Private number platform authentication detection method and device

Abstract

The invention relates to the technical field of privacy communication. The invention provides a privacy number platform authentication detection method and device. The method comprises the following steps: performing warehousing management on customer information, enterprise information, reporting scenes, number data and account information related to a privacy number platform; various types of quality inspection are carried out on each privacy number of the privacy number platform, call ticket detection of clients is realized by analyzing call scenes, call records and call ticket calling and called parties of the clients, the various types of quality inspection comprise at least one type of multi-layer progressive quality inspection, and the multi-layer progressive quality inspection comprises secondary auditing and at least two call ticket detection after AI quality inspection; a privacy number or a client passing through a plurality of types of quality inspection is allowed to access the communication module for privacy number communication. According to the method, the multi-level authentication method is realized through multiple types of quality inspection, so that the problem of lack of authentication detection for practical application of the privacy number in the prior art is effectively solved, behaviors such as violation and fraud can be found in time, and complaints caused by high-frequency calling and the like can be avoided.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method and device for detecting authentication of a privacy number platform. Background Art

[0002] Privacy communication products are communication products that protect the privacy of both parties in communication. They solve the problems of privacy protection in interpersonal communication, data protection in interaction between people and platforms and applications, and enterprise business management. The privacy communication business is based on relevant regulations and implements relevant responsibilities. With the advantages of mastering the full stack of core technologies from network to data, it meets the rigid needs of users such as "privacy protection, enterprise data security, and service quality control". By providing intermediate numbers and establishing communications between the caller and the called party, it protects the real number information of both parties and facilitates enterprise communication management. However, in the development of the privacy number business, the following problems are often encountered:

[0003] The real-name channel of privacy numbers / customers' privacy numbers are mistakenly used in illegal and irregular scenarios, or are used beyond the scenarios reported by the enterprise; frequent calls from customers cause the called number customers to be disgusted, resulting in complaints about the visible privacy number X; corporate employees use the company-assigned mobile phone numbers / work privacy numbers for personal purposes, which does not meet the needs of corporate communication management.

[0004] Therefore, it is necessary to provide a privacy number platform authentication detection method and device to solve the above problems. Summary of the invention

[0005] The present invention intends to provide a privacy number platform authentication detection method and device to solve the medium technical problems in the prior art. The technical problems to be solved by the present invention are achieved through the following technical solutions.

[0006] The first aspect of the present invention proposes a privacy number platform authentication detection method, which includes: storing and managing customer information, enterprise information, reporting scenarios, number data, and account information related to the privacy number platform; performing multiple quality inspections on each privacy number of the privacy number platform, specifically including simultaneous access to AI quality inspection, complaint detection, call bill detection, customer authentication, and product authentication, and implementing customer call bill detection by analyzing the customer's various call scenarios, call records, and call bill callees. The multiple quality inspections include at least one multi-layer progressive quality inspection, and the multi-layer progressive quality inspection includes a secondary review after the AI ​​quality inspection, and at least two call bill inspections; allowing privacy numbers or customers that have passed multiple quality inspections to access the communication module for privacy number communication.

[0007] The second aspect of the present invention proposes a privacy number platform authentication detection device, which adopts the privacy number platform authentication detection method described in the first aspect of the present invention. The privacy number platform authentication detection device includes: a warehousing management module, which is used to store customer information, enterprise information, reporting scenarios, number data, and account information related to the privacy number platform; multiple quality inspection modules, which are used to perform multiple quality inspections on each privacy number of the privacy number platform, specifically including simultaneous access to AI quality inspection, complaint detection, call list detection, customer authentication, and product authentication, and realize customer call list detection by analyzing the customer's various call scenarios, call records, and call list callers and called parties. The multiple quality inspections include at least one multi-layer progressive quality inspection, and the multi-layer progressive quality inspection includes a secondary review after the AI ​​quality inspection, and at least two call list inspections; a communication processing module, which performs authentication and control on privacy number communications according to the above-mentioned multiple quality inspection modules and related strategies, allowing privacy numbers or customers that have passed multiple quality inspections to access the communication module for privacy number communications, and intercepting calls that have not passed the authentication to ensure the security of privacy communication services.

[0008] The third aspect of the present invention provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the privacy number platform authentication detection method described in the first aspect of the present invention.

[0009] The fourth aspect of the present invention provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the privacy number platform authentication detection method described in the first aspect of the present invention.

[0010] The embodiments of the present invention include the following advantages:

[0011] Compared with the prior art, the present invention manages the customer information, enterprise information, filing scenarios, number data, and account information related to the privacy number platform; conducts multiple quality inspections on each privacy number of the privacy number platform, specifically including simultaneous access to AI quality inspection, complaint detection, call list detection, customer authentication, and product authentication, and realizes customer call list detection by analyzing the customer's various call scenarios, call records, and call list callers and called parties. The multiple quality inspections include at least one multi-layer progressive quality inspection, and the multi-layer progressive quality inspection includes a secondary review after the AI ​​quality inspection, and at least two call list inspections; privacy numbers or customers that have passed multiple quality inspections are allowed to access the communication module for privacy number communication. A multi-level authentication method is implemented through multiple quality inspections to automatically detect privacy numbers, which effectively solves the problem of lack of authentication detection for practical application of privacy numbers in the prior art, can timely discover violations, fraud-related behaviors, and can avoid complaints caused by high-frequency calls. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a flowchart of an example of the privacy number platform authentication detection method of the present invention;

[0013] Figure 2 It is a schematic diagram of an application example of the privacy number platform authentication detection method of the present invention;

[0014] Figure 3 It is a structural block diagram of the privacy number platform authentication detection device of the present invention;

[0015] Figure 4 is a schematic structural diagram of an electronic device embodiment according to the present invention;

[0016] Figure 5 It is a schematic diagram of the structure of a computer-readable medium embodiment according to the present invention. DETAILED DESCRIPTION

[0017] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0018] In view of the above problems, the present invention provides an authentication detection method and device for a privacy number platform. The present invention stores and manages customer information, enterprise information, reporting scenarios, number data, and account information related to the privacy number platform; performs multiple quality checks on each privacy number on the privacy number platform, specifically by analyzing the customer's various call scenarios, call records, and call list callers and called parties, to implement customer call list detection, allowing privacy numbers or customers that have passed multiple quality checks to access the communication module for privacy number communication. Through multiple quality checks, a multi-level authentication method is implemented to automatically detect privacy numbers, effectively solving the problem of lack of authentication detection for practical applications of privacy numbers in the prior art, and timely discovering violations, fraud-related behaviors, and avoiding complaints caused by high-frequency calls.

[0019] Specifically, the blacklist number management module, the customer scenario model analysis module for discovering calls, the product authentication module, the customer authentication module, and the platform communication processing module are established through the relevant complaint departments, platform AI quality inspection, and manual quality inspection. The present invention can improve the accuracy of authentication detection of privacy number services, effectively identify illegal scenarios and block them in time, reduce the possibility of fraud in privacy number services, and realize multiple authentication capabilities to meet the inbound and outbound call management needs of operators and corporate customers.

[0020] It should be noted that the method of the present invention has a wide range of applications, and is particularly suitable for business scenarios mainly including food delivery, online car-hailing, express delivery, insurance, financial services and other fields. Fraud-related scenarios mainly include false orders or fraud-related orders, ticket refunds and changes, false loans, impersonating customer service and other types.

[0021] Example 1

[0022] Refer to the following Figure 1 , Figure 2 , the contents of the present invention will be described in detail.

[0023] Figure 1 It is a step flow chart of an example of the privacy number platform authentication detection method of the present invention.

[0024] like Figure 1 As shown, in step S101, customer information, enterprise information, reporting scenarios, number data, and interactive account information related to the privacy number platform are stored and managed.

[0025] Specifically, the privacy account platform can communicate with the analysis software, and the privacy account platform can communicate with the customer portal or query interface. For details, please refer to Figure 2 The privacy account platform includes a central platform and multiple sub-platforms that can communicate with the central platform.

[0026] Furthermore, the privacy number platform includes a channel management module or a customer management module. Specifically, the channel management module or the customer management module is used to store customer information, enterprise information, reporting scenarios, number data, interactive account information, etc. related to the privacy number platform, that is, to complete the warehousing management. Enterprise information includes, for example, food delivery, online car-hailing, express delivery, insurance, financial services and other enterprises. In addition, it also includes a software research provider, which is used to provide audio writing and text data converted from sensitive words to the privacy number platform. Optionally, it also includes a complaint monitoring module, which can communicate with relevant outsourced complaint departments and privacy number platform complaint departments to obtain customer complaint data.

[0027] In a specific implementation, insurance company a submits one or more privacy numbers to the privacy number platform after real-name registration, reports the application scenario, company information, number data, obtains interactive account information, and connects to the platform interface service.

[0028] Specifically, the privacy number platform provides privacy numbers for both parties (calling party and called party) who need to communicate, so as to protect the actual numbers of the calling party and the called party, and further protect the privacy information of the calling party and the called party.

[0029] Optionally, a number binding relationship (sometimes also referred to as a "binding relationship") is formed between the calling number, the privacy number (eg, a virtual number) and the called number for management and control.

[0030] Specifically based on the insurance order number, insurance company a establishes a number binding relationship between number A (such as account manager) - number X - number B (such as policy customer) through the platform interface so as to use the private number to initiate a call to the customer.

[0031] Similar application scenarios include: a food delivery platform establishes a number binding relationship between number A (e.g., a delivery man) - number X - number B (e.g., an ordering customer); an online car-hailing platform establishes a number binding relationship between number A (e.g., a driver) - number X - number B (e.g., a car-using customer); an express logistics platform establishes a number binding relationship between number A (e.g., a courier) - number X - number B (e.g., a consignee), etc. Through the above binding, both parties can use a private number to make calls.

[0032] It should be noted that the purpose of the present invention is to protect the privacy of the numbers of both parties in the call and to provide convenience for corporate customers to monitor service quality and avoid harassment complaints and illegal use. The above is only an optional example and cannot be understood as a limitation of the present invention.

[0033] Next, in step S102, multiple quality inspections are performed on each privacy number of the privacy number platform, including simultaneous access to AI quality inspection, complaint inspection, call record inspection, customer authentication, and product authentication. The customer's call record inspection is implemented by analyzing the customer's various call scenarios, call records, and call party and party on the call record. The multiple quality inspections include at least one multi-layer progressive quality inspection, and the multi-layer progressive quality inspection includes a secondary review after the AI ​​quality inspection and at least two call record inspections.

[0034] Specifically, multiple quality inspections are performed on each privacy number on the privacy number platform, including simultaneous access to AI quality inspection, complaint inspection, call record inspection, customer authentication, and product authentication.

[0035] Optionally, a complaint monitoring module, a customer authentication module, and a product authentication module are respectively provided corresponding to complaint quality inspection, customer authentication, and product authentication. In addition, a call list module corresponding to call list detection is also included. For details, please refer to Figure 2 .

[0036] Furthermore, the multiple quality checks include at least one multi-layer progressive quality check.

[0037] In this example, multi-layer progressive quality inspection includes a second review after AI quality inspection.

[0038] In a specific embodiment, Figure 2 As shown, the analysis software is used to conduct AI quality inspection on each historical recording of the privacy account platform, specifically converting the sound into text and filtering sensitive words. The sensitive words are divided into various types such as fraud and deception, such as football betting, explosives, pinhole photography, etc.

[0039] Specifically, while conducting AI quality inspection on each historical recording of the privacy account platform, real-time monitoring and manual monitoring are also carried out.

[0040] A blacklist database is established using complaint data collected by relevant departments, and a complaint monitoring module is used to conduct complaint detection.

[0041] Specifically, the complaint work orders of multiple complaint departments or platforms are monitored in real time. When the quality inspection finds that the current privacy number of the privacy number platform is involved in a complaint work order, the current privacy number is stored in the blacklist library. When the complaint monitoring module finds that there is no complaint about the current privacy number of the privacy number platform, it is determined that the current privacy number has passed the complaint detection.

[0042] The at least two call record checks of the multi-layer progressive quality inspection include: before accessing the communication module for privacy number communication, performing a call record check on historical call record data, and after accessing the communication module for privacy number communication, performing another call record check on the generated call record.

[0043] Preferably, call record detection of historical call record data is performed according to preset rules to determine scene access and customer access.

[0044] Specifically, the preset rules include: the cumulative number of calls of the same number binding relationship (for example, represented by AXB) shall not exceed the specified number of the corresponding call scenario, wherein the number binding relationship includes the number binding relationship between the privacy number, the first party using the privacy number, and the second party using the privacy number. The first party is, for example, the calling party, and the second party is, for example, the called party.

[0045] Furthermore, the preset rule also includes: within a natural day, the cumulative number of calls for the same main number and called number combination shall not exceed a specific number.

[0046] For the privacy number service, in the AXB binding relationship, X represents the privacy number or private number, A and B are two service beneficiaries who keep each other confidential, namely the first party and the second party, and neither user A nor user B knows the other's real number. The called number used in mutual communication is X. Therefore, according to the above business scenario, the call records of historical call record data are checked according to preset rules.

[0047] In a specific implementation, when the cumulative number of calls for the same A number-X number-B number binding relationship exceeds the specified number (e.g., N number) of the corresponding call scenario, the call record containing the A number-X number-B number binding relationship is determined to be a risky call record. The specified number N is divided by the scenario access level. The scenario access level includes a level division according to the business scenarios corresponding to food delivery, online car-hailing, express delivery, insurance, and financial services.

[0048] In another specific implementation, when the cumulative number of calls of the same combination of calling number A and called number B (regardless of number X) in a natural day exceeds a specific number (e.g., M times), the call record containing the same combination of calling number A and called number B is determined to be a risky call record, and the specific number M is divided by the customer access level. The customer access level is determined by using a user risk model.

[0049] Specifically, the user risk model is based on the existing machine learning model and uses the user data collected by the privacy number platform. Specifically, the user's mobile phone number, user ID, and number binding relationship marked as fraudulent are used to establish a training data set for incremental training of the existing risk model to obtain the user risk model. The mobile phone number or user ID to be identified is input into the user risk model to obtain the customer access level.

[0050] It should be noted that the above is only described as an optional example and should not be understood as a limitation to the present invention.

[0051] In another specific implementation, when the current enterprise uses the current privacy number on the privacy number platform, a call record check (ie, the first call record check) is performed on the historical call record data related to the current enterprise and the current privacy number.

[0052] For the first call record detection, the generated call record is detected using the customer scenario model to determine whether the current call record is a disturbing call record (such as a harassing call). Specifically, the current call record is input into the customer scenario model, and the scenario corresponding to the current privacy number is output. When the output scenario exceeds the reported scenario, it is determined to be a disturbing call record. When the output scenario does not exceed the reported scenario, it is determined to be a normal call record.

[0053] Optionally, the interference probability corresponding to the current privacy number can also be output. When the output interference probability is greater than the specified probability, it is determined to be an interference call record. When the output interference probability is less than or equal to the specified probability, it is determined to be a normal call record.

[0054] In a specific implementation, for food delivery or logistics business scenarios, customers limit the daily binding frequency of X number or outbound call frequency to less than or equal to 300 times, the allowed calling period is from 6 am to 8 pm, and the maximum single call duration is less than 5 minutes. For online car-hailing scenarios, customers limit the daily binding frequency of X number to less than or equal to 200 times, the allowed calling period is 24 hours, and the maximum single call duration is less than 10 minutes. For insurance or financial scenarios, customers limit the daily binding frequency of X number to less than or equal to 100 times, the allowed calling period is from 8 am to 8 pm, and the maximum single call duration is less than 60 minutes.

[0055] Next, after accessing the communication module to conduct private number communication, the generated call record is checked again, that is, two call record checks are completed.

[0056] For the customer authentication module, its function is mainly to provide authentication services to the customer as needed. The customer can set the incoming blacklist and whitelist of voice or SMS and the outgoing blacklist and whitelist according to the account according to its own requirements to form a customer authentication strategy. The customer is the counterparty of the enterprise. For example, insurance company A uses a private number to communicate with multiple customers for insurance business. When communicating for insurance business, the call list information fed back by the private number platform is used to determine whether the relevant private number is involved in fraud, so as to achieve customer authentication.

[0057] According to the product-level authentication policy combination corresponding to the product service package selected when the privacy account is listed on the privacy account platform, the following authentications are performed during private communication: voice incoming authentication policy, voice outgoing authentication policy, SMS incoming authentication policy, SMS outgoing authentication policy, content authentication policy, and code number authentication policy, specifically including authentication policies such as landline incoming call restriction, blacklist number restriction, whitelist number restriction, etc.

[0058] For example, when insurance company A applies to list a privacy number, the privacy number platform sets the authentication strategy for the product package according to the application reporting scenario: in the voice call authentication strategy, all fixed-line number segments are set to blacklist, and the effect is that fixed-line number calls are blocked; in the SMS content authentication strategy, "zgpin*an" is set as the SMS signature whitelist. If only the signature containing "zgpin*an" can pass the authentication, SMS can be sent and received. If the signature does not contain "zgpin*an", authentication cannot be passed, that is, SMS cannot be sent or received;

[0059] It should be noted that in the present invention, the communication processing module of the privacy number platform actually processes the call according to the above-mentioned blacklist and whitelist authentication module, the analysis module of the customer scenario model, the customer authentication module, and the product authentication module, so as to intercept the calls that fail to pass the authentication. In addition, the module functions may also include frequency control, content filtering and other functions;

[0060] Optionally, the customer may actively participate in setting the blacklist and whitelist authentication policy of the customer authentication module through the customer portal or query interface, or the call control module.

[0061] In another embodiment, the privacy number platform can be connected to the analysis software, issue an alarm based on the AI ​​quality inspection results of the analysis software, and submit it for secondary review to determine whether there are any violations. The violations specifically include pornography, violence, fraud, etc. When it is determined that there are violations in the secondary review, the determined illegal numbers will be stored in the blacklist library, the customer to whom the number belongs will be downgraded, and notified to make rectifications.

[0062] While conducting AI quality inspection, the privacy account platform supports real-time monitoring and manual monitoring. When violations are confirmed, they are submitted for secondary review to determine whether the confirmed illegal numbers should be stored in the blacklist.

[0063] It should be noted that the above is only described as an optional example and should not be understood as a limitation to the present invention.

[0064] Next, in step S103, the private number or customer that has passed various quality checks is allowed to access the communication module for private number communication.

[0065] Specifically, when it is determined that the multi-layer progressive quality inspection has been passed, including complaint detection, the customer and privacy number that have passed the AI ​​quality inspection access the communication processing module to conduct privacy number communication to generate a call record.

[0066] Next, the generated call slip is sent to the call slip module, and the call slip detection is performed again to determine whether the current call slip contains disturbing behavior (specifically, call harassment behavior). When it is determined that the call slip frequency of the privacy number or customer is greater than the predetermined frequency, and there is disturbing behavior (specifically, call harassment behavior), the privacy number corresponding to the current call slip is stopped from communicating. When it is determined that the call slip frequency of the privacy number or customer is less than or equal to the predetermined frequency, and there is no disturbing behavior (specifically, call harassment behavior), the privacy number is allowed to continue subsequent calls and call slip detection.

[0067] It should be noted that the above is only described as an optional example and should not be understood as a limitation to the present invention.

[0068] In addition, the drawings are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the drawings do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0069] Compared with the prior art, the present invention manages the customer information, enterprise information, filing scenarios, number data, and account information related to the privacy number platform; conducts multiple quality inspections on each privacy number of the privacy number platform, specifically including simultaneous access to AI quality inspection, complaint detection, call list detection, customer authentication, and product authentication, and realizes customer call list detection by analyzing the customer's various call scenarios, call records, and call list callers and called parties. The multiple quality inspections include at least one multi-layer progressive quality inspection, and the multi-layer progressive quality inspection includes a secondary review after the AI ​​quality inspection, and at least two call list inspections; privacy numbers or customers that have passed multiple quality inspections are allowed to access the communication module for privacy number communication. A multi-level authentication method is implemented through multiple quality inspections to automatically detect privacy numbers, which effectively solves the problem of lack of authentication detection for practical application of privacy numbers in the prior art, can timely discover violations, fraud-related behaviors, and can avoid complaints caused by high-frequency calls.

[0070] Example 2

[0071] The following are embodiments of the device of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments of the present invention, please refer to the method embodiments of the present invention.

[0072] Figure 3 It is a structural diagram of an example of a privacy number platform authentication detection device according to the present invention.

[0073] The second aspect of the present disclosure provides a privacy number platform authentication detection device 300, which adopts the privacy number platform authentication detection method described in the first aspect of the present invention.

[0074] Reference Figure 3 The privacy number platform authentication detection device 300 includes an inventory management module 310, multiple quality inspection modules 320, and a communication processing module 330.

[0075] In a specific implementation, the warehousing management module 310 is used to manage the customer information, enterprise information, reporting scenarios, number data, and account information related to the privacy number platform. The multiple quality inspection modules 320 are used to perform multiple quality inspections on each privacy number of the privacy number platform, specifically including simultaneous access to AI quality inspection, complaint detection, call list detection, customer authentication, and product authentication. By analyzing the customer's various call scenarios, call records, and call list callers and called parties, the customer's call list detection is implemented. The multiple quality inspections include at least one multi-layer progressive quality inspection, and the multi-layer progressive quality inspection includes a secondary review after the AI ​​quality inspection, and at least two call list inspections. The communication processing module 330 performs authentication and control on privacy number communications according to the above-mentioned multiple quality inspection modules and related strategies, allowing privacy numbers or customers that have passed multiple quality inspections to access the communication module for privacy number communications, and intercepting calls that have not passed the authentication to ensure the security of privacy communication services.

[0076] According to an optional implementation, when it is determined that the multi-layer progressive quality inspection has been passed and the complaint inspection has been passed, it is determined that multiple quality inspections have been passed; the at least two call record inspections of the multi-layer progressive quality inspection include: before accessing the communication module for privacy number communication, performing a call record inspection on historical call record data, and after accessing the communication module for privacy number communication, performing another call record inspection on the generated call record.

[0077] According to an optional implementation mode, the customer's call record detection is implemented by analyzing the customer's call scenarios, call records, and call list caller and caller, which specifically includes:

[0078] Call record detection of historical call record data is performed according to preset rules to determine scenario access and customer access. The preset rules include: the cumulative number of calls for the same number binding relationship shall not exceed the specified number of times for the corresponding call scenario, and the number binding relationship includes the number binding relationship between a privacy number, a first party using the privacy number, and a second party using the privacy number; within a natural day, the cumulative number of calls for the same main number and called number combination shall not exceed a specific number of times.

[0079] According to an optional implementation method, the generated call record is detected using a customer scenario model to determine whether the current call record is a fraudulent call record. Specifically, the current call record is input into the customer scenario model to output the fraud probability corresponding to the current call record.

[0080] According to an optional implementation method, models are divided according to the reporting scenario, industry and customer access level, and various types of risks are identified according to different models. The daily binding frequency of privacy numbers, outbound call frequency, call time period control and maximum call duration are restricted according to different models.

[0081] For the first call record detection, the generated call record is detected using the customer scenario model to determine whether the current call record is a disturbing call record. Specifically, the current call record is input into the customer scenario model, and the scenario corresponding to the current privacy number is output. When the output scenario exceeds the reported scenario, it is determined to be a disturbing call record. When the output scenario does not exceed the reported scenario, it is determined to be a normal call record.

[0082] According to the optional implementation method, for food delivery or logistics business scenarios, the daily binding frequency of the privacy number or the outbound call frequency is limited to less than or equal to 300 times, the allowed calling period is from 6 am to 8 pm, and the maximum single call duration is less than 5 minutes. For online car-hailing scenarios, the daily binding frequency of the privacy number is limited to less than or equal to 200 times, the allowed calling period is 24 hours, and the maximum single call duration is less than 10 minutes; for insurance or financial scenarios, the binding frequency of the privacy number is limited to less than or equal to 100 times, the allowed calling period is from 8 am to 8 pm, and the maximum single call duration is less than 60 minutes.

[0083] According to an optional implementation method, access analysis software, issue an alarm based on the AI ​​quality inspection result of the analysis software, and submit it for secondary review to determine whether it is a violation number. When it is determined to be a violation number, the determined violation number is stored in a blacklist library; while performing AI quality inspection, real-time recording and monitoring are performed. When it is determined to be a violation scenario, it is submitted to secondary review to determine whether it is a violation number. When it is determined to be a violation number, the determined violation number is stored in a blacklist library.

[0084] According to an optional implementation, the customer may actively participate in the blacklist and whitelist authentication through a customer portal or query interface, or through a call control module.

[0085] According to an optional implementation method, based on the product-level authentication policy combination, the following multiple authentications are performed on the current privacy number during private communication: voice incoming authentication policy, voice outgoing authentication policy, SMS incoming authentication policy, SMS outgoing authentication policy, content authentication policy, and code number authentication policy.

[0086] Compared with the prior art, the present invention manages the customer information, enterprise information, filing scenarios, number data, and account information related to the privacy number platform; conducts multiple quality inspections on each privacy number of the privacy number platform, specifically including simultaneous access to AI quality inspection, complaint detection, call list detection, customer authentication, and product authentication, and realizes customer call list detection by analyzing the customer's various call scenarios, call records, and call list callers and called parties. The multiple quality inspections include at least one multi-layer progressive quality inspection, and the multi-layer progressive quality inspection includes a secondary review after the AI ​​quality inspection, and at least two call list inspections; privacy numbers or customers that have passed multiple quality inspections are allowed to access the communication module for privacy number communication. A multi-level authentication method is implemented through multiple quality inspections to automatically detect privacy numbers, which effectively solves the problem of lack of authentication detection for practical application of privacy numbers in the prior art, can timely discover violations, fraud-related behaviors, and can avoid complaints caused by high-frequency calls.

[0087] Figure 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

[0088] like Figure 4 As shown, the electronic device is presented in the form of a general computing device. The processor may be one or more and work in coordination. The present invention does not exclude distributed processing, that is, the processor may be dispersed in different physical devices. The electronic device of the present invention is not limited to a single entity, but may also be the sum of multiple physical devices.

[0089] The memory stores a computer executable program, which is usually a machine-readable code. The computer-readable program can be executed by the processor to enable the electronic device to perform the method of the present invention, or at least part of the steps in the method.

[0090] The memory includes a volatile memory, such as a random access memory unit (RAM) and / or a cache memory unit, and may also be a non-volatile memory, such as a read-only memory unit (ROM).

[0091] Optionally, in this embodiment, the electronic device further includes an I / O interface, which is used for the electronic device to exchange data with an external device. The I / O interface can represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of a variety of bus structures.

[0092] It should be understood that Figure 4 The electronic device shown is only an example of the present invention, and the electronic device of the present invention may also include elements or components not shown in the above examples. For example, some electronic devices also include display units such as display screens, and some electronic devices also include human-computer interaction elements such as buttons, keyboards, etc. As long as the electronic device can execute the computer-readable program in the memory to implement the method of the present invention or at least part of the steps of the method, it can be considered as an electronic device covered by the present invention.

[0093] Through the above description of the implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by combining software with necessary hardware. Figure 5 As shown, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of commands to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiment of the present invention.

[0094] The software product may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0095] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with a command execution system, device, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0096] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0097] The computer-readable medium carries one or more programs (eg, computer-executable programs). When the one or more programs are executed by a device, the computer-readable medium implements the method of the present disclosure.

[0098] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0099] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several commands to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiment of the present invention.

[0100] The exemplary embodiments of the present invention are specifically shown and described above. It should be understood that the present invention is not limited to the detailed structure, configuration or implementation method described herein; on the contrary, the present invention is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended claims.

Claims

1. A privacy number platform authentication detection method, characterized in that: The privacy number platform authentication detection method includes: The customer information, enterprise information, reporting scenarios, number data, and account information related to the privacy account platform are stored and managed; Conduct multiple quality checks on each privacy account and its customers on the privacy account platform, including simultaneous access to AI quality checks, complaint checks, call record checks, customer authentication, and product authentication. By analyzing each customer's call scenario, call records, and call list callers and called parties, the customer's call record checks are implemented. The multiple quality checks include at least one multi-layer progressive quality check, which includes a secondary review after the AI ​​quality check and at least two call record checks. Private numbers or customers that have passed various quality checks are allowed to access the communication module for private number communication.

2. The privacy number platform authentication detection method according to claim 1, characterized in that: Further including: When it is determined that the multi-layer progressive quality inspection has been passed and the complaint inspection has been passed, it is determined that the multiple quality inspections have been passed; The at least two call record checks of the multi-layer progressive quality inspection include: before accessing the communication module for privacy number communication, performing a call record check on historical call record data, and after accessing the communication module for privacy number communication, performing another call record check on the generated call record.

3. The privacy number platform authentication detection method according to claim 1, characterized in that: The customer's call record detection is realized by analyzing the customer's call scenarios, call records and call list caller and caller, specifically including: Perform call record detection on historical call record data according to preset rules to determine scene access and customer access, wherein the preset rules include: The cumulative number of calls for the same number binding relationship shall not exceed the specified number of the corresponding call scenario, and the number binding relationship includes the number binding relationship between the privacy number, the first party using the privacy number, and the second party using the privacy number; The cumulative number of calls for the same primary number and called number combination within a natural day shall not exceed a specific number.

4. The privacy number platform authentication detection method according to claim 1, characterized in that: include: The generated call record is detected using the customer scenario model to determine whether the current call record is a fraudulent call record. Specifically, the current call record is input into the customer scenario model to output the fraudulent probability corresponding to the current call record.

5. The privacy number platform authentication detection method according to claim 4 is characterized in that: include: Models are divided according to the reporting scenarios, industries and customer access levels, and various risks are identified based on different models. The frequency of daily binding of privacy numbers, outbound call frequency, call time control and maximum call duration are also limited based on different models. For the first call record detection, the generated call record is detected using the customer scenario model to determine whether the current call record is a disturbing call record. Specifically, the current call record is input into the customer scenario model, and the scenario corresponding to the current privacy number is output. When the output scenario exceeds the reported scenario, it is determined to be a disturbing call record. When the output scenario does not exceed the reported scenario, it is determined to be a normal call record.

6. The privacy number platform authentication detection method according to claim 4, characterized in that: include: For food delivery or logistics business scenarios, the daily binding frequency of private numbers or outbound call frequency is limited to less than or equal to 300 times, the allowed calling period is from 6 am to 8 pm, and the maximum single call duration is less than 5 minutes; For online ride-hailing scenarios, the daily binding frequency of private numbers is limited to less than or equal to 200 times, the call period is allowed to be 24 hours, and the maximum single call duration is less than 10 minutes; For insurance or financial scenarios, the frequency of binding a privacy number is limited to less than or equal to 100 times, the allowed calling period is from 8 am to 8 pm, and the maximum duration of a single call is less than 60 minutes.

7. The privacy number platform authentication detection method according to claim 1, characterized in that: include: Access the analysis software, issue an alarm based on the AI ​​quality inspection results of the analysis software, and submit it for secondary review to determine whether it is a violation number. When it is determined to be a violation number, the determined violation number is stored in the blacklist library; While conducting AI quality inspection, real-time recording and monitoring are carried out. When it is determined that it is a violation scenario, it is submitted for secondary review to determine whether it is an illegal number. When it is determined to be an illegal number, the confirmed illegal number will be stored in the blacklist library.

8. The privacy number platform authentication detection method according to claim 1, characterized in that: include: Customers can actively participate in blacklist and whitelist authentication through the customer portal or query interface, or through the call control module.

9. The privacy number platform authentication detection method according to claim 1, characterized in that: include: According to the product-level authentication policy combination, the following multiple authentications are performed on the current privacy number during private communication: voice incoming authentication policy, voice outgoing authentication policy, SMS incoming authentication policy, SMS outgoing authentication policy, content authentication policy, and code number authentication policy.

10. A privacy number platform authentication detection device, characterized in that: It implements the privacy number platform authentication detection method described in any one of claims 1 to 9, and the privacy number platform authentication detection device includes: The storage management module is used to store and manage customer information, enterprise information, reporting scenarios, number data, and account information related to the privacy account platform; Multiple quality inspection modules are used to perform multiple quality inspections on each privacy number on the privacy number platform, specifically including simultaneous access to AI quality inspection, complaint inspection, call bill inspection, customer authentication, and product authentication. By analyzing the customer's call scenarios, call records, and call bill callers and called parties, the customer's call bill inspection is realized. The multiple quality inspections include at least one multi-layer progressive quality inspection, which includes a secondary review after the AI ​​quality inspection and at least two call bill inspections. The communication processing module authenticates and controls privacy number communications based on the above-mentioned multiple quality inspection modules and related strategies, allowing privacy numbers or customers that have passed multiple quality inspections to access the communication module for privacy number communications, and intercepting calls that have not passed the authentication to ensure the security of privacy communication services.

Images