINR threshold information corresponding to each SINR category according to the SINR values of the multiple candidate cells, the initial SINR threshold information corresponding to the multiple SINR categories and the historical fallback information, the RSRP category with the largest threshold in the multiple RSRP threshold information is the target RSRP category, and the SINR category with the largest threshold in the multiple SINR threshold information is the target SINR category; then, according to the multiple RSRP threshold information and the multiple SINR threshold information, the RSRP values, SINR values and historical fallback information of the multiple candidate cells, the candidate cells belonging to each RSRP category and the candidate cells belonging to each SINR category are determined. The number of cells is selected, so that multiple candidate cells are classified. Then, based on the number of candidate cells belonging to each category, the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category are calculated, and the candidate cell belonging to the target RSRP category with the smallest Gini coefficient in the RSRP category and the target SINR category with the smallest Gini coefficient in the SINR category are determined as the target candidate cells. Since the candidate cells in the target candidate cells belong to the RSRP category with the largest RSRP threshold and the SINR category with the largest SINR threshold, the candidate cells in the target candidate cells are RSRP-quality cells and SINR-quality cells. The target candidate cell with the largest RSRP value or the largest SINR value in the target candidate cells is determined as the voice fallback cell. The voice fallback cell has high RSRP and high SINR, so that the cell with high signal strength and good quality is determined as the voice fallback cell, thereby improving user perception.

[0106] In some embodiments, S120, determining RSRP threshold information corresponding to each RSRP category based on RSRP values of multiple candidate cells, initial RSRP threshold information corresponding to multiple RSRP categories, and historical fallback information, includes:

[0107] S121: Determine first RSRP threshold information corresponding to each RSRP category based on RSRP values of multiple candidate cells and initial RSRP threshold information corresponding to multiple RSRP categories, and define the RSRP category with the largest threshold among the multiple first RSRP threshold information as the target RSRP category.

[0108] The first RSRP threshold information may be initial RSRP threshold information; or the initial RSRP threshold information may be modified according to RSRP values of multiple candidate cells to obtain the first RSRP threshold information.

[0109] In one example, the RSRP category with the highest threshold value among multiple first RSRP threshold information is the "Good" category, and the "Good" category is then designated as the target RSRP category. A preset condition may be that the Gini coefficient for each category is calculated based on the number of candidate cells in each category and historical rollback information, with the target RSRP category having the smallest Gini coefficient. The RSRP values of the multiple candidate cells fall within the range [-105, -74], where the RSRP value is expressed in dBm. The initial RSRP threshold information corresponding to the "Good" RSRP category is an RSRP value greater than or equal to -79 dBm. If, after verification, the initial RSRP threshold information is found to not meet the preset condition, the initial threshold information is modified, resulting in the first RSRP threshold information corresponding to the "Good" RSRP category being an RSRP value greater than or equal to -80 dBm.

[0110] S122: Determine the number of candidate cells belonging to each RSRP category according to the first RSRP threshold information corresponding to each RSRP category.

[0111] The mobile terminal classifies the multiple candidate cells according to the first RSRP threshold information corresponding to each RSRP category, and determines the RSRP category to which each candidate cell belongs.

[0112] In an example, the RSRP category to which each candidate cell belongs is shown in Table 3.

[0113] Table 3 RSRP category of each candidate cell

[0114]

[0115] S123 , determining the number of first candidate cells that successfully fall back in each RSRP category and the number of second candidate cells that failed fall back in each RSRP category according to the number of candidate cells belonging to each RSRP category and historical fallback information.

[0116] When the mobile terminal falls back to the candidate cell in each RSRP category during the past period of time, the fallback may succeed or fail.

[0117] The first candidate cell refers to a candidate cell to which the mobile terminal has successfully performed voice fallback in the past; the second candidate cell refers to a candidate cell to which the mobile terminal has failed to perform voice fallback in the past.

[0118] The mobile terminal determines the number of first candidate cells that successfully fall back in each RSRP category and the number of second candidate cells that failed fall back in each RSRP category based on the number of candidate cells belonging to each RSRP category and historical fallback information.

[0119] In an example, the number of first candidate cells that successfully fall back in each RSRP category and the number of second candidate cells that fail fall back in each RSRP category are shown in Table 4.

[0120] Table 4 Number of first candidate cells and second candidate cells

[0121] RSRP Category Number of first candidate cells Number of second candidate cells total good 7 2 9 middle 1 1 2 Difference 1 3 4

[0122] S124 , calculating the Gini coefficient of each RSRP category according to the number of first candidate cells and the number of second candidate cells in each RSRP category.

[0123] The calculation formula of the Gini coefficient is: Where Gini(D) represents the Gini coefficient, and k represents the decision classification of the feature.

[0124] In the embodiment of the present application, the decision classification is divided into two categories: fallback success and fallback failure, so k=2; P k Represents the probability of each classification, that is, the number of samples classified as fallback success or fallback failure in the sample divided by the total number of samples.

[0125] In one example, the Gini coefficient for each RSRP category is calculated as follows:

[0126] Here, Gini(RSRP=good) represents the Gini coefficient when the RSRP category is “good”.

[0127] Here, Gini(RSRP=Medium) represents the Gini coefficient for RSRP category “Medium”.

[0128] Here, Gini(RSRP=poor) represents the Gini coefficient when the RSRP category is “poor”.

[0129] S125 : When the Gini coefficient of the target RSRP category is the smallest, determine that the first RSRP threshold information corresponding to each RSRP category is the RSRP threshold information corresponding to each RSRP category.

[0130] The mobile terminal compares the Gini coefficients of each RSRP category, and when the Gini coefficient of the target RSRP category is the smallest, determines the first RSRP threshold information corresponding to each RSRP category as the RSRP threshold information corresponding to each RSRP category.

[0131] When the Gini coefficient of the target RSRP category is not the minimum, repeat steps S121-S125 until the Gini coefficient of the target RSRP category is the minimum, and determine that the first RSRP threshold information corresponding to each RSRP category is the RSRP threshold information corresponding to each RSRP category.

[0132] In one example, the target RSRP category is "good", and the Gini coefficients of each RSRP category are compared. If the target RSRP category is the category with the smallest Gini coefficient, the first RSRP threshold information corresponding to each RSRP category is determined to be the RSRP threshold information corresponding to each RSRP category.

[0133] The method provided in the embodiment of the present application determines the RSRP threshold information corresponding to each RSRP category based on the RSRP values of multiple candidate cells, initial RSRP threshold information corresponding to multiple RSRP categories, and historical fallback information. In this way, when classifying the candidate cells based on the RSRP threshold information, RSRP-high-quality cells and non-RSRP-high-quality cells in the candidate cells can be divided into different categories.

[0134] In some embodiments, S120, determining SINR threshold information corresponding to each SINR category based on SINR values of multiple candidate cells, initial SINR threshold information corresponding to multiple SINR categories, and historical fallback information, includes:

[0135] S126: Determine first SINR threshold information corresponding to each SINR category based on the SINR values of the multiple candidate cells and the initial SINR threshold information corresponding to the multiple SINR categories, and the SINR category with the largest threshold among the multiple first SINR threshold information is the target SINR category.

[0136] The first SINR threshold information may be initial SINR threshold information; or the initial SINR threshold information may be modified according to SINR values of multiple candidate cells to obtain the first SINR threshold information.

[0137] In one example, the SINR category with the largest threshold value among multiple first SINR threshold information is category "good", and category "good" is the target SINR category. The preset condition can be that the Gini coefficient of each category is calculated based on the number of candidate cells in each category and historical fallback information, and the Gini coefficient of the target SINR category is the smallest. The SINR values of the multiple candidate cells belong to the interval [-6, 10], the unit of the SINR value is dB, and the initial SINR threshold information corresponding to the SINR category "good" is an SINR value greater than or equal to 2dB. After verification, it is found that the initial SINR threshold information does not meet the preset condition, and the initial threshold information is modified to obtain the first SINR threshold information corresponding to the SINR category "good" as an SINR value greater than or equal to 3dB.

[0138] S127: Determine the number of candidate cells belonging to each SINR category according to the first SINR threshold information corresponding to each SINR category.

[0139] The mobile terminal classifies the multiple candidate cells according to the first SINR threshold information corresponding to each SINR category, and determines the SINR category to which each candidate cell belongs.

[0140] In an example, the SINR category to which each candidate cell belongs is shown in Table 5.

[0141] Table 5 SINR category of each candidate cell

[0142]

[0143] S128 : Determine the number of third candidate cells that successfully fall back in each SINR category and the number of fourth candidate cells that fail fall back in each SINR category according to the number of candidate cells belonging to each SINR category and historical fallback information.

[0144] When the mobile terminal falls back to the candidate cell in each SINR category in the past period of time, the fallback may be successful or unsuccessful.

[0145] The third candidate cell refers to a candidate cell to which the mobile terminal has successfully performed voice fallback in the past; the fourth candidate cell refers to a candidate cell to which the mobile terminal has failed to perform voice fallback in the past.

[0146] The mobile terminal determines the number of third candidate cells that successfully fall back in each SINR category and the number of fourth candidate cells that fail fallback in each SINR category based on the number of candidate cells belonging to each SINR category and historical fallback information.

[0147] In an example, the number of third candidate cells that successfully fall back in each SINR category and the number of fourth candidate cells that fail fall back in each SINR category are shown in Table 6.

[0148] Table 6 Number of third candidate cells and number of fourth candidate cells

[0149] SINR Category Number of third candidate cells Number of fourth candidate cells total good 1 7 8 middle 3 1 4 Difference 2 1 3

[0150] S129: Calculate the Gini coefficient of each SINR category according to the number of third candidate cells and the number of fourth candidate cells in each SINR category.

[0151] The calculation formula of the Gini coefficient is: Where Gini(D) represents the Gini coefficient, and k represents the decision classification of the feature.

[0152] In the embodiment of the present application, the decision classification is divided into two categories: fallback success and fallback failure, so k=2; P k Represents the probability of each classification, that is, the number of samples classified as fallback success or fallback failure in the sample divided by the total number of samples.

[0153] In one example, the Gini coefficient for each SINR category is calculated as follows:

[0154] Here, Gini(SINR=good) represents the Gini coefficient when the SINR category is "good".

[0155] Here, Gini(SINR=medium) represents the Gini coefficient for the SINR category of “medium”.

[0156] Here, Gini(SINR=poor) represents the Gini coefficient when the SINR category is "poor".

[0157] S1210: When the Gini coefficient of the target SINR category is the smallest, determine that the first SINR threshold information corresponding to each SINR category is the SINR threshold information corresponding to each SINR category.

[0158] The mobile terminal compares the Gini coefficients of each SINR category, and when the Gini coefficient of the target SINR category is the smallest, determines that the first SINR threshold information corresponding to each SINR category is the SINR threshold information corresponding to each SINR category.

[0159] When the Gini coefficient of the target SINR category is not the minimum, the above steps S126-S1210 are repeated until the Gini coefficient of the determined target SINR category is the minimum, and the first SINR threshold information corresponding to each SINR category is determined to be the SINR threshold information corresponding to each SINR category.

[0160] In one example, the target SINR category is "good", and the Gini coefficients of each SINR category are compared. If the target SINR category is the category with the smallest Gini coefficient, the first SINR threshold information corresponding to each SINR category is determined to be the SINR threshold information corresponding to each SINR category.

[0161] The method provided in the embodiment of the present application determines the SINR threshold information corresponding to each SINR category based on the SINR values of multiple candidate cells, initial SINR threshold information corresponding to multiple SINR categories, and historical fallback information. In this way, when classifying the candidate cells based on the SINR threshold information, cells with high SINR quality and cells with low SINR quality among the candidate cells can be divided into different categories.

[0162] In some embodiments, S150, based on the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category, determining a target candidate cell belonging to a target RSRP category with the smallest Gini coefficient among the RSRP categories and a target SINR category with the smallest Gini coefficient among the SINR categories, includes:

[0163] First, the RSRP Gini coefficient is calculated based on the Gini coefficients of the multiple RSRP categories and the ratio of the number of candidate cells belonging to each RSRP category to the number of the multiple candidate cells.

[0164] Calculate the ratio of the number of candidate cells belonging to each RSRP category to the number of multiple candidate cells to obtain the ratio corresponding to each RSRP category. Then calculate the product of the Gini coefficient of each RSRP category and the ratio corresponding to the category to obtain the product corresponding to each RSRP category. Add the products corresponding to each RSRP category to obtain the RSRP Gini coefficient.

[0165] In one example, the formula for calculating the RSRP Gini coefficient is as follows:

[0166]

[0167] Among them, Gini(RSRP) represents the RSRP Gini coefficient, Indicates the ratio of the number of candidate cells with RSRP category of "good" to the number of all candidate cells. Indicates the ratio of the number of candidate cells with RSRP category "medium" to the number of all candidate cells. Indicates the ratio of the number of candidate cells with RSRP category of "poor" to the number of all candidate cells.

[0168] Then, the SINR Gini coefficient is calculated based on the Gini coefficients of the multiple SINR categories and the ratio of the number of candidate cells belonging to each SINR category to the number of the multiple candidate cells.

[0169] Calculate the ratio of the number of candidate cells belonging to each SINR category to the number of multiple candidate cells to obtain the ratio corresponding to each SINR category. Then calculate the product of the Gini coefficient of each SINR category and the ratio corresponding to the category to obtain the product corresponding to each SINR category. Add the products corresponding to each RSRP category to obtain the SINR Gini coefficient.

[0170] In one example, the formula for calculating the SINR Gini coefficient is as follows:

[0171]

[0172] Among them, Gini(SINR) represents the SINR Gini coefficient, Indicates the ratio of the number of candidate cells with a "good" SINR category to the number of all candidate cells. Indicates the ratio of the number of candidate cells with SINR category "medium" to the number of all candidate cells. Indicates the ratio of the number of candidate cells with an SINR category of "poor" to the number of all candidate cells among multiple candidate cells.

[0173] Then, the first candidate cell is determined according to the RSRP Gini coefficient and the SINR Gini coefficient.

[0174] In some embodiments, determining the first candidate cell according to the RSRP Gini coefficient and the SINR Gini coefficient includes:

[0175] When the RSRP Gini coefficient is less than the SINR Gini coefficient, the candidate cell belonging to the target RSRP category is determined as the first candidate cell;

[0176] When the SINR Gini coefficient is less than the RSRP Gini coefficient, the candidate cell belonging to the target SINR category is determined as the first candidate cell.

[0177] In this step, the candidate cell belonging to the target RSRP category or the candidate cell belonging to the target SINR category is determined to be the first candidate cell. Because the target RSRP category is the RSRP category with the largest threshold and the target SINR category is the SINR category with the largest threshold, the candidate cell in the determined first candidate cell is an RSRP high-quality cell or an SINR high-quality cell.

[0178] Finally, the target candidate cell is determined according to the Gini coefficient of each category in the first candidate cell.

[0179] In some embodiments, when a candidate cell belonging to a target RSRP category is determined to be a first candidate cell, determining the target candidate cell according to the Gini coefficient of each category in the first candidate cell includes:

[0180] According to the Gini coefficient of each SINR category in the first candidate cell, a candidate cell of the target SINR category is determined as the target candidate cell.

[0181] In this step, the first candidate cell belongs to the target RSRP category, and the candidate cell of the target SINR category in the first candidate cell is determined as the target candidate cell. In this way, the candidate cell in the target candidate cell belongs to the RSRP category with the largest RSRP threshold and the SINR category with the largest SINR threshold. Therefore, the candidate cell in the target candidate cell is an RSRP high-quality cell and an SINR high-quality cell.

[0182] In the embodiment of the present application, target candidate cells with high RSRP and high SINR are determined, and any cell among the target candidate cells is used as a voice fallback cell, so that a cell with high signal strength and good quality can be determined as a voice fallback cell.

[0183] In some embodiments, when a candidate cell belonging to a target SINR category is determined to be a first candidate cell, determining the target candidate cell according to the Gini coefficient of each category in the first candidate cell includes:

[0184] According to the Gini coefficient of each RSRP category in the first candidate cell, a candidate cell of the target RSRP category is determined as the target candidate cell.

[0185] In this step, the first candidate cell belongs to the target SINR category, and the candidate cell of the target RSRP category in the first candidate cell is determined as the target candidate cell. In this way, the candidate cell in the target candidate cell belongs to the RSRP category with the largest RSRP threshold and the SINR category with the largest SINR threshold. Therefore, the candidate cell in the target candidate cell is an RSRP high-quality cell and an SINR high-quality cell.

[0186] In the embodiment of the present invention, target candidate cells with high RSRP and high SINR quality are determined, and any cell among the target candidate cells is used as a voice fallback cell, so that a cell with high signal strength and good quality can be determined as a voice fallback cell.

[0187] In some embodiments, the mobile terminal uses a decision tree model to determine the target candidate cell belonging to the target RSRP category with the smallest Gini coefficient among the RSRP categories and the target SINR category with the smallest Gini coefficient among the SINR categories based on the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category.

[0188] Specifically, the decision tree model may include a root node, the root node is divided into a first sub-node and a second sub-node, and the first sub-node is divided into a third sub-node.

[0189] The mobile terminal determines the RSRP values, SINR values, Gini coefficients of each RSRP category, and Gini coefficients of each SINR category of all candidate cells as data in the root node of the decision tree.

[0190] The mobile terminal calculates the RSRP Gini coefficients of multiple candidate cells based on the Gini coefficient of each RSRP category.

[0191] In one example, the RSRP Gini coefficient is calculated as follows:

[0192]

[0193] Among them, Gini(RSRP) represents the RSRP Gini coefficient, Indicates the ratio of the number of candidate cells with RSRP category of "good" to the number of all candidate cells. Indicates the ratio of the number of candidate cells with RSRP category "medium" to the number of all candidate cells. Indicates the ratio of the number of candidate cells with RSRP category of "poor" to the number of all candidate cells.

[0194] The mobile terminal calculates the SINR Gini coefficients of multiple candidate cells based on the Gini coefficient of each SINR category.

[0195] In one example, the method for calculating the SINR Gini coefficient is as follows:

[0196]

[0197] Among them, Gini(SINR) represents the SINR Gini coefficient, Indicates the ratio of the number of candidate cells with a "good" SINR category to the number of all candidate cells. Indicates the ratio of the number of candidate cells with SINR category "medium" to the number of all candidate cells. Indicates the ratio of the number of candidate cells with an SINR category of "poor" to the number of all candidate cells among multiple candidate cells.

[0198] Then, the mobile terminal compares the RSRP Gini coefficients and SINR Gini coefficients of the multiple candidate cells.

[0199] When the RSRP Gini coefficient is less than the SINR Gini coefficient, the RSRP value and SINR value of the candidate cell belonging to the target RSRP category, as well as the Gini coefficient of each SINR category in the multiple candidate cells, are determined as data in the first node of the decision tree, and the remaining data is determined as data in the second child node of the decision tree. The mobile terminal then determines the RSRP value and SINR value of the candidate cell belonging to the target SINR category in the first node as data in the third child node, and determines the candidate cell belonging to the target SINR category as the target candidate cell.

[0200] When the SINR Gini coefficient is less than the RSRP Gini coefficient, the RSRP value and SINR value of the candidate cell belonging to the target SINR category, as well as the Gini coefficient of each RSRP category in the multiple candidate cells, are determined as data in the first node of the decision tree, and the remaining data is determined as data in the second child node of the decision tree. The mobile terminal then determines the RSRP value and SINR value of the candidate cell belonging to the target RSRP category in the first node as data in the third child node, and determines the candidate cell belonging to the target RSRP category as the target candidate cell.

[0201] In an embodiment of the present invention, the candidate cells in the target candidate cells belong to the RSRP category with the largest RSRP threshold and the SINR category with the largest SINR threshold. Therefore, the candidate cells in the target candidate cells are RSRP high-quality cells and SINR high-quality cells. By using any cell in the target candidate cells as a voice fallback cell, a cell with high signal strength and good quality can be determined as a voice fallback cell.

[0202] The embodiment of the present application also provides a device for determining a voice fallback cell, such as Figure 2 As shown, the apparatus 200 for determining a voice fallback cell may include: an acquisition module 210 , a determination module 220 and a calculation module 230 .

[0203] An acquisition module 210 is configured to acquire RSRP values, SINR values, and historical fallback information of multiple candidate cells, where the historical fallback information includes fallback success or fallback failure;

[0204] Determination module 220 is configured to determine RSRP threshold information corresponding to each RSRP category based on RSRP values of multiple candidate cells, initial RSRP threshold information corresponding to multiple RSRP categories, and historical fallback information, and determine SINR threshold information corresponding to each SINR category based on SINR values of multiple candidate cells, initial SINR threshold information corresponding to multiple SINR categories, and historical fallback information; wherein the RSRP category with the largest threshold in the multiple RSRP threshold information is the target RSRP category, and the SINR category with the largest threshold in the multiple SINR threshold information is the target SINR category; further configured to determine the number of candidate cells belonging to each RSRP category and each SINR category based on the multiple RSRP threshold information and the multiple SINR threshold information, the RSRP values, SINR values, and historical fallback information of the multiple candidate cells;

[0205] a calculation module 230, configured to calculate a Gini coefficient for each RSRP category and a Gini coefficient for each SINR category based on the number of candidate cells belonging to each category;

[0206] The determination module 220 is further used to determine, based on the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category, a target RSRP category with the smallest Gini coefficient among the RSRP categories and a target SINR category with the smallest Gini coefficient among the SINR categories; and is further used to determine that the target candidate cell with the largest RSRP value or the largest SINR value among the target candidate cells is a voice fallback cell.

[0207] The device for determining the voice fallback cell provided by the present application first obtains the RSRP values, SINR values and historical fallback information of multiple candidate cells, and determines the RSRP threshold information corresponding to each RSRP category according to the RSRP values of the multiple candidate cells, the initial RSRP threshold information corresponding to the multiple RSRP categories and the historical fallback information, and determines the SINR threshold information corresponding to each SINR category according to the SINR values of the multiple candidate cells, the initial SINR threshold information corresponding to the multiple SINR categories and the historical fallback information. The RSRP category with the largest threshold in the multiple RSRP threshold information is the target RSRP category, and the SINR category with the largest threshold in the multiple SINR threshold information is the target SINR category; then, according to the multiple RSRP threshold information and the multiple SINR threshold information, the RSRP values, SINR values and historical fallback information of the multiple candidate cells, the RSRP values belonging to each RSRP category and the SINR values belonging to each SINR category are determined. The number of other candidate cells is calculated, and thus the classification of multiple candidate cells is completed; then, according to the number of candidate cells belonging to each category, the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category are calculated, and the candidate cell belonging to the target RSRP category with the smallest Gini coefficient in the RSRP category and the target SINR category with the smallest Gini coefficient in the SINR category is determined as the target candidate cell. Since the candidate cell in the target candidate cell belongs to the RSRP category with the largest RSRP threshold and the SINR category with the largest SINR threshold, the candidate cell in the target candidate cell is an RSRP-quality cell and an SINR-quality cell; the target candidate cell with the largest RSRP value or the largest SINR value in the target candidate cell is determined to be the voice fallback cell, and the RSRP and SINR of the voice fallback cell are high-quality, so that the cell with high signal strength and good quality is determined as the voice fallback cell, thereby improving user perception.

[0208] In some embodiments, the determination module 220 may be specifically configured to:

[0209] Determine, based on the RSRP values of the multiple candidate cells and the initial RSRP threshold information corresponding to the multiple RSRP categories, the first RSRP threshold information corresponding to each RSRP category, and the RSRP category with the largest threshold among the multiple first RSRP threshold information as the target RSRP category;

[0210] Determining the number of candidate cells belonging to each RSRP category according to the first RSRP threshold information corresponding to each RSRP category;

[0211] Determine, based on the number of candidate cells belonging to each RSRP category and historical fallback information, the number of first candidate cells in each RSRP category that have successfully fallen back, and the number of second candidate cells in each RSRP category that have failed fallback;

[0212] Calculate the Gini coefficient of each RSRP category based on the number of first candidate cells and the number of second candidate cells in each RSRP category;

[0213] When the Gini coefficient of the target RSRP category is the smallest, the first RSRP threshold information corresponding to each RSRP category is determined to be the RSRP threshold information corresponding to each RSRP category.

[0214] The apparatus provided in the embodiment of the present application determines RSRP threshold information corresponding to each RSRP category based on the RSRP values of multiple candidate cells, initial RSRP threshold information corresponding to multiple RSRP categories, and historical fallback information. In this way, when classifying candidate cells based on the RSRP threshold information, RSRP-high-quality cells and non-RSRP-high-quality cells in the candidate cells can be divided into different categories.

[0215] In some embodiments, the determination module 220 may further be specifically configured to:

[0216] Determine, according to the SINR values of the multiple candidate cells and the initial SINR threshold information corresponding to the multiple SINR categories, the first SINR threshold information corresponding to each SINR category, and the SINR category with the largest threshold among the multiple first SINR threshold information is the target SINR category;

[0217] Determining the number of candidate cells belonging to each SINR category according to the first SINR threshold information corresponding to each SINR category;

[0218] Determine, based on the number of candidate cells belonging to each SINR category and historical fallback information, the number of third candidate cells that successfully fall back in each SINR category and the number of fourth candidate cells that failed fallback in each SINR category;

[0219] Calculate the Gini coefficient of each SINR category according to the number of third candidate cells and the number of fourth candidate cells in each SINR category;

[0220] When the Gini coefficient of the target SINR category is the smallest, the first SINR threshold information corresponding to each SINR category is determined to be the SINR threshold information corresponding to each SINR category.

[0221] The apparatus provided in the embodiment of the present application determines the SINR threshold information corresponding to each SINR category based on the SINR values of multiple candidate cells, the initial SINR threshold information corresponding to multiple SINR categories, and the historical fallback information. In this way, when classifying the candidate cells according to the SINR threshold information, cells with high SINR quality and cells with low SINR quality among the candidate cells can be divided into different categories.

[0222] In some embodiments, the determination module 220 may further be specifically configured to:

[0223] Calculating an RSRP Gini coefficient based on the Gini coefficients of the multiple RSRP categories and a ratio of the number of candidate cells belonging to each RSRP category to the number of the multiple candidate cells;

[0224] Calculating an SINR Gini coefficient according to the Gini coefficients of the multiple SINR categories and a ratio of the number of candidate cells belonging to each SINR category to the number of the multiple candidate cells;

[0225] Determine the first candidate cell based on the RSRP Gini coefficient and the SINR Gini coefficient;

[0226] The target candidate cell is determined according to the Gini coefficient of each category in the first candidate cell.

[0227] In some embodiments, the determination module 220 may be specifically configured to:

[0228] When the RSRP Gini coefficient is less than the SINR Gini coefficient, the candidate cell belonging to the target RSRP category is determined as the first candidate cell;

[0229] When the SINR Gini coefficient is less than the RSRP Gini coefficient, the candidate cell belonging to the target SINR category is determined as the first candidate cell.

[0230] The device provided by the embodiment of the present invention determines target candidate cells with high RSRP and high SINR quality. By using any of the target candidate cells as a voice fallback cell, a cell with high signal strength and good quality can be determined as a voice fallback cell.

[0231] In some embodiments, the determination module 220 may further be specifically configured to:

[0232] When a candidate cell belonging to the target RSRP category is determined as the first candidate cell, a candidate cell of the target SINR category is determined as the target candidate cell according to the Gini coefficient of each SINR category in the first candidate cell.

[0233] The device provided in the embodiment of the present application determines the target candidate cells with high RSRP and high SINR quality. By using any of the target candidate cells as the voice fallback cell, the cell with high signal strength and good quality can be determined as the voice fallback cell.

[0234] In some embodiments, the determination module 220 may further be specifically configured to:

[0235] When a candidate cell belonging to the target SINR category is determined as the first candidate cell, a candidate cell of the target RSRP category is determined as the target candidate cell according to the Gini coefficient of each category in the first candidate cell and the Gini coefficient of each RSRP category in the first candidate cell.

[0236] The device provided by the embodiment of the present invention determines target candidate cells with high RSRP and high SINR quality. By using any of the target candidate cells as a voice fallback cell, a cell with high signal strength and good quality can be determined as a voice fallback cell.

[0237] The apparatus for determining a voice fallback cell provided in the embodiment of the present application performs Figure 1 Each step in the method shown can achieve the technical effect of determining a cell with high signal strength and good quality as a voice fallback cell, thereby improving user perception. For the sake of brevity, it will not be described in detail here.

[0238] Figure 3 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0239] The electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0240] Specifically, the processor 301 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0241] The memory 302 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 302 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 302 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 302 is a non-volatile solid-state memory. In a specific embodiment, the memory 302 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0242] The processor 301 reads and executes the computer program instructions stored in the memory 302 to implement Figure 1 Any one of the methods for determining a voice fallback cell in the illustrated embodiments.

[0243] In one example, the electronic device may further include a communication interface 303 and a bus 310. Figure 3 As shown, the processor 301 , the memory 302 , and the communication interface 303 are connected via a bus 310 and communicate with each other.

[0244] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0245] Bus 310 comprises hardware, software or both, couples the parts of electronic equipment to each other.For example, and not limitation, bus can comprise accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations.In suitable cases, bus 310 can comprise one or more buses.Although the present application embodiment describes and shows specific bus, the application considers any suitable bus or interconnection.

[0246] The electronic device can execute the method for determining the voice fallback cell in the embodiment of the present application, thereby realizing the combination Figure 1 The method for determining the voice fallback cell is described.

[0247] In addition, in conjunction with the method for determining a voice fallback cell in the above embodiments, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the methods for determining a voice fallback cell in the above embodiments is implemented.

[0248] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0249] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0250] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0251] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A method for determining a voice fallback cell, characterized in that: The method comprises: Obtain RSRP values, SINR values, and historical fallback information of multiple candidate cells, wherein the historical fallback information includes fallback success or fallback failure; Determine, according to the RSRP values of the multiple candidate cells, the initial RSRP threshold information corresponding to the multiple RSRP categories, and the historical fallback information, the RSRP threshold information corresponding to each of the RSRP categories, and determine, according to the SINR values of the multiple candidate cells, the initial SINR threshold information corresponding to the multiple SINR categories, and the historical fallback information, the SINR threshold information corresponding to each of the SINR categories; wherein the RSRP category with the largest threshold value among the multiple RSRP threshold information is the target RSRP category, and the SINR category with the largest threshold value among the multiple SINR threshold information is the target SINR category; Determining, according to the multiple RSRP threshold information and the multiple SINR threshold information, the RSRP values, the SINR values, and the historical fallback information of the multiple candidate cells, the number of candidate cells belonging to each RSRP category and the number of candidate cells belonging to each SINR category; Calculating a Gini coefficient for each RSRP category and a Gini coefficient for each SINR category according to the number of candidate cells belonging to each category; Determining, according to the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category, a target candidate cell belonging to a target RSRP category with the smallest Gini coefficient among the RSRP categories and a target SINR category with the smallest Gini coefficient among the SINR categories; Determine the target candidate cell with the largest RSRP value or the largest SINR value among the target candidate cells as the voice fallback cell.

2. The method according to claim 1, characterized in that The determining, according to the RSRP values of the multiple candidate cells, the initial RSRP threshold information corresponding to the multiple RSRP categories, and the historical fallback information, the RSRP threshold information corresponding to each of the RSRP categories includes: Determining, according to the RSRP values of the multiple candidate cells and the initial RSRP threshold information corresponding to the multiple RSRP categories, first RSRP threshold information corresponding to each of the RSRP categories, wherein the RSRP category with the largest threshold among the multiple first RSRP threshold information is the target RSRP category; Determining the number of candidate cells belonging to each of the RSRP categories according to the first RSRP threshold information corresponding to each of the RSRP categories; Determining, according to the number of candidate cells belonging to each RSRP category and the historical fallback information, the number of first candidate cells in each RSRP category that successfully fallback, and the number of second candidate cells in each RSRP category that failed fallback; Calculating a Gini coefficient for each of the RSRP categories according to the number of first candidate cells and the number of second candidate cells in each of the RSRP categories; When the Gini coefficient of the target RSRP category is the smallest, determining that the first RSRP threshold information corresponding to each of the RSRP categories is the RSRP threshold information corresponding to each of the RSRP categories.

3. The method according to claim 1, characterized in that The determining, according to the SINR values of the multiple candidate cells, the initial SINR threshold information corresponding to the multiple SINR categories, and the historical fallback information, the SINR threshold information corresponding to each SINR category includes: Determine, according to the SINR values of the multiple candidate cells and the initial SINR threshold information corresponding to the multiple SINR categories, first SINR threshold information corresponding to each SINR category, wherein the SINR category with the largest threshold among the multiple first SINR threshold information is the target SINR category; Determining the number of candidate cells belonging to each SINR category according to the first SINR threshold information corresponding to each SINR category; Determining, according to the number of candidate cells belonging to each SINR category and the historical fallback information, the number of third candidate cells that successfully fall back in each SINR category and the number of fourth candidate cells that failed fallback in each SINR category; Calculating a Gini coefficient for each SINR category according to the number of third candidate cells and the number of fourth candidate cells in each SINR category; When the Gini coefficient of the target SINR category is the smallest, determining the first SINR threshold information corresponding to each SINR category is the SINR threshold information corresponding to each SINR category.

4. The method according to claim 1, wherein The determining, according to the Gini coefficient of each of the RSRP categories and the Gini coefficient of each of the SINR categories, a target candidate cell belonging to a target RSRP category with the smallest Gini coefficient among the RSRP categories and a target SINR category with the smallest Gini coefficient among the SINR categories, includes: Calculating an RSRP Gini coefficient according to the Gini coefficients of the multiple RSRP categories and a ratio of the number of candidate cells belonging to each RSRP category to the number of the multiple candidate cells; Calculating an SINR Gini coefficient according to the Gini coefficients of the plurality of SINR categories and a ratio of the number of candidate cells belonging to each SINR category to the number of the plurality of candidate cells; Determining a first candidate cell according to the RSRP Gini coefficient and the SINR Gini coefficient; The target candidate cell is determined according to the Gini coefficient of each category in the first candidate cells.

5. The method according to claim 4, characterized in that The determining a first candidate cell according to the RSRP Gini coefficient and the SINR Gini coefficient includes: When the RSRP Gini coefficient is less than the SINR Gini coefficient, determining a candidate cell belonging to the target RSRP category as the first candidate cell; When the SINR Gini coefficient is less than the RSRP Gini coefficient, a candidate cell belonging to the target SINR category is determined as the first candidate cell.

6. The method according to claim 5, characterized in that When it is determined that the candidate cell belonging to the target RSRP category is the first candidate cell, determining the target candidate cell according to the Gini coefficient of each category in the first candidate cell includes: According to the Gini coefficient of each SINR category in the first candidate cells, a candidate cell of the target SINR category is determined as the target candidate cell.

7. The method according to claim 5, characterized in that When it is determined that the candidate cell belonging to the target SINR category is the first candidate cell, determining the target candidate cell according to the Gini coefficient of each category in the first candidate cell includes: According to the Gini coefficient of each of the RSRP categories in the first candidate cells, a candidate cell of the target RSRP category is determined as the target candidate cell.

8. A device for determining a voice fallback cell, characterized in that: The device comprises: An acquisition module is used to obtain RSRP values, SINR values and historical fallback information of multiple candidate cells, wherein the historical fallback information includes fallback success or fallback failure; a determination module, configured to determine the RSRP threshold information corresponding to each of the RSRP categories based on the RSRP values of the multiple candidate cells, the initial RSRP threshold information corresponding to the multiple RSRP categories, and the historical fallback information, and determine the SINR threshold information corresponding to each of the SINR categories based on the SINR values of the multiple candidate cells, the initial SINR threshold information corresponding to the multiple SINR categories, and the historical fallback information; wherein the RSRP category with the largest threshold value among the multiple RSRP threshold information is the target RSRP category, and the SINR category with the largest threshold value among the multiple SINR threshold information is the target SINR category; and further configured to determine the number of candidate cells belonging to each of the RSRP categories and each of the SINR categories based on the multiple RSRP threshold information and the multiple SINR threshold information, the RSRP values, the SINR values, and the historical fallback information of the multiple candidate cells; a calculation module, configured to calculate a Gini coefficient of each RSRP category and a Gini coefficient of each SINR category according to the number of candidate cells belonging to each category; The determination module is used to determine, based on the Gini coefficient of each RSRP category and the Gini coefficient of each SINR category, a target RSRP category with the smallest Gini coefficient among the RSRP categories and a target SINR category with the smallest Gini coefficient among the SINR categories; and is also used to determine that the target candidate cell with the largest RSRP value or the largest SINR value among the target candidate cells is a voice fallback cell.

9. An electronic device, characterized in that: The device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the method for determining a voice fallback cell according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the method for determining a voice fallback cell according to any one of claims 1 to 7 is implemented.

Images