A terminal function determination method, apparatus, device, and storage medium

Abstract

The application provides a terminal function determination method and device, equipment and a storage medium, relates to the technical field of communication, and is used for improving the accuracy of terminal function determination. The method comprises the following steps: obtaining device information of a target terminal, permanent network information of the target terminal, service information of the target terminal, consumption information of the target terminal and user complaint information of the target terminal; inputting the device information of the target terminal, the permanent network information of the target terminal, the service information of the target terminal, the consumption information of the target terminal and the user complaint information of the target terminal into a function determination model to obtain a function determination result; and the function determination result is used for indicating whether the target terminal supports a voice over long-term evolution (VoLTE) function.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method, apparatus, device and storage medium for determining terminal functions. Background Technology

[0002] Voice over Long-Term Evolution (VoLTE) refers to the technology of transmitting voice communication over a Long-Term Evolution (LTE) network using the Internet Protocol (IP). Compared to traditional 2G and 3G voice communication, VoLTE can provide a higher quality and faster voice call experience, and can also be used simultaneously with data services.

[0003] For operators, analyzing whether a terminal supports VoLTE is crucial. This helps operators determine which users can enjoy high-quality VoLTE calls, thereby providing better service and user experience.

[0004] Currently, when analyzing whether terminal devices support VoLTE, operators only focus on base station information or the network standards supported by the terminal, which can easily lead to misjudgments of terminal functionality. Therefore, how to accurately identify whether a terminal supports VoLTE has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for determining terminal functions, which improves the accuracy of terminal function determination.

[0006] In a first aspect, this application provides a method for determining terminal functions. The method includes: acquiring device information of a target terminal, persistent network information of the target terminal, service information of the target terminal, consumption information of the target terminal, and user complaint information of the target terminal; inputting the device information of the target terminal, persistent network information of the target terminal, service information of the target terminal, consumption information of the target terminal, and user complaint information of the target terminal into a function determination model to obtain a function determination result; the function determination result is used to indicate whether the target terminal supports the Long Term Evolution Voice Bearer (VoLTE) function.

[0007] The technical solution provided in this application offers at least the following benefits: It allows for a comprehensive analysis of whether a target terminal supports VoLTE functionality by utilizing data related to the target terminal, such as device information, persistent network information, service information, consumption information, and user complaint information. This improves the accuracy of determining whether a target terminal supports VoLTE. Furthermore, analyzing data related to the target terminal using a functional determination model to determine VoLTE support can more accurately identify potential correlations and trends within the data, thereby enhancing the accuracy of target terminal functionality determination.

[0008] In one possible implementation, before inputting the target terminal's device information, persistent network information, service information, consumption information, and user complaint information into the function determination model, the method further includes: acquiring at least one terminal's device information, persistent network information, service information, consumption information, and user complaint information to establish at least one training sample set; the terminal's device information includes the terminal's model and supported network types; the terminal's persistent network information includes the persistent network type; the terminal's service information includes VoLTE service information, VoLTE traffic volume, and operator information; the terminal's consumption information includes the VoLTE function's registration status; and the terminal's user complaint information includes the number of 3G complaints; based on at least one training sample set, using the model, supported network type, persistent network type, VoLTE service information, VoLTE traffic volume, operator information, VoLTE function's registration status, and 3G complaint count of each terminal included in the training sample set as feature fields to construct at least one decision tree; one decision tree corresponds to one training sample set; and a function determination model is generated based on at least one decision tree.

[0009] In one possible implementation, the method further includes: when the target terminal does not support VoLTE, performing correlation analysis on the target terminal's device information, the target terminal's persistent network information, the target terminal's service information, the target terminal's consumption information, and the target terminal's user complaint information based on preset association rules to obtain the reason why the target terminal does not support VoLTE; and determining the target migration strategy corresponding to the reason based on the reason so that the user's terminal side supports VoLTE.

[0010] In one possible implementation, the target migration strategy is one of multiple migration strategies, which include at least one of the following: replacing the target terminal, replacing the target terminal's SIM card slot, subscribing to VoLTE service, turning on the VoLTE switch of the target terminal, or updating the target terminal's system version.

[0011] In one possible implementation, the preset association rules are determined based on an association rule algorithm.

[0012] In one possible implementation, the target terminal's device information includes the target terminal's model number; the target terminal's service information includes voice service subscription information, VoLTE function registration information, and operator information; the target terminal's consumption information includes VoLTE call volume; the reasons include at least one of the following: the target terminal's hardware does not support VoLTE function, the target terminal's SIM card slot is incompatible with VoLTE function, the target terminal's system version is not updated, the target terminal has not subscribed to VoLTE service, or the target terminal has not turned on VoLTE; the preset association rules include at least one of the following: the association between one or more of the voice service subscription information, the target terminal's model number, VoLTE function registration information, VoLTE call volume, and operator information, and one or more of the target terminal's hardware not supporting VoLTE function; the association between one or more of the terminal's model number, VoLTE function subscription information, VoLTE function registration information, and operator information, and one or more of the target terminal's SIM card slot incompatibility, the target terminal's system version not updated, the target terminal not turning on VoLTE, or the target terminal not subscribing to VoLTE service.

[0013] Secondly, this application provides a terminal function determination device. The control device includes: an acquisition module, used to acquire device information of a target terminal, persistent network information of the target terminal, service information of the target terminal, consumption information of the target terminal, and user complaint information of the target terminal; and a processing module, used to input the device information of the target terminal, persistent network information of the target terminal, service information of the target terminal, consumption information of the target terminal, and user complaint information of the target terminal into a function determination model to obtain a function determination result; the function determination result is used to indicate whether the target terminal supports the Long Term Evolution Voice Bearer (VoLTE) function.

[0014] In one possible implementation, the acquisition module is further configured to acquire at least one terminal's device information, persistent network information, service information, consumption information, and user complaint information to establish at least one training sample set; the terminal's device information includes the terminal's model and supported network types; the terminal's persistent network information includes the persistent network type; the terminal's service information includes VoLTE service information, VoLTE traffic volume, and operator information; the terminal's consumption information includes the VoLTE function's registration status; and the terminal's user complaint information includes the number of 3G complaints; the processing module is further configured to, based on at least one training sample set, use the model, supported network type, persistent network type, VoLTE service information, VoLTE traffic volume, operator information, VoLTE function's registration status, and the number of 3G complaints for each terminal included in the training sample set as feature fields to construct at least one decision tree; one decision tree corresponds to one training sample set; and the processing module is further configured to generate a function determination model based on at least one decision tree.

[0015] In one possible implementation, the processing module is further configured to, when the target terminal does not support VoLTE, perform correlation analysis on the target terminal's device information, the target terminal's persistent network information, the target terminal's service information, the target terminal's consumption information, and the target terminal's user complaint information based on preset correlation rules to obtain the reason why the target terminal does not support VoLTE; based on the reason, determine the target migration strategy corresponding to the reason so that the user's terminal side supports VoLTE.

[0016] In one possible implementation, the target migration strategy is one of multiple migration strategies, which include at least one of the following: replacing the target terminal, replacing the target terminal's SIM card slot, subscribing to VoLTE service, turning on the VoLTE switch of the target terminal, or updating the target terminal's system version.

[0017] In one possible implementation, the preset association rules are determined based on an association rule algorithm.

[0018] In one possible implementation, the target terminal's device information includes the target terminal's model number; the target terminal's service information includes voice service subscription information, VoLTE function registration information, and operator information; the target terminal's consumption information includes VoLTE call volume; the reasons include at least one of the following: the target terminal's hardware does not support VoLTE function, the target terminal's SIM card slot is incompatible with VoLTE function, the target terminal's system version is not updated, the target terminal has not subscribed to VoLTE service, or the target terminal has not turned on VoLTE; the preset association rules include at least one of the following: the association between one or more of the voice service subscription information, the target terminal's model number, VoLTE function registration information, VoLTE call volume, and operator information, and one or more of the target terminal's hardware not supporting VoLTE function; the association between one or more of the terminal's model number, VoLTE function subscription information, VoLTE function registration information, and operator information, and one or more of the target terminal's SIM card slot incompatibility, the target terminal's system version not updated, the target terminal not turning on VoLTE, or the target terminal not subscribing to VoLTE service.

[0019] Thirdly, this application provides an electronic device comprising: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to perform a method for determining terminal functions as described in the first aspect and any possible implementation thereof.

[0020] Fourthly, this application provides a computer program product that, when run on a computer, causes the computer to execute the steps of the related methods described in the first aspect, so as to achieve the determination of the terminal function described in the first aspect.

[0021] Fifthly, this application provides a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by a processor of a server, enables the server to perform the determination of terminal functions as provided in the first aspect and any possible implementation thereof; or, when the instructions in the computer-readable storage medium are executed by a processor of a client, enables the client to perform the determination of terminal functions as provided in the second aspect and any possible implementation thereof.

[0022] The beneficial effects of the second to fifth aspects mentioned above can be referred to the first aspect, and will not be repeated here. Attached Figure Description

[0023] 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, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the composition of a terminal function determination system provided in an embodiment of this application;

[0025] Figure 2 This is a schematic diagram of the composition of a data acquisition device provided in an embodiment of this application;

[0026] Figure 3 A network topology diagram of a carrier big data platform provided in this application embodiment;

[0027] Figure 4 A flowchart illustrating a method for determining terminal functions provided in an embodiment of this application;

[0028] Figure 5 A structural diagram of multiple decision trees in a random forest provided in an embodiment of this application;

[0029] Figure 6 A flowchart illustrating another method for determining terminal functions provided in this application embodiment;

[0030] Figure 7 A flowchart illustrating another method for determining terminal functions provided in this application embodiment;

[0031] Figure 8 This is a schematic diagram of the structure of a determining device provided in an embodiment of this application;

[0032] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0033] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0034] It should be noted that in the embodiments of this application, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplarily" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0035] To facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0036] To improve the accuracy of terminal function determination, the application embodiments provide a method for determining terminal functions. This method comprehensively analyzes whether a terminal supports VoLTE functionality by utilizing data related to the user's terminal, such as device information, persistent network information, service information, consumption information, and user complaint information. This improves the accuracy of determining whether a terminal supports VoLTE. Furthermore, analyzing user-terminal-related data using a function determination model to determine VoLTE support can more accurately identify potential correlations and trends within the data, thereby further improving the accuracy of determining whether a terminal supports VoLTE.

[0037] Figure 1 This is a schematic diagram illustrating the composition of a terminal function determination system provided in an embodiment of this application. Figure 1 As shown, the determination system 100 includes a data acquisition device 101 and a determination device 102.

[0038] The data acquisition device 101 and the determination device 102 can be connected via wired or wireless means. For example, the data acquisition device 101 and the determination device 102 can be connected via a wireless local area network.

[0039] The data acquisition device 101 is used to acquire and store data from the operator's proprietary big data platform. This includes, for example, terminal device information, terminal's persistent network information, terminal service information, terminal consumption information, and terminal user complaint information.

[0040] For example, the data acquisition device 101 may be a single server, or it may be a server cluster consisting of multiple servers. In some embodiments, the server cluster may also be a distributed cluster.

[0041] The determining device 102 is used to determine whether the terminal supports VoLTE function.

[0042] For example, the determining device 102 may be a single server, or it may be a server cluster consisting of multiple servers. In some embodiments, the server cluster may also be a distributed cluster.

[0043] The above example illustrates that the data acquisition device 101 and the determination device 102 are different devices. In other embodiments, the data acquisition device 101 and the determination device 102 may be the same device, and both may be integrated on the same server. This application does not specifically limit this.

[0044] Figure 2 This is a schematic diagram illustrating the composition of a data acquisition device provided in an embodiment of this application. Figure 2 As shown, the data acquisition device 101 includes: a server 201, a probe 202, a switch 203, and a disk array 204. In some embodiments, the number of servers 201, probes 202, switches 203, and disk arrays 204 may also be multiple.

[0045] Understandably, the data acquisition device 101, consisting of server 201, probe 202, switch 203 and disk array 204, can achieve rapid data conversion and display by making full use of the functions and advantages of each component, thereby improving development efficiency and meeting the processing needs of cross-domain and multi-platform information.

[0046] In some embodiments, server 201 is the main component of data acquisition device 101, used for storing, managing, and processing data. Server 201 typically has high-performance hardware configurations, such as large-capacity memory, multi-core processors, and high-speed disk arrays, to support the processing and storage of large-scale data. These servers 201 undertake the task of unified storage and transformation of data and provide rapid data visualization capabilities. Additionally, as... Figure 3 As shown, server 201 can be located in the data parsing layer, platform application layer, log collection layer, etc.

[0047] In some embodiments, probe 202 is a network device used to collect network-related data, such as network traffic, latency, and packet loss rate. By monitoring network-related data, potential problems can be identified in a timely manner, and corresponding measures can be taken for optimization and improvement. Additionally, as... Figure 3 As shown, probe 202 can be located in the probe acquisition layer.

[0048] In some embodiments, switch 203 is a network device used to connect multiple computers and other network devices to enable the transmission of data packets within a local area network (LAN). Switch 203 is responsible for forwarding data packets from the source device to the destination device to facilitate communication between devices. By properly configuring and managing the switch, the efficiency and stability of data transmission can be improved.

[0049] In some embodiments, disk array 204 is a collection of physical disks that, by combining and managing these disks, provide a high-capacity, high-performance data storage solution. Disk array 204 undertakes the task of storing large amounts of data, providing high data read / write speeds and redundancy fault tolerance, ensuring data security and reliability. Additionally, as... Figure 3 As shown, disk array 204 can be located in the data parsing layer, log collection layer, etc.

[0050] Optionally, the data acquisition device 101 may include four servers 201, two probes 202, four switches 203, and four disk arrays 204.

[0051] In some embodiments, the plurality of servers 201 may include Linux servers.

[0052] The Linux server is equipped with a PostgreSQL database and a geographic application based on the PostGis database.

[0053] In some embodiments, a Linux server is a network server built on a Linux system. Linux servers are commonly used for network and system management, database management, and web services.

[0054] In this embodiment, a PostgreSQL database is used to store and manage relevant data of mobile network users, including user information, base station information, location data, etc. PostgreSQL is a powerful relational database with excellent data processing and querying capabilities.

[0055] In some embodiments, after reading the point, line, and polygon geographic data from the terminal, the Linux server can use the GeoPandas library to process the data. Furthermore, it can call corresponding coordinate system transformation functions to convert the terminal's point, line, and polygon geographic data from one coordinate system to another. For example, converting the WGS84 coordinate system to the BD009 coordinate system.

[0056] The method for determining terminal functions provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0057] Figure 4This is a flowchart illustrating a method for determining terminal functions according to an embodiment of this application. Figure 4 As shown, the method includes the following steps:

[0058] S101, Determine that the device obtains the target terminal's device information, the target terminal's resident network information, the target terminal's service information, the target terminal's consumption information, and the target terminal's user complaint information.

[0059] In some embodiments, the device information of the target terminal may include the target terminal's type allocation code (TAC), the target terminal's brand, the target terminal's type, the network types supported by the target terminal, the number of SIM card slots the target terminal has, the functions supported by the target terminal, and the frequency band information supported by the target terminal.

[0060] The TAC of the target terminal is composed of a portion of characters and / or numbers from the International Mobile Equipment Identity (IMEI). For example, it can be the first six digits of the IMEI code. The terminal's TAC is used to identify the manufacturer and model of the target terminal.

[0061] Optionally, based on the number of SIM card slots available in the target terminal, it can be determined whether the target terminal is a dual-SIM target terminal.

[0062] Optionally, based on the functions supported by the target terminal, it can be determined whether the target terminal supports VoLTE functionality.

[0063] Optionally, based on the frequency band information supported by the target terminal, it can be determined whether the target terminal supports low-frequency channels (e.g., 900MHz band) of the Long Term Evolution (LTE) network of general mobile communication technologies.

[0064] In some embodiments, the persistent network information of the target terminal may include persistent base station, geographical location information of the persistent base station, total dwell time of the persistent base station, persistent cell, geographical location information of the persistent cell, total dwell time of the persistent cell, persistent network type, total dwell time of the persistent network, longest dwell time on the 3G network, and geographical location information of the 3G cell with the longest dwell time.

[0065] Optionally, based on the geographical location information of the permanent base station, information such as the city and district / county where the permanent base station is located can be determined.

[0066] Optionally, the persistent cells can include 2G persistent cells, 3G persistent cells, 4G persistent cells, and 5G persistent cells. The latitude and longitude of the cell can be determined based on its geographical location information. For example, the latitude and longitude of the 3G cell with the longest dwell time can be determined based on its geographical location information.

[0067] In some embodiments, the service information of the target terminal may include VoLTE service registration information, traffic information, call volume information, 5G function activation information, circuit switch fallback (CSFB) count, voice call service activation information, wireless fixed-line service activation information, operator information, and Internet of Things (IoT) service activation information.

[0068] Optionally, based on traffic information, the data traffic that the target terminal can use on a 3G or 4G network can be determined.

[0069] Optionally, based on call volume information, it can be determined whether the target terminal has made a voice call on the 3G network, or the call volume of the target terminal on the 3G network, 4G network, or VoLTE network.

[0070] Optionally, based on operator information, it can be determined whether the target terminal is a virtual operator service provided by a third-party operator, or a target terminal that uses other major operator networks to provide communication services.

[0071] In some embodiments, the consumption information of the target terminal may include the type of the contracted package, the name of the contracted package, the price of the contracted package, the total consumption amount of the target terminal in the three months prior to the current month, the total call duration and total data usage of the target terminal in the three months prior to the current month, the total data usage of the target terminal in the three months prior to the current month, the call duration and data usage of the target terminal in the current month, the consumption information of the converged services of the target terminal in the three months prior to the current month, the usage information of the target terminal, the usage information of the 5G network, the group information to which the target terminal's mobile phone number belongs, and the information of the account to which the target terminal belongs.

[0072] Converged services can include services that integrate different mobile communication networks, such as the integration of 3G and 4G networks, or the integration of mobile communication networks and broadband networks.

[0073] Optionally, based on the target terminal's call duration and data usage in the current month, it can be determined whether the target terminal exceeded the call duration or data usage stipulated in the contracted package in the past billing cycle.

[0074] Optionally, based on the target terminal's consumption information of converged services in the three months prior to the current month, it can be determined whether the target terminal has activated one or more of the aforementioned converged services.

[0075] Optionally, based on the target terminal's usage information, it can be determined whether the target terminal has enabled the Do Not Disturb function and whether it has enabled primary and secondary SIM cards.

[0076] Optionally, based on 5G network usage information, it can be determined whether the target terminal has activated 5G network services.

[0077] Optionally, based on the group information to which the target terminal's mobile phone number belongs, it can be determined whether the target terminal's mobile phone number belongs to a group user.

[0078] Optionally, the status of the target terminal can be determined based on the information of the account to which the target terminal belongs. For example, the user is using the converged service of the target terminal.

[0079] In some embodiments, the user complaint information of the target terminal may include the user's geographical location information at the time of the complaint, the user's identity information, the name of the grid where the user is located at the time of the complaint, the responsible department within the operator responsible for handling user complaints, the type or nature of the user complaint event, the channel or method of the user complaint, the content of the user complaint event, the number of times the user has repeatedly complained about the same issue, the service type of the user complaint, the network type of the user complaint, the environmental information of the user's geographical location at the time of the complaint, the complaint level of the user complaint, and the name of the base station where the user is residing at the time of the complaint.

[0080] Optionally, based on user identity information, a user's special status can be determined, such as a VIP customer, military personnel, or person with disabilities. Additionally, based on user identity information, a user's status level can also be determined, such as a VIP level.

[0081] Optionally, the type or nature of user complaints may include poor network signal, inadequate service, etc.

[0082] Optionally, user complaints can be submitted via telephone, online, or other means.

[0083] S102. The determining device inputs the target terminal's device information, the target terminal's resident network information, the target terminal's service information, the target terminal's consumption information, and the target terminal's user complaint information into the function determining model to obtain the function determining result.

[0084] The function determination result is used to indicate whether the target terminal supports the Long Term Evolution Voice Bearer (VoLTE) function.

[0085] In some embodiments, the function-determined model can be a model based on the random forest algorithm, or a model based on algorithms such as support vector machines or k-nearest neighbor classification.

[0086] Understandably, determining whether a target terminal supports VoLTE is a binary classification problem in machine learning. Random forest algorithms typically achieve high accuracy when handling classification problems.

[0087] like Figure 5 The diagram showing the structure of multiple decision trees in a random forest demonstrates how voting or averaging predictions across multiple decision trees can reduce the risk of overfitting and improve the overall model's accuracy. Furthermore, the random forest algorithm is highly capable of handling data with high-dimensional features (such as the aforementioned terminal device information, terminal's persistent network information, terminal's service information, terminal's consumption information, and terminal's user complaint information). When partitioning nodes in each decision tree, the random forest selects the best splitting feature from a randomly chosen subset of features. This helps address the curse of dimensionality and improves the model's generalization ability.

[0088] For example, step S102 can be implemented by the following code.

[0089] clf1=RandomForestRegressor(n_estimators=108, max_depth=7, min_samples_leaf=10);

[0090] clf1.fit(traindata,trainlabel);

[0091] res=clf1.predict(testdata);

[0092] based on Figure 4 The embodiments shown in this application provide a method for determining terminal functionality. This method comprehensively analyzes whether a terminal supports VoLTE functionality by utilizing data related to the user's terminal, such as device information, persistent network information, service information, consumption information, and user complaint information. This improves the accuracy of determining whether a terminal supports VoLTE. Furthermore, analyzing user-terminal-related data using a functionality determination model to determine VoLTE support can more accurately identify potential correlations and trends within the data, thereby further improving the accuracy of the determination.

[0093] In some embodiments, before the determining device inputs the terminal's device information, the terminal's persistent network information, the terminal's service information, the terminal's consumption information, and the terminal's user complaint information into the function determining model, that is, before step S102, such as... Figure 6 The method shown may also include the following steps:

[0094] S201. The device determines that it acquires device information, resident network information, service information, consumption information and user complaint information of at least one terminal to establish at least one training sample set.

[0095] In some embodiments, the determining device has determined whether the at least one terminal supports VoLTE functionality.

[0096] For example, the determining device selects 200,000 terminals whose VoLTE functionality has been determined to be supported from among the device information, resident network information, service information, consumption information, and user complaint information of 1 million terminals.

[0097] In some embodiments, step S201 can be implemented as steps a1-a3 as described below.

[0098] Step a1: The device performs data preprocessing operations on the acquired device information, resident network information, service information, consumption information, and user complaint information of at least one terminal.

[0099] In some embodiments, data preprocessing operations may include default value filling, outlier handling, data transformation, etc.

[0100] It's understandable that some fields might be missing from the acquired data. For example, terminal device information might only include fields such as supported network types, number of SIM card slots, supported functions, and supported frequency bands, missing fields like the device type allocation code (TAC), brand, and type. Since data with missing fields may contain crucial information for analyzing whether a terminal supports VoLTE, directly deleting such data would affect the objectivity and accuracy of the analysis results.

[0101] For example, when some fields are missing in the data, the determining device can first use the fit method to calculate the size of the relevant values ​​in the data matrix, and then use the transform method to fill in the missing fields in the data matrix.

[0102] For example, default value filling can be implemented using the following code.

[0103] from sklearn.impute import SimpleImputer

[0104] import numpy as np

[0105] imp=SimpleImputer(missing_values=np.nan, strategy='mean')

[0106] imp.fit(X)

[0107] Train = imp.transform(X1)

[0108] Exception handling can be implemented using the following code.

[0109] From sklearn.ensemble import IsolationForest

[0110] predictions=IsolationForest().fit(data).predict(data)

[0111] In addition, the types of data acquired include discrete, continuous, and binary types. To facilitate processing and analysis, data transformation is required.

[0112] For example, the acquired data can be standardized by removing the mean and normalizing the variance, that is, the data can be transformed into a normal distribution with a mean of 0 and a variance of 1.

[0113] For data such as latitude and longitude, a one-dimensional clustering method was used for data transformation. Specifically, latitude and longitude data were clustered using the K-means clustering algorithm, the resulting clusters were merged into the same label, and the number of each label was counted as a feature representing the network classification attribute of the region, thus achieving the goal of converting continuous data into discrete data.

[0114] Step a2: The determining device constructs a sample for each of the multiple terminals based on the device information, resident network information, service information, consumption information, and user complaint information of at least one terminal after data preprocessing.

[0115] In some embodiments, the sample for each terminal consists of the terminal's device information, persistent network information, service information, consumption information, and user complaint information.

[0116] Step a3: The device determines that it randomly generates multiple training sample sets based on the samples from each terminal.

[0117] Each training sample set includes samples from one or more terminals.

[0118] In some embodiments, samples from one or more terminals are drawn from samples from multiple terminals each time to generate a sample set; then, samples from one or more terminals are drawn from samples from multiple terminals with replacement to generate a sample set; and so on, to randomly generate multiple sample sets.

[0119] The sequence number and number of samples in each sample set may be different.

[0120] For example, if the samples of m terminals are D1, D2, D3...Dm respectively; randomly select samples of one or more terminals from the samples of m terminals to generate a sample set n1; wherein the sample set n1 includes samples D1, D3, D4 and D8.

[0121] From the samples of m terminals, samples of one or more terminals are randomly selected to generate a sample set n2; wherein the sample set n2 includes samples D4, D5, D9, D10 and D17.

[0122] S202. The determining device uses at least one training sample set as feature fields to construct at least one decision tree, including the model of each terminal included in the training sample set, the supported network type, the resident network type, VoLTE service information, VoLTE traffic volume, operator information, VoLTE function registration status, and the number of 3G complaints.

[0123] In some embodiments, step S202 can be implemented as steps b1-b5 as described below.

[0124] Step b1: Determine that the device performs annotation operations on each field in the training sample set.

[0125] In some embodiments, the determining device may label each terminal sample with an attribute tag indicating whether it supports VoLTE functionality. A value of 0 represents no support, and a value of 1 represents support.

[0126] For example, the above annotation operation can be implemented by the following code.

[0127] # Convert a string column to an integer

[0128] def str_column_to_int(dataset,column):

[0129] class_values=[row[column]for row in dataset]

[0130] unique = set(class_values)

[0131] lookup = dict()

[0132] for i,value in enumerate(unique):

[0133] lookup[value] = i

[0134] for row in dataset:

[0135] row[column]=lookup[row[column]]

[0136] return lookup

[0137] # Split the dataset into k folds

[0138] def cross_validation_split(dataset,n_folds):

[0139] dataset_split = list()

[0140] dataset_copy = list(dataset)

[0141] fold_size=len(dataset) / n_folds

[0142] for iin range(n_folds):

[0143] fold = list()

[0144] while len(fold) <fold_size:

[0145] index=randrange(len(dataset_copy))

[0146] fold.append(dataset_copy.pop(index))

[0147] dataset_split.append(fold)

[0148] return dataset_split

[0149] Step b2: Determine the feature fields based on the training sample set after the annotation operation.

[0150] In some embodiments, based on the training sample set that has undergone the above-described annotation operation, the determining device can obtain the weight coefficient between each field included in the sample of each terminal and the above-described attribute label based on the SelectFromModel method, and perform regularization processing on the weight coefficient to reflect the importance of the field.

[0151] Furthermore, the determining device can use fields with weight coefficients greater than a preset threshold as feature fields. Understandably, if the weight coefficient is greater than the preset threshold, it indicates that the field is more important.

[0152] Optionally, the preset threshold can be 0.1.

[0153] For example, the method for determining the above feature fields can be implemented by the following code.

[0154] sfm=SelectFromModel(estimator=DecisionTreeRegressor(),threshold=0.1)

[0155] sfm.fit_transform(X,Y)

[0156] For example, the device determines that the terminal model, supported network type, resident network type, VoLTE service information, VoLTE traffic volume, operator information, VoLTE function registration status, and number of 3G complaints included in the training sample set are used as feature fields.

[0157] Step b3: Determine the entropy of each feature field.

[0158] In some embodiments, the determining device may use an information entropy formula to calculate the entropy of each feature field. The information entropy formula measures the purity and importance of each field.

[0159] Step b4: The determination device calculates the information gain corresponding to the entropy of each feature field.

[0160] Information gain is used to characterize the amount of information a feature field provides. The greater the information gain, the more information the feature field contains, and the more important the feature field is.

[0161] Step b5: Select the feature field with the largest information gain as the optimal feature of the current node of a decision tree.

[0162] In some embodiments, after performing step b5, the optimal feature of the current node is excluded, and steps b1-b5 are recursively repeated based on other feature fields until one of the following two conditions is met:

[0163] (1) All samples under the current node belong to the same category, so there is no need to further divide them.

[0164] (2) All feature fields have been cycled through.

[0165] S203. The determining device generates the function determination model based on the at least one decision tree.

[0166] In some embodiments, the determining device randomly combines at least one decision tree to generate a functionally determined model.

[0167] In some embodiments, for an established functionally determined model, the accuracy requirements of the functionally determined model can be improved by adjusting its hyperparameters.

[0168] For example, the hyperparameters of a function-determined model include the following:

[0169] sklearn.ensemble.RandomForestClassifier(

[0170] n_estimators = 100,

[0171] criterion = 'gini',

[0172] max_depth = None

[0173] min_samples_split=2,

[0174] min_samples_leaf = 1,

[0175] min_weight_fraction_leaf=0.0,

[0176] max_features = 'auto',

[0177] max_leaf_nodes = None

[0178] min_impurity_decrease = 0.0,

[0179] min_impurity_split = None

[0180] class_weight = None,

[0181] random_state=None,bootstrap=True,

[0182] oob_score = False

[0183] n_jobs = None,

[0184] verbose = 0,

[0185] warm_start=False)

[0186] In some embodiments, the determining device can prevent overfitting of the functional determination model by adjusting parameters related to pruning.

[0187] The parameters that the determination device can adjust include: the number of decision trees n_estimator, the maximum depth of the decision trees max_depth, and the minimum number of samples in the leaf nodes of the decision trees.

[0188] For example, given the number of decision trees, the parameter range of the depth of the decision trees, and the range of the number of samples in the leaf nodes of the decision trees, the RandomizedSearchCV function algorithm is used within this given range to randomly sample and traverse the parameters, outputting the optimal accuracy of the model, which is taken as the accuracy corresponding to the optimal parameter combination, thus obtaining the set of parameter combinations with the best model fit.

[0189] For example, the above parameter adjustment process can be implemented by the following code.

[0190]

[0191]

[0192] In some embodiments, such as Figure 7 As shown, the method includes the following steps:

[0193] S301. When the target terminal does not support VoLTE, the device performs correlation analysis on device information, resident network information, service information, consumption information and user complaint information based on preset association rules to obtain the reason why the target terminal does not support VoLTE.

[0194] Among them, the preset association rules are used to determine the association between at least one of the following: device information, resident network information, service information, consumption information, and user complaint information, and the reason why the target terminal does not support the VoLTE function.

[0195] In some embodiments, the reasons why the target terminal does not support VoLTE functionality may include the following two: reasons why the hardware does not support VoLTE functionality and reasons why the software does not support VoLTE functionality.

[0196] The reasons for hardware-independent VoLTE support may include at least one of the following:

[0197] (1) The target terminal does not have the hardware capability to support VoLTE.

[0198] It is understandable that some target terminals were not designed or manufactured with VoLTE functionality in mind, resulting in a lack of the hardware capabilities required to support VoLTE.

[0199] (2) The card slot is incompatible with VoLTE functionality.

[0200] Understandably, some SIM card slots may only support specific network standards, such as 3G or 2G, while VoLTE functionality requires LTE network support. Therefore, if the target terminal's SIM card slot does not support LTE, meaning the SIM card slot is incompatible with VoLTE, the target terminal will experience VoLTE incompatibility.

[0201] The reasons for not supporting VoLTE functionality in the software may include at least one of the following:

[0202] (1) The target terminal's system version is too low.

[0203] Understandably, in order to support VoLTE, the target terminal's operating system needs to have the corresponding VoLTE protocol and features. Therefore, if the target terminal's system version is too low, it will not meet the requirements for VoLTE, and thus the target terminal will not be able to support VoLTE.

[0204] (2) The target terminal has not signed up for VoLTE service.

[0205] Understandably, the target terminal may need to sign up for a corresponding VoLTE service with an operator before using the VoLTE function. If the target terminal has not signed up for a corresponding VoLTE service, the operator may restrict the VoLTE function of the target terminal, thus making the target terminal not support the VoLTE function.

[0206] (3) VoLTE is not enabled on the target terminal.

[0207] Understandably, the target terminal's software settings will have a VoLTE switch. If this switch is not turned on, the target terminal will not be able to support the VoLTE function.

[0208] Optionally, the relationship between at least one of the device information, resident network information, service information, consumption information, and user complaint information and the reason why the target terminal does not support VoLTE function can be one-to-one, many-to-one, or one-to-many.

[0209] For example, the association between at least one of the following—device information, persistent network information, service information, consumption information, and user complaint information—and the reason why the target terminal does not support VoLTE functionality may include at least one of the following:

[0210] (1) The relationship between one or more of the following: the subscription information of voice services, the model of the target terminal, the registration information of VoLTE function, VoLTE call volume, and operator information, and the fact that the hardware of the target terminal does not support VoLTE function.

[0211] For example, when the voice service subscription information is "unsubscribed," the target terminal model is a non-VoLTE terminal, the VoLTE function registration information is "unregistered," the VoLTE call volume is "none," and the operator information is "non-virtual operator," there is a correlation between all items in the voice service subscription information, the target terminal model, the VoLTE function registration information, the VoLTE call volume, and the operator information and the fact that the target terminal's hardware does not support the VoLTE function.

[0212] (2) The relationship between one or more of the target terminal's model, VoLTE function subscription information, VoLTE function registration information, operator information, and one or more of the following: incompatibility of the target terminal's card slot, outdated target terminal system version, or VoLTE switch not turned on.

[0213] For example, if the target terminal is a VoLTE terminal, the VoLTE function subscription information is not subscribed, the VoLTE function registration information is not registered, and the operator information is a non-virtual operator, there is a correlation between the target terminal model, VoLTE function subscription information, VoLTE function registration information, and all items in the operator information and one or more of the following: the target terminal's SIM card slot is incompatible, the target terminal's system version is not updated, or the VoLTE switch is not turned on.

[0214] In some embodiments, the preset association rules are determined based on an association rule algorithm. This association rule algorithm can be the Apriori algorithm. Furthermore, the determination of the preset association rules can be found in the detailed description of steps b1-b3 below.

[0215] S302. The determining device determines the target migration strategy corresponding to the cause based on the cause, so that the user's target terminal side supports VoLTE function.

[0216] The target migration strategy is one of multiple migration strategies, which include at least one of the following: replacing the target terminal, replacing the target terminal's SIM card slot, subscribing to VoLTE service, turning on the VoLTE switch on the target terminal, or updating the target terminal's system version.

[0217] In some embodiments, if the target terminal does not have the hardware capability to support VoLTE, replacing the target terminal device will be used as the target migration strategy.

[0218] In some embodiments, if the cause is card slot incompatibility, replacing the card slot of the target terminal is used as the target migration strategy.

[0219] In some embodiments, if the reason is that the target terminal system version is too low, updating the target terminal system version is used as the target migration strategy.

[0220] In some embodiments, if the reason is not having subscribed to VoLTE services, subscribing to VoLTE services is used as the target migration strategy.

[0221] In some embodiments, the reason is that if the VoLTE switch is not enabled, the VoLTE switch of the target terminal will be enabled as the target migration strategy.

[0222] In some embodiments, after the target migration strategy is determined, the determining device may issue a reminder to the user to guide the user to the business hall to perform operations related to the target migration strategy, so that the user's target terminal side supports VoLTE function.

[0223] In some embodiments, this application also provides a method for determining preset association rules, including the following steps:

[0224] Step b1: Based on the device information, resident network information, service information, consumption information and user complaint information of multiple terminals that do not support VoLTE function, the device uses the Apriori algorithm to filter out frequent itemsets that meet the preset minimum support.

[0225] Frequent itemsets are those whose support is greater than a preset minimum support. For example, an itemset may include {product A, product B}. If the preset minimum support is 0.3 and the support of {product A, product B} is 0.4, then {product A, product B} is a frequent itemset.

[0226] For example, filtering frequent itemsets can be achieved using the following code.

[0227]

[0228]

[0229]

[0230] Step b2: The determination device generates at least one candidate association rule based on frequent itemsets.

[0231] In some embodiments, the determining device generates all possible candidate association rules by randomly combining each item in the frequent itemset.

[0232] For example, for a frequent itemset {A,B,C}, possible rules include: {A}->{B,C}, {B}->{A,C}, {C}->{A,B}, etc.

[0233] Step b3: The determination device uses confidence to filter target association rules based on at least one candidate association rule.

[0234] The target association rule is the aforementioned preset association rule.

[0235] In some embodiments, the determining device may obtain the confidence level of each candidate association rule and select the candidate association rule with the lowest confidence level as the target association rule.

[0236] For example, the generation of target association rules can be achieved using the following code.

[0237] #Generation Rules

[0238] rules=apriori.generateRules(L,supportData,minConf=0.5)

[0239] It should also be noted that, based on the method in the above embodiments, the accuracy of matching target migration strategies for target terminals that do not support VoLTE function reaches over 90%, and the matching rate is also improved by about 20%. Compared with related technologies that only focus on base station-side information or the network standards supported by the terminal, this method improves efficiency and success rate, and provides a better user experience.

[0240] This application embodiment can divide the control device into functional modules according to the above method example. For example, each function can be divided into its own functional modules. The integrated modules can be implemented in hardware or software. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0241] When dividing each function into modules according to its corresponding function. Figure 8 The determining device from the above embodiments is shown. For example... Figure 8 As shown, the determining device 800 includes an acquisition module 801 and a processing module 802. The acquisition module 801 and the processing module 802 are connected.

[0242] The acquisition module 801 is used to acquire the target terminal's device information, the target terminal's persistent network information, the target terminal's service information, the target terminal's consumption information, and the target terminal's user complaint information.

[0243] The processing module 802 is used to input the device information of the target terminal, the persistent network information of the target terminal, the service information of the target terminal, the consumption information of the target terminal, and the user complaint information of the target terminal into the function determination model to obtain the function determination result; the function determination result is used to indicate whether the target terminal supports the Long Term Evolution Voice Bearer (VoLTE) function.

[0244] The processing module 802 is also used to determine whether to activate the secondary carrier based on the service demand rate, the actual transmission rate and the predicted signal-to-noise ratio.

[0245] In some embodiments, before inputting the target terminal's device information, target terminal's persistent network information, target terminal's service information, target terminal's consumption information, and target terminal's user complaint information into the function determination model, the acquisition module 801 is further configured to acquire at least one terminal's device information, persistent network information, service information, consumption information, and user complaint information to establish at least one training sample set; the terminal's device information includes the terminal's model and supported network types; the terminal's persistent network information includes the persistent network type; the terminal's service information includes VoLTE service information, VoLTE call volume, and operator information; the terminal's consumption information includes the VoLTE function's registration status; and the terminal's user complaint information includes the number of 3G complaints.

[0246] The processing module 802 is further configured to construct at least one decision tree based on at least one training sample set, using the model of each terminal included in the training sample set, the supported network type, the resident network type, VoLTE service information, VoLTE traffic volume, operator information, VoLTE function registration status and 3G complaint number as feature fields; one decision tree corresponds to one training sample set.

[0247] The processing module 802 is also used to generate a functional determination model based on at least one decision tree.

[0248] In some embodiments, the processing module 802 is further configured to, when the target terminal does not support VoLTE functionality, perform correlation analysis on the device information of the target terminal, the persistent network information of the target terminal, the service information of the target terminal, the consumption information of the target terminal, and the user complaint information of the target terminal based on preset correlation rules, to obtain the reason why the target terminal does not support VoLTE functionality.

[0249] The processing module 802 is further configured to determine the target migration strategy corresponding to the cause based on the cause, so that the user's target terminal side supports VoLTE function.

[0250] The target migration strategy is one of multiple migration strategies, which include at least one of the following: changing the user's target terminal, changing the SIM card slot of the user's target terminal, subscribing to VoLTE service, enabling VoLTE on the user's target terminal, or updating the system version of the user's target terminal. The preset association rules are determined based on an association rule algorithm.

[0251] The target terminal's equipment information includes the target terminal's model; the target terminal's service information includes voice service subscription information, VoLTE function registration information, and operator information; the target terminal's consumption information includes VoLTE call volume.

[0252] The reasons include at least one of the following: the target terminal's hardware does not support VoLTE, the target terminal's SIM card slot is incompatible with VoLTE, the target terminal's system version is not updated, the target terminal has not signed up for VoLTE service, or the target terminal has not turned on the VoLTE switch.

[0253] The preset association rules include at least one of the following: the association between one or more of the following: voice service subscription information, target terminal model, VoLTE function registration information, VoLTE call volume, and operator information, and one or more of the following: the target terminal hardware does not support VoLTE function; or the association between one or more of the following: terminal model, VoLTE function subscription information, VoLTE function registration information, and operator information, and one or more of the following: incompatibility of the target terminal's SIM card slot, outdated system version of the target terminal, VoLTE switch not turned on for the target terminal, and no VoLTE service subscription for the target terminal.

[0254] Of course, the determining device 800 includes, but is not limited to, the unit modules listed above. Furthermore, the specific functions that the aforementioned functional units can implement include, but are not limited to, the functions corresponding to the method steps in the above embodiments. For a detailed description of other modules of the determining device 800, please refer to the detailed description of their corresponding method steps; these will not be repeated here in the embodiments of this application.

[0255] In an exemplary embodiment, this application also provides an electronic device. Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 9 As shown, the electronic device may include a processor 901 and a memory 902; the memory 902 stores instructions executable by the processor 901; when the processor 901 is configured to execute instructions, the electronic device causes the electronic device to implement the method described in the foregoing method embodiments.

[0256] In an exemplary embodiment, this application also provides a computer-readable storage medium storing computer program instructions thereon; when the computer program instructions are executed by an electronic device, the electronic device causes the electronic device to perform the method described in the foregoing embodiments. The computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0257] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope 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.

Claims

1. A method for determining terminal functions, characterized in that, include: Obtain the target terminal's device information, the target terminal's persistent network information, the target terminal's service information, the target terminal's consumption information, and the target terminal's user complaint information; The system acquires device information, persistent network information, service information, consumption information, and user complaint information of at least one terminal to establish at least one training sample set. The device information includes the terminal's model and supported network types. The persistent network information includes the persistent network type. The service information includes VoLTE service information, VoLTE call volume, and operator information. The consumption information includes the VoLTE function registration status. The user complaint information includes the number of 3G complaints. Based on the at least one training sample set, the model of each terminal included in the training sample set, the supported network type, the persistent network type, the VoLTE service information, the VoLTE traffic volume, the operator information, the registration status of the VoLTE function, and the number of 3G complaints are used as feature fields to construct at least one decision tree; one decision tree corresponds to one training sample set. Based on the at least one decision tree, generate a function determination model; The device information, persistent network information, service information, consumption information, and user complaint information of the target terminal are input into the function determination model to obtain the function determination result; the function determination result is used to indicate whether the target terminal supports the Long Term Evolution Voice Bearer (VoLTE) function.

2. The method according to claim 1, characterized in that, The method further includes: If the target terminal does not support VoLTE, based on preset association rules, the device information, the persistent network information, the service information, the consumption information, and the user complaint information of the target terminal are analyzed to determine the reason why the target terminal does not support VoLTE. Based on the aforementioned reasons, a target migration strategy corresponding to those reasons is determined to enable the user's terminal to support the VoLTE function.

3. The method according to claim 2, characterized in that, The target migration strategy is one of a plurality of migration strategies, which include at least one of the following: Replace the target terminal, replace the SIM card slot of the target terminal, subscribe to VoLTE service, turn on the VoLTE switch of the target terminal, and update the system version of the target terminal.

4. The method according to claim 3, characterized in that, The preset association rules are determined based on an association rule algorithm.

5. The method according to claim 3, characterized in that, The device information of the target terminal includes the model of the target terminal; the service information of the target terminal includes the voice service subscription information, the VoLTE function registration information, and the operator information; the consumption information of the target terminal includes VoLTE call volume. The reasons include at least one of the following: the hardware of the target terminal does not support VoLTE function, the card slot of the target terminal is not compatible with VoLTE function, the system version of the target terminal is not updated, the target terminal has not signed up for VoLTE service, or the VoLTE switch of the target terminal is not turned on. The preset association rule includes at least one of the following: The relationship between one or more of the following: the voice service subscription information, the target terminal model, the VoLTE function registration information, the VoLTE call volume, and the operator information, and one or more of the following: the target terminal's hardware does not support the VoLTE function. The relationship between one or more of the following: the terminal model, the VoLTE function subscription information, the VoLTE function registration information, and the operator information, and one or more of the following: incompatibility with the target terminal's SIM card slot, outdated system version of the target terminal, VoLTE not turned on on the target terminal, and no VoLTE service subscription on the target terminal.

6. A device for determining terminal functions, characterized in that, include: The acquisition module is used to acquire the device information of the target terminal, the persistent network information of the target terminal, the service information of the target terminal, the consumption information of the target terminal, and the user complaint information of the target terminal. The acquisition module is further configured to acquire device information, persistent network information, service information, consumption information, and user complaint information of at least one terminal to establish at least one training sample set; the device information of the terminal includes the terminal model and supported network types; the persistent network information of the terminal includes the persistent network type; the service information of the terminal includes VoLTE service information, VoLTE call volume, and operator information; the consumption information of the terminal includes the registration status of the VoLTE function; and the user complaint information of the terminal includes the number of 3G complaints. The processing module is configured to, based on the at least one training sample set, use the model of each terminal included in the training sample set, the supported network type, the persistent network type, the VoLTE service information, the VoLTE traffic volume, the operator information, the registration status of the VoLTE function, and the number of 3G complaints as feature fields to construct at least one decision tree; one decision tree corresponds to one training sample set; The processing module is further configured to generate a function determination model based on the at least one decision tree; The processing module is further configured to input the device information of the target terminal, the persistent network information of the target terminal, the service information of the target terminal, the consumption information of the target terminal, and the user complaint information of the target terminal into the function determination model to obtain the function determination result; the function determination result is used to indicate whether the target terminal supports the Long Term Evolution Voice Bearer (VoLTE) function.

7. The apparatus according to claim 6, characterized in that, The device further includes: The analysis module is used to perform correlation analysis on the target terminal's device information, the target terminal's persistent network information, the target terminal's service information, the target terminal's consumption information, and the target terminal's user complaint information based on preset correlation rules when the target terminal does not support VoLTE functionality, in order to obtain the reason why the target terminal does not support VoLTE functionality. The determination module is used to determine the target migration strategy corresponding to the reason based on the reason, so that the user's terminal side supports the VoLTE function.

8. An electronic device, characterized in that, The electronic device includes: a processor and a memory; The memory stores instructions that the processor can execute; When the processor is configured to execute the instructions, the electronic device performs the method as described in any one of claims 1-5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes: computer software instructions; When the computer software instructions are executed in an electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1-5.

Images