Interruption awareness knowledge identification method and apparatus, electronic device, storage medium, and product

Abstract

The disclosure provides an interruption awareness identification method, device, electronic equipment, storage medium and product. The method comprises: obtaining a target user set, the target user set comprising at least one target user; obtaining a first flow rate of each target user in the target user set at an interruption time and a first port recovery number of each target user in the target user set at the interruption time; and determining that the target user is an interruption awareness user if the first flow rate of the target user at the interruption time is not less than a first preset flow rate or the first port recovery number of the target user at the interruption time is not less than a first preset port number.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of interrupt awareness recognition, and in particular, to an interrupt awareness recognition method and device, an electronic device, a storage medium, and a product. BACKGROUND

[0002] In related interrupt awareness recognition schemes, whether a target user perceives an interrupt is determined only by the frequency of the interrupt, which results in low accuracy of interrupt awareness recognition of the target user. SUMMARY

[0003] The present disclosure provides an interrupt awareness recognition method, device, electronic device, storage medium, and product to solve the problems in related technologies.

[0004] A first aspect embodiment of the present disclosure provides an interrupt awareness recognition method, which comprises:

[0005] obtaining a target user set, the target user set comprising at least one target user;

[0006] obtaining a first flow rate of each target user in the target user set at an interrupt time and a first port recovery number of each target user in the target user set at the interrupt time;

[0007] if the first flow rate of the target user at the interrupt time is not less than a first preset flow rate or the first port recovery number of the target user at the interrupt time is not less than a first preset port number, determining that the target user is an interrupt-aware user.

[0008] In an embodiment, obtaining a target user set comprises:

[0009] obtaining message records of each user at a Radius server, wherein one user corresponds to at least one message record, and each message record contains a message type, a message timestamp, and a username corresponding to the message;

[0010] filtering, from the message records of the Radius server, Radius message records of the first message type to obtain all Radius message records of the first message type;

[0011] determining a first user set based on the usernames corresponding to the messages in all Radius message records of the first message type;

[0012] filtering, from the first user set, message records with a message timestamp within a first preset time interval to obtain a second user set, the first preset time interval being used to indicate a non-network change operation time interval;

[0013] Based on the second user set, a target user set is determined, and a username corresponding to a message in the target user set corresponds to at least one message timestamp.

[0014] In an embodiment, the first flow rate of each target user in the target user set at the interruption time is obtained, including:

[0015] According to the username and the message timestamp corresponding to the message in the second user set, the last message record corresponding to the username and the message timestamp corresponding to the message is found from the message record of the Radius server;

[0016] The first online time and the first flow of the target user in the message record in the second user set are obtained, and the second online time and the second flow of the target user in the last message record are obtained;

[0017] Based on the first online time and the second online time, the online time difference of the target user is determined, and based on the first flow and the second flow, the flow difference of the target user is determined;

[0018] The flow difference is divided by the online time difference to obtain the first flow rate of the target user at the interruption time.

[0019] In an embodiment, before the first online time and the first flow of the target user in the message record in the second user set are obtained, and the second online time and the second flow of the target user in the last message record are obtained, the method provided by the present disclosure further includes:

[0020] The message record in the second user set and the last message record are merged to obtain a third user set;

[0021] The message records in the third user set are grouped according to the username corresponding to the message to obtain the message records of each target user at different message timestamps;

[0022] The message records of each target user at different message timestamps are sorted according to the order of the message timestamps from small to large to obtain the message records of each target user sorted in the order of the message timestamps from small to large.

[0023] In an embodiment, the first port recycling number of each target user in the target user set at the interruption time is obtained, including:

[0024] According to the username corresponding to the message in the target user set, the message record of the Radius server corresponding to the username is screened out from the message record of the Radius server;

[0025] The NAT public network port segment change value of each type of Radius server message record corresponding to the username is determined.

[0026] adding the NAT public network port segment change value of each type of Radius server message record corresponding to the username to obtain a NAT public network address port number corresponding to the username, the NAT public network address port number corresponding to the username at least including a NAT public network address port number corresponding to the username at the interruption time and a NAT public network address port number corresponding to the username at the time before interruption;

[0027] subtracting the NAT public network address port number corresponding to the username at the time before interruption from the NAT public network address port number corresponding to the username at the interruption time to obtain a first port recycling number of the target user at the interruption time.

[0028] In an embodiment, the NAT public network port segment change value of each type of Radius server message record corresponding to the username is determined, including:

[0029] determining the message records containing the second message type from the Radius server message records corresponding to the username to obtain a fourth user set;

[0030] grouping the fourth user set according to a first preset rule to obtain at least two fifth user sets, the fifth user set including a message type and a reason type of charging end of each message record;

[0031] determining a message identifier and a reason type identifier of charging end of each message record in the fifth user set based on the message type and the reason type of charging end of each message record in the fifth user set;

[0032] determining the NAT public network port segment change value of each type of Radius server message record corresponding to the username in the fifth user set based on the message identifier, the reason type identifier of charging end and a second preset rule of each message record in the fifth user set.

[0033] A second aspect embodiment of the present disclosure provides a device for identifying interruption awareness, the device comprising:

[0034] a first obtaining unit configured to obtain a target user set, the target user set including at least one target user;

[0035] a second obtaining unit configured to obtain a first flow rate of each target user in the target user set at an interruption time and a first port recycling number of each target user in the target user set at the interruption time;

[0036] The determining unit is configured to determine that the target user is an interruption-aware user if the first flow rate of the target user at the interruption moment is not less than a first preset flow rate or the first port recovery number of the target user at the interruption moment is not less than a first preset port number.

[0037] A third aspect of the present disclosure provides an electronic device, comprising:

[0038] The at least one processor and the memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect of the present disclosure.

[0039] A fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to perform the method described in the first aspect of the present disclosure.

[0040] A fifth aspect of the present disclosure provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the method described in the first aspect of the present disclosure.

[0041] In summary, the present disclosure provides an interruption-aware identification method, comprising: obtaining a target user set, wherein the target user set comprises at least one target user; obtaining a first flow rate of each target user in the target user set at an interruption moment and a first port recovery number of each target user in the target user set at the interruption moment; and determining that the target user is an interruption-aware user if the first flow rate of the target user at the interruption moment is not less than a first preset flow rate or the first port recovery number of the target user at the interruption moment is not less than a first preset port number.

[0042] According to the scheme provided by the present disclosure, by obtaining a target user set, wherein the target user set comprises at least one target user; obtaining a first flow rate of each target user in the target user set at an interruption moment and a first port recovery number of each target user in the target user set at the interruption moment; and determining that the target user is an interruption-aware user if the first flow rate of the target user at the interruption moment is not less than a first preset flow rate or the first port recovery number of the target user at the interruption moment is not less than a first preset port number, the target user can be determined to be aware of the interruption by combining the first flow rate of the target user at the interruption moment and the first port recovery number of the target user at the interruption moment, thereby improving the identification accuracy of the target user aware of the interruption.

[0043] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0045] Figure 1 A flowchart illustrating the interruption sensing and identification method provided in this embodiment of the disclosure;

[0046] Figure 2 A flowchart illustrating a method for obtaining a target user set provided in an embodiment of this disclosure;

[0047] Figure 3 A flowchart illustrating the method for obtaining the first flow rate of a target user at the moment of interruption, provided in an embodiment of this disclosure;

[0048] Figure 4 A flowchart illustrating the method for obtaining message records of each target user sorted by message timestamp from smallest to largest according to an embodiment of this disclosure;

[0049] Figure 5 A flowchart illustrating the method for obtaining the number of first port reclaimed by a target user at the time of interruption, provided in an embodiment of this disclosure;

[0050] Figure 6 A flowchart illustrating the method for determining the NAT public port segment change value of message records of each type of Radius server corresponding to a username in the fifth user set, as provided in an embodiment of this disclosure;

[0051] Figure 7 A flowchart illustrating the interruption-aware identification method provided as an application example of this disclosure;

[0052] Figure 8 This is a schematic diagram of the structure of the interruption sensing and identification device provided in the embodiments of this disclosure;

[0053] Figure 9 This is a schematic diagram of the hardware composition structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0054] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0055] In order for those skilled in the art to better understand the technical solutions described in the embodiments of the present disclosure, before introducing the embodiments of the present disclosure, the technical terms in the embodiments of the present disclosure are explained as follows.

[0056] The home broadband access online and offline process: the home broadband dial-up online process: the PPP protocol (Point-to-Point Protocol over Ethernet, PPPoE) client on the Ethernet is an optical network unit (Optical Network Unit, ONU), the PPPoE server / access server is an IP metropolitan area network boundary network gateway (Broadband Network Gateway, BNG) device, and the AAA server is a Radius server. The PPPoE protocol process runs between the ONU and the BNG, and the Radius protocol process runs between the BNG and the Radius server. Among them, the PPPoE client sends a PADI message to the PPPoE server device to start the PPPoE access; the PPPoE server sends a PADO message to the client; the client initiates a PADR request to the PPPoE server according to the response; the PPPoE server generates a Session id and sends it to the client through PADS; the client and the PPPoE server perform PPP link control protocol (Link Control Protocol, LCP) negotiation to establish link layer communication; the PPPoE server sends a Challenge message to the authentication client to provide a 128-bit Challenge; after receiving the Challenge message, the client sends the MD5 algorithm result of the password and the Challenge in the Response response message to the PPPoE server; the PPPoE server sends the Challenge, Challenge-Password, and username to the Radius user authentication server for authentication; the Radius user authentication server judges whether the user is legal according to the user information, and then sends an authentication success / failure message to the PPPoE server. If successful, the user is authorized with the negotiation parameters and related service attributes of the user. If the authentication fails, the process ends here; the PPPoE server returns the authentication result to the client; the user performs NCP (such as IPCP) negotiation and obtains the planned IP address and other parameters through the PPPoE server; if the authentication is successful, the PPPoE server initiates a billing start request to the Radius user authentication server; the Radius user authentication server responds to the billing start request message; the user is authenticated and has obtained legal rights, and can normally develop network services. When the user wants to terminate the network service, the network connection can be disconnected through the PPPoE.

[0057] Home line flow: PPPoE user offline process includes two cases of user voluntary offline and abnormal offline. When offline normally, the user sends Terminate-Request to the PPPoE server through the PPPoE client; the PPPoE server returns Terminate-Ack message to the PPPoE client; the PPPoE server sends the message of charging stop request to the AAA server; the AAA server returns the response of charging stop request message to the authentication point; when offline abnormally, the PPPoE server detects the PPPoE client, and when it is found that the PPPoE client does not respond, the PPPoE server considers that the user has logged off, and initiates the charging stop request to the AAA server.

[0058] Radius authentication protocol: Radius authentication protocol is a protocol based on a client / server structure, and its client is initially a network access server (NAS), and any computer running Radius client software can become a Radius client. Radius message types include authentication request class, authorization class and charging class, and commonly used are request access, receive access, reject access, charging request and charging response. Radius protocol authentication mechanism is flexible, and can adopt PAP, CHAP or Unix login authentication and other ways. Radius is an extensible protocol, and all its work is based on Attribute-Length-Value vector. Due to the simplicity and explicitness of Radius protocol, it is widely used, including ordinary telephone Internet, ADSL Internet, cell broadband Internet, IP telephone, Virtual Private Dialup Networks (VPDN) based on dial-up users, mobile phone prepaid and other services.

[0059] Network address translation (NAT): It is a technology for converting private addresses used in a local network into global IP addresses when connecting to the Internet, mainly to solve the problem of IPv4 address shortage. NAT includes static conversion, dynamic conversion and network address port translation (NAPT) three implementation ways, and the current IP metropolitan network NAT conversion is actually NAPT, which can map multiple internal addresses to a legal public network address, but different protocol port numbers correspond to different internal addresses. In this way, one-to-many mapping of public and private addresses can be realized, effectively improving the utilization rate of public addresses.

[0060] Deep packet inspection (DPI): DPI is an application layer-based traffic detection and control technology, which can be used to identify online services and user behavior. The so-called "deep" is compared with the normal message analysis level. The normal message detection only analyzes the content below layer 4 of the IP packet, including the source address, destination address, source port, destination port and protocol type. Using the DPI system can view the content of layers 2 to 7 of the Open System Interconnect (OSI) model, and perform deep detection on different network application layer loads (such as HTTP, DNS, etc.). It can find, identify and classify packets containing specific data or code payloads. The DPI device can filter and control the detected traffic according to the pre-defined policy by detecting and analyzing the traffic and message content at the key points of the network, and can complete the functions of fine identification of services on the link, analysis of service traffic flow direction, statistics of service traffic proportion, service proportion shaping, and application layer denial of service attack, filtering of viruses and Trojan horses, and control of abuse of P2P.

[0061] In the related interrupt awareness identification scheme, whether the target user is aware of the interrupt is determined only by the frequency of the interrupt, resulting in low accuracy of the target user interrupt awareness identification.

[0062] In order to guarantee and improve the use quality of the home broadband user, the operator will evaluate and analyze the use quality of the user. When evaluating and analyzing the use quality of the user, two aspects are mainly included, one is the quality of the online process, such as whether the access speed is high or not, whether the access success rate is high or not, etc.; the other is to evaluate whether the interrupt occurs in the use process. In the prior art, the offline situation of the home broadband dial-up authentication is often used to represent the interrupt situation of the network, so as to be used as an important index for the user perception analysis and evaluation.

[0063] Two schemes related to the home broadband user interrupt awareness identification method in the related art will be briefly introduced as follows:

[0064] Scheme A: Scheme A identifies the interrupt situation of the user online through the interrupt record of the authentication protocol. This judgment is mainly based on the protocol information between the dial-up terminal and the authentication server, but does not judge whether the user is using at the time of interrupt, so it can only identify the interrupt, but cannot identify the interrupt awareness.

[0065] Scheme B: Scheme B identifies whether the user is using and further identifies whether the user is aware of the interrupt by combining the change of the user traffic. In addition to identifying the connection protocol interrupt, this kind of technology also combines the change of the user traffic near the interrupt time point to identify the interrupt awareness.

[0066] In related technologies, the offline reason and offline frequency in the offline record of the user broadband authentication protocol Radius are mainly used for broadband access interruption identification, which is used to represent the interruption of the user perception, and needs to be used in combination with other quality perception indicators for evaluating the network use quality and perception of the user.

[0067] In the above scheme, the following defects exist:

[0068] The interruption record of the authentication protocol is used to identify the interruption of the user online, and the actual use of the user is ignored.

[0069] In related technologies, the change of the user traffic is used to determine whether the user is using and to identify whether the user perceives the interruption. However, the existing collection technology needs to deploy a large number of server computing and storage resources, and the data volume is extremely large and needs a long processing time. At present, the user traffic collection method mainly has the following two kinds:

[0070] First, the traffic of a single user can be collected in the access network. The user traffic is collected in the access network mainly by monitoring the traffic of the ONU, and the traffic collection task needs to be deployed on the network management for each ONU. This traffic collection method needs to deploy a large number of storage and computing resources.

[0071] Second, the user traffic is counted by using the DPI record. The DPI device deployed at the IP metropolitan area network outlet can distinguish the traffic and service composition of each home broadband user. However, the DPI generates 70G of data records per 10G of outlet bandwidth per day, about 90 million rows of data. For the metropolitan area network with T-level outlet, the DPI needs to consume a large amount of storage resources. The user-level operation time is in the order of hours, and the calculation time is too long. In addition, the DPI can only collect and record the traffic reaching the metropolitan area network outlet, and cannot record the traffic in the network, so there is an incomplete situation in the judgment of the use of the traffic of a single user.

[0072] In addition, in the related technology of the IP metropolitan area network, due to the shortage of IPv4 public network addresses, in order to meet the business use demand of the user, the NAT technology is introduced. For each home broadband user, during the access and online period, the BNG will allocate a new public network address port segment or recover the idle public network address port segment which is no longer used by the user according to the use of the NAT public network address port resource of each user. The intermediate billing message of the Radius can be used to obtain the allocation and recovery of these public network address port segments, and only the related configuration needs to be opened on the BNG device.

[0073] In order to solve the defects in the related art, the present disclosure obtains a target user set, the target user set including at least one target user; obtains a first flow rate of each target user in the target user set at an interruption time and a first port recovery number of each target user in the target user set at the interruption time; if the first flow rate of the target user at the interruption time is not less than a first preset flow rate or the first port recovery number of the target user at the interruption time is not less than a first preset port number, the target user is determined to be an interruption-aware user, the target user can be determined whether to perceive the interruption in combination with the first flow rate of the target user at the interruption time and the first port recovery number of the target user at the interruption time, and then the identification accuracy of the target user perceiving the interruption can be improved.

[0074] The present disclosure will be further described in detail below in combination with the drawings and specific embodiments.

[0075] As shown in Figure 1 , a flowchart of an interruption-aware identification method provided by an embodiment of the present disclosure is shown. The interruption-aware identification method provided by the embodiment of the present disclosure includes the following steps: Figure 1

[0076] Step 101, obtaining a target user set, the target user set including at least one target user;

[0077] In an embodiment, the target user refers to a user who has experienced an interruption.

[0078] In an embodiment, the target user can be a user who has experienced an interruption once or a user who has experienced multiple interruptions.

[0079] In an embodiment, the target user set can be directly obtained from the interruption record, or the target user set can be screened from the interruption record.

[0080] Step 102, obtaining a first flow rate of each target user in the target user set at an interruption time and a first port recovery number of each target user in the target user set at the interruption time;

[0081] In an embodiment, the first flow rate is used to indicate the average flow rate of the user at the interruption time.

[0082] In an embodiment, since the flow rate when the user is online and the flow rate when the user is interrupted are obviously different in size, by obtaining the first flow rate of each target user in the target user set at the interruption time, the target user range can be further narrowed, and the identification accuracy of the interruption-aware user can be improved.

[0083] In an embodiment, the first port recovery number is used to determine whether the user is in an active online state.

[0084] ​In an embodiment, when determining whether the target user is aware of the interruption according to the first flow rate of the target user at the interruption time, there may be a false negative due to the low first flow rate. Therefore, by obtaining the first port recovery number of each target user at the interruption time, the recognition accuracy of the interruption-aware user can be further improved.

[0085] In an embodiment, since there can be multiple interruption times for each target user, the first flow rate of each target user at each interruption time and the first port recovery number of each target user at each interruption time in the target user set can be obtained.

[0086] Step 103: If the first flow rate of the target user at the interruption time is not less than the first preset flow rate or the first port recovery number of the target user at the interruption time is not less than the first preset port number, it is determined that the target user is an interruption-aware user.

[0087] In an embodiment, the first preset flow rate is usually the average of the first flow rate when the user is online and active, for example, the first preset flow rate can be 1 Mbps. The specific value of the first preset flow rate is not limited in the present disclosure.

[0088] In an embodiment, the first preset port number is usually the average of the first port recovery number, for example, the first preset port number can be 512. The specific value of the first preset port number is not limited in the present disclosure.

[0089] In an embodiment, a regression algorithm or a baseline learning algorithm can be used to optimize the first preset flow rate and the first preset port number to obtain more accurate first preset flow rate and first preset port number, thereby improving the recognition accuracy of the interruption-aware user.

[0090] In an embodiment, the above interruption-aware recognition method can be applied to the mining of poor-quality users who are offline. After actively interviewing the mined users, the proportion of users who feedback online problems in the successfully interviewed users reaches 50%, which is 28% higher than the hit rate of 22% of the users mined according to the offline frequency alone.

[0091] In an embodiment, as shown in Figure 2 the target user set is obtained, including:

[0092] Step 201: Obtain the message record of each user in the Radius server, wherein one user corresponds to at least one message record, and each message record contains a message type, a message timestamp, and a username corresponding to the message;

[0093] In an embodiment, the message type of the message record includes a billing start message type, a billing end message type, and an intermediate billing message type.

[0094] In an embodiment, the message timestamp is used to indicate the time of the message.

[0095] In an embodiment, the message timestamp of each message record corresponding to one user is different.

[0096] In an embodiment, the message timestamp of message records corresponding to multiple users can be the same or different.

[0097] In an embodiment, the Radius server can be configured to send the log to one or more destinations, such as a local file system, a syslog log server, or a database. That is, if the log is sent to the local file system, the message record of each user on the Radius server can be obtained from the local file system; if the log is sent to the syslog log server, the message record of each user on the Radius server can be obtained from the syslog log server; and if the log is sent to the database, the message record of each user on the Radius server can be obtained from the Radius message record database.

[0098] Step 202, filtering out the Radius message records of the message type being the first message type from the message records of the Radius server to obtain all the Radius message records of the message type being the first message type;

[0099] In an embodiment, the first message type refers to the charging end message type.

[0100] In an embodiment, by filtering out the Radius message records of the message type being the first message type from the message records of the Radius server to obtain all the Radius message records of the message type being the first message type, the user corresponding to the charging end message in the Radius server can be preliminarily filtered out.

[0101] Step 203, determining a first user set based on the username corresponding to the message in all the Radius message records of the message type being the first message type;

[0102] In an embodiment, based on the username corresponding to the message in all the Radius message records of the message type being the first message type, the set of users indicated by the username is determined as the first user set.

[0103] Step 204, filtering out the message records with the message timestamp being within a first preset time interval from the first user set to obtain a second user set, the first preset time interval being used to indicate a non-network change operation time interval;

[0104] In an embodiment, the network change operation time interval refers to a time period during which the network is adjusted, such as a network update operation time interval and a network structure adjustment operation time interval.

[0105] In an embodiment, the time interval with the lowest online traffic can be determined as the network change operation time interval, such as from 1 a.m. to 6 a.m.

[0106] In an embodiment, by filtering out the message records with the message timestamps within the first preset time interval from the first user set, the users interrupted due to network change operation can be excluded from the first user set, thereby reducing the misidentification of users being interrupted while using the network and reducing the false positive rate.

[0107] Step 205, determining a target user set based on the second user set, wherein one message in the target user set corresponds to at least one message timestamp.

[0108] In an embodiment, the message records in the second user set include the username corresponding to the message, the message timestamp, the message charging end reason, the message online time, and the uplink and downlink traffic during the online period.

[0109] In an embodiment, the message records in the target user set only include the username corresponding to the message and the message timestamp.

[0110] In an embodiment, the fact that one message in the target user set corresponds to at least one message timestamp means that the same user can have one or more interruption situations.

[0111] In an embodiment, as shown in the first flow rate of each target user in the target user set at the interruption moment is obtained, including: Figure 3

[0112] Step 301, finding the last message record corresponding to the username and the message timestamp of the message from the message records of the Radius server according to the username and the message timestamp of the message in the second user set;

[0113] In an embodiment, the last message record corresponding to the username and the message timestamp of the message means the message record with the same username and the adjacent previous message timestamp.

[0114] Step 302, obtaining the first online time and the first traffic of the message record of the target user in the second user set, and obtaining the second online time and the second traffic of the last message record of the target user;

[0115] In an embodiment, the first online time refers to the online time of the target user in the second user set.​

[0116] In one embodiment, the first traffic refers to the uplink and downlink traffic of the target user during the period when the second user is online.

[0117] In one embodiment, the second online time refers to the time the target user was online in the previous message record.

[0118] In one embodiment, the second traffic refers to the uplink and downlink traffic of the target user during the period when the target user was online in the previous message record.

[0119] In one embodiment, the target user's first online time and first traffic can be obtained directly from the target user's message records in the second user set, and the target user's second online time and second traffic can be obtained from the target user's previous message record.

[0120] Step 303: Based on the first online time and the second online time, determine the online time difference of the target user; and based on the first traffic and the second traffic, determine the traffic difference of the target user;

[0121] In one embodiment, the difference between the first online time and the second online time is used to obtain the online time difference of the target user, and the difference between the first traffic and the second traffic is used to obtain the traffic difference of the target user.

[0122] In one embodiment, the traffic difference for a target user reflects the traffic changes of the same user at adjacent message timestamps.

[0123] Step 304: Compare the flow difference with the online time difference to obtain the first flow rate of the target user at the time of interruption.

[0124] In one embodiment, the first flow rate refers to the average flow rate of the target user at adjacent message timestamps.

[0125] In one embodiment, by comparing the traffic difference with the online time difference, the first flow rate of the target user at the time of interruption can be obtained, and the magnitude of the first flow rate can be used to determine whether the target user is using the network.

[0126] In one embodiment, since the traffic collection in the relevant scheme uses a dedicated traffic collection system, it requires a lot of resources. However, in this application, the traffic volume of the target user is determined based on the message records of the Radius server, without the need to add additional equipment, thereby reducing resource consumption.

[0127] In one embodiment, such as Figure 4 As shown, before obtaining the target user's first online time and first traffic in the message records of the second user set; and before obtaining the target user's second online time and second traffic in the previous message record, the interruption identification method further includes:

[0128] Step 401, merging the message records in the second user set and the last message record to obtain a third user set;

[0129] In an embodiment, the message records in the third user set include a username corresponding to a message, a message timestamp, a message charging end reason, a message online time, and uplink and downlink traffic during the online period.

[0130] Step 402, grouping the message records in the third user set according to the username corresponding to the message to obtain message records of each target user at different message timestamps;

[0131] Step 403, sorting the message records of each target user at different message timestamps in ascending order of the message timestamp to obtain message records of each target user sorted in ascending order of the message timestamp.

[0132] In an embodiment, through the foregoing steps 402 and 403, the first online time, the second online time, the first traffic, and the second traffic can be directly obtained from two adjacent message records of the same user.

[0133] In an embodiment, as shown in Figure 5 the first port recovery number of each target user in the target user set at the interruption moment is obtained, including:

[0134] Step 501, filtering, according to the username corresponding to the message, the message records of the Radius server from the message records of the Radius server;

[0135] In an embodiment, the message types of the message records of the Radius server filtered from the message records of the Radius server include an authentication request message type, an authentication success message type, an authentication rejection message type, a charging start message type, an intermediate charging message type, and a charging end message type.

[0136] Step 502, determining the NAT public network port segment change value of each type of message record of the Radius server corresponding to the username;

[0137] In an embodiment, the NAT public network port segment change value of each type of message record of the Radius server corresponding to the username can be determined according to a preset rule.

[0138] In an embodiment, the NAT public network port segment change value of each type of message record of the Radius server corresponding to the username can also be determined according to a preset value.

[0139] Step 503, summing up the NAT public network port segment change value of each type of Radius server message record corresponding to the username to obtain the NAT public network address port number corresponding to the username, wherein the NAT public network address port number corresponding to the username at least includes the NAT public network address port number corresponding to the username at the interruption time and the NAT public network address port number corresponding to the username at the time before the interruption;

[0140] In an embodiment, by summing up the NAT public network port segment change value of each type of Radius server message record corresponding to the username, the NAT public network address port number corresponding to the username can be obtained, and then the NAT public network address port number corresponding to the username at each message timestamp can be obtained.

[0141] In an embodiment, since there can be multiple interruption times corresponding to the username, the NAT public network address port number corresponding to the username can include multiple NAT public network address port numbers corresponding to the username at the interruption time and the NAT public network address port number corresponding to the username at the time before the interruption.

[0142] Step 504, subtracting the NAT public network address port number corresponding to the username at the interruption time from the NAT public network address port number corresponding to the username at the time before the interruption to obtain the first port recovery number of the target user at the interruption time.

[0143] In an embodiment, the first port refers to the NAT public network port.

[0144] In an embodiment, the first port recovery number of the target user at the interruption time refers to the number of the first port recovered due to the interruption.

[0145] In an embodiment, by subtracting the NAT public network address port number corresponding to the username at the interruption time from the NAT public network address port number corresponding to the username at the time before the interruption to obtain the first port recovery number of the target user at the interruption time, whether the target user is in the online state can be reflected.

[0146] In an embodiment, as shown in FIG. 6, determining the NAT public network port segment change value of each type of Radius server message record corresponding to the username includes: Figure 6

[0147] Step 601, determining the message record containing the second message type from the message record of the Radius server corresponding to the username to obtain a fourth user set; ​

[0148] In an embodiment, the second message type refers to a message type carrying a NAT public network port segment.

[0149] In an embodiment, the second message type includes a charging start message type, a charging end message type, and an intermediate charging message type carrying a NAT public network port segment.

[0150] Step 602, grouping the fourth user set according to a first preset rule to obtain at least two fifth user sets, each of the fifth user sets including a message type of each message record and a reason type of charging end;

[0151] In an embodiment, grouping the fourth user set according to the first preset rule refers to grouping the fourth user set according to a username corresponding to a message, a public network address indicated in the message, a starting public network port number indicated in the message, and an ending public network port number indicated in the message.

[0152] In an embodiment, the username corresponding to the message, the public network address indicated in the message, the starting public network port indicated in the message, and the ending public network port indicated in the message of the message records in the same fifth user set are all the same.

[0153] In an embodiment, the username corresponding to the message, the public network address indicated in the message, the starting public network port indicated in the message, and the ending public network port indicated in the message of the message records in different fifth user sets are all different or not all the same.

[0154] In an embodiment, the reason type of charging end includes a normal end type and an abnormal end type.

[0155] In an embodiment, after grouping the fourth user set according to the first preset rule, the messages in each group can be sorted in ascending order of message timestamp, to obtain message records of the target user in a time flow.

[0156] Step 603, determining a message identifier and a reason type identifier of charging end of each message record in the fifth user set based on the message type and the reason type of charging end of each message record in the fifth user set.

[0157] In an embodiment, based on the message type and the reason type of charging end of each message record in the fifth user set, different English letters can be used to determine the message identifier and the reason type identifier of charging end of each message record in the fifth user set.

[0158] In an embodiment, based on the message type and the reason type of the charging end of each message record in the fifth user set, different numbers can also be used to determine the message identification and the reason type identification of the charging end of each message record in the fifth user set.

[0159] Specifically,

[0160] In an embodiment, if the message type of the message record in the fifth user set is the charging start message type, the message identification can be determined as 2.

[0161] In an embodiment, if the message type of the message record in the fifth user set is the charging end message type, the message identification can be determined as 1.

[0162] In an embodiment, if the reason type of the charging end is the abnormal end type, the reason type identification of the charging end can be determined as a number greater than 0; if the reason type of the charging end is the normal end type, the reason type identification of the charging end can be determined as 0.

[0163] In an embodiment, if the message type of the message record in the fifth user set is the intermediate charging message type and the reason type of the charging end is the abnormal end type, the message identification can be determined as 2.

[0164] In an embodiment, if the message type of the message record in the fifth user set is the intermediate charging message type and the reason type of the charging end is the normal end type, the message identification can be determined as 1.

[0165] In step 604, based on the message identification, the reason type identification of the charging end and the second preset rule of each message record in the fifth user set, the NAT public network port segment change value of each type of Radius server corresponding to the username in the fifth user set is determined.

[0166] In an embodiment, if the message type of the first message record in the fifth user set is the intermediate charging message type and the reason type of the charging end is the abnormal end type, the NAT public network port segment change value of the first message record in the fifth user set is determined as 0.

[0167] In an embodiment, if the message type of the message record other than the first message record in the fifth user set is the intermediate charging message type and the reason type of the charging end is the abnormal end type, the NAT public network port segment change value of the first message record in the fifth user set is determined as the difference between the starting public network port number indicated in the message and the ending public network port number indicated in the message.

[0168] In an embodiment, if the message type in the fifth user set is an intermediate charging message type and the reason type of the charging end is a normal end type, the NAT public network port segment change value of the first message record in the fifth user set is determined as the difference between the end public network port number indicated in the message and the start public network port number indicated in the message.

[0169] In an embodiment, after determining the message identification of each message record in the fifth user set and the reason type of the charging end based on the message type and the reason type of the charging end of each message record in the fifth user set, the method further comprises:

[0170] The messages in the fifth user set are sorted in ascending order of the message time stamp to obtain a sorted fifth user set;

[0171] In an embodiment, the message records in the sorted fifth user set are message records of a same target user in a time flow.

[0172] The message records in the fifth user set that meet a third preset rule are deleted to obtain a sixth user set;

[0173] In an embodiment, the third preset rule refers to a preset rule for removing duplicates.

[0174] In an embodiment, the third preset rule can also include message records with incomplete key information.

[0175] In an embodiment, deleting the message records in the fifth user set that meet the third preset rule to obtain the sixth user set specifically comprises: deleting the message records in the fifth user set that meet the conditions of the message type being an intermediate charging message type, the reason type of the charging end being a normal end type, and the message identification being 1 to obtain the sixth user set; and deleting the message records in the fifth user set that meet the conditions of the message identification and the reason type of the charging end of adjacent two message records being the same and the message identification being 2 to obtain the sixth user set.

[0176] Based on the message identification, the reason type identification of the charging end, and a second preset rule of each message record in the sixth user set, the NAT public network port segment change value of the message records of each type of Radius server corresponding to the username in the sixth user set is determined.

[0177] In an embodiment, by determining the NAT public network port segment change value of the message record of each type of Radius server corresponding to the username in the sixth user set based on the message identifier, the reason type identifier of the charging end, and the second preset rule of each message record in the sixth user set, the number of message records participating in the calculation can be reduced, and the cleaning of the message records can be realized.

[0178] In an embodiment, determining the NAT public network port segment change value of the message record of each type of Radius server corresponding to the username comprises:

[0179] Determining the message record containing the third message type from the message record of the Radius server corresponding to the username to obtain a seventh user set;

[0180] In an embodiment, the third message type refers to a message type that does not carry the NAT public network port segment.

[0181] In an embodiment, the third message type includes an authentication request message type, an authentication success message type, an authentication rejection message type, and an intermediate charging message type that does not carry the NAT public network port segment.

[0182] Determining the NAT public network port segment change value of the message record of each type of Radius server corresponding to the username in the seventh user set as a first preset value.

[0183] In an embodiment, since the first preset value is the NAT public network port segment change value, the message type in the message record of each type of Radius server corresponding to the username in the seventh user set is a message type that does not carry the NAT public network port segment, and therefore the first preset value is usually 0.

[0184] In an embodiment, after determining the NAT public network port segment change value of the message record of each type of Radius server corresponding to the username in the seventh user set as the first preset value, the knowledge identification method further comprises merging the NAT public network port segment change value of the message record of each type of Radius server corresponding to the username in the fifth user set with the NAT public network port segment change value of the message record of each type of Radius server corresponding to the username in the seventh user set as the first preset value to obtain an eighth user set.

[0185] In an embodiment, since the allocated NAT public network port segment will change over time, the eighth user set needs to be grouped according to the username corresponding to the message, and the grouped eighth user set needs to be sorted in ascending order of the message timestamp.

[0186] In an embodiment, the message records in the eighth user set are filtered to obtain message records of the message type being the billing end message type and the reason type for the billing end being the non-Host Request type.

[0187] To sum up, the scheme provided by the disclosure has the following advantages:

[0188] Firstly, by obtaining a target user set including at least one target user, obtaining a first flow rate of each target user in the target user set at an interruption time and a first port recovery number of each target user in the target user set at the interruption time, if the first flow rate of the target user at the interruption time is not less than a first preset flow rate or the first port recovery number of the target user at the interruption time is not less than a first preset port number, the target user is determined to be an interruption-aware user. The target user can be determined to be aware of the interruption in combination with the first flow rate of the target user at the interruption time and the first port recovery number of the target user at the interruption time, and thus the identification accuracy of the target user aware of the interruption can be improved.

[0189] Secondly, by filtering the message records with the message timestamps in a first preset time interval from the first user set, the user interrupted due to the network change operation can be excluded from the first user set, and thus the misidentification of the user interrupted while using the network can be reduced, and the false positive rate can be reduced.

[0190] Thirdly, the traffic size of the target user is determined according to the message records of the Radius server, without the need to increase additional equipment, and thus the resource consumption can be reduced.

[0191] Thirdly, by subtracting the NAT public address port number corresponding to the username at the interruption time from the NAT public address port number corresponding to the username at the time before the interruption, the first port recovery number of the target user at the interruption time is obtained, which can reflect whether the target user is in the online state.

[0192] Thirdly, by determining the NAT public port segment change value of each type of message record of the Radius server corresponding to the username in the sixth user set based on the message identifier, the reason type identifier for the billing end, and the second preset rule of each message record in the sixth user set, the number of message records participating in the calculation can be reduced, and thus the message records can be cleaned.

[0193] The interruption-aware identification method provided by the disclosure is further described below with an application example:

[0194] As shown in Figure 7 , the target user set is obtained, the first flow rate of each target user in the target user set at the interruption time is obtained, and the first port recovery number of each target user in the target user set at the interruption time is obtained. Figure 7A flowchart of an interrupt awareness identification method provided by the present disclosure for an application example. The interrupt awareness identification method provided by the present disclosure for the application example includes the following steps:

[0195] Step 701, obtaining message records of each user in a Radius server, wherein one user corresponds to at least one message record, and each message record contains a message type, a message timestamp, and a username corresponding to the message;

[0196] Step 702, filtering out Radius message records of the first message type from the message records of the Radius server to obtain all Radius message records of the first message type;

[0197] Step 703, determining a first user set based on the usernames corresponding to the messages in all Radius message records of the first message type;

[0198] Step 704, filtering out message records in the first preset time interval from the first user set to obtain a second user set, wherein the first preset time interval is used to indicate a non-network change operation time interval;

[0199] Step 705, determining a target user set based on the second user set, wherein the username corresponding to one message in the target user set corresponds to at least one message timestamp;

[0200] Step 706, searching for a previous message record corresponding to the username and the message timestamp of the message from the message records of the Radius server according to the username and the message timestamp of the message in the second user set;

[0201] In an embodiment, the first online time and the first traffic of the target user in the message records in the second user set are obtained, and the second online time and the second traffic of the target user in the previous message record are obtained. The interrupt awareness identification method further includes:

[0202] Merging the message records in the second user set and the previous message record to obtain a third user set;

[0203] Grouping the message records in the third user set according to the username corresponding to the message to obtain message records of each target user at different message timestamps;

[0204] Sorting the message records of each target user at different message timestamps in ascending order of the message timestamp to obtain message records of each target user sorted in ascending order of the message timestamp.

[0205] Step 707, obtaining a first online time and a first traffic of the target user in the second user set of message records; and obtaining a second online time and a second traffic of the target user in the last message record;

[0206] Step 708, determining an online time difference of the target user based on the first online time and the second online time; and determining a traffic difference of the target user based on the first traffic and the second traffic;

[0207] Step 709, obtaining a first flow rate of the target user at the interruption time by comparing the traffic difference with the online time difference;

[0208] Step 710, filtering out the message records of the Radius server corresponding to the username from the message records of the Radius server according to the username corresponding to the target user set of messages;

[0209] Step 711, determining the message records containing the second message type from the message records of the Radius server corresponding to the username, to obtain a fourth user set;

[0210] Step 712, grouping the fourth user set according to a first preset rule to obtain at least two fifth user sets, the fifth user set including the message type and the reason type of charging end of each message record;

[0211] Step 713, determining the message identification and the reason type of charging end of each message record in the fifth user set based on the message type and the reason type of charging end of each message record in the fifth user set;

[0212] Step 714, determining the NAT public network port segment change value of each type of message record of the Radius server corresponding to the username in the fifth user set based on the message identification, the reason type of charging end of each message record in the fifth user set, and a second preset rule;

[0213] Step 715, summing up the NAT public network port segment change value of each type of message record of the Radius server corresponding to the username to obtain the number of NAT public network address ports corresponding to the username;

[0214] In an embodiment, the number of NAT public network address ports corresponding to the username at least includes the number of NAT public network address ports corresponding to the username at the interruption time and the number of NAT public network address ports corresponding to the username at the time before the interruption.

[0215] Step 716, the number of NAT public network address ports corresponding to the username at the interruption time is subtracted from the number of NAT public network address ports corresponding to the username at the time before interruption, to obtain the first port recycling number of the target user at the interruption time;

[0216] Step 717, if the first flow rate of the target user at the interruption time is not less than the first preset flow rate or the first port recycling number of the target user at the interruption time is not less than the first preset port number, it is determined that the target user is an interruption-aware user.

[0217] In order to implement the interruption-aware identification method provided by the embodiments of the present disclosure, the embodiments of the present disclosure also provide an interruption-aware identification device, as shown in Figure 8 The structure schematic diagram of the interruption-aware identification device provided by the embodiments of the present disclosure is shown in FIG. 8. Figure 8 The interruption-aware identification device 800 includes:

[0218] The first acquisition unit 801 is configured to acquire a target user set, wherein the target user set includes at least one target user;

[0219] The second acquisition unit 802 is configured to acquire a first flow rate of each target user in the target user set at an interruption time and a first port recycling number of each target user in the target user set at the interruption time;

[0220] The determination unit 803 is configured to determine that the target user is an interruption-aware user if the first flow rate of the target user at the interruption time is not less than a first preset flow rate or the first port recycling number of the target user at the interruption time is not less than a first preset port number.

[0221] In an embodiment, the first acquisition unit 801 is specifically configured to:

[0222] Acquire message records of each user in a Radius server, wherein one user corresponds to at least one message record, and each message record contains a message type, a message timestamp and a username corresponding to the message;

[0223] Filter out Radius message records of the first message type from the message records of the Radius server to obtain all Radius message records of the first message type;

[0224] Determine a first user set based on the usernames corresponding to the messages in all Radius message records of the first message type;

[0225] filtering, from the first user set, a message record with a message timestamp within a first preset time interval to obtain a second user set, the first preset time interval being used to indicate a non-network change operation time interval;

[0226] determining a target user set based on the second user set, one message in the target user set corresponding to at least one message timestamp.

[0227] In an embodiment, the second obtaining unit 802 is specifically configured to:

[0228] finding, from the message record of the Radius server, a last message record corresponding to the username and the message timestamp of the message according to the username and the message timestamp of the message in the second user set;

[0229] obtaining a first online time and a first traffic of the target user in the message record in the second user set, and obtaining a second online time and a second traffic of the target user in the last message record;

[0230] determining an online time difference of the target user based on the first online time and the second online time, and determining a traffic difference of the target user based on the first traffic and the second traffic;

[0231] obtaining a first flow rate of the target user at the interruption moment by comparing the traffic difference with the online time difference.

[0232] In an embodiment, the interruption awareness identification apparatus 800 further includes a sorting unit configured to:

[0233] merging the message record in the second user set and the last message record to obtain a third user set;

[0234] grouping the message records in the third user set according to the username of the message to obtain message records of each target user at different message timestamps;

[0235] sorting the message records of each target user at different message timestamps according to the message timestamp in ascending order to obtain message records of each target user sorted in ascending order of the message timestamp.

[0236] In an embodiment, the second obtaining unit 802 is specifically configured to:

[0237] filtering, from the message record of the Radius server, a message record of the Radius server corresponding to the username according to the username of the message in the target user set;

[0238] determining a NAT public network port segment change value of each type of Radius server message record corresponding to the username;

[0239] summing the NAT public network port segment change value of each type of Radius server message record corresponding to the username to obtain a NAT public network address port number corresponding to the username, the NAT public network address port number corresponding to the username at least including a NAT public network address port number corresponding to the username at the interruption time and a NAT public network address port number corresponding to the username at the time before interruption;

[0240] subtracting the NAT public network address port number corresponding to the username at the time before interruption from the NAT public network address port number corresponding to the username at the interruption time to obtain a first port recycling number of the target user at the interruption time.

[0241] In an embodiment, the second obtaining unit 802 is specifically configured to:

[0242] determining, from the message records of the Radius server corresponding to the username, message records containing the second message type to obtain a fourth user set;

[0243] grouping the fourth user set according to a first preset rule to obtain at least two fifth user sets, the fifth user set including a message type and a reason type of charging end of each message record;

[0244] determining, based on the message type and the reason type of charging end of each message record in the fifth user set, a message identifier and a reason type identifier of charging end of each message record in the fifth user set;

[0245] determining, based on the message identifier, the reason type identifier of charging end and a second preset rule, a NAT public network port segment change value of each type of Radius server message record corresponding to the username in the fifth user set.

[0246] It should be noted that the interruption awareness identification device provided in the above embodiments is only exemplified by the division of the above program modules when identifying the interruption awareness, and in actual application, the above processing can be completed by different program modules according to needs, that is, the internal structure of the interruption awareness identification device is divided into different program modules to complete all or part of the above processing. In addition, the interruption awareness identification device provided in the above embodiments and the interruption awareness identification method provided in the method embodiments of the present disclosure belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0247] Figure 9A schematic diagram of a hardware composition structure of an electronic device provided by an embodiment of the present disclosure is shown in Figure 9 The electronic device 900 includes at least one processor 902, and a memory 901 connected with the at least one processor 902 in communication. The memory 901 stores instructions executable by the at least one processor 902, and the instructions are executed by the at least one processor 902 to implement steps of the interrupt-awareness identification method of the embodiment of the present disclosure.

[0248] Optionally, the electronic device can be an interrupt-awareness identification apparatus of an embodiment of the present disclosure, and the electronic device can implement corresponding procedures implemented by the interrupt-awareness identification apparatus in each method of an embodiment of the present disclosure. For brevity, details are not described herein.

[0249] It can be understood that the electronic device further includes a communication interface 903. The various components in the electronic device are coupled together through a bus system 904. It can be understood that the bus system 904 is used to realize the connection communication between the components. The bus system 904 includes a data bus, a power supply bus, a control bus and a state signal bus in addition to the data bus. However, for the purpose of clear illustration, all kinds of buses are marked as the bus system 904 in Figure 9 .

[0250] It can be understood that the memory 901 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of RAM can be used, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).The memory 901 described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable type of memory.

[0251] The method disclosed in the embodiments of the present application can be applied to the processor 902 or implemented by the processor 902. The processor 902 can be an integrated circuit chip having a processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the processor 902 or the instruction in the form of software. The processor 902 described above can be a general processor, a DSP, or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The processor 902 can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application. The general processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiments of the present application, the hardware decoding processor can be directly embodied to complete the execution, or the combination of hardware and software modules in the decoding processor can be used to complete the execution. The software module can be located in the storage medium, which is located in the memory 901, and the processor 902 reads the information in the memory 901 to complete the steps of the above method in combination with the hardware.

[0252] In the exemplary embodiments, the electronic device can be implemented by one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), FPGAs, general-purpose processors, controllers, MCUs, microprocessors (Microprocessors), or other electronic elements, for executing the above-mentioned methods.

[0253] The embodiments of the present application also provide a non-transitory computer-readable storage medium storing computer instructions, which are used to make a computer execute the steps of the interrupt-aware knowledge identification method provided by the embodiments of the present application.

[0254] Optionally, the computer-readable storage medium can be applied to the interrupt-aware knowledge identification apparatus in the embodiments of the present application, and the computer instructions make the computer execute the corresponding processes implemented by the interrupt-aware knowledge identification apparatus in the methods of the embodiments of the present application. For brevity, details are not described herein.

[0255] The embodiments of the present application also provide a computer program product, which comprises a computer program, and the computer program is used to implement the steps of the interrupt-aware knowledge identification method provided by the embodiments of the present application when executed by a processor.

[0256] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are merely exemplary. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0257] The units described as separate components above can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place or distributed on multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0258] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0259] Those of ordinary skill in the art can understand that all or part of the steps of the above method embodiments can be completed by a program instructing related hardware, and the foregoing program can be stored in a computer readable storage medium, and the program executes the steps of the above method embodiments when executed; and the foregoing storage medium includes mobile storage devices, ROM, RAM, magnetic disks or optical disks and various storage media that can store program codes.

[0260] Alternatively, the integrated unit of the present application, if implemented in the form of a software functional module and sold or used as an independent product, can also be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present application. The foregoing storage medium includes mobile storage devices, ROM, RAM, magnetic disks or optical disks and various storage media that can store program codes.

[0261] The above merely illustrates the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An interruption sensing and recognition method, characterized in that, include: Obtain a target user set, wherein the target user set includes at least one target user: Retrieve message records for each user on the Radius server. Each user corresponds to at least one message record, and each message record contains the message type, message timestamp, and the username corresponding to the message. Filter out Radius message records with the message type of the first message type from the message records of the Radius server to obtain all Radius message records with the message type of the first message type; The first user set is determined based on the usernames corresponding to the messages in all Radius message records of the first message type. Message records whose message timestamps are within a first preset time interval are filtered from the first user set to obtain a second user set. The first preset time interval is used to indicate the time interval of non-network change operations. Based on the second user set, a target user set is determined, wherein in the target user set, the username corresponding to each message corresponds to at least one message timestamp; Obtain the first flow rate of each target user in the target user set at the time of interruption and the first port recycling number of each target user in the target user set at the time of interruption; If the target user's first flow rate at the time of interruption is not less than the first preset flow rate, or the target user's first port recovery number at the time of interruption is not less than the first preset port number, then the target user is determined to be an interruption-aware user.

2. The method according to claim 1, characterized in that, The step of obtaining the first flow rate of each target user in the target user set at the time of interruption includes: Based on the username and message timestamp corresponding to the message in the second user set, search the message record of the Radius server for the previous message record corresponding to the username and message timestamp of the message; Obtain the first online time and first traffic of the target user in the message record of the second user set; and obtain the second online time and second traffic of the target user in the previous message record; Based on the first online time and the second online time, determine the online time difference of the target user; and based on the first traffic and the second traffic, determine the traffic difference of the target user; By comparing the flow difference with the online time difference, the first flow rate of the target user at the moment of interruption is obtained.

3. The method according to claim 2, characterized in that, The first online time and first traffic of the target user are obtained from the message records of the second user set; Before obtaining the target user's second online time and second traffic in the previous message record, the method further includes: Merge the message records in the second user set with the previous message record to obtain the third user set; Based on the username corresponding to the message, the message records in the third user set are grouped to obtain the message records of each target user at different message timestamps; The message records of each target user at different message timestamps are sorted in ascending order of message timestamps to obtain the message records of each target user sorted in ascending order of message timestamps.

4. The method according to claim 1, characterized in that, The step of obtaining the number of first port reclamations for each target user in the target user set at the time of interruption includes: Based on the username corresponding to the message in the target user set, filter out the message record of the Radius server corresponding to the username from the message record of the Radius server; Determine the NAT public port segment change value of the message record for each type of Radius server corresponding to the username; The NAT public port segment change values ​​of the message records of each type of Radius server corresponding to the username are summed to obtain the number of NAT public address ports corresponding to the username. The number of NAT public address ports corresponding to the username includes at least the number of NAT public address ports corresponding to the username at the time of interruption and the number of NAT public address ports corresponding to the username at the time before interruption. The difference between the number of NAT public network address ports corresponding to the username at the time of interruption and the number of NAT public network address ports corresponding to the username before the interruption is used to obtain the first number of ports reclaimed by the target user at the time of interruption.

5. The method according to claim 4, characterized in that, The determination of the NAT public port segment change value of the message record for each type of Radius server corresponding to the username includes: The fourth user set is obtained by determining the message record containing the second message type from the message record of the Radius server corresponding to the username; The fourth user set is grouped according to the first preset rule to obtain at least two fifth user sets. The fifth user set includes the message type and the reason type for the end of billing for each message record. Based on the message type and the billing termination reason type of each message record in the fifth user set, determine the message identifier and the billing termination reason type identifier of each message record in the fifth user set; Based on the message identifier, the billing termination reason type identifier, and the second preset rule for each message record in the fifth user set, the NAT public port segment change value of the message record of each type of Radius server corresponding to the username in the fifth user set is determined.

6. An interruption sensing and identification device, characterized in that, include: The first acquisition unit is configured to acquire a target user set, wherein the target user set includes at least one target user: Retrieve message records for each user on the Radius server. Each user corresponds to at least one message record, and each message record contains the message type, message timestamp, and the username corresponding to the message. Filter out Radius message records with the message type of the first message type from the message records of the Radius server to obtain all Radius message records with the message type of the first message type; The first user set is determined based on the usernames corresponding to the messages in all Radius message records of the first message type. Message records whose message timestamps are within a first preset time interval are filtered from the first user set to obtain a second user set. The first preset time interval is used to indicate the time interval of non-network change operations. Based on the second user set, a target user set is determined, wherein in the target user set, the username corresponding to each message corresponds to at least one message timestamp; The second acquisition unit is used to acquire the first flow rate of each target user in the target user set at the time of interruption and the first port recycling number of each target user in the target user set at the time of interruption; The determining unit is configured to determine the target user as an interruption-aware user if the target user's first flow rate at the time of interruption is not less than a first preset flow rate or the target user's first port recovery number at the time of interruption is not less than a first preset port number.

7. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 5.

9. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

Images