Abnormal number shutdown method and device based on risk assessment and medium

Abstract

The invention relates to the technical field of big data processing, in particular to an abnormal number shutdown method and device based on risk assessment and a medium, and the method comprises the steps: building a risk assessment model through collecting multi-source data and selecting a random forest algorithm as a core algorithm, and dynamically selecting a suitable shutdown strategy according to a risk assessment result; marking positive and negative samples, and updating the model through the positive and negative samples; and the historical shutdown record or the number of times of resetting is counted, and the two are combined with the risk level to evaluate whether the number is an abnormal number or not. According to the method and the device, the abnormal number can be shut down in real time, the number is effectively prevented from being maliciously reused, meanwhile, the accuracy of judging the normal number is improved, and the misjudgment rate of the number is reduced.

Description

Technical Field

[0001] The present application relates to the field of big data processing technology, and in particular to a method, device and medium for shutting down abnormal numbers based on risk assessment. Background Art

[0002] As telecommunications network fraud becomes increasingly rampant, communications operators need effective strategies to curb the proliferation of fraudulent numbers.

[0003] The existing number suspension mechanism mostly adopts a single static strategy, which is often forced suspension or simple online live authentication before resuming the service. This approach is insufficient in dealing with the ever-changing fraud methods, and often leads to the following problems: normal user numbers are sometimes mistakenly suspended due to overly strict policies, which leads to user experience and complaints; fraudulent numbers can be resuming the service through simple online live authentication, which cannot effectively prevent malicious reuse; the accuracy of identifying abnormal numbers is low; after identifying abnormal numbers, they cannot be shut down in a timely manner.

[0004] Therefore, how to effectively prevent abnormal numbers from being maliciously reused is an issue that needs to be addressed urgently. Summary of the invention

[0005] The present application provides a method for shutting down abnormal numbers based on risk assessment, which can effectively prevent abnormal numbers from being maliciously reused, shut down abnormal numbers in real time, and improve the accuracy of determining normal numbers.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme:

[0007] In a first aspect, the present invention provides a method for shutting down an abnormal number based on risk assessment, the method comprising:

[0008] Collect multi-source data of the number and use a pre-trained risk assessment model to assess the risk level of the number, where the risk assessment model is built based on a random forest algorithm;

[0009] Executing a strategy corresponding to the risk level of the number according to the risk level of the number, the strategy including initiating a shutdown request for the number to the operator's number management system and sending a liveness authentication request to the number;

[0010] If the number is subject to the liveness authentication strategy, the liveness authentication result of the number is obtained, and the number with the failed result is used as a positive sample, and the number with the passed result is used as a negative sample;

[0011] Constructing a corresponding decision tree sub-model according to the positive sample and the negative sample, and updating the risk assessment model based on the decision tree sub-model to obtain a target model;

[0012] Using the target model to evaluate the risk level of the number, to obtain a target risk level;

[0013] If the number is subject to the policy of initiating a shutdown request to the operator's number management system and the result of its liveness authentication is passed, a request to restore the number is initiated to the operator's number management system;

[0014] Obtain the number of shutdowns and restarts of the number, and determine whether the number is an abnormal number in combination with the target risk level. If so, initiate a shutdown request for the abnormal number to the operator's number management system.

[0015] In a preferred example of the present application, it can be further configured that the multi-source data includes historical abnormal work order data of the number, normal complaint work order data, user behavior data and device usage data.

[0016] In a preferred example of the present application, it can be further configured to include:

[0017] Inputting the multi-source data into a big data platform, integrating the multi-source data according to dimensions, and obtaining training data;

[0018] The risk assessment model is trained using the training data to obtain the pre-trained risk assessment model.

[0019] In a preferred example of the present application, it can be further configured that the strategy corresponding to the risk level is executed on the number according to the risk level of the number, if the number is executed with the liveness authentication strategy, the result of the liveness authentication of the number is obtained, and the number with the result of failure is taken as a positive sample, and the number with the result of passing is taken as a negative sample, including:

[0020] When the risk level of the number is medium risk, a shutdown request for the number is sent to the operator's number management system, and then a liveness authentication request is sent to the number. If the liveness authentication result is passed, a restoration request for the number is sent to the operator's number management system, and the number is added to the negative sample. Otherwise, the number is added to the positive sample.

[0021] When the risk level of the number is low risk, a liveness authentication request is sent to the number. If the liveness authentication result is passed, the number is added to the negative sample. Otherwise, a shutdown request for the number is initiated to the operator's number management system, and the number is added to the positive sample.

[0022] In a preferred example of the present application, it can be further configured to include:

[0023] The number of shutdown times of the number is obtained. If the number of shutdown times of the number is greater than a preset threshold, when the risk level of the number is medium risk, no request for reactivation of the number is initiated to the operator's number management system.

[0024] In a preferred example of the present application, it can be further configured that the operator's number management system includes:

[0025] Operator billing system or CRM system.

[0026] In a second aspect, the present application provides a device for shutting down abnormal numbers based on risk assessment, the device comprising:

[0027] A data collection module, used to collect multi-source data of numbers and evaluate the risk level of the numbers using a pre-trained risk assessment model, wherein the risk assessment model is built based on a random forest algorithm;

[0028] A policy execution module is used to execute a policy corresponding to the risk level of the number according to the risk level of the number, wherein the policy includes initiating a shutdown request for the number to the operator's number management system and sending a liveness authentication request to the number; if the liveness authentication policy is executed on the number, the result of the liveness authentication of the number is obtained, and the number with the result of failure is used as a positive sample, and the number with the result of passing is used as a negative sample;

[0029] A model updating module, configured to construct a corresponding decision tree sub-model according to the positive sample and the negative sample, update the risk assessment model based on the decision tree sub-model to obtain a target model; and use the target model to assess the risk level of the number to obtain a target risk level;

[0030] The shutdown module is used to initiate a shutdown request to the operator's number management system for the number if the number is subject to the policy of initiating a shutdown request to the operator's number management system and the result of its liveness authentication is passed; obtain the number of shutdown times and the number of restart times of the number, and determine whether the number is an abnormal number in combination with the target risk level. If so, initiate a shutdown request for the abnormal number to the operator's number management system.

[0031] In a third aspect, the present application provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for shutting down an abnormal number based on risk assessment as described in any one of the above items are implemented.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium having a program stored thereon, wherein when the program is executed by a processor, the method for shutting down an abnormal number based on risk assessment as described in any one of the above items is implemented.

[0033] In a fifth aspect, the present application provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the method for shutting down an abnormal number based on risk assessment as described in any one of the above.

[0034] In summary, compared with the prior art, the technical solution provided in the embodiment of the present application has at least the following beneficial effects:

[0035] The present application provides a method for shutting down abnormal numbers based on risk assessment, which provides a comprehensive data basis for risk assessment by collecting multi-source data. The random forest algorithm is selected as the core algorithm to construct the risk assessment model, so that the model has the advantages of strong adaptability and easy interpretation. The appropriate shutdown strategy is dynamically selected according to the risk assessment results, so that the method has a high degree of flexibility and can take different actions according to the risk score and historical behavior of the number. By marking positive and negative samples and updating the model through positive and negative samples, more accurate training data is provided for the risk assessment model, thereby obtaining more accurate assessment results, effectively reducing erroneous shutdowns, and improving user experience. By counting the historical shutdown records or the number of restarts, the two are combined with the risk level to evaluate whether the number is an abnormal number, and the abnormal number can be shut down in real time, effectively preventing the number from being maliciously reused, while improving the accuracy of judging normal numbers and reducing the rate of misjudgment of numbers. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of a method for shutting down an abnormal number based on risk assessment is provided for one embodiment of the present application.

[0037] Figure 2 A structural diagram of an abnormal number shutdown device based on risk assessment provided in one embodiment of the present application. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] In one embodiment of the present application, a method for shutting down abnormal numbers based on risk assessment is provided. Figure 1 As shown, the method includes:

[0040] S100: Collect multi-source data of the number, and use a pre-trained risk assessment model to assess the risk level of the number, where the risk assessment model is built based on a random forest algorithm.

[0041] Specifically, the multi-source data includes information from multiple data sources, including operator work orders, user behavior and device data. The risk assessment model is built based on the random forest algorithm, and the assessment process includes the following steps:

[0042] (1) Data preparation: Integrate data from multiple sources, including number history, behavioral data, complaint records, and fraud case history. Then, clean the data, handle missing values ​​and outliers, and extract key features.

[0043] (2) Model construction: The random forest algorithm is selected as the core algorithm because of its strong adaptability and easy interpretation. The model is trained using the processed data and optimized by adjusting parameters (such as the number and depth of trees).

[0044] (3) Performance evaluation: Cross-validation and test set were used to evaluate the model performance, with a focus on the ROC AUC score to measure the classification ability of the model.

[0045] (4) Model tuning: Based on the evaluation results, fine-tune the model, which may include feature selection, weight adjustment, etc.

[0046] (5) Deployment and application: Deploy the trained model to the system to implement automated risk assessment of new numbers. Dynamically update the risk level and generate a risk score for subsequent risk management decisions.

[0047] (6) Monitoring and maintenance: Monitor the performance of the model in the production environment to promptly identify and resolve potential problems. Regularly collect new data and update the model to maintain its accuracy and timeliness.

[0048] In a preferred embodiment, the multi-source data includes the number's historical abnormal work order data, normal complaint work order data, user behavior data, and device usage data. In this embodiment, by using multi-source data to evaluate the risk level of the number, the accuracy of the evaluation result is improved.

[0049] In a preferred embodiment, the multi-source data is input into a big data platform, and the multi-source data is integrated according to the dimensions to obtain training data; the risk assessment model is trained using the training data to obtain the pre-trained risk assessment model. In this embodiment, by connecting with the big data platform, these data can be updated in real time and used as the basis for model evaluation, thereby improving the real-time performance of number shutdown. In particular, on the data analysis platform, the system can identify and mark positive and negative samples based on preset rules, providing more accurate training data for subsequent risk models.

[0050] S200: executing a policy corresponding to the risk level on the number according to the risk level of the number, wherein the policy includes initiating a shutdown request for the number to the operator's number management system and sending a liveness authentication request to the number.

[0051] Specifically, the risk levels are divided into high risk, medium risk, low risk and no risk. According to the risk assessment results, this step dynamically selects the appropriate shutdown strategy, which includes: (1) Forced shutdown: High-risk numbers are directly forced to shut down, and online live authentication is not allowed to restart the machine, and only offline business halls are supported to restart the machine; (2) Shut down first and then authenticate: Medium-risk numbers are shut down first, and users can restart the machine after passing online live authentication; (3) Authentication first and then shutdown: For low-risk numbers, users are required to pass online live authentication before deciding whether to shut down; (4) SMS reminder: Only SMS reminder, no other operations; (5) Limit the number of restarts: For numbers that have been shut down multiple times, limit their online restart times to reduce the repeated use of malicious numbers.

[0052] The risk level of the number can be obtained by numerical classification, that is, an appropriate shutdown strategy can be selected according to the numerical value, including: when the risk score is greater than 0.9 or the number of restarts is greater than or equal to 3, a forced shutdown strategy is selected; when the risk score is greater than 0.7 but not more than 0.9, a shutdown-first-then-authentication strategy is selected; when the risk score is greater than 0.5 but not more than 0.7, an authentication-first-then-shutdown strategy is selected; when the risk score is less than or equal to 0.5, an SMS reminder strategy is selected.

[0053] The request for the number to the operator's number management system includes initiating a request to the operator's operator billing system or CRM system. This method integrates a module that interfaces with the number management system, and can interface with the number management system in real time, thereby improving the real-time nature of number operations.

[0054] S300: If the liveness authentication strategy is executed on the number, the liveness authentication result of the number is obtained, and the number with the failed result is used as a positive sample, and the number with the passed result is used as a negative sample.

[0055] Specifically, the liveness authentication strategy is to send a liveness authentication request to the number, and use an https-based interface to interact with a third-party system when sending. The liveness authentication is liveness detection, which is a method of determining the real physiological characteristics of an object in some identity authentication scenarios, and is usually used when performing real-name authentication.

[0056] S400: constructing a corresponding decision tree sub-model according to the positive sample and the negative sample, and updating the risk assessment model based on the decision tree sub-model to obtain a target model.

[0057] Specifically, the model is retrained using positive and negative sample data, and the structure or parameters of the model are adjusted to obtain a target model with more accurate evaluation results.

[0058] S500: Using the target model to evaluate the risk level of the number to obtain a target risk level.

[0059] S600: If the number is subject to the policy of initiating a shutdown request to the operator's number management system and the result of the liveness authentication is passed, a request for reactivation of the number is initiated to the operator's number management system.

[0060] S700: Obtain the number of shutdowns and restarts of the number, and determine whether the number is an abnormal number in combination with the target risk level. If so, initiate a shutdown request for the abnormal number to the operator's number management system.

[0061] Specifically, if the number has multiple shutdown records or restart times, and the target risk level is high risk, the number is determined to be an abnormal number, and the strategy of shutting down the number is directly executed. Usually, when the shutdown record or the number of restart times is greater than 3 and the target risk level is high risk, it is determined to be an abnormal number.

[0062] In this embodiment, by collecting multi-source data, a comprehensive data foundation is provided for risk assessment. The random forest algorithm is selected as the core algorithm to construct the risk assessment model, so that the model has the advantages of strong adaptability and easy to explain. According to the risk assessment results, a suitable shutdown strategy is dynamically selected, so that the method has a high degree of flexibility and can take different actions according to the risk score and historical behavior of the number. By marking positive and negative samples and updating the model through positive and negative samples, more accurate training data is provided for the risk assessment model, thereby obtaining more accurate assessment results, effectively reducing erroneous shutdowns, and improving user experience. By counting the historical shutdown records or the number of restarts, the two are combined with the risk level to evaluate whether the number is an abnormal number, and the abnormal number can be shut down in real time, effectively preventing the number from being maliciously reused, while improving the accuracy of judging normal numbers and reducing the misjudgment rate of numbers.

[0063] In some embodiments, executing a policy corresponding to the risk level on the number according to the risk level of the number, if the number is subject to the liveness authentication policy, obtaining the liveness authentication result of the number, taking the number with the failed result as a positive sample, and taking the number with the passed result as a negative sample, includes:

[0064] When the risk level of the number is medium risk, a shutdown request for the number is sent to the operator's number management system, and then a liveness authentication request is sent to the number. If the liveness authentication result is passed, a restoration request for the number is sent to the operator's number management system, and the number is added to the negative sample. Otherwise, the number is added to the positive sample.

[0065] When the risk level of the number is low risk, a liveness authentication request is sent to the number. If the liveness authentication result is passed, the number is added to the negative sample. Otherwise, a shutdown request for the number is initiated to the operator's number management system, and the number is added to the positive sample.

[0066] In this embodiment, by executing different response strategies for numbers of different risk levels, this method is different from static rule-based shutdown. Instead, the shutdown strategy can be dynamically adjusted according to real-time data, effectively reducing erroneous shutdowns and improving user experience.

[0067] In some embodiments, it also includes:

[0068] The number of shutdown times of the number is obtained. If the number of shutdown times of the number is greater than a preset threshold, when the risk level of the number is medium risk, no request for reactivation of the number is initiated to the operator's number management system.

[0069] In specific implementation, if the number is shut down more than a preset threshold and the risk level of the number is determined to be medium risk, the restoration process will not be executed even if the liveness authentication process is passed, that is, no restoration request for the number will be initiated to the operator's number management system.

[0070] In this embodiment, it is possible to prevent the number from being reused by simply performing online liveness authentication, thereby effectively preventing malicious reuse.

[0071] In some embodiments, the operator's number management system includes:

[0072] Operator billing system or CRM system.

[0073] In specific implementation, the CRM system (Customer relationship management system) is a customer relationship management system that helps telecommunications companies manage interactions with customers, services, billing information, and provide personalized services, thereby enhancing customer satisfaction and improving operational efficiency. This method uses an integrated communication module to connect to the operator's billing system or CRM system using HTTPS requests to perform operations such as shutting down or resuming a service.

[0074] In this embodiment, the real-time and reliability of the shutdown operation are ensured, and abnormal numbers can be shut down in a timely manner.

[0075] This application also provides a device for shutting down abnormal numbers based on risk assessment. Figure 2 As shown, the device comprises:

[0076] A data collection module 100 is used to collect multi-source data of numbers and evaluate the risk level of the numbers using a pre-trained risk assessment model, wherein the risk assessment model is constructed based on a random forest algorithm;

[0077] A policy execution module 200 is used to execute a policy corresponding to the risk level of the number according to the risk level of the number, wherein the policy includes initiating a shutdown request for the number to the operator's number management system and sending a liveness authentication request to the number; if the liveness authentication policy is executed on the number, the result of the liveness authentication of the number is obtained, and the number with the result of failure is used as a positive sample, and the number with the result of passing is used as a negative sample;

[0078] A model updating module 300 is used to construct a corresponding decision tree sub-model according to the positive sample and the negative sample, update the risk assessment model based on the decision tree sub-model to obtain a target model; and use the target model to assess the risk level of the number to obtain a target risk level;

[0079] The shutdown module 400 is used to initiate a request to the operator's number management system to restore the number if the number is subject to the policy of initiating a shutdown request to the operator's number management system and the result of its liveness authentication is passed; obtain the number of shutdown times and the number of restoration times of the number, and determine whether the number is an abnormal number in combination with the target risk level. If so, initiate a shutdown request for the abnormal number to the operator's number management system.

[0080] The functional implementation of each module in the above-mentioned abnormal number shutdown device based on risk assessment corresponds to the steps in the above-mentioned abnormal number shutdown method embodiment based on risk assessment, and its functions and implementation processes will not be repeated here one by one.

[0081] The present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the abnormal number shutdown method based on risk assessment as described in any of the above embodiments are implemented.

[0082] The present application also provides a computer-readable storage medium, on which a program is stored, wherein the computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The working process, working details and technical effects of the computer-readable storage medium provided in this embodiment can be found in the above embodiment of a method for shutting down abnormal numbers based on risk assessment, which will not be repeated here.

[0083] The application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the method for shutting down abnormal numbers based on risk assessment as described in any of the above embodiments.

[0084] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0085] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above-mentioned embodiments only express several implementation methods of the present application, and their descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several deformations and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of the patent of this application shall be based on the attached claims.

Claims

1. A method for shutting down abnormal numbers based on risk assessment, characterized in that: include: Collect multi-source data of the number and use a pre-trained risk assessment model to assess the risk level of the number, where the risk assessment model is built based on a random forest algorithm; Executing a strategy corresponding to the risk level of the number according to the risk level of the number, the strategy including initiating a shutdown request for the number to the operator's number management system and sending a liveness authentication request to the number; If the number is subject to the liveness authentication strategy, the liveness authentication result of the number is obtained, and the number with the failed result is used as a positive sample, and the number with the passed result is used as a negative sample; Constructing a corresponding decision tree sub-model according to the positive sample and the negative sample, and updating the risk assessment model based on the decision tree sub-model to obtain a target model; Using the target model to evaluate the risk level of the number, to obtain a target risk level; If the number is subject to the policy of initiating a shutdown request to the operator's number management system and the result of its liveness authentication is passed, a request to restore the number is initiated to the operator's number management system; Obtain the number of shutdowns and restarts of the number, and determine whether the number is an abnormal number in combination with the target risk level. If so, initiate a shutdown request for the abnormal number to the operator's number management system.

2. The method for shutting down abnormal numbers based on risk assessment according to claim 1 is characterized in that: The multi-source data includes the number's historical abnormal work order data, normal complaint work order data, user behavior data, and device usage data.

3. The method for shutting down abnormal numbers based on risk assessment according to claim 2 is characterized in that: Also includes: Inputting the multi-source data into a big data platform, integrating the multi-source data according to dimensions, and obtaining training data; The risk assessment model is trained using the training data to obtain the pre-trained risk assessment model.

4. The method for shutting down abnormal numbers based on risk assessment according to claim 1, characterized in that: The method includes: executing a strategy corresponding to the risk level of the number according to the risk level of the number, obtaining a result of the liveness authentication of the number if the liveness authentication strategy is executed on the number, taking the number with the failed result as a positive sample and the number with the passed result as a negative sample, including: When the risk level of the number is medium risk, a shutdown request for the number is sent to the operator's number management system, and then a liveness authentication request is sent to the number. If the liveness authentication result is passed, a restoration request for the number is sent to the operator's number management system, and the number is added to the negative sample. Otherwise, the number is added to the positive sample. When the risk level of the number is low risk, a liveness authentication request is sent to the number. If the liveness authentication result is passed, the number is added to the negative sample. Otherwise, a shutdown request for the number is initiated to the operator's number management system, and the number is added to the positive sample.

5. The method for shutting down abnormal numbers based on risk assessment according to claim 4 is characterized in that: Also includes: The number of shutdown times of the number is obtained. If the number of shutdown times of the number is greater than a preset threshold, when the risk level of the number is medium risk, no request for reactivation of the number is initiated to the operator's number management system.

6. The method for shutting down abnormal numbers based on risk assessment according to claim 1, characterized in that: The operator's number management system includes: Operator billing system or CRM system.

7. A device for shutting down abnormal numbers based on risk assessment, characterized in that: include: A data collection module, used to collect multi-source data of numbers and evaluate the risk level of the numbers using a pre-trained risk assessment model, wherein the risk assessment model is built based on a random forest algorithm; A policy execution module, configured to execute a policy corresponding to the risk level of the number according to the risk level of the number, wherein the policy includes initiating a shutdown request for the number to the operator's number management system and sending a liveness authentication request to the number; If the number is subject to the liveness authentication strategy, the liveness authentication result of the number is obtained, and the number with the failed result is used as a positive sample, and the number with the passed result is used as a negative sample; A model updating module, configured to construct a corresponding decision tree sub-model according to the positive sample and the negative sample, update the risk assessment model based on the decision tree sub-model to obtain a target model; and use the target model to assess the risk level of the number to obtain a target risk level; The shutdown module is used to initiate a shutdown request to the operator's number management system for the number if the number is subject to the policy of initiating a shutdown request to the operator's number management system and the result of its liveness authentication is passed; obtain the number of shutdown times and the number of restart times of the number, and determine whether the number is an abnormal number in combination with the target risk level. If so, initiate a shutdown request for the abnormal number to the operator's number management system.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for shutting down an abnormal number based on risk assessment according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, wherein when the program is executed by a processor, the method for shutting down an abnormal number based on risk assessment according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising computer instructions, characterized in that: When executed by a processor, the computer instructions implement the steps of the method for shutting down abnormal numbers based on risk assessment as described in claims 1 to 6.

Images