Voice quality optimization method and device, equipment, storage medium and product

Abstract

The invention discloses a voice quality optimization method and device, equipment, a storage medium and a product, and relates to the technical field of communication, and the method comprises the steps: based on an RSRP sequence of each user equipment, recognizing each fast fading equipment with an RSRP fluctuation value exceeding a preset fluctuation threshold value from each user equipment through a preset recurrent neural network; determining a communication cell to which each fast fading device belongs according to the temporary identifier of each fast fading device, and determining the communication cell meeting a preset device scale condition and a fast fading device distribution condition as a fast fading cell; determining a voice problem cell from the fast fading cells according to the service quality identifier of each fast fading device in the fast fading cells; and voice quality optimization is carried out on voice problem equipment in the voice problem cell, and the voice problem equipment is fast fading equipment for executing voice services. Therefore, the influence of the fast fading phenomenon on the voice quality is reduced, and the voice quality is improved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to voice quality optimization methods, apparatus, devices, storage media, and products. Background Technology

[0002] Fast fading refers to the phenomenon where the strength of a received radio signal changes rapidly over a short period of time. In communication networks, voice services are a basic communication service, and their quality directly affects user experience and network reliability. Fast fading can cause voice signals to be interrupted, distorted, or delayed.

[0003] Currently, testing and analysis of fast fading phenomena require significant manpower and time, making it difficult to efficiently detect fast-fading cells. Furthermore, when optimizing voice service quality in fast-fading cells, voice services are often processed together with other data services (such as video services and file downloads), without considering the extreme sensitivity of voice services to network quality. This can easily lead to an imbalance in network resource contention, such as high-priority voice services being squeezed out by non-real-time services, resulting in degraded voice quality.

[0004] In summary, how to reduce the impact of fast fading on speech quality in order to improve speech quality has become a pressing technical problem that needs to be solved in this field. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, device, storage medium, and product for optimizing voice quality, aiming to reduce the impact of fast fading on voice quality and thus improve voice quality.

[0006] To achieve the above objectives, this application proposes a speech quality optimization method, which includes:

[0007] Based on the RSRP (Reference Signal Receiving Power) sequence of each user equipment, a preset recurrent neural network is used to identify fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold from each user equipment.

[0008] The communication cell to which each fast fading device belongs is determined based on the temporary identifier of each fast fading device, and the communication cell that meets the preset device size conditions and fast fading device distribution conditions is determined as a fast fading cell.

[0009] Based on the Quality of Service (QoS) identifiers of each fast-fading device in the fast-fading cell, identify the voice problem cell from the fast-fading cell;

[0010] Voice quality optimization is performed on the voice-prone devices in the cell with voice problems, wherein the voice-prone devices are fast-fading devices performing voice services.

[0011] In one embodiment, before the step of identifying fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold from each user equipment using a preset recurrent neural network based on the RSRP sequence of each user equipment, the method further includes:

[0012] Acquire MRO data (Measurement Report of Event Type) collected by the base station, and extract RSRP data, temporary identifiers and timestamps of each user equipment from the MRO data;

[0013] Based on the temporary identifier and the timestamp, the RSRP data of each user equipment is organized into an RSRP sequence arranged in chronological order.

[0014] In one embodiment, the step of identifying fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold from each user equipment using a preset recurrent neural network based on the RSRP sequences of each user equipment includes:

[0015] For each user equipment, the RSRP sequence of the user equipment is input into a preset recurrent neural network to obtain the fast fading device identification result output by the recurrent neural network. The recurrent neural network is used to determine the RSRP fluctuation value of the user equipment within a preset time window based on the RSRP sequence, and to determine the user equipment as a fast fading device when the RSRP fluctuation value exceeds a preset fluctuation threshold.

[0016] In one embodiment, the step of determining the communication cell to which each fast fading device belongs based on the temporary identifier of each fast fading device, and determining the communication cell that meets the preset device size conditions and fast fading device distribution conditions as a fast fading cell, includes:

[0017] Based on the association rules between the temporary identifier of each fast fading device and the global identifier of the cell, the communication cell to which each fast fading device belongs is determined;

[0018] Determine the number of user equipment in each of the aforementioned communication cells, and the first proportion of the fast fading devices;

[0019] A communication cell whose number of user equipment exceeds a preset number threshold and whose proportion of the first equipment exceeds a first preset proportion threshold is identified as a fast fading cell.

[0020] In one embodiment, the step of determining a voice problem cell from the fast-fading cells based on the QoS identifiers of each fast-fading device in the fast-fading cell includes:

[0021] Based on the Quality of Service (QoS) identifier of each fast fading device in the fast fading cell, the target fast fading device for performing voice services is determined from the fast fading cell;

[0022] Obtain the second device percentage of the target fast-fading device in the fast-fading cell, and the average daily traffic volume of the fast-fading cell;

[0023] A fast-fading cell is defined as a cell with a voice problem if the proportion of the second device exceeds the second preset proportion threshold and the average daily call volume exceeds the preset call volume threshold.

[0024] In one embodiment, the step of optimizing the voice quality of voice-prone devices in the voice-prone cell includes:

[0025] Switch the application network of the voice problem device in the cell to the LTE (Long Term Evolution) network;

[0026] In the LTE network, establish a voice service based on VoLTE (Voice over LTE, LTE Voice Bearer) for the device with the voice problem.

[0027] Furthermore, to achieve the above objectives, this application also proposes a speech quality optimization device, which includes:

[0028] The fast fading device identification module is used to identify fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold from each user device based on the RSRP sequence of each user device through a preset recurrent neural network.

[0029] The fast fading cell determination module is used to determine the communication cell to which each fast fading device belongs based on the temporary identifier of each fast fading device, and to determine the communication cell that meets the preset device size conditions and fast fading device distribution conditions as a fast fading cell.

[0030] The voice problem cell determination module is used to determine the voice problem cell from the fast fading cells based on the quality of service identifier of each fast fading device in the fast fading cell;

[0031] The voice quality optimization module is used to optimize the voice quality of voice-prone devices in the voice-prone cell, wherein the voice-prone devices are fast-fading devices that perform voice services.

[0032] In addition, to achieve the above objectives, this application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the speech quality optimization method described above.

[0033] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the speech quality optimization method described above.

[0034] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the speech quality optimization method described above.

[0035] This application proposes a voice quality optimization method. Based on the RSRP sequence of each user equipment (UE), a pre-defined recurrent neural network is used to identify fast-fading devices whose RSRP fluctuation values ​​exceed a pre-defined fluctuation threshold. The temporary identifier of each fast-fading device is used to determine the communication cell to which it belongs, and communication cells that meet pre-defined equipment size and fast-fading device distribution conditions are identified as fast-fading cells. Based on the service quality identifier of each fast-fading device in the fast-fading cell, voice problem cells are identified from the fast-fading cells. Voice quality optimization is performed on the voice problem devices in the voice problem cells, where the voice problem devices are fast-fading devices performing voice services.

[0036] In summary, the recurrent neural network used in this application for automated identification of fast-fading devices can quickly and accurately identify fast-fading devices with abnormal RSRP fluctuations and further determine fast-fading cells, reducing the manpower and time costs of identifying fast-fading cells. Furthermore, considering the extreme sensitivity of voice services to network quality, based on the identification of fast-fading cells, the application further combines the service quality identifiers corresponding to the fast-fading devices to identify voice problem cells within the fast-fading cells, and optimizes the voice quality of voice problem devices in these cells. This ensures that voice services can obtain sufficient network resources in fast-fading scenarios, improving the user's voice quality. Attached Figure Description

[0037] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating an embodiment of the speech quality optimization method of this application.

[0040] Figure 2 This is a schematic diagram of RSRP data changes provided in Embodiment 2 of the speech quality optimization method of this application;

[0041] Figure 3 This is a schematic diagram of the speech quality optimization process provided in Embodiment 3 of the speech quality optimization method of this application;

[0042] Figure 4 This is a schematic diagram of the module structure of the voice quality optimization device according to an embodiment of this application;

[0043] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the voice quality optimization method in the embodiments of this application.

[0044] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0045] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0046] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0047] Fast fading refers to the phenomenon where the strength of a received radio signal changes rapidly over a short period of time. In communication networks, voice services are a basic communication service, and their quality directly affects user experience and network reliability. Fast fading can cause voice signals to be interrupted, distorted, or delayed.

[0048] Currently, testing and analysis of fast fading phenomena require significant manpower and time, making it difficult to efficiently detect fast-fading cells. Furthermore, when optimizing voice service quality in fast-fading cells, voice services are often processed together with other data services (such as video services and file downloads), without considering the extreme sensitivity of voice services to network quality. This can easily lead to an imbalance in network resource contention, such as high-priority voice services being squeezed out by non-real-time services, resulting in degraded voice quality.

[0049] In summary, how to reduce the impact of fast fading on speech quality in order to improve speech quality has become a pressing technical problem that needs to be solved in this field.

[0050] The main solution of this application embodiment is as follows: Based on the RSRP sequence of each user equipment, a preset recurrent neural network is used to identify each fast fading device whose RSRP fluctuation value exceeds a preset fluctuation threshold from each user equipment; the communication cell to which each fast fading device belongs is determined according to the temporary identifier of each fast fading device, and the communication cell that meets the preset equipment size conditions and fast fading device distribution conditions is determined as a fast fading cell; the voice problem cell is determined from the fast fading cells according to the service quality identifier of each fast fading device in the fast fading cell; the voice quality of the voice problem device in the voice problem cell is optimized, wherein the voice problem device is a fast fading device performing voice services.

[0051] This application provides a solution that uses a recurrent neural network to automatically identify fast-fading devices. This can quickly and accurately identify fast-fading devices with abnormal RSRP fluctuations and further determine fast-fading cells, reducing the manpower and time costs of identifying fast-fading cells. At the same time, considering the extreme sensitivity of voice services to network quality, based on the identification of fast-fading cells, the solution further combines the service quality identifiers corresponding to the fast-fading devices to determine voice problem cells within the fast-fading cells, and optimizes the voice quality of voice problem devices in the voice problem cells. This ensures that voice services can obtain sufficient network resources in fast-fading scenarios and improves the voice quality for users.

[0052] It should be noted that the executing entity in this embodiment can be a communication network control device with data processing, network communication and program execution functions, such as a core network, server, voice quality optimization terminal, etc., or an electronic device capable of realizing the above functions.

[0053] Based on this, embodiments of this application provide a method for optimizing voice quality, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the voice quality optimization method of this application.

[0054] In this embodiment, the voice quality optimization method includes steps S10 to S40:

[0055] Step S10: Based on the RSRP sequence of each user equipment, identify each fast fading device whose RSRP fluctuation value exceeds the preset fluctuation threshold from each user equipment through a preset recurrent neural network.

[0056] It should be noted that RSRP is used to measure the power intensity of the reference signal received by a user equipment from a base station. It is an indicator for evaluating signal quality and reflects the signal coverage between the user equipment and the base station. A Recurrent Neural Network (RNN) is a neural network with short-term memory capabilities, capable of modeling and learning sequential data. In this embodiment, the RNN learns the RSRP sequence data of each user equipment, capturing its time-series features and patterns, thereby identifying fast-fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold. Fast-fading devices refer to user equipment, such as mobile phones and tablets, where the received signal power fluctuates significantly due to rapid changes in the signal propagation path.

[0057] For each user equipment, based on its reference signal received power sequence, a recurrent neural network is used to filter out fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold. The preset fluctuation threshold can be set based on the actual application scenario, and this embodiment does not impose a specific limitation on it.

[0058] Step S20: Determine the communication cell to which each fast fading device belongs based on the temporary identifier of each fast fading device, and determine the communication cell that meets the preset device size conditions and fast fading device distribution conditions as a fast fading cell.

[0059] It should be noted that the temporary identifier (NextGenerationAccessPointIdentifier, NG-AP-ID) is a unique identifier used to temporarily identify user equipment during communication, which facilitates the identification and management of user equipment in the communication network.

[0060] A communication cell refers to a basic communication unit in a communication network, consisting of an area covered by a base station.

[0061] Based on the temporary identifiers of each identified fast-fading device, the communication cell to which these devices belong is determined. Then, communication cells that meet preset device size and fast-fading device distribution conditions are selected and designated as fast-fading cells. The preset device size and fast-fading device distribution conditions are pre-defined criteria for selecting fast-fading cells. For example, the device size condition involves the number of user devices in the communication cell, and the fast-fading device distribution condition involves the distribution density of fast-fading devices in the communication cell. The number of user devices in the fast-fading cell meets the device size condition, and the distribution density of fast-fading devices meets the fast-fading device distribution condition.

[0062] Step S30: Identify the voice problem cell from the fast fading cells based on the QoS identifier of each fast fading device in the fast fading cell;

[0063] It should be noted that the Quality of Service Identifier (QI) is an identifier that identifies the service quality level of different services. Different QI values ​​correspond to different service priorities and service quality requirements. In NR networks, it is usually called 5QI (5G Quality of Service Indicator). The value of 5QI ranges from 1 to 255. The lower the value, the higher the service priority. The 5QI value corresponding to voice services is 1, which means that voice services have the highest QoS requirements. Therefore, when network resources are limited, the service quality of voice services is guaranteed first.

[0064] Among the identified fast-fading cells, based on the QoS identifier corresponding to each fast-fading device, the fast-fading cells with voice problems are further identified, namely, voice problem cells.

[0065] Step S40: Optimize the voice quality of the voice problem equipment in the voice problem cell, wherein the voice problem equipment is a fast fading equipment performing voice services.

[0066] Identify the fast-fading device (i.e., the problematic voice device) currently performing voice services in the problematic voice cell. The problematic voice device has a current 5QI value of 1, and implement voice quality optimization measures for the problematic voice device.

[0067] It is worth mentioning that in this embodiment, data processing in the communication network is carried out in steps, first addressing physical layer issues and then addressing service layer issues. Specifically, identifying fast-fading devices and then fast-fading cells from each user equipment is a physical layer issue. Identifying voice-problem cells and devices within fast-fading cells is a service layer issue. Compared to processing physical and service layer data simultaneously, i.e., directly identifying voice-problem devices and voice-problem cells from each user equipment, this hierarchical processing method can optimize the balance between the accuracy and computational complexity of target recognition (user equipment recognition to be optimized), making it more efficient.

[0068] This embodiment provides a voice quality optimization method that uses a recurrent neural network to automatically identify fast-fading devices. This method can quickly and accurately identify fast-fading devices with abnormal RSRP fluctuations and further determine fast-fading cells, reducing the manpower and time costs of identifying fast-fading cells. Furthermore, considering the extreme sensitivity of voice services to network quality, based on the identification of fast-fading cells, the method further combines the service quality identifiers corresponding to the fast-fading devices to identify voice problem cells within the fast-fading cells. Voice quality optimization is then performed on the voice problem devices in these cells, ensuring that voice services can obtain sufficient network resources in fast-fading scenarios and improving the user's voice quality.

[0069] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description and will not be repeated hereafter. Furthermore, steps S50 to S60 may be included before step S10:

[0070] Step S50: Obtain MRO data collected by the base station, and extract RSRP data, temporary identifier and timestamp of each user equipment from the MRO data;

[0071] It should be noted that MRO data is data reported by user equipment to the base station periodically or under specific conditions. This data is usually unprocessed and contains measurement information of the user equipment on the surrounding wireless environment. MRO data includes parameters such as RSRP data, temporary identifiers, and timestamps of the user equipment. This data can reflect the wireless signal status and network environment information of the user equipment during communication. Among them, the timestamp records the acquisition time of each parameter. By combining the RSRP data and timestamp of the user equipment corresponding to the same temporary identifier, the change of RSRP of the user equipment over time during movement can be determined, thereby analyzing whether the equipment has a fast fading phenomenon.

[0072] The system acquires MRO data collected by the base station through a specific data acquisition interface or system, and extracts reference signal received power data, temporary identifiers for uniquely identifying user equipment, and timestamps recording the data acquisition time from the acquired MRO data.

[0073] Step S60: Based on the temporary identifier and timestamp, organize the RSRP data of each user equipment into an RSRP sequence arranged in time sequence.

[0074] Based on the extracted temporary identifiers and timestamp information, the RSRP data of each user device are arranged and organized in chronological order to construct an RSRP sequence arranged in time sequence.

[0075] In one feasible embodiment, step S10 may include step S101:

[0076] Step S101: For each user equipment, the RSRP sequence of the user equipment is input into a preset recurrent neural network to obtain the fast fading device identification result output by the recurrent neural network. The recurrent neural network is used to determine the RSRP fluctuation value of the user equipment within a preset time window based on the RSRP sequence, and to determine the user equipment as a fast fading device when the RSRP fluctuation value exceeds a preset fluctuation threshold.

[0077] For each user equipment (UE), the acquired and organized RSRP sequence arranged in time sequence is used as input data and transmitted to a pre-built and trained recurrent neural network (RNN). This RNN has the ability to perform deep learning and feature extraction on the RSRP sequence and can output the fast fading device identification result for the UE, i.e., whether the UE is a fast fading device. Specifically, the RNN can accurately analyze the change pattern of RSRP over time based on the input RSRP sequence to determine the RSRP fluctuation value of the UE within a preset time window. The preset time window can be set according to actual service needs, for example, it can be a relatively short period of time (such as a few seconds to tens of seconds) to capture short-term fluctuations in the RSRP signal. Then, the calculated RSRP fluctuation value is compared with a preset fluctuation threshold. If the RSRP fluctuation value exceeds the preset fluctuation threshold, it indicates that the signal received power of the UE in the current network environment has fluctuated significantly within the preset time window, and the UE can be identified as a fast fading device.

[0078] For example, the RSRP time series {x1,x2,...,x} for each user equipment t}, where x t Let x be the RSRP value at time step t. The RSRP sequence is input into a recurrent neural network (RNN), which consists of an input layer, an RNN layer, and a fully connected layer. The input layer of the RNN processes the RSRP value x for each time step sequentially. t In the RNN layer of this recurrent neural network, the hidden state h t The update formula is:

[0079] h t =σ(W hh h t-1 +W xh x t +b h );

[0080] Among them, h t It is the hidden state at the current time step, x t It is the input RSRP value at time step t, W hh and W xh It is the weight matrix, b h σ is the bias term, and σ is the activation function.

[0081] Ultimately, the hidden state h t Connect to the fully connected layer and output the user classification probability: y = Sigmoid(W o h t +b o), where Sigmoid is an activation function, W o It is the weight matrix of the fully connected layer, b o It is the bias vector of the fully connected layer, y∈[0,1]. A value close to 1 indicates that the user equipment is a fast-fading user equipment, and a value close to 0 indicates that the user equipment is normal.

[0082] Furthermore, in another feasible implementation, multiple fast fading device identification modes are pre-set. For example, in deep learning mode, based on the RSRP sequence of each user equipment, a pre-set recurrent neural network is used to identify fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold from each user equipment. In the first data statistics mode, fast fading devices can be directly determined by analyzing the RSRP fluctuation of each user equipment. That is, based on MRO data analysis, it is determined whether there is a device in each user equipment whose RSRP fluctuation value exceeds a preset fluctuation threshold (e.g., 10 dBm) for n consecutive cycles. If so, the user equipment is determined to be a fast fading device. Figure 2 As shown in the figure, the horizontal axis represents time. The figure displays the RSRP data of a user equipment (UE) over three cycles, with each cycle spaced 5 seconds apart. If the RSRP fluctuation value exceeds a preset fluctuation threshold of 10 dBm within these three cycles, the UE can be identified as a fast-fading device. In the second data statistics mode, fast-fading devices can be identified based on the coverage and fluctuation of each UE's RSRP. For example, if a UE's RSRP remains below -110 dBm for 15 seconds, it is marked as a weak-coverage device. During the weak-coverage period, if the instantaneous fluctuation value of RSRP exceeds 15 dB (e.g., a sudden drop from -105 dBm to -120 dBm), the UE is identified as a fast-fading device.

[0083] Based on the first and / or second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to the first and second embodiments described above can be referred to the above description and will not be repeated hereafter. Based on this, step S20 may include steps S201 to S203:

[0084] Step S201: Determine the communication cell to which each fast fading device belongs based on the association rules between the temporary identifier of each fast fading device and the global identifier of the cell.

[0085] It should be noted that the Cell Global Identifier (CGI) is an identifier used to uniquely identify a communication cell globally.

[0086] Based on the pre-established association rules between the temporary identifiers of each fast-fading device and the global identifier of the cell (such as a specific identifier mapping table), the communication cell to which each fast-fading device belongs is determined.

[0087] Step S202: Determine the number of user equipment in each communication cell and the proportion of the first equipment in fast fading devices;

[0088] Based on determining the communication cell to which each fast-fading device belongs, for all communication cells, the number of user equipment in each communication cell is counted, and the proportion of fast-fading devices in the number of user equipment in that communication cell is calculated, i.e., the first device proportion.

[0089] Step S203: The communication cell in which the number of user equipment exceeds a preset number threshold and the proportion of the first equipment exceeds a first preset proportion threshold is identified as a fast fading cell.

[0090] Communication cells with more than a preset number of user devices and a first device ratio exceeding a first preset ratio threshold are identified as fast fading cells. There can be multiple fast fading cells, thereby accurately identifying communication cells that are more severely affected by fast fading.

[0091] For example, when classifying all communication cells, if the number of user devices in a communication cell is greater than 500 and the proportion of fast-fading devices to the number of user devices is greater than 'a', then the communication cell is identified as a fast-fading cell.

[0092] It's worth noting that there are currently two main methods for identifying fast-fading cells: one is through routine network testing or complaint handling. Based on daily network traversal tests or complaint handling, rapid signal fading is detected by replaying test logs, thus identifying fast-fading cells. However, routine network testing has significant limitations. It cannot traverse and test all cells or the coverage area within a cell; secondly, network testing is labor-intensive, requiring on-site testing by optimization engineers, consuming significant resources and being inefficient, making it unsuitable for large-scale implementation across the entire network. Furthermore, the discovery of fast-fading cells through user complaints already has a noticeable impact on users, requiring substantial subsequent repair work, which is time-consuming and ineffective. The other method is through CELLDT (CellDataTracking, a tool for tracking and measuring latency) data for fast-fading cell identification. CELLDT data identifies fast-fading cells based on signal changes for each user within a continuous unit of time. However, CELLDT data packets are large, requiring customized subscriptions and are difficult to parse; continuous customization can impact certain services. This embodiment uses a recurrent neural network to automatically identify fast-fading devices and thus determine fast-fading cells, improving work efficiency.

[0093] In one feasible embodiment, step S30 may include steps S301 to S303:

[0094] Step S301: Based on the QoS identifier of each fast-fading device in the fast-fading cell, determine the target fast-fading device for performing voice services from the fast-fading cell.

[0095] For identified fast-fading cells, the fast-fading devices currently performing voice services are selected based on the QoS identifier corresponding to each fast-fading device, and these are identified as target fast-fading devices. Through this selection process, the focus can be placed on the user group currently making voice calls, thereby improving the network quality perception of this user group.

[0096] Step S302: Obtain the percentage of second devices in the target fast-fading device in the fast-fading cell, and the average daily traffic volume of the fast-fading cell;

[0097] After identifying the target fast-fading devices, data statistics are performed for each fast-fading cell. Specifically, on the one hand, the number of target fast-fading devices in the fast-fading cell is counted, and their proportion in the total number of fast-fading devices in the cell is calculated, i.e., the proportion of the second device is counted. On the other hand, voice service data of the fast-fading cell over a period of time (such as daily, weekly, etc.) is collected and analyzed to calculate the average daily call volume of the fast-fading cell. The average daily call volume is an indicator of the busyness of voice services in a communication cell, reflecting the average activity level of users conducting voice communication services within the communication cell.

[0098] Step S303: The fast fading cell with the second device ratio exceeding the second preset ratio threshold and the daily average call volume exceeding the preset call volume threshold is identified as a voice problem cell.

[0099] Cells with a high proportion of fast-fading devices exceeding a second preset proportion threshold and a daily average call volume exceeding a preset call volume threshold are ultimately identified as voice problem cells. The second preset proportion threshold and the preset call volume threshold can be set based on actual application scenarios; this embodiment does not impose specific limitations on them. These voice problem cells have a high proportion of target fast-fading devices performing voice services and exhibit high service activity, making them more likely to experience voice quality issues due to fast fading. Therefore, they are target cells requiring focused voice quality optimization.

[0100] In one feasible embodiment, step S40 may include steps S401 to S402:

[0101] Step S401: Switch the application network of the voice problem device in the voice problem cell from the NR network to the LTE network;

[0102] It should be noted that NR networks are the wireless access technology for fifth-generation mobile communication, used to enable wireless communication connections between mobile devices (such as mobile phones, tablets, and other user devices) and base stations. LTE networks are the wireless access technology for fourth-generation mobile communication, used to provide high-speed, stable wireless data transmission services.

[0103] For identified voice problem cells, based on the identification information of voice problem devices in the cell and handover requirements, and according to preset network handover strategies and procedures, the application network of all voice problem devices in the cell is triggered to switch from the current New Radio (NR) network to the Long Term Evolution (LTE) network. This network handover operation leverages the relatively mature and stable characteristics of the LTE network to improve voice quality issues caused by fast fading in the NR network.

[0104] Step S402: Establish a VoLTE-based voice service for the device with voice problems in the LTE network.

[0105] It should be noted that VoLTE is a voice transmission technology based on the LTE network, which allows users to make high-quality voice calls directly on the LTE network using their own devices.

[0106] After a device with voice problems successfully switches to an LTE network, a VoLTE-based voice service is established for the device in the LTE network environment. This ensures that the device can enjoy stable and high-quality voice communication services after switching networks, effectively solving the problem of poor voice quality caused by the rapid fading of NR networks and improving the user's voice communication experience.

[0107] It is worth mentioning that in the early stages of construction, NR networks have difficulty covering all locations of all communication cells. Therefore, in this embodiment, the continuity of user voice service experience is ensured through the mobility management mechanism between NR and LTE networks (the mechanism that maintains service continuity when user equipment switches between different networks). When NR network coverage is insufficient, the continuously covered LTE network is used as the underlying coverage, and timely switching from NR to LTE network is performed to effectively reduce the impact of NR network signal fading on user voice call quality.

[0108] Therefore, in this embodiment, by accurately identifying cells with voice problems caused by fast fading and taking measures such as switching the application network of the voice problem device from the NR network to the LTE network and establishing a VoLTE-based voice service in the LTE network, the stability of the LTE network and the high-quality characteristics of VoLTE technology are effectively utilized to successfully reduce the adverse effects of fast fading on user voice quality, significantly improve the clarity, stability and reliability of voice calls, and bring users a better voice communication experience.

[0109] For example, in a feasible implementation scenario, the voice quality optimization process is as follows: Figure 3 As shown, the voice quality optimization process specifically includes: First, identifying fast-fading devices using a recurrent neural network based on the MRO data collected by the base station. The MRO data includes the RSRP data, temporary identifiers, and timestamps of each user equipment. Then, determining fast-fading cells based on the distribution of fast-fading devices, where the proportion of fast-fading devices and the number of user equipment in fast-fading cells are higher than in normal communication cells. Next, determining voice problem cells based on the average daily traffic volume of each fast-fading cell and the service quality identifiers of each fast-fading device. Finally, optimizing the voice quality of voice problem devices in voice problem cells.

[0110] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the speech quality optimization method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0111] This application also provides a voice quality optimization device; please refer to... Figure 4 The voice quality optimization device includes:

[0112] The fast fading device identification module 10 is used to identify fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold from each user device based on the RSRP sequence of each user device through a preset recurrent neural network.

[0113] The fast fading cell determination module 20 is used to determine the communication cell to which each fast fading device belongs based on the temporary identifier of each fast fading device, and to determine the communication cell that meets the preset equipment scale conditions and fast fading device distribution conditions as a fast fading cell.

[0114] The voice problem cell determination module 30 is used to determine the voice problem cell from the fast fading cells based on the quality of service identifier of each fast fading device in the fast fading cell;

[0115] The voice quality optimization module 40 is used to optimize the voice quality of voice problem devices in a voice problem cell, wherein the voice problem device is a fast fading device that performs voice services.

[0116] Optionally, the voice quality optimization device further includes a data processing module, which is used for:

[0117] Acquire MRO data collected by the base station, and extract RSRP data, temporary identifiers and timestamps of each user equipment from the MRO data;

[0118] Based on the temporary identifier and timestamp, the RSRP data of each user equipment is organized into an RSRP sequence arranged in time order.

[0119] Optionally, the fast fading device identification module 10 is also used for:

[0120] For each user equipment, the RSRP sequence of the user equipment is input into a preset recurrent neural network to obtain the fast fading device identification result output by the recurrent neural network. The recurrent neural network is used to determine the RSRP fluctuation value of the user equipment within a preset time window based on the RSRP sequence. When the RSRP fluctuation value exceeds the preset fluctuation threshold, the user equipment is identified as a fast fading device.

[0121] Optionally, the fast fading cell determination module 20 is also used for:

[0122] Based on the association rules between the temporary identifier of each fast-fading device and the global identifier of the cell, the communication cell to which each fast-fading device belongs is determined;

[0123] Determine the number of user devices in each communication cell and the percentage of the first device in the fast fading device category;

[0124] A communication cell whose number of user devices exceeds a preset threshold and whose proportion of the first device exceeds a first preset proportion threshold is identified as a fast fading cell.

[0125] Optionally, the voice problem cell determination module 30 is also used for:

[0126] Based on the Quality of Service (QoS) identifiers of each fast-fading device in the fast-fading cell, the target fast-fading device for performing voice services is determined from the fast-fading cell.

[0127] Obtain the percentage of second devices in the target fast-fading cell, and the average daily traffic volume of the fast-fading cell;

[0128] Cells with fast fading where the proportion of second devices exceeds the second preset proportion threshold and the average daily call volume exceeds the preset call volume threshold are identified as cells with voice problems.

[0129] Optionally, the voice quality optimization module 40 is also used for:

[0130] Switch the application network of voice-prone devices in the voice-prone cell from the NR network to the LTE network;

[0131] Establish VoLTE-based voice services for devices with voice issues in LTE networks.

[0132] The speech quality optimization apparatus provided in this application, employing the speech quality optimization method described in the above embodiments, can reduce the impact of fast fading on speech quality, thereby improving speech quality. Compared with the prior art, the beneficial effects of the speech quality optimization apparatus provided in this application are the same as those of the speech quality optimization method provided in the above embodiments, and other technical features in the speech quality optimization apparatus are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0133] This application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the voice quality optimization method in the first embodiment described above.

[0134] The following is for reference. Figure 5 It shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of this application. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0135] like Figure 5 As shown, the electronic device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the electronic device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication device 1009 allows the electronic device to exchange data with other devices wirelessly or via wired communication. Although the diagrams show electronic devices with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0136] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0137] The electronic device provided in this application embodiment employs the speech quality optimization method described in the above embodiments, enabling efficient extraction and display of knowledge from massive multi-source data. Compared with the prior art, the beneficial effects of the electronic device provided in this application embodiment are the same as those of the speech quality optimization method provided in the above embodiments, and other technical features of this electronic device are the same as those disclosed in the speech quality optimization method of the previous embodiment, and will not be repeated here.

[0138] It should be understood that the various parts disclosed in the embodiments of this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0139] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0140] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the speech quality optimization method in the above embodiments.

[0141] The computer-readable storage medium provided in this application embodiment may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0142] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0143] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by an electronic device, the electronic device causes the following to occur: Based on the RSRP sequence of each user device, the electronic device identifies each fast fading device whose RSRP fluctuation value exceeds a preset fluctuation threshold from each user device through a preset recurrent neural network; determines the communication cell to which each fast fading device belongs based on the temporary identifier of each fast fading device, and identifies communication cells that meet preset device size conditions and fast fading device distribution conditions as fast fading cells; determines voice problem cells from the fast fading cells based on the service quality identifier of each fast fading device in the fast fading cells; and optimizes the voice quality of the voice problem devices in the voice problem cells, wherein the voice problem devices are fast fading devices performing voice services.

[0144] Computer program code for performing the operations of the embodiments of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0145] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0146] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0147] The readable storage medium provided in this application embodiment is a computer-readable storage medium. This medium stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned speech quality optimization method, enabling efficient extraction and display of knowledge from massive amounts of multi-source data. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application embodiment are the same as those of the speech quality optimization method provided in the above embodiments, and will not be repeated here.

[0148] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the voice quality optimization method described above.

[0149] The computer program product provided in this application embodiment can extract useful information from data generated by information technology systems. Compared with the prior art, the beneficial effects of the computer program product provided in this application embodiment are the same as the beneficial effects of the voice quality optimization method provided in the above embodiments, and will not be repeated here.

[0150] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for optimizing speech quality, characterized in that, The speech quality optimization method includes: Based on the RSRP sequence of each user equipment, a preset recurrent neural network is used to identify fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold from each user equipment. The communication cell to which each fast fading device belongs is determined based on the temporary identifier of each fast fading device, and the communication cell that meets the preset device size conditions and fast fading device distribution conditions is determined as a fast fading cell. Based on the Quality of Service (QoS) identifiers of each fast-fading device in the fast-fading cell, identify the voice problem cell from the fast-fading cell; Voice quality optimization is performed on the voice-prone devices in the cell with voice problems, wherein the voice-prone devices are fast-fading devices performing voice services.

2. The speech quality optimization method as described in claim 1, characterized in that, Before the step of identifying fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold from each user equipment using a preset recurrent neural network based on the RSRP sequences of each user equipment, the method further includes: Acquire MRO data collected by the base station, and extract RSRP data, temporary identifiers and timestamps of each user equipment from the MRO data; Based on the temporary identifier and the timestamp, the RSRP data of each user equipment is organized into an RSRP sequence arranged in chronological order.

3. The speech quality optimization method as described in claim 1, characterized in that, The step of identifying fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold from each user equipment based on the RSRP sequence of each user equipment using a preset recurrent neural network includes: For each user equipment, the RSRP sequence of the user equipment is input into a preset recurrent neural network to obtain the fast fading device identification result output by the recurrent neural network. The recurrent neural network is used to determine the RSRP fluctuation value of the user equipment within a preset time window based on the RSRP sequence, and to determine the user equipment as a fast fading device when the RSRP fluctuation value exceeds a preset fluctuation threshold.

4. The speech quality optimization method as described in claim 1, characterized in that, The step of determining the communication cell to which each fast fading device belongs based on the temporary identifier of each fast fading device, and determining the communication cell that meets the preset device size conditions and fast fading device distribution conditions as a fast fading cell, includes: Based on the association rules between the temporary identifier of each fast fading device and the global identifier of the cell, the communication cell to which each fast fading device belongs is determined; Determine the number of user equipment in each of the aforementioned communication cells, and the first proportion of the fast fading devices; A communication cell whose number of user equipment exceeds a preset number threshold and whose proportion of the first equipment exceeds a first preset proportion threshold is identified as a fast fading cell.

5. The speech quality optimization method as described in claim 1, characterized in that, The step of determining the voice problem cell from the fast-fading cells based on the quality of service identifiers of each fast-fading device in the fast-fading cells includes: Based on the Quality of Service (QoS) identifier of each fast fading device in the fast fading cell, the target fast fading device for performing voice services is determined from the fast fading cell; Obtain the second device percentage of the target fast-fading device in the fast-fading cell, and the average daily traffic volume of the fast-fading cell; A fast-fading cell is defined as a cell with a voice problem if the proportion of the second device exceeds the second preset proportion threshold and the average daily call volume exceeds the preset call volume threshold.

6. The speech quality optimization method as described in claim 1, characterized in that, The step of optimizing the voice quality of devices with voice problems in the problematic cell includes: Switch the application network of the voice problem device in the cell with the voice problem from the NR network to the LTE network; Establish a VoLTE-based voice service for the device with the voice problem in the LTE network.

7. A voice quality optimization device, characterized in that, The voice quality optimization device includes: The fast fading device identification module is used to identify fast fading devices whose RSRP fluctuation values ​​exceed a preset fluctuation threshold from each user device based on the RSRP sequence of each user device through a preset recurrent neural network. The fast fading cell determination module is used to determine the communication cell to which each fast fading device belongs based on the temporary identifier of each fast fading device, and to determine the communication cell that meets the preset device size conditions and fast fading device distribution conditions as a fast fading cell. The voice problem cell determination module is used to determine the voice problem cell from the fast fading cells based on the quality of service identifier of each fast fading device in the fast fading cell; The voice quality optimization module is used to optimize the voice quality of voice-prone devices in the voice-prone cell, wherein the voice-prone devices are fast-fading devices that perform voice services.

8. An electronic device, characterized in that, The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the voice quality optimization method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the speech quality optimization method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the speech quality optimization method as described in any one of claims 1 to 6.

Images