User service exception processing method and device

Abstract

The application discloses a user service exception processing method and device, wherein the method comprises the following steps: obtaining service information of a user and corresponding service subscription data; inputting the service information of the user and the corresponding service subscription data into a detector model to obtain characteristic values of the user; inputting the characteristic values of the user into a decision tree model trained to obtain a matching result of the characteristic values of the user; determining abnormal information according to the matching result and executing a preset solution corresponding to the abnormal information. According to the application, the characteristic values of the user are determined based on the service information and the service subscription data of the user, a decision tree model is constructed to have the ability to detect and alarm the abnormal information of the user, the problems existing in the service of the user are mined in advance, the abnormal information of the user is discovered in time, the processing efficiency of the complaint of the user is improved, and the customer satisfaction is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of business support, in particular to a user service exception processing method and device. BACKGROUND

[0002] Mobile number portability (MNP) allows users to freely choose mobile, Unicom, Telecom and other operators while keeping the same number, and allows users to change the mobile subscription network within the same local network in the same country without changing the original MSISDN number (Mobile Subscriber International ISDN / PSTN number, the number called by a calling user to call a mobile user in a GSM PLMN). After the user subscribes to a new network, a new IMSI (SIM card / USIM card) is allocated to the MNP user to ensure that all user services are not affected by the old subscription network and are provided by the new subscription network.

[0003] In order to support MNP services, the operating network needs to be constructed according to the system architecture to ensure the normal execution of MNP services. MNP services include a carry-out process and a carry-in process. The carry-out process mainly includes a service query process and an authorization code application process, wherein the service query process is embedded in the authorization code application process. The carry-in process can send an effective request to the CSMS (processing number porting related service processes, saving the most authoritative and full number porting database) to request completion of user number porting after the user selects a network package and other services. The CSMS completes the user number porting according to the set effective broadcast rule at the next effective time window. The carry-out processing process of the MNP is consistent with the provincial sale logic. This logic belongs to the business rules that have been deposited for many years, and the rules are complex. In use, the carry-out user cannot normally communicate with the in-network user of the operator. This situation is generally caused by the failure of part of the instructions during the carry-out sale.

[0004] The above situation causes the following defects in the prior art when processing MNP:

[0005] 1. The related data of the service platform, support system and the like are not output, and do not have exception detection and alarm capabilities. Only after receiving user complaints can problems be found, which leads to the inability to find and solve problems in a timely manner.

[0006] 2. After receiving user complaints, joint analysis across departments is required to find problems, develop solutions, consume huge manpower, take a long time to locate problems, and it is difficult to solidify the solution after completion.

[0007] 3. The formulated solution is generally assembled by the maintenance personnel of the support system manually, and the subsequent reasonable verification and checking mechanism is not provided, so that unreasonable assembly or abnormal execution exists, and the time span from user complaint to final solution is long. SUMMARY

[0008] In view of the above problems, the present application is proposed in order to provide a user service exception processing method and device which overcomes the above problems or at least partially solves the above problems.

[0009] According to one aspect of the present application, a user service exception processing method is provided, which comprises:

[0010] obtaining service information of a user and corresponding service subscription data;

[0011] inputting the service information of the user and the corresponding service subscription data into a detector model to obtain a feature value of the user;

[0012] inputting the feature value of the user into a trained decision tree model to obtain a matching result of the feature value of the user;

[0013] determining abnormal information according to the matching result, and executing a preset solution corresponding to the abnormal information.

[0014] According to another aspect of the present application, a user service exception processing device is provided, which comprises:

[0015] an obtaining module adapted to obtain service information of a user and corresponding service subscription data;

[0016] a feature value module adapted to input the service information of the user and the corresponding service subscription data into a detector model to obtain a feature value of the user;

[0017] a matching module adapted to input the feature value of the user into a trained decision tree model to obtain a matching result of the feature value of the user;

[0018] an executing module adapted to determine abnormal information according to the matching result, and execute a preset solution corresponding to the abnormal information.

[0019] According to still another aspect of the present application, an electronic device is provided, which comprises a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus;

[0020] the memory is used to store at least one executable instruction, and the executable instruction makes the processor execute the operation corresponding to the above-mentioned user service exception processing method.

[0021] According to still another aspect of the present application, there is provided a computer storage medium having stored therein at least one executable instruction, which causes a processor to perform operations corresponding to the user service exception handling method as described above.

[0022] According to the user service exception handling method and device of the present application, the service information of a user and corresponding service subscription data are acquired; the service information of the user and corresponding service subscription data are input into a detector model to obtain characteristic values of the user; the characteristic values of the user are input into a decision tree model trained to obtain a matching result of the characteristic values of the user; according to the matching result, an exception information is determined, and a preset solution corresponding to the exception information is executed. According to the present application, the characteristic values of the user are determined based on the service information and service subscription data of the user, and the decision tree model is constructed to have the ability to detect and alarm the user exception information, so as to find the problems existing in the service of the user in advance, discover the exception information of the user in time, improve the processing efficiency of the user complaint, and improve the customer satisfaction.

[0023] The above description is only a summary of the technical solutions of the present application. In order to enable one of ordinary skill in the art to better understand the technical means of the present application and implement it according to the content of the description, and in order to enable the above and other purposes, characteristics and advantages of the present application to be more apparent and understandable, the specific embodiments of the present application are described below. BRIEF DESCRIPTION OF DRAWINGS

[0024] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a better understanding of the preferred embodiments, and are not to be considered as limiting of the present application. Moreover, in the drawings, like reference numerals refer to similar components throughout the several views. In the drawings:

[0025] Figure 1 A flow chart of a user service exception handling method according to one embodiment of the present application is shown;

[0026] Figure 2 An operational network system architecture diagram according to one embodiment of the present application is shown;

[0027] Figure 3 A number portability network flow diagram according to one embodiment of the present application is shown;

[0028] Figure 4 A functional block diagram of a user service exception handling device according to one embodiment of the present application is shown;

[0029] Figure 5 A structural diagram of an electronic device according to one embodiment of the present application is shown. DETAILED DESCRIPTION

[0030] Exemplary embodiments of the present disclosure will be described hereinafter with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art.

[0031] Figure 1 A flow chart of a user service exception processing method according to an embodiment of the present disclosure is shown. As shown in the figure, the user service exception processing method specifically includes the following steps: Figure 1

[0032] In step S101, the service information of the user and the corresponding service subscription data are acquired.

[0033] In this embodiment, the user is a number portability user. According to the service information of the number portability user and the corresponding service subscription data, the abnormal information existing in the service of the number portability user is found in time. In addition to the number portability user, this embodiment can also be used for users who can acquire service information and service subscription data to determine the abnormal information that may exist in the user, etc., which is not limited here. In order to better understand this embodiment, the number portability user is taken as an example for description hereinafter.

[0034] For the number portability user, in order to support the number portability service, the operation network can adopt a number portability service system as shown in the figure. Figure 2 ​The system architecture is shown. The system structure includes the CSMS built by the Ministry of Industry and Information Technology, which processes the NP (Number Portability) related business processes, and saves the most authoritative and full NPDB (Number Portability Database); the group SMS / SOA is composed of two parts of SMS subsystem and SOA subsystem. Among them, the SMS subsystem integrates the full NPDB, the data is obtained from the CSMS, and is responsible for distribution within the network; the SOA subsystem is responsible for forwarding the business messages between the provincial SOA and the CSMS; the ENUMDNS integrates the NPDB, obtains the NP data from the group SMS, and provides NP related data query services for devices such as MMS center. The provincial LSMS manages the local NPDB, and is responsible for synchronizing the NP data to the related network elements. The provincial SOA is combined with the provincial CRM, and is responsible for processing the NP related business; the existing network HLR / HSS: saves the ported user information, and the VMSC ID of the user is the NP MSC; the data of other non-ported users remains unchanged; the ported HLR / HSS is used to save the ported user data, process the routing query of the external network number, and make different responses according to the different states (ported, non-NP, inter-network NP, etc.) of the user; the NP MSC simulates the location update operation of the ported user, sets the VMSC ID of the ported user in the HLR to the NP MSC, and processes the voice and short message business of the ported user in the NP business.

[0035] The number portability process can be as shown in Figure 3 When step 7 is implemented, the provincial BOSS sends instructions to each business platform on the network side to execute the ported user cancellation, and the ported user cancellation processing process is consistent with the provincial user cancellation logic, but because the logic belongs to the business rules which have been deposited for many years, the rules are complex, and the situation that the ported user cannot normally communicate with the operator in the network occurs from time to time, resulting in user complaints. According to the user complaint, all the platforms and business support systems of the original operator's network are required to be checked one by one, and after the checking, a solution is developed, the instructions are manually assembled and sent to the network side to repair the state of each platform on the network side of the user, and the abnormal information of the user is solved. The whole processing process needs to spend more manpower and time, the processing efficiency is low, and the dependence on business personnel is strong.

[0036] Based on the above problems, the embodiment starts from the user, and predicts the service exception after the user number portability based on the user's own service information and corresponding service subscription data, so as to repair in time. The user's service information includes the registration information and state value of the user on at least one service platform. The service platform includes service platforms such as HSS, IMS, broadband platform, etc. The user's service information can be obtained by collecting all the registration information and state value of the user on all service platforms in the network. If the user has no registration information for a certain service platform, the state value of the user of the service platform can be set to NA accordingly. The user's service information collected is recorded according to the order of different service platforms, such as HSS, IMS, broadband platform, …, and the state value of the user of each service platform is recorded, such as N = [1, NA, 0, …]. The user's service subscription data is obtained according to the service support system, and the service subscription data of the user for each service platform is obtained, such as user service subscription data P = [pri1, pri2, pri3, …].

[0037] Step S102, input the user's service information and corresponding service subscription data into the detector model to obtain the user's feature value.

[0038] The user's service information N and corresponding service subscription data P are input into the detector model, the detector model performs matrix multiplication on the user's service information N and corresponding service subscription data P to obtain the user's correlation matrix C = N * P, and the user's correlation matrix C is used as the user's feature value.

[0039] Step S103, input the user's feature value into the decision tree model trained to obtain the user's feature value matching result.

[0040] The training of the decision tree model needs to be based on the user standard feature value. For the user standard feature value, the historical user's service information and service subscription data can be used to determine. Specifically, the historical user's service information and corresponding service subscription data are obtained; the historical user's service information and corresponding service subscription data are input into the detector model as sample data to obtain the historical user's correlation matrix. For example, the user's service information N0, N1, … and the user's service subscription data P0, P1, … obtained by the network side of the full number portability user are input into the detector model, the user's service information N and service subscription data P are multiplied by the detector model to obtain the historical user's correlation matrix C0, C1, …, and the historical user's correlation matrix is subjected to semi-supervised learning to obtain the user standard correlation matrix C NPAs standard feature values ​​for users, these serve as a baseline for recording user business order data and user business information. Furthermore, when performing semi-supervised learning on the association matrix of historical users, considering the complexity of business data, business personnel within the domain can be involved to label the business information of historical users and the corresponding business order data. Based on semi-supervised learning, the standard feature values ​​for users are finally extracted.

[0041] The detector model can also be continuously and dynamically corrected through deep machine learning. It uses the registration information, status values ​​and business order data of number portability users on various business platforms and business support systems as basic data, and extracts user standard feature values ​​through semi-supervised learning.

[0042] After obtaining the user's standard feature values, the training process of the decision tree model is as follows: First, acquire the business information and corresponding subscription data of historically anomalous users. Historically anomalous users can be identified based on user complaint information. Then, their business information and subscription data are acquired. This information is input into the detector model to obtain the feature values ​​of the historically anomalous users. Unsupervised classification is then performed based on the historically anomalous users' feature values ​​and the user's standard feature values ​​to classify and identify various types of anomalous information and their corresponding anomalous feature values. For example, if a historically anomalous user's complaint is that a user who has switched cards cannot use their new card after switching, while the old card works normally, the anomalous situation is determined to be a VoLTE cancellation failure by comparing it with the user's standard value. The corresponding anomalous feature value is the historically anomalous user's feature value C. x0 The complaint information of historical abnormal users indicates that users who have ported out are unable to answer calls from their original operator. By comparing this information with user standard values, the specific abnormal situation is determined to be an abnormal user status on the HSS, and the corresponding abnormal feature value is the feature value C of historical abnormal users. x1 For identified anomalies, to ensure accurate resolution, relevant business personnel can mark the anomalies and pre-define solutions for each anomaly, resulting in a decision tree model. The pre-defined solutions specifically construct an instruction library for each anomaly scenario, such as instructions for unsubscribing from VoLTE, account cancellation when transferring out of service, and broadband cancellation. One or a set of pre-defined instructions are provided for each anomaly, forming a pre-defined solution. An anomaly is VoLTE unsubscription failure, with an anomaly feature value C. x0 The default solution is to resend the VoLTE unsubscribe command; the abnormal situation is an abnormal user status on the HSS, with the abnormal characteristic value C. x1The corresponding preset solution is to resend the customer order instruction and the like. By analyzing the complaint information of the historical abnormal user, the feature values of the historical abnormal user and the standard feature values of the user are unsupervised classified, so as to obtain the decision tree model.

[0043] The decision tree model contains the standard feature values of the user and the abnormal feature values. The preset solution is provided for the abnormal feature values. For the number portability user, the feature values of the number portability user are input into the trained decision tree model, the feature values of the user are compared with the standard feature values of the user, whether the feature values of the user are consistent with the standard feature values of the user is judged, if the comparison result is consistent, it is indicated that the service of the number portability user is not prone to abnormality, and the number portability user can not be processed. If the comparison result is inconsistent, it is indicated that the service of the number portability user is prone to abnormality, the feature values of the user are matched with the abnormal feature values in the decision tree model, a matching result containing the abnormal feature values matched with the feature values of the user is obtained, so that the abnormal information possibly existing in the number portability user is discovered in time, the time consumption of solving the abnormality is shortened, and the problem of solving failure caused by manual error is avoided.

[0044] In step S104, the abnormal information is determined according to the matching result, and the preset solution corresponding to the abnormal information is executed.

[0045] After the matching result is obtained, the specific abnormal information and the preset solution corresponding to the abnormal information can be determined according to the abnormal feature values contained in the matching result. The preset solution corresponding to the abnormal information is executed, so that the abnormal information can be repaired in time and the normal operation of the user service is ensured.

[0046] According to the user service abnormality processing method provided by the application, the business information and the corresponding business subscription data of the user are obtained, the feature values of the user are obtained by inputting the business information and the corresponding business subscription data of the user into the detector model, the feature values of the user are input into the trained decision tree model, the matching result of the feature values of the user is obtained, the abnormal information is determined according to the matching result, and the preset solution corresponding to the abnormal information is executed. According to the application, the feature values of the user are determined based on the business information and the business subscription data of the user, the decision tree model is constructed to detect and alarm the abnormal information of the user, the problems existing in the user service are mined in advance, the abnormal information of the user is discovered in time, the processing efficiency of the user complaint is improved, and the customer satisfaction is improved.

[0047] Figure 4 A functional block diagram of a user service abnormality processing device according to an embodiment of the application is shown. As shown in Figure 4 The user service abnormality processing device includes the following modules:

[0048] The acquisition module 410 is adapted to acquire service information of a user and corresponding service subscription data.

[0049] The feature value module 420 is adapted to input the service information of the user and the corresponding service subscription data into a detector model to obtain a feature value of the user.

[0050] The matching module 430 is adapted to input the feature value of the user into the trained decision tree model to obtain a matching result of the feature value of the user.

[0051] The execution module 440 is adapted to determine abnormal information according to the matching result and execute a preset solution corresponding to the abnormal information.

[0052] Optionally, the feature value module is further adapted to input the service information of the user and the corresponding service subscription data into the detector model for matrix multiplication to obtain a correlation matrix of the user as the feature value of the user.

[0053] Optionally, the apparatus further comprises a standard feature value module 450.

[0054] The standard feature value module 450 is adapted to acquire service information of a historical user and corresponding service subscription data, input the service information of the historical user and the corresponding service subscription data as sample data into a detector model to obtain a correlation matrix of the historical user, and perform semi-supervised learning on the correlation matrix of the historical user to obtain a standard correlation matrix of the user as a standard feature value of the user.

[0055] Optionally, the service information of the user comprises registration information and / or a state value of the user on at least one service platform.

[0056] Optionally, the apparatus further comprises a decision tree model training module 460.

[0057] The decision tree model training module 460 is adapted to acquire service information of a historical abnormal user and corresponding service subscription data, input the service information of the historical abnormal user and the corresponding service subscription data into a detector model to obtain a feature value of the historical abnormal user, perform unsupervised classification according to the feature value of the historical abnormal user and a standard feature value of a user, mark an abnormal information on a result of the unsupervised classification, determine an abnormal feature value corresponding to the abnormal information, and preset a solution corresponding to the abnormal information to obtain a decision tree model.

[0058] Optionally, the matching module 420 is further adapted to input the feature value of the user into the trained decision tree model, compare the feature value of the user with the standard feature value of the user, determine whether the feature value of the user is consistent with the standard feature value of the user, if not, match the feature value of the user with an abnormal feature value in the decision tree model to obtain a matching result containing the abnormal feature value matched with the feature value of the user.

[0059] Optionally, the user is a number portability user.

[0060] The above modules are described with reference to the corresponding description in the method embodiments, and will not be described here again.

[0061] The application further provides a non-volatile computer storage medium, which stores at least one executable instruction, and the computer executable instruction can execute the user service exception processing method in any method embodiment.

[0062] Figure 5 A structural schematic diagram of an electronic device according to one embodiment of the application is shown, and the specific embodiments of the application do not limit the specific implementation of the electronic device.

[0063] As shown in Figure 5 The electronic device can include a processor 502, a communications interface 504, a memory 506, and a communications bus 508.

[0064] Among them:

[0065] The processor 502, the communications interface 504, and the memory 506 complete mutual communication through the communications bus 508.

[0066] The communications interface 504 is used to communicate with network elements of other devices, such as clients or other servers.

[0067] The processor 502 is used to execute the program 510, and specifically can execute the related steps in the above user service exception processing method embodiments.

[0068] Specifically, the program 510 can include program code, and the program code includes computer operation instructions.

[0069] The processor 502 can be a central processing unit CPU, or an application specific integrated circuit ASIC, or one or more integrated circuits configured to implement embodiments of the application. One or more processors included in the electronic device can be the same type of processor, such as one or more CPUs; or can be different types of processors, such as one or more CPUs and one or more ASICs.

[0070] A memory 506, for storing the program 510. The memory 506 can include a high speed RAM memory, and can also include a non-volatile memory, such as at least one disk memory.

[0071] The program 510 can be specifically configured to enable the processor 502 to perform the user service exception handling method in any of the above method embodiments. The specific implementation of each step in the program 510 can refer to the corresponding description in the corresponding step and unit in the above user service exception handling embodiments, which will not be described here. It can be clearly understood by those skilled in the art that, for the convenience and brevity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above method embodiments, which will not be described here.

[0072] The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems can be used with programs in accordance with the teachings herein. The structure required to construct such a system is apparent from the above description. Moreover, the inventive is not intended to be realized on any specific programming language. It will be appreciated that there are many programming languages that can be used to implement the teachings of the present invention described herein, and that the description above with respect to one specific language is merely meant to disclose the best mode of the present invention.

[0073] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been described in detail in order not to obscure the understanding of this description.

[0074] Similarly, it is to be understood that the above description is only illustrative of the aspects of the present application and that numerous modifications can be made by those skilled in the art to the inventive concepts described herein. For example, the steps of the methods described above can be performed in a different order than was described, and / or various steps can be modified, eliminated, or added. Similarly, the steps of the methods described above can be performed by hardware components or using hardware components combined with software components. In another example, the various features of the application described herein can be implemented in software or hardware, including but not limited to any conventional computing components, virtual systems, or other devices. As such, it is not the intention of the inventor or the assignee to limit the application to the recited method steps and specific combinations of hardware components or software components. Accordingly, the scope of the present application should be determined not with reference to the above description, but instead with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

[0075] Those skilled in the art will appreciate that the modules in the apparatuses in the embodiments can be adapted and placed in one or more apparatuses other than the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and furthermore can be split into multiple sub-modules or sub-units or sub-components. Any combination of all the features disclosed in the specification (including the accompanying claims, abstract and drawings), and any method or process or apparatus of any combination of the features disclosed in the specification (including the accompanying claims, abstract and drawings) can be taken, except that at least some of such features and / or processes or units are mutually exclusive, unless explicitly stated otherwise. Each feature disclosed in the specification (including the accompanying claims, abstract and drawings) can be replaced by alternative features providing the same, equivalent, or similar functions unless stated explicitly otherwise.

[0076] Furthermore, those skilled in the art will appreciate that different embodiments of the application have different features and that some features of one embodiment can not be present in another embodiment. It should be noted that any of the features described in the specification (including the accompanying claims, abstract and drawings) can be used in any combination with any of the features described in the specification (including the accompanying claims, abstract and drawings), unless explicitly stated otherwise.

[0077] The various component embodiments of the application can be implemented in hardware, or as software modules running in one or more processors, or in combinations thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components of the user service exception handling apparatus according to the embodiments of the application. The application can also be implemented as a program (for example, a computer program and a computer program product) for executing any or all of the methods described herein on a device or apparatus (for example, a computer). Such a program implementing the application can be stored on a computer readable medium, or can be in the form of one or more signals. Such a signal can be downloaded from an Internet website, or can be available for

[0078] It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of both hardware and software, and any combination thereof. In a unitary claim, several devices or means can be listed, comprising means which can be implemented by one and the same hardware item. The use of the word "a" or "an" does not exclude the presence of a plurality of such elements, nor does it imply that a single element is to be used.

Claims

1. A method for handling user service exceptions, characterized in that, The methods include: Obtain user business information and corresponding business order data; The user's business information and corresponding business order data are input into the detector model to obtain the user's feature values; The user's feature values ​​are input into the trained decision tree model to obtain the user's feature value matching result; The training process of the decision tree model includes: acquiring business information and corresponding business order data of historical abnormal users; inputting the business information and corresponding business order data of historical abnormal users into the detector model to obtain the feature values ​​of the historical abnormal users; performing unsupervised classification based on the feature values ​​of historical abnormal users and user standard feature values, marking the unsupervised classification results as abnormal information, determining the abnormal feature values ​​corresponding to the abnormal information, and pre-setting the solutions corresponding to the abnormal information to obtain the decision tree model; the user standard feature values ​​are determined through the business information and business order data of historical users. Based on the matching results, anomaly information is determined, and a preset solution corresponding to the anomaly information is executed.

2. The method according to claim 1, characterized in that, The step of inputting the user's business information and corresponding business order data into the detector model to obtain the user's feature values ​​further includes: The user's business information and corresponding business order data are input into the detector model for matrix multiplication to obtain the user's association matrix as the user's feature value.

3. The method according to claim 1, characterized in that, The method further includes: Obtain historical user business information and corresponding business order data; The historical users’ business information and corresponding business order data are used as sample data and input into the detector model to obtain the association matrix of historical users. Semi-supervised learning is performed on the association matrix of the historical users to obtain the standard association matrix of users as the standard feature values ​​of users.

4. The method according to any one of claims 1-3, characterized in that, The user's business information includes the user's registration information and / or status value on at least one business platform.

5. The method according to claim 1, characterized in that, The step of inputting the user's feature values ​​into the trained decision tree model to obtain the user's feature value matching result further includes: The user's feature values ​​are input into the trained decision tree model, and the user's feature values ​​are compared with the user's standard feature values ​​to determine whether the user's feature values ​​are consistent with the user's standard feature values. If not, the user's feature values ​​are matched with the abnormal feature values ​​in the decision tree model to obtain a matching result containing abnormal feature values ​​that match the user's feature values.

6. The method according to claim 1, characterized in that, The user in question is a user who has switched mobile networks while keeping their number.

7. A user service exception handling device, characterized in that, The device includes: The acquisition module is suitable for acquiring users' business information and corresponding business order data. The feature value module is adapted to input the user's business information and corresponding business order data into the detector model to obtain the user's feature value; The matching module is adapted to input the user's feature values ​​into the trained decision tree model to obtain the user's feature value matching results; The training process of the decision tree model includes: acquiring business information and corresponding business order data of historical abnormal users; inputting the business information and corresponding business order data of historical abnormal users into the detector model to obtain the feature values ​​of the historical abnormal users; performing unsupervised classification based on the feature values ​​of historical abnormal users and user standard feature values, marking the unsupervised classification results as abnormal information, determining the abnormal feature values ​​corresponding to the abnormal information, and pre-setting the solutions corresponding to the abnormal information to obtain the decision tree model; the user standard feature values ​​are determined through the business information and business order data of historical users. The execution module is adapted to determine the abnormal information based on the matching result and execute the preset solution corresponding to the abnormal information.

8. An electronic device, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the user service exception handling method as described in any one of claims 1-6.

9. A computer storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the user service exception handling method as described in any one of claims 1-6.

Images