Terminal identity association relationship determination method and apparatus, device, and storage medium

Abstract

The application provides a terminal identification association relationship determination method and device, equipment and a storage medium, and relates to the technical field of communication. The method comprises the following steps: obtaining the terminal identification of a full-network dual-card terminal user; obtaining the WiFi address of the terminal identification logging into the network in a preset time period to form a WiFi address table, wherein the WiFi address comprises a MAC address; screening the terminal identification pairs with the same MAC address at the same time from the WiFi address table, and determining the two terminal identifications included in each terminal identification pair as the two terminal identifications corresponding to the same dual-card terminal. The technical scheme provided by the application can accurately identify the corresponding relationship of the two terminal identifications of the partial in-network dual-card terminal by using the characteristic that the WiFi addresses of the two terminal identifications corresponding to the same dual-card terminal are the same.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a method for determining terminal identifier association, a device for determining terminal identifier association, a computer device, and a computer-readable storage medium. Background Technology

[0002] As communication technology matures and the demographic dividend expires, telecom operators are increasingly focusing on competing for existing customers. Currently, dual-SIM dual-standby phones are the most common, allowing multiple operators' SIM cards to be inserted into a single device. Identifying whether a phone is fully populated with SIM cards from one operator or shares the same SIM card slots with other operators is an unavoidable aspect of operators' SIM card slot management business.

[0003] Dual-SIM terminals have two SIM card slots, each corresponding to a unique IMEI (International Mobile Equipment Identity) to distinguish between the two slots. In a communication network, each slot functions as an independent terminal device. However, operators cannot directly determine which two IMEIs belong to the same terminal based on the terminal's network registration information, thus making it impossible to obtain the IMEI data of dual-SIM terminals currently in service.

[0004] To determine which two IMEIs correspond to the same dual-SIM terminal, the following solutions have been proposed:

[0005] Operators accumulate user data over a period of time to analyze user movement trajectories and compare whether these trajectories overlap or are similar. This allows them to determine which two IMEIs correspond to the same dual-SIM device based on the terminal's location. However, this method requires monitoring all IMEIs on the network for a considerable period and mapping all user movement trajectories before comparison. However, it cannot accurately distinguish between groups with similar movement trajectories (e.g., university students living in the same building). Furthermore, some dual-SIM devices may have their two SIM card slots mounted on base stations of different network standards (2G / 3G / 4G / 5G). Since different network standards have different cell coverage areas and location standards, determining the location of dual-SIM devices can lead to significant errors. Therefore, comparing user movement trajectories not only rarely identifies the two IMEIs of the same dual-SIM device, but also has a high probability of misjudgment, resulting in low accuracy.

[0006] The association between IMEIs is determined based on the characteristics of switching between two SIM cards in different slots, having the same operator registration name, and not being able to make voice calls in both slots at the same time. However, the slot characteristics used by these methods are not universal. For example, the occurrence of situations such as switching slots, having the same registration name, and having a call coming in while the SIM card in one slot is making a call is relatively random. Therefore, these methods can rarely accurately identify the two IMEIs of the same dual-SIM terminal. Summary of the Invention

[0007] This invention was completed to at least partially solve the technical problem in the prior art that operators cannot accurately obtain the IMEI data of dual-SIM terminals on the network.

[0008] According to one aspect of the present invention, a method for determining terminal identifier association is provided, the method comprising:

[0009] Obtain the terminal identifier of all dual-SIM terminal users across the network;

[0010] Obtain the WiFi addresses of the terminal identifier that logged into the network within a preset time period, and form a WiFi address table, wherein the WiFi addresses include MAC addresses; and,

[0011] Filter out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, and determine the two terminal identifiers in each terminal identifier pair as the two terminal identifiers corresponding to the same dual-SIM terminal.

[0012] Optionally, after filtering out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, the method further includes:

[0013] Each terminal identifier pair is checked to see if each of the two terminal identifiers in the pair corresponds to a user of this operator.

[0014] If both terminal identifiers in a certain terminal identifier pair correspond to users of this operator, the terminal identifier pair is stored in the first result table.

[0015] If, in response to a terminal identifier pair containing only one of the two terminal identifiers, the terminal identifier pair corresponds to a user of this operator, the terminal identifier pair is stored in the second result table.

[0016] Optionally, obtaining the WiFi addresses of the terminal identifiers that logged into the network within a preset time period to form a WiFi address table includes:

[0017] Based on the access information of the operator's smart gateway, the terminal identifiers and corresponding MAC addresses and IP addresses of all dual-SIM terminals accessing each smart gateway within a preset time period are obtained, resulting in the MAC address-terminal identifier-IP address mapping relationship, and a WiFi address table is formed based on all obtained MAC address-terminal identifier-IP address mapping relationships; and / or,

[0018] Using fixed-line deep packet inspection technology, application information passing through the operator's fixed-line network within a preset time period is identified. This application information includes terminal identifiers, thereby obtaining the MAC address-terminal identifier-IP address mapping relationship, and forming a WiFi address table based on all obtained MAC address-terminal identifier-IP address mapping relationships; and / or,

[0019] This operator's service application obtains the terminal identifiers and corresponding MAC addresses and IP addresses of dual-SIM terminal users within a preset time period, generates the MAC address-terminal identifier-IP address mapping, and forms a WiFi address table based on all obtained MAC address-terminal identifier-IP address mappings; and / or,

[0020] By obtaining the terminal identifier and corresponding MAC address and IP address of dual-SIM terminal users within a preset time period through the official website of this operator, the mapping relationship between MAC address, terminal identifier and IP address is obtained, and a WiFi address table is formed based on all the obtained mapping relationships between MAC address, terminal identifier and IP address.

[0021] Optionally, the method further includes:

[0022] After obtaining the IP address corresponding to the terminal identifier, check whether the fixed network IP address is an IPv6 address or an IPv4 address;

[0023] In response to the fact that the fixed network IP address is an IPv6 address, all obtained MAC address-terminal identifier-IPv6 address mappings are placed into the WiFi address table;

[0024] In response to the fact that the fixed network IP address is an IPv4 address, all the obtained MAC address-terminal identifier-IPv4 address correspondences are placed into a preparatory table. From the preparatory table, IPv4 addresses that correspond to the same MAC address and appear more than a preset number of times at different times are selected as the determined IPv4 addresses. All MAC address-terminal identifier-determined IPv4 address correspondences are then placed into the WiFi address table.

[0025] Optionally, the method further includes:

[0026] The location information and traffic usage information of the terminal identifier within a preset time period are obtained, as well as the terminal model of the terminal identifier, and a location table, a traffic usage table, and a terminal model table are formed respectively.

[0027] After filtering out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, the remaining terminal identifiers are stored in the first intermediate table.

[0028] Based on the location table and the terminal model table, the terminal identifiers in the first intermediate table are grouped, and terminal identifiers with the same location information and the same terminal model at the same time are grouped into the same group; and...

[0029] For cases where each group contains only one terminal identifier, the dual-SIM terminal containing that single terminal identifier is identified as a dual-SIM terminal with only one SIM card from this operator installed. For cases where each group contains two terminal identifiers, the dual-SIM terminal containing both terminal identifiers is identified as a dual-SIM terminal with at least one SIM card from this operator installed. For cases where each group contains more than two terminal identifiers, based on the data usage table, terminal identifiers whose data usage time overlaps with the other terminal identifiers in the same group are selected from the group, and the dual-SIM terminal containing the selected terminal identifiers is identified as a dual-SIM terminal with only one SIM card from this operator installed.

[0030] Optionally, obtaining the location information of the terminal identifier within a preset time period to form a location table includes:

[0031] Obtain the location information of the terminal identifier within a preset time period, and randomly select N1 days from the location information for sampling;

[0032] In each sampling day, select the location and corresponding time period where each terminal identifier has the longest occurrence time within a given time period to obtain the correspondence between terminal identifier, location, and location time period; and,

[0033] A location table is formed based on the obtained correspondence between all terminal identifiers, locations, and location time periods.

[0034] Optionally, obtaining the traffic usage information of the terminal identifier within a preset time period to form a traffic usage table includes:

[0035] Obtain the traffic usage information of the terminal identifier within a preset time period, and randomly select N2 days from the traffic usage information for sampling;

[0036] Record the time periods for each terminal identifier's traffic usage on each sampling day to obtain the correspondence between terminal identifier and traffic time period; and,

[0037] A traffic usage table is generated based on the obtained correspondence between all terminal identifiers and traffic time periods.

[0038] Optionally, after grouping terminal identifiers with the same location information and terminal model at the same time into the same group, the method further includes:

[0039] Store the packets containing only one terminal identifier into the second intermediate table;

[0040] According to the first filtering rule, a portion of terminal identifiers are selected from the second intermediate table and stored in the second result table. The first filtering rule is to filter terminal identifiers corresponding to dual-SIM terminal users who have not used data traffic and voice within a period exceeding a first preset time threshold; and / or,

[0041] According to the second filtering rule, a portion of terminal identifiers are selected from the second intermediate table and stored in the second result table. The second filtering rule is to select terminal identifiers that have re-accessed the base station cell after disappearing from the access base station cell for no more than a second preset time threshold; and / or,

[0042] According to the third filtering rule, some terminal identifiers are selected from the second intermediate table and stored in the second result table. The third filtering rule is to filter terminal identifiers that have not used the operator's network traffic at all for a period of time exceeding the third preset time threshold, but have used the operator's network traffic normally for the rest of the time.

[0043] The dual-SIM terminal containing the terminal identifier stored in the second result table is identified as a dual-SIM terminal with one user identity card from this operator and one user identity card from another operator installed; and,

[0044] After filtering over a preset period, the remaining terminal identifiers in the second intermediate table are stored in the third result table, and the dual-SIM terminal containing the terminal identifier stored in the third result table is identified as a dual-SIM terminal with one user identification card of this operator installed and the other card slot not inserted.

[0045] Optionally, after grouping terminal identifiers with the same location information and terminal model at the same time into the same group, the method further includes:

[0046] Store the group containing the two terminal identifiers into the third intermediate table;

[0047] Based on the traffic usage table, groups with completely non-overlapping traffic usage times for two terminal identifiers within the same group are selected from the third intermediate table; and...

[0048] The filtered groups are stored in the first result table, and the remaining groups in the third intermediate table are stored in the second result table. The first result table stores groups whose two terminal identifiers both correspond to users of this operator, and the second result table stores groups whose two terminal identifiers correspond to users of this operator only one.

[0049] Optionally, after grouping terminal identifiers with the same location information and terminal model at the same time into the same group, the method further includes:

[0050] Packets containing more than two terminal identifiers are stored in the fourth intermediate table;

[0051] Based on the traffic usage table, select terminal identifiers whose traffic usage time overlaps with the other terminal identifiers in the same group from the fourth intermediate table, and store the selected terminal identifiers into the second intermediate table.

[0052] Obtain the ID number and corresponding terminal identifier registered by dual-SIM terminal users when they conduct business with this operator, and form a table of registered user ID numbers; and,

[0053] Based on the registrant ID number table, at least two terminal identifiers corresponding to the same registrant ID number are selected from the remaining terminal identifiers in the fourth intermediate table, and the selected terminal identifiers are stored in the first result table.

[0054] According to another aspect of the present invention, a terminal identifier association determination device is provided, the device comprising:

[0055] The first acquisition module is configured to acquire the terminal identifier of all dual-SIM terminal users across the network.

[0056] The second acquisition module is configured to acquire the WiFi addresses of the network logged into by the terminal identifier within a preset time period, forming a WiFi address table, wherein the WiFi addresses include MAC addresses; and

[0057] The filtering module is configured to filter out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, and to determine the two terminal identifiers included in each pair of terminal identifiers as two terminal identifiers corresponding to the same dual-SIM terminal.

[0058] According to another aspect of the present invention, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the aforementioned terminal identifier association determination method.

[0059] According to another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the processor performs the aforementioned terminal identifier association determination method.

[0060] The technical solution provided by this invention may include the following beneficial effects:

[0061] The terminal identifier association determination method provided by this invention utilizes the characteristic that the two terminal identifiers corresponding to the same dual-SIM terminal have the same WiFi address when logging into the network. First, the WiFi address table formed within a preset time period is statistically analyzed. If it is found that the same MAC address corresponds to two different terminal identifiers at the same time, then these two terminal identifiers are considered to correspond to the same dual-SIM terminal. According to this rule, multiple terminal identifier pairs with the same MAC address are selected from the terminal identifiers of dual-SIM terminal users across the entire network. Each terminal identifier pair includes two terminal identifiers that correspond to the same dual-SIM terminal, thereby accurately identifying the correspondence between the two terminal identifiers of some dual-SIM terminals on the network.

[0062] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0063] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0064] Figure 1 A flowchart illustrating a method for determining terminal identifier association relationships provided in an embodiment of the present invention;

[0065] Figure 2 A flowchart illustrating another method for determining terminal identifier association provided in an embodiment of the present invention;

[0066] Figure 3 This is a schematic diagram of the terminal identifier association determination device provided in an embodiment of the present invention;

[0067] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the specific implementation methods of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific implementation methods described herein are for illustration and explanation only and are not intended to limit the present invention.

[0069] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence; furthermore, in the absence of conflict, the embodiments and features in the embodiments of this invention can be arbitrarily combined with each other. In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the convenience of describing this invention and has no specific meaning in itself. Therefore, "module," "part," or "unit" can be used interchangeably.

[0070] The inventors discovered that, within the service resources of an operator's network, determining which two IMEIs correspond to the same dual-SIM terminal can be based on the following dimensions: being in the same location within the same time period, having the same terminal model, having the same WiFi address when logging into the network (if it is IPv4, then within the same time period; if it is IPv6, then not within the same time period), having different traffic volumes within the same time period, and having the same ID number registered when handling the business.

[0071] The above dimensions are categorized as follows:

[0072] 1) Determining factors: These are the factors that can determine whether two IMEIs belong to the same dual-SIM terminal, including location, terminal model, WiFi address, and data usage.

[0073] Determinants can be further divided into positive determinants and negative determinants.

[0074] Positive determinant factors: location, device model, and WiFi address, which can be used to positively filter IMEIs that may belong to the same dual-SIM device.

[0075] Negative determining factor: Using data traffic can be used to determine which two IMEIs do not belong to the same dual-SIM terminal.

[0076] 2) Ambiguous factors: Although the registrant's ID number and frequently used contact person cannot completely determine which two IMEIs belong to the same dual-SIM terminal, the probability that two IMEIs with the same factor belong to the same dual-SIM terminal is relatively high. This can be used to confirm IMEIs that cannot be identified by the determined factors.

[0077] The factors used to confirm the association between terminal identifiers are divided into two dimensions: definite factors and fuzzy factors. Deterministic factors are fixed and can determine the association between terminal identifiers, but they are group-oriented. Fuzzy factors include user behavior, which can only vaguely confirm the association between terminal identifiers and are specific. Using both dimensions together for mutual confirmation can achieve better results.

[0078] In order to overcome the shortcomings of the existing technology, the present invention provides a technical solution that can obtain the IMEI association relationship of dual-SIM terminals on the network more accurately and comprehensively based on the above-mentioned factors. The following is a detailed description through specific embodiments.

[0079] Figure 1 This is a flowchart illustrating a method for determining the association relationship of terminal identifiers according to an embodiment of the present invention. The method is applied to an operator platform. Operators establish the correspondence between terminals and users through IMEI (International Mobile Equipment Identity), IMSI (International Mobile Subscriber Identity), and telephone numbers. Each dual-SIM terminal includes two card slots, each slot corresponding to one IMEI. Each SIM card inserted into one slot corresponds to one IMSI. Each SIM card is assigned a telephone number when purchased by the user, and all corresponding user information is entered into the operator's system. However, in practical applications, the IMEI registered by a dual-SIM terminal can only be the IMEI of the primary SIM card. Therefore, operators cannot obtain the IMEI data of dual-SIM terminals already in operation based solely on the registered data. This invention comprehensively considers the shortcomings of existing solutions and proposes a more accurate and comprehensive implementation scheme for confirming the correspondence between the two IMEIs of a dual-SIM terminal.

[0080] like Figure 1 As shown, the method includes the following steps S101 to S103.

[0081] S101. Obtain the terminal identifier of all dual-SIM terminal users across the network.

[0082] The terminal identifier can be an IMEI. Since each of the two SIM card slots in a dual-SIM terminal corresponds to a unique IMEI across the entire network, the two SIM card slots of the dual-SIM terminal can be effectively distinguished. Of course, in addition to the IMEI, the terminal identifier can also be other identification information that can distinguish the two SIM card slots of a dual-SIM terminal, and this invention does not impose any restrictions on this.

[0083] Before a terminal leaves the factory, each of the two SIM card slots of a dual-SIM terminal is assigned a unique IMEI across the entire network. By collecting and analyzing terminal data from the terminal manufacturer, the terminal identifiers of all dual-SIM terminal users across the entire network can be obtained. Of course, the terminal identifiers of all dual-SIM terminal users across the entire network can also be obtained through other means.

[0084] S102. Obtain the WiFi (Wireless Fidelity) addresses of the network logged in by the terminal identifier within a preset time period, and form a WiFi address table. The WiFi addresses include MAC addresses (Media Access Control Address, also known as LAN addresses).

[0085] The preset time period can be set and adjusted by those skilled in the art according to actual needs; for example, it can be set to 1 month, 2 months, or 3 months. After collecting the WiFi addresses of terminal identifiers of all dual-SIM terminal users across the network within the preset time period, the data in this dimension is appropriately processed to obtain the terminal identifier-WiFi address correspondence, and then stored in the WiFi address table in the database.

[0086] S103. Filter out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, and determine the two terminal identifiers included in each pair of terminal identifier pairs as two terminal identifiers corresponding to the same dual-SIM terminal.

[0087] In this embodiment, taking advantage of the fact that the two terminal identifiers corresponding to the same dual-SIM terminal have the same WiFi address when logging into the network, the WiFi address table formed within a preset time period is first statistically analyzed. If it is found that the same MAC address corresponds to two different terminal identifiers at the same time, it is considered that these two terminal identifiers correspond to the same dual-SIM terminal. According to this rule, multiple terminal identifier pairs with the same MAC address are selected from the terminal identifiers of dual-SIM terminal users across the entire network. Each pair of terminal identifiers includes two terminal identifiers that correspond to the same dual-SIM terminal, thereby accurately identifying the correspondence between the two terminal identifiers (IMEI) of some dual-SIM terminals on the network.

[0088] In one specific embodiment, steps S104 to S106 are further included after step S103.

[0089] S104. Detect whether each pair of terminal identifiers corresponds to a user of this operator;

[0090] S105. In response to a terminal identifier pair containing two terminal identifiers that both correspond to users of this operator, store the terminal identifier pair in the first result table (i.e., ...). Figure 2 The results are in Table D).

[0091] S106. In response to the fact that only one of the two terminal identifiers in a certain terminal identifier pair corresponds to a user of this operator, the terminal identifier pair is stored in the second result table (i.e., ...). Figure 2 Results Table A).

[0092] In this embodiment, after screening out terminal identifier pairs with the same MAC address, it can be determined that each of these terminal identifier pairs corresponds to the same dual-card terminal. At this time, it is further required to determine whether each of the two terminal identifiers included in each terminal identifier pair corresponds to a user of the local operator. If both of the two terminal identifiers included in a certain terminal identifier pair correspond to users of the local operator, that is, the two card slots corresponding to the two terminal identifiers are both inserted with Subscriber Identity Module (SIM) cards of the local network, the terminal identifier pair is stored in the result table D; if only one of the two terminal identifiers included in a certain terminal identifier pair corresponds to a user of the local operator, and the other terminal identifier corresponds to a user of another operator, that is, the two Subscriber Identity Modules inserted into the two card slots corresponding to the two terminal identifiers belong to different operators, one is a local network Subscriber Identity Module, and the other is an off-network Subscriber Identity Module, the terminal identifier pair is stored in the result table A. The local operator can carry out subsequent marketing services in a targeted manner according to the data recorded in the result table A and the result table D.

[0093] In a specific implementation, step S102 specifically includes any one or more of the following steps S102a to S102d.

[0094] S102a. Obtain, based on the access information of the smart gateway of the local operator, the terminal identifiers, corresponding MAC addresses and IP addresses (Internet Protocol Address) of all dual-card terminals accessing each smart gateway within a preset time period, so as to obtain a MAC address - terminal identifier - IP address correspondence, and form a WiFi address table based on all the obtained MAC address - terminal identifier - IP address correspondences.

[0095] In this step, the smart gateway is a type of network device, which is the key to the intelligence of the local area network, and generally supports virtual network access, WiFi access, wired broadband access, etc. Through the smart gateway, functions such as information collection, information input, information output, centralized control, remote control, and linkage control of various devices in the local area network including sensors, network devices, cameras, and hosts can be realized. The smart gateways of some manufacturers can obtain the terminal identifier (IMEI) of the device accessing the gateway.

[0096] S102b. Use the fixed network deep packet inspection technology to identify the application information passing through the fixed network of the local operator within the preset time period, where the application information includes the terminal identifier, so as to obtain the MAC address - terminal identifier - IP address correspondence, and form a WiFi address table based on all the obtained MAC address - terminal identifier - IP address correspondences.

[0097] In this step, fixed-line deep packet inspection (DPI) technology is used. DPI is an application-layer traffic detection and control technology that analyzes traffic and packet content at key points in the network to identify various applications (APPs) and their content. Therefore, fixed-line DPI technology can identify application information passing through the operator's fixed-line network. Many terminal applications can obtain the IMEI of their respective terminals and upload application information containing the IMEI to the server. The server can then use fixed-line DPI technology to obtain the IMEI and MAC address of some terminals under a specific IP address, thus obtaining the MAC address-terminal identifier-IP address mapping and forming a WiFi address table.

[0098] S102c. Obtain the terminal identifier and corresponding MAC address and IP address of dual-SIM terminal users within a preset time period through the operator's business processing application, obtain the MAC address-terminal identifier-IP address correspondence, and form a WiFi address table based on all obtained MAC address-terminal identifier-IP address correspondences.

[0099] In this step, the IP address and MAC address of the dual-SIM terminal user's device identifier can be obtained using an application (such as a mobile service portal) developed by the operator to facilitate user transactions. Specifically, when a user applies for a service, they log in to the operator's service application using their mobile phone number. The application can then obtain the device identifier (IMEI), IP address, and MAC address of the user's dual-SIM terminal.

[0100] Currently, apart from system-level applications, general applications can only obtain the IMEI of the SIM card slot where the user has set the data SIM card (also known as a data SIM card). If the user switches the data SIM card, the IMEI of the other SIM card slot can be obtained. Therefore, after a period of time, the two IMEIs corresponding to the two SIM card slots of the same dual-SIM terminal can be obtained under a certain WiFi address.

[0101] S102d. Obtain the terminal identifier and corresponding MAC address and IP address of dual-SIM terminal users within a preset time period through the official website of this operator's business processing, obtain the MAC address-terminal identifier-IP address correspondence, and form a WiFi address table based on all obtained MAC address-terminal identifier-IP address correspondences.

[0102] In this step, the IP address and MAC address of the dual-SIM terminal user's device identifier can be obtained from the official website of this operator. Specifically, when logging in on the mobile phone, the browser sends a message to the server containing the browser type. When applying for services, the user logs in to the official website of this operator using their mobile phone number. The website server can then obtain the device identifier (IMEI), IP address, and MAC address of the dual-SIM terminal held by the logged-in user, and select the user with the local IP address from among them.

[0103] Of course, the method in step S102d requires 2-3 verifications, because the terminal used by the user to log in to the official website of this operator's business may not be the same terminal as the terminal with the login number. You can select 2-3 times the data with the same login number and IP address, and then match the login number with the terminal identifier (IMEI) to obtain a more accurate MAC address-terminal identifier-IP address correspondence.

[0104] In this embodiment, one or more of the methods for obtaining terminal identifiers under WiFi addresses in steps S102a to S102d can be selected according to actual needs to obtain the correspondence between WiFi addresses and the terminal identifiers appearing under the corresponding WiFi addresses, thereby obtaining a WiFi address table. Of course, the WiFi address field of terminal identifiers not in the fixed network (which can be simply referred to as "this network") of this operator is recorded as NULL.

[0105] In one specific embodiment, step S102 further includes the following steps S102e to S102g.

[0106] S102e. After obtaining the IP address corresponding to the terminal identifier through any one or more of steps S102a to S102d, detect whether the fixed network IP address is an IPv6 address or an IPv4 address.

[0107] Fixed-line IP addresses are divided into two types: IPv6 addresses and IPv4 addresses. IPv4 is short for Internet Protocol version 4, also known as the fourth version of the Internet Protocol, and is the fourth revision in the development of the Internet Protocol. IPv6 is short for Internet Protocol version 6, also known as the sixth version of the Internet Protocol, and is the next-generation IP protocol designed by the Internet Engineering Task Force (IETF) to replace IPv4.

[0108] Currently, there are two fixed network access methods: IPv4 addresses and IPv6 addresses. IPv4 addresses are dynamically assigned, while IPv6 addresses are fixed. Therefore, they need to be processed separately. The following steps S102f and S102g describe them respectively.

[0109] S102f. In response to the fact that the fixed network IP address is an IPv6 address, put all the obtained MAC address-terminal identifier-IPv6 address correspondences into the WiFi address table.

[0110] In this embodiment, the IPv6 address is processed by directly placing all the MAC address-terminal identifier-IPv6 address correspondences obtained by the methods described in steps S102a to S102d above into the WiFi address table.

[0111] S102g. In response to the fact that the fixed network IP address is an IPv4 address, all the obtained MAC address-terminal identifier-IPv4 address correspondences are placed into a preparatory table. From the preparatory table, IPv4 addresses that correspond to the same MAC address and appear more than a preset number of times at different times are selected as determined IPv4 addresses. All MAC address-terminal identifier-determined IPv4 address correspondences are placed into the WiFi address table.

[0112] In this embodiment, the processing method for IPv4 addresses is as follows: First, all MAC address-terminal identifier-IPv4 address correspondences obtained through the methods described in steps S102a to S102d are placed into a preliminary table. Since IPv4 addresses change dynamically, it is necessary to identify which IPv4 addresses appearing on different dates within a preset time period belong to the same physical gateway (MAC). Then, IPv4 addresses appearing multiple times under the same MAC address within that time period are selected. If they are under the same MAC address, these IPv4 addresses are considered to belong to the same physical gateway. These IPv4 addresses are then used as the basis for statistical analysis of the IPv4 addresses and the terminal identifiers (IMEIs) that have appeared at the corresponding time. Finally, all the statistically analyzed MAC address-terminal identifier-IPv4 address correspondences are placed into a WiFi address table.

[0113] In one specific embodiment, steps S107A to S107C are included before step S103.

[0114] S107A. Obtain the location information of the terminal identifier within a preset time period and form a location table.

[0115] In this step, the operator obtains the location corresponding to each terminal identifier within a preset time period, forming a terminal identifier-location-location time period correspondence table (i.e., location table).

[0116] S107B. Obtain the traffic usage information of the terminal identifier within a preset time period and form a traffic usage table.

[0117] In this step, the operator obtains the traffic usage information corresponding to each terminal identifier within a preset time period, forming a terminal identifier-traffic usage time period correspondence table (i.e., traffic usage table).

[0118] S107C. Obtain the terminal model of the terminal identifier and form a terminal model table.

[0119] In this step, the operator obtains the terminal model corresponding to each terminal identifier, forming a terminal identifier-terminal model correspondence table (i.e., a terminal model table). The terminal models corresponding to the two terminal identifiers (IMEIs) of the same dual-SIM terminal must be the same.

[0120] In this embodiment, after obtaining the terminal identifier of all dual-SIM terminal users across the network, data can be collected on the location, terminal model, WiFi address, and traffic of all dual-SIM terminal users across the network. After appropriate processing, the data is stored in the corresponding data table in the database for subsequent use. The data granularity can be 1 month, 2 months, or 3 months.

[0121] Accordingly, steps S108 to S112 are included after step S103.

[0122] S108. After filtering out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, store the remaining terminal identifiers into the first intermediate table (i.e., Figure 2 Intermediate table F in the middle;

[0123] S109 Groups the terminal identifiers in the first intermediate table based on the location table and the terminal model table, and groups terminal identifiers that have the same location information and the same terminal model at the same time into the same group.

[0124] S110. For cases where each group contains only one terminal identifier, the dual-SIM terminal containing the terminal identifier is determined to be a dual-SIM terminal with only one user identification card of this operator installed.

[0125] S111. For cases where each group contains two terminal identifiers, the dual-SIM terminal containing the two terminal identifiers is determined to be a dual-SIM terminal with at least one user identification card of this operator installed.

[0126] S112. For cases where each group contains more than two terminal identifiers, based on the traffic usage table, select terminal identifiers whose traffic usage time overlaps with the other terminal identifiers in the same group, and determine the dual-SIM terminal containing the selected terminal identifier as a dual-SIM terminal with only one user identification card of this operator installed.

[0127] In this embodiment, after using one of the positive factors, the "WiFi address table", to initially filter the terminal identifiers of all dual-SIM terminal users in the network, the remaining terminal identifiers after the initial screening are stored in the intermediate table F. Then, the other positive factors, the "location table" and the "terminal model table", are used to group the terminal identifiers in the intermediate table F, and the terminal identifiers that have the same location information and the same terminal model at the same time are grouped into the same group. If the number of terminal identifiers in a certain group is equal to 1, then the dual-SIM terminal containing that terminal identifier is determined to be a dual-SIM terminal with only one user identification card (SIM card) installed in the same operator. One SIM card slot in this dual-SIM terminal contains the same operator's SIM card, while the other SIM card slot may contain a different operator's SIM card or be empty. If the number of terminal identifiers in a certain group is equal to 2, it means that the two terminal identifiers in this group correspond to the same dual-SIM terminal. Therefore, the dual-SIM terminal containing both terminal identifiers in this group is determined to be a dual-SIM terminal with at least one user identification card (SIM card) installed in the same operator. One SIM card slot in this dual-SIM terminal contains the same operator's SIM card, while the other SIM card slot may contain either the same operator's SIM card or a different operator's SIM card. If the number of terminal identifiers in a certain group is greater than 2, then based on the traffic usage table, terminal identifiers whose traffic usage time overlaps with the other terminal identifiers in the same group are selected from this group. The dual-SIM terminal containing the selected terminal identifier is determined to be a dual-SIM terminal with only one user identification card (SIM card) installed in the same operator's SIM card slot.

[0128] In one specific embodiment, step S107A specifically includes the following steps A1 to A3.

[0129] A1. Obtain the location information of the terminal identifier within a preset time period, and randomly select N1 days from the location information for sampling;

[0130] A2. Select the location and corresponding time period with the longest time for each terminal identifier in a time period in each sampling day to obtain the correspondence between terminal identifier, location and location time period;

[0131] A3. Form a location table based on the obtained correspondence between all terminal identifiers, locations, and location time periods.

[0132] In this embodiment, the locations of all terminal identifiers within a preset time period are statistically analyzed. Then, N1 days (which can be adjusted according to the required accuracy) are randomly selected from the preset time period for sampling. On each sampling day, the location and corresponding time period with the longest duration of each terminal identifier are selected for a certain time period. The time periods selected on each sampling day are different. For example, the time period from 10:00 to 20:00 on one sampling day is selected, while the time period from 11:00 to 22:00 on another sampling day is selected. It can be seen that not only do the time periods selected on each sampling day not completely overlap, but their durations can also be different. Furthermore, the duration of the time periods selected on each sampling day should not be too short, for example, not less than 2 hours. The location with the longest duration of terminal identifiers is selected to reduce the calculation error in subsequent steps. The granularity of the time period corresponding to this location can be down to the hour, and the location can be represented by longitude and latitude, thus forming a correspondence between terminal identifier - longitude - latitude - location start time - location end time.

[0133] Taking N1 = 3 days as an example, the location table obtained for a certain IMEI is shown in Table 1 below.

[0134] Table 1

[0135]

[0136] Since the two SIM card slots of a dual-SIM terminal may reside in different network standards, and operators often use the base station triangulation method to calculate the latitude and longitude of the terminal, the positioning accuracy may vary due to the differences between 4G / 5G base stations. Therefore, this invention suggests reducing the precision of latitude and longitude to accommodate the positioning deviations of base stations with different network standards.

[0137] In one specific embodiment, step S107B specifically includes the following steps B1 to B3.

[0138] B1. Obtain the traffic usage information of the terminal identifier within a preset time period, and randomly select N2 days from the traffic usage information for sampling;

[0139] B2. Record the time period for each terminal identifier to use traffic in each sampling day, and obtain the correspondence between terminal identifier and traffic time period;

[0140] B3. Generate a traffic usage table based on the obtained correspondence between all terminal identifiers and traffic time periods.

[0141] The user needs to configure which SIM card a dual-SIM terminal uses for data transmission. Only one SIM card can generate data traffic at a time on the same dual-SIM terminal, corresponding to the IMEI of that SIM slot. If two IMEIs generate data traffic simultaneously, it indicates that they are not on the same dual-SIM terminal.

[0142] In this embodiment, the traffic usage information of all terminal identifiers within a preset time period is statistically analyzed. Then, N2 days (which can be adjusted according to the accuracy requirements) are randomly selected from the preset time period for sampling. The mobile network traffic corresponding to each terminal identifier in each sampling day is statistically analyzed to form a correspondence between terminal identifier, traffic start time, and traffic end time.

[0143] The following table, Table 2, shows the traffic usage for a specific IMEI, with N2 = 3 days as an example.

[0144] Table 2

[0145]

[0146]

[0147] In one specific embodiment, steps S113 to S118 are further included after step S109.

[0148] S113. Store the packet containing only one terminal identifier into the second intermediate table (i.e. Figure 2 (intermediate table G in the middle);

[0149] S114. According to the first filtering rule, select a portion of terminal identifiers from the second intermediate table and store them in the second result table (i.e., ...). Figure 2 In the result table A), the first filtering rule is to filter the terminal identifiers corresponding to dual-SIM terminal users who have not used data traffic and voice within a time exceeding the first preset time threshold.

[0150] S115. Select some terminal identifiers from the second intermediate table and store them in the second result table according to the second filtering rule. The second filtering rule is to filter terminal identifiers that have re-accessed the base station cell after the time they disappeared from the access base station cell does not exceed the second preset time threshold.

[0151] S116. Select some terminal identifiers from the second intermediate table and store them in the second result table according to the third filtering rule. The third filtering rule is to filter terminal identifiers that have not used the operator's network traffic at all for a period of time exceeding the third preset time threshold, but have used the operator's network traffic normally for the rest of the time.

[0152] S117. The dual-SIM terminal containing the terminal identifier stored in the second result table is determined to be a dual-SIM terminal with one user identity card of this operator and one user identity card of another operator installed.

[0153] S118. After filtering according to a preset period, store the remaining terminal identifiers in the second intermediate table into the third result table (i.e., Figure 2 The result table H) is used to determine the dual-SIM terminal where the terminal identifier stored in the third result table is located. The dual-SIM terminal is defined as having one user identification card of this operator installed and the other card slot not inserted.

[0154] It should be noted that one or more of the above steps S114, S115, and S116 can be executed according to actual needs. The first, second, and third preset time thresholds can be set and adjusted by those skilled in the art according to actual needs, and the present invention does not limit their specific values.

[0155] In this embodiment, after grouping the terminal identifiers in the intermediate table F, if the number of terminal identifiers in a certain group is equal to 1, then the terminal identifiers of that group are stored in the intermediate table G. This indicates that only one card slot in a dual-SIM terminal has a user identification card of this operator installed. Therefore, no other related terminal identifier can be found. Then, the other card slot may have a user identification card of another operator installed (i.e., a user identification card from another network), or it may not have a card inserted. The method described in steps S114, S115 and S116 can be used for further filtering. Specifically, for dual-SIM terminal users who haven't used data or voice for a long time, it's highly likely that the dual-SIM terminal still has a SIM card used to carry services. Therefore, this part of the terminal identifier is stored in result table A. For base station cells with confirmed good signal strength, if a terminal identifier (let's say terminal identifier 1) suddenly disappears from the base station cell after accessing it and then re-accesses it, and this happens multiple times, it indicates that in the two SIM card slots of the dual-SIM terminal containing terminal identifier 1, the SIM card inserted in the slot corresponding to the other terminal identifier (let's say terminal identifier 2) is occupying the terminal's radio frequency due to a call, causing the SIM card corresponding to terminal identifier 1 to lose signal strength. If the SIM card inserted into the SIM card slot cannot receive broadcast messages sent by the base station, then this terminal identifier 1 is also stored in result table A. Compare the data usage of the SIM cards corresponding to each terminal identifier in intermediate table G within a preset time period. For terminal identifiers that have no data usage on their own network for a certain period (e.g., several days) but use their own network data normally for the rest of the time (e.g., N3 days in a month with no periodicity) and normal data usage on the rest of the time), it indicates that the dual-SIM terminal containing these terminal identifiers likely also has a SIM card from another network installed. Therefore, this terminal identifier is also stored in result table A. The resulting result table A shows that the dual-SIM terminal containing the terminal identifier has one SIM card from their own network and one SIM card from another network installed.

[0156] Since the situations corresponding to the above three screening methods may not necessarily appear in a single dual-SIM terminal in a short period of time, the probability of these situations appearing in the same dual-SIM terminal can be increased by extending the observation period. Therefore, terminal identifiers that cannot be determined after the first screening using the above three methods can be stored in intermediate table I. After a period of data accumulation, the terminal identifiers in intermediate table I will be screened again using the above three methods, and the terminal identifiers that meet the above screening rules will be stored in result table A. After multiple periods of screening, the remaining terminal identifiers will be stored in result table H. The dual-SIM terminal containing the terminal identifier recorded in result table H has a user identification card installed in the card slot corresponding to the terminal identifier, while the other card slot is empty.

[0157] In one specific embodiment, steps S119 to S121 are further included after step S109.

[0158] S119. Store the packet containing two terminal identifiers into the third intermediate table (i.e. Figure 2 Intermediate table B in the middle;

[0159] S120. Based on the traffic usage table, filter out groups from the third intermediate table where the traffic usage times of two terminal identifiers under the same group do not overlap completely;

[0160] S121. Store the filtered groups into the first result table (i.e., ...). Figure 2 The remaining groups from the third intermediate table are stored in the second result table (i.e., the result table D), and the result table D is stored in the second result table (i.e., the result table D). Figure 2 The result table A in the middle, wherein the first result table stores groups in which both terminal identifiers correspond to users of this operator, and the second result table stores groups in which only one of the two terminal identifiers corresponds to users of this operator.

[0161] In this embodiment, after grouping the terminal identifiers in intermediate table F, if the number of terminal identifiers in a certain group is equal to 2, the terminal identifiers of that group are stored in intermediate table B, indicating that at least one card slot in a dual-SIM terminal has a user identification card from this operator installed. For further identification, the terminal identifiers in intermediate table B need to be filtered using a negative factor, the "traffic table." Specifically, the traffic usage time of two terminal identifiers under the same group in intermediate table B is compared, and groups with completely non-overlapping traffic usage times under the same group are selected from intermediate table B. The two terminal identifiers corresponding to the selected groups are then stored in result table D, while the two terminal identifiers corresponding to the remaining groups are stored in result table A. The two user identification cards inserted into the two card slots corresponding to the two terminal identifiers of the group stored in result table A belong to different operators: one is a user identification card from this network, and the other is a user identification card from a different network. The two card slots corresponding to the two terminal identifiers of the group stored in result table D both contain user identification cards from this network.

[0162] In one specific embodiment, steps S109 are further included in steps S122 to S125.

[0163] S122. Store packets containing more than two terminal identifiers into the fourth intermediate table (i.e., Figure 2 Intermediate table C);

[0164] S123. Based on the traffic usage table, filter out terminal identifiers whose traffic usage time overlaps with the other terminal identifiers in the same group from the fourth intermediate table, and store the filtered terminal identifiers into the second intermediate table (i.e., Figure 2(intermediate table G in the middle);

[0165] S124. Obtain the ID number and corresponding terminal identifier registered by dual-SIM terminal users when they conduct business with this operator, and form a table of registered ID numbers;

[0166] In this step, when a user applies for a SIM card service at an operator, they need to register their ID number with their real name. Then the operator can obtain the ID number registered by the dual-SIM terminal user and find the terminal identifier (IMEI) corresponding to the mobile phone number through the registered ID number, thereby forming a terminal identifier-registered person ID number correspondence table (i.e., the registrant ID number table).

[0167] S125. Based on the registrant ID number table, at least two terminal identifiers corresponding to the same registrant ID number are selected from the remaining terminal identifiers in the fourth intermediate table, and the selected terminal identifiers are stored in the first result table (i.e., Figure 2 Results Table D).

[0168] In this embodiment, after grouping the terminal identifiers in the intermediate table F, if the number of terminal identifiers in a certain group is greater than 2, the terminal identifiers of that group are stored in the intermediate table C. The dual-SIM terminal users corresponding to the terminal identifiers recorded in the intermediate table C are people with the same group characteristics. They may be people who use the same terminal and have the same movement trajectory and use the same local area network, such as college students living in the same dormitory building. For this type of terminal identifier, secondary screening can be performed by changing the sampling conditions of location and Wi-Fi address.

[0169] To further identify the terminal identifiers, the negative factor "traffic table" is used to filter the terminal identifiers in intermediate table C. Specifically, the traffic usage time of each terminal identifier in the same group in intermediate table C is compared, and terminal identifiers whose traffic usage time overlaps with the other terminal identifiers in the same group are selected from intermediate table C and stored in intermediate table G. Then, these terminal identifiers stored from intermediate table C to intermediate table G are processed using the aforementioned steps S114 to S118, and these terminal identifiers are deleted from intermediate table C. For the remaining terminal identifiers in intermediate table C after the above filtering, the fuzzy factor "registrant ID number table" is used for further filtering. Specifically, terminal identifiers with the same registrant ID number are identified, and at least two terminal identifiers corresponding to the same registrant ID number are selected, that is, the number of terminal identifiers with the same registrant ID number is greater than or equal to 2. Terminal identifiers that meet this condition are likely multiple terminals used by the same person, which can be regarded as the same marketing unit from a marketing perspective. These selected terminal identifiers are stored in result table D, and the remaining terminal identifiers are stored in result table E.

[0170] The terminal identifiers in Result Table E are terminal identifiers that cannot be confirmed. These terminal identifiers can be used as input to re-enter the WiFi address table, location table, and traffic usage table for the next cycle of data accumulation and observation. At the same time, the acquisition parameters of the WiFi address table, location table, and traffic usage table can be adjusted, such as increasing the number of sampling days and lengthening the time period selected in each sampling day, and then the filtering can be carried out again according to the aforementioned steps.

[0171] Of course, in addition to the registrant ID number table, operators can also statistically analyze the contact numbers of all dual-SIM terminal users over a period of time, filter out frequently used contact numbers, and form a terminal identifier-frequently used contact number correspondence table (i.e., the frequently used contact number table). Then, based on the frequently used contact number table, the remaining terminal identifiers in the fourth intermediate table are filtered to identify two terminal identifiers with the same frequently used contact number, which are then stored in the first result table (i.e., ...). Figure 2 Results Table D).

[0172] like Figure 2 As shown, after the aforementioned filtering steps, four result tables are obtained: Result Table D, Result Table A, Result Table H, and Result Table E. In Result Table D, for the dual-SIM terminals corresponding to the terminal identifiers, both SIM cards in both slots are local network user identification cards. In Result Table A, for the dual-SIM terminals corresponding to the terminal identifiers, one SIM card slot contains a local network user identification card, and the other slot contains a user identification card from another network. In Result Table H, for the dual-SIM terminals corresponding to the terminal identifiers, only one SIM card slot contains a local network user identification card, while the other slot is empty. Result Table E records the terminal identifiers to be confirmed; data from one period can be accumulated and filtered again according to the aforementioned steps.

[0173] It should be noted that the order of the above steps is only a specific example to illustrate the embodiments of the present invention. The present invention does not limit the order of the above steps, and those skilled in the art can adjust them as needed in practical applications; moreover, the order of execution is not limited by the number of the above steps.

[0174] The terminal identifier association determination method provided in this invention combines multiple confirmation factors based on operator resources. It utilizes the characteristic that two terminal identifiers of the same dual-SIM terminal will appear multiple times in the same WiFi environment within the same time period to confirm the association between the two terminal identifiers. It also utilizes the characteristic that the same dual-SIM terminal has the same spatiotemporal movement point to confirm the association between the two terminal identifiers. Furthermore, it utilizes the characteristic that the two SIM card slots on the same dual-SIM terminal cannot simultaneously use mobile network traffic to confirm the association between the two terminal identifiers. By comprehensively utilizing the above methods, the coverage of the determined terminal identifier correspondence can be increased, and the accuracy of the judgment can be increased through multiple verification methods, thereby accurately and comprehensively confirming the correspondence between the two terminal identifiers of a dual-SIM terminal.

[0175] Figure 3 This is a schematic diagram of the terminal identifier association determination device provided in an embodiment of the present invention. Figure 3 As shown, the device includes: a first acquisition module 301, a second acquisition module 302, and a filtering module 303.

[0176] The first acquisition module 301 is configured to acquire the terminal identifiers of all dual-SIM terminal users on the network; the second acquisition module 302 is configured to acquire the WiFi addresses of the terminal identifiers that log in to the network within a preset time period, forming a WiFi address table, wherein the WiFi addresses include MAC addresses; the filtering module 303 is configured to filter out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, and determine the two terminal identifiers included in each pair of terminal identifiers as two terminal identifiers corresponding to the same dual-SIM terminal.

[0177] In one specific embodiment, the device further includes a first detection module 304 and a storage module 305.

[0178] The first detection module 304 is configured to, after the filtering module 303 filters out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, detect whether each of the two terminal identifiers in each terminal identifier pair corresponds to a user of the same operator. The storage module 305 is configured to, when the detection result of the first detection module 304 is that both terminal identifiers in a terminal identifier pair correspond to users of the same operator, store the terminal identifier pair in a first result table; and when the detection result of the first detection module 304 is that only one of the two terminal identifiers in a terminal identifier pair corresponds to a user of the same operator, store the terminal identifier pair in a second result table.

[0179] In one specific embodiment, the second acquisition module 302 includes one or more of the first to fourth acquisition units.

[0180] The first acquisition unit is configured to acquire the terminal identifier and corresponding MAC address and IP address of all dual-SIM terminals that access each smart gateway within a preset time period based on the access information of the smart gateway of this operator, obtain the MAC address-terminal identifier-IP address correspondence, and form a WiFi address table based on all the obtained MAC address-terminal identifier-IP address correspondences.

[0181] The second acquisition unit is configured to use fixed network deep packet inspection technology to identify application information passing through the operator's fixed network within a preset time period. The application information includes terminal identifiers, thereby obtaining the MAC address-terminal identifier-IP address correspondence, and forming a WiFi address table based on all obtained MAC address-terminal identifier-IP address correspondences.

[0182] The third acquisition unit is configured to acquire the terminal identifier and corresponding MAC address and IP address of dual-SIM terminal users within a preset time period through the operator's business processing application, obtain the MAC address-terminal identifier-IP address correspondence, and form a WiFi address table based on all obtained MAC address-terminal identifier-IP address correspondences;

[0183] The fourth acquisition unit is configured to obtain the terminal identifier and corresponding MAC address and IP address of dual-SIM terminal users within a preset time period through the official website of this operator's business processing, obtain the MAC address-terminal identifier-IP address correspondence, and form a WiFi address table based on all obtained MAC address-terminal identifier-IP address correspondences.

[0184] In one specific embodiment, the device further includes a second detection module 306.

[0185] The second detection module 306 is configured to detect whether the fixed network IP address is an IPv6 address or an IPv4 address after the second acquisition module 302 obtains the IP address corresponding to the terminal identifier. The second acquisition module 302 is further configured to, when the detection result of the second detection module 306 indicates that the fixed network IP address is an IPv6 address, add all obtained MAC address-terminal identifier-IPv6 address correspondences to the WiFi address table; and when the detection result of the second detection module 306 indicates that the fixed network IP address is an IPv4 address, add all obtained MAC address-terminal identifier-IPv4 address correspondences to a preliminary table, filter out IPv4 addresses corresponding to the same MAC address that appear more than a preset threshold number of times at different times from the preliminary table as determined IPv4 addresses, and add all MAC address-terminal identifier-determined IPv4 address correspondences to the WiFi address table.

[0186] In one specific embodiment, the device further includes: a third acquisition module 307, a fourth acquisition module 308, a fifth acquisition module 309, and a grouping module 310.

[0187] The third acquisition module 307 is configured to acquire the location information of the terminal identifier within a preset time period and form a location table; the fourth acquisition module 308 is configured to acquire the traffic usage information of the terminal identifier within a preset time period and form a traffic usage table; the fifth acquisition module 309 is configured to acquire the terminal model of the terminal identifier and form a terminal model table; the storage module 305 is further configured to, after the filtering module 303 filters out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, store the remaining terminal identifiers after filtering into a first intermediate table; the grouping module 310 is configured to group the terminal identifiers in the first intermediate table based on the location table and the terminal model table, and group those with the same location information at the same time. Terminals with the same terminal model are grouped together. If each group contains only one terminal identifier, the dual-SIM terminal containing that single identifier is identified as having only one SIM card installed by the operator. If each group contains two terminal identifiers, the dual-SIM terminal containing both identifiers is identified as having at least one SIM card installed by the operator. If each group contains more than two terminal identifiers, based on the data usage table, terminal identifiers whose data usage time overlaps with other terminal identifiers in the same group are selected, and the dual-SIM terminal containing the selected terminal identifier is identified as having only one SIM card installed by the operator.

[0188] In one specific embodiment, the third acquisition module 307 includes: a first sampling unit, a selection unit, and a first forming unit.

[0189] The first sampling unit is configured to obtain the location information of the terminal identifier within a preset time period, and randomly select N1 days from the location information for sampling; the selection unit is configured to select the location and corresponding time period of each terminal identifier in a time period in each sampling day, and obtain the correspondence between terminal identifier-location-location time period; the first forming unit is configured to form a location table based on all the obtained correspondences between terminal identifier-location-location time period.

[0190] In one specific embodiment, the fourth acquisition module 308 includes: a second sampling unit, a recording unit, and a second forming unit.

[0191] The second extraction unit is configured to obtain the traffic usage information of the terminal identifier within a preset time period, and randomly select N2 days from the traffic usage information for sampling; the recording unit is configured to record the time period of traffic usage of each terminal identifier in each sampling day, and obtain the correspondence between terminal identifier and traffic time period; the second forming unit is configured to form a traffic usage table based on all the obtained correspondences between terminal identifier and traffic time period.

[0192] In one specific embodiment, the storage module 305 is further configured to, after the grouping module 310 groups terminal identifiers with the same location information and terminal model at the same time into the same group, store the group containing only one terminal identifier into the second intermediate table. The filtering module 303 may include one or more of the first to third filtering units, wherein the first filtering unit is configured to filter out a portion of terminal identifiers from the second intermediate table and store them into the second result table according to a first filtering rule, wherein the first filtering rule is to filter terminal identifiers corresponding to dual-SIM terminal users who have not used data traffic and voice for a period exceeding a first preset time threshold; the second filtering unit is configured to filter out a portion of terminal identifiers from the second intermediate table and store them into the second result table according to a second filtering rule, wherein the second filtering rule is to filter terminal identifiers that have re-accessed the base station cell after disappearing from the access base station cell for no more than a second preset time threshold; the third filtering unit is configured to filter out a portion of terminal identifiers from the second intermediate table and store them into the second result table according to a third filtering rule, wherein the third filtering rule is to filter terminal identifiers that have not used the operator's network traffic for a period exceeding a third preset time threshold but have used the operator's network traffic normally for the rest of the time. The storage module 305 is further configured to determine the dual-SIM terminal containing the terminal identifier stored in the second result table as a dual-SIM terminal that has one user identification card of this operator and one user identification card of another operator installed; and, after filtering by a preset period, to store the remaining terminal identifiers in the second intermediate table into the third result table, and to determine the dual-SIM terminal containing the terminal identifier stored in the third result table as a dual-SIM terminal that has one user identification card of this operator installed and the other card slot is not inserted.

[0193] In one specific embodiment, the storage module 305 is further configured to, after the grouping module 310 groups terminal identifiers with the same location information and terminal model at the same time into the same group, store the group containing two terminal identifiers into a third intermediate table. The filtering module 303 is further configured to, based on the traffic usage table, filter out groups in the same group whose traffic usage times for two terminal identifiers do not overlap completely from the third intermediate table; the storage module 305 is further configured to, store the groups filtered out by the filtering module 303 from the third intermediate table into a first result table, and store the remaining groups in the third intermediate table into a second result table, wherein the first result table stores groups in which both terminal identifiers correspond to users of the same operator, and the second result table stores groups in which only one of the two terminal identifiers corresponds to users of the same operator.

[0194] In one specific embodiment, the device further includes a sixth acquisition module 311.

[0195] The storage module 305 is further configured to, after the grouping module 310 groups terminal identifiers with the same location information and terminal model at the same time into the same group, store the group containing more than two terminal identifiers into the fourth intermediate table; the filtering module 303 is further configured to, based on the traffic usage table, filter terminal identifiers from the fourth intermediate table whose traffic usage time overlaps with the other terminal identifiers in the same group; the storage module 305 is further configured to, store the terminal identifiers filtered by the filtering module 303 from the fourth intermediate table into the second intermediate table; the sixth acquisition module is configured to, acquire the ID number and corresponding terminal identifier registered by the dual-SIM terminal user when handling business with this operator, and form a registrant ID number table; the filtering module 303 is further configured to, based on the registrant ID number table, filter at least two terminal identifiers corresponding to the same registrant ID number from the remaining terminal identifiers in the fourth intermediate table; the storage module 305 is further configured to, store the terminal identifiers filtered by the filtering module 303 from the remaining terminal identifiers in the fourth intermediate table into the first result table.

[0196] The terminal identifier association determination device provided in this embodiment of the invention combines multiple confirmation factors based on operator resources. It utilizes the characteristic that the two terminal identifiers of the same dual-SIM terminal will appear multiple times in the same WiFi environment at the same time period to confirm the association relationship between the two terminal identifiers. It also utilizes the characteristic that the two dual-SIM terminals have the same spatiotemporal movement points to confirm the association relationship between the two terminal identifiers. Furthermore, it utilizes the characteristic that the two SIM card slots on the same dual-SIM terminal cannot use mobile network traffic at the same time to confirm the association relationship between the two terminal identifiers. By comprehensively utilizing the above methods, the coverage of the determined terminal identifier correspondence can be increased, and the accuracy of the judgment can be increased through multiple verification methods, thereby accurately and comprehensively confirming the correspondence relationship between the two terminal identifiers of the dual-SIM terminal.

[0197] Based on the same technical concept, embodiments of the present invention also provide a computer device, such as... Figure 4 As shown, the computer device includes a memory 401 and a processor 402. The memory 401 stores a computer program. When the processor 402 runs the computer program stored in the memory 401, the processor 402 executes the aforementioned terminal identifier association determination method.

[0198] Based on the same technical concept, the present invention also provides a computer-readable storage medium storing a computer program thereon, wherein when the computer program is executed by a processor, the processor executes the aforementioned terminal identifier association determination method.

[0199] In summary, the terminal identifier association determination method, apparatus, computer equipment, and storage medium provided in this embodiment of the invention divide the factors used to confirm the terminal identifier association into two dimensions: definite factors and fuzzy factors. By using the two dimensions in combination, and taking advantage of the characteristics that the two terminal identifiers of the same dual-SIM terminal will appear multiple times in the same WiFi environment at the same time period, the characteristics that the two spatiotemporal movement points of the same dual-SIM terminal are the same, and the characteristics that the two SIM card slots on the same dual-SIM terminal cannot use mobile network traffic at the same time, the correspondence between the two terminal identifiers of the dual-SIM terminal can be accurately and comprehensively confirmed.

[0200] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0201] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining terminal identifier association, characterized in that, include: Obtain the terminal identifier of all dual-SIM terminal users across the network; Obtain the WiFi addresses of the terminal identifier that logged into the network within a preset time period, and form a WiFi address table, wherein the WiFi addresses include MAC addresses; and, Filter out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, and determine the two terminal identifiers in each terminal identifier pair as the two terminal identifiers corresponding to the same dual-SIM terminal; The method further includes: The location information and traffic usage information of the terminal identifier within a preset time period are obtained, as well as the terminal model of the terminal identifier, and a location table, a traffic usage table, and a terminal model table are formed respectively. After filtering out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, the remaining terminal identifiers are stored in the first intermediate table. Based on the location table and the terminal model table, the terminal identifiers in the first intermediate table are grouped, and terminal identifiers with the same location information and the same terminal model at the same time are grouped into the same group; and... For cases where each group contains only one terminal identifier, the dual-SIM terminal containing that single terminal identifier is identified as a dual-SIM terminal with only one SIM card from this operator installed. For cases where each group contains two terminal identifiers, the dual-SIM terminal containing both terminal identifiers is identified as a dual-SIM terminal with at least one SIM card from this operator installed. For cases where each group contains more than two terminal identifiers, based on the traffic usage table, terminal identifiers whose traffic usage time overlaps with the other terminal identifiers in the same group are selected from the group, and the dual-SIM terminal containing the selected terminal identifier is identified as a dual-SIM terminal with only one SIM card from this operator installed.

2. The method according to claim 1, characterized in that, After filtering out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, the process also includes: Each terminal identifier pair is checked to see if each of the two terminal identifiers in the pair corresponds to a user of this operator. If both terminal identifiers in a certain terminal identifier pair correspond to users of this operator, the terminal identifier pair is stored in the first result table. If, in response to a terminal identifier pair containing only one of the two terminal identifiers, the terminal identifier pair corresponds to a user of this operator, the terminal identifier pair is stored in the second result table.

3. The method according to claim 1 or 2, characterized in that, The step of obtaining the WiFi addresses of the terminal identifiers that log in to the network within a preset time period and forming a WiFi address table includes: Based on the access information of the operator's smart gateway, the terminal identifiers and corresponding MAC addresses and IP addresses of all dual-SIM terminals accessing each smart gateway within a preset time period are obtained, resulting in the MAC address-terminal identifier-IP address mapping relationship, and a WiFi address table is formed based on all obtained MAC address-terminal identifier-IP address mapping relationships; and / or, Using fixed-line deep packet inspection technology, application information passing through the operator's fixed-line network within a preset time period is identified. This application information includes terminal identifiers, thereby obtaining the MAC address-terminal identifier-IP address mapping relationship, and forming a WiFi address table based on all obtained MAC address-terminal identifier-IP address mapping relationships; and / or, This operator's service application obtains the terminal identifiers and corresponding MAC addresses and IP addresses of dual-SIM terminal users within a preset time period, generates the MAC address-terminal identifier-IP address mapping, and forms a WiFi address table based on all obtained MAC address-terminal identifier-IP address mappings; and / or, By obtaining the terminal identifier and corresponding MAC address and IP address of dual-SIM terminal users within a preset time period through the official website of this operator, the mapping relationship between MAC address, terminal identifier and IP address is obtained, and a WiFi address table is formed based on all the obtained mapping relationships between MAC address, terminal identifier and IP address.

4. The method according to claim 3, characterized in that, Also includes: After obtaining the IP address corresponding to the terminal identifier, check whether the fixed network IP address is an IPv6 address or an IPv4 address; In response to the fact that the fixed network IP address is an IPv6 address, all obtained MAC address-terminal identifier-IPv6 address mappings are placed into the WiFi address table; In response to the fact that the fixed network IP address is an IPv4 address, all the obtained MAC address-terminal identifier-IPv4 address correspondences are placed into a preparatory table. From the preparatory table, IPv4 addresses that correspond to the same MAC address and appear more than a preset number of times at different times are selected as the determined IPv4 addresses. All MAC address-terminal identifier-determined IPv4 address correspondences are then placed into the WiFi address table.

5. The method according to claim 1, characterized in that, The step of obtaining the location information of the terminal identifier within a preset time period to form a location table includes: Obtain the location information of the terminal identifier within a preset time period, and randomly select N1 days from the location information for sampling; In each sampling day, select the location and corresponding time period where each terminal identifier has the longest occurrence time within a given time period to obtain the correspondence between terminal identifier, location, and location time period; and, A location table is formed based on the obtained correspondence between all terminal identifiers, locations, and location time periods.

6. The method according to claim 1, characterized in that, The step of obtaining the traffic usage information of the terminal identifier within a preset time period and forming a traffic usage table includes: Obtain the traffic usage information of the terminal identifier within a preset time period, and randomly select N2 days from the traffic usage information for sampling; Record the time periods for each terminal identifier's traffic usage on each sampling day to obtain the correspondence between terminal identifier and traffic time period; and, A traffic usage table is generated based on the obtained correspondence between all terminal identifiers and traffic time periods.

7. The method according to any one of claims 1, 5-6, characterized in that, After grouping terminals with the same location information and terminal model at the same time into the same group, the following is also included: Store the packets containing only one terminal identifier into the second intermediate table; According to the first filtering rule, a portion of terminal identifiers are selected from the second intermediate table and stored in the second result table. The first filtering rule is to filter terminal identifiers corresponding to dual-SIM terminal users who have not used data traffic and voice within a period exceeding a first preset time threshold; and / or, According to the second filtering rule, a portion of terminal identifiers are selected from the second intermediate table and stored in the second result table. The second filtering rule is to select terminal identifiers that have re-accessed the base station cell after disappearing from the access base station cell for no more than a second preset time threshold; and / or, According to the third filtering rule, some terminal identifiers are selected from the second intermediate table and stored in the second result table. The third filtering rule is to filter terminal identifiers that have not used the operator's network traffic at all for a period of time exceeding the third preset time threshold, but have used the operator's network traffic normally for the rest of the time. The dual-SIM terminal containing the terminal identifier stored in the second result table is identified as a dual-SIM terminal with one user identity card from this operator and one user identity card from another operator installed; and, After filtering over a preset period, the remaining terminal identifiers in the second intermediate table are stored in the third result table, and the dual-SIM terminal containing the terminal identifier stored in the third result table is identified as a dual-SIM terminal with one user identification card of this operator installed and the other card slot not inserted.

8. The method according to claim 7, characterized in that, After grouping terminals with the same location information and terminal model at the same time into the same group, the following is also included: Store the group containing the two terminal identifiers into the third intermediate table; Based on the traffic usage table, groups with completely non-overlapping traffic usage times for two terminal identifiers within the same group are selected from the third intermediate table; and... The filtered groups are stored in the first result table, and the remaining groups in the third intermediate table are stored in the second result table. The first result table stores groups whose two terminal identifiers both correspond to users of this operator, and the second result table stores groups whose two terminal identifiers correspond to users of this operator only one.

9. The method according to claim 7, characterized in that, After grouping terminals with the same location information and terminal model at the same time into the same group, the following is also included: Packets containing more than two terminal identifiers are stored in the fourth intermediate table; Based on the traffic usage table, select terminal identifiers whose traffic usage time overlaps with the other terminal identifiers in the same group from the fourth intermediate table, and store the selected terminal identifiers into the second intermediate table. Obtain the ID number and corresponding terminal identifier registered by dual-SIM terminal users when they apply for services with this operator, and form a table of registered user ID numbers; and, Based on the registrant ID number table, at least two terminal identifiers corresponding to the same registrant ID number are selected from the remaining terminal identifiers in the fourth intermediate table, and the selected terminal identifiers are stored in the first result table.

10. A device for determining terminal identifier association, characterized in that, include: The first acquisition module is configured to acquire the terminal identifier of all dual-SIM terminal users across the network. The second acquisition module is configured to acquire the WiFi addresses of the network logged into by the terminal identifier within a preset time period, forming a WiFi address table, wherein the WiFi addresses include MAC addresses; and The filtering module is configured to filter out terminal identifier pairs with the same MAC address at the same time from the WiFi address table, and to determine the two terminal identifiers included in each pair of terminal identifiers as two terminal identifiers corresponding to the same dual-SIM terminal. The third acquisition module is configured to acquire the location information of the terminal identifier within a preset time period and form a location table. The fourth acquisition module is configured to acquire the traffic usage information of the terminal identifier within a preset time period and form a traffic usage table; The fifth acquisition module is configured to acquire the terminal model of the terminal identifier and form a terminal model table; The storage module is configured to store the remaining terminal identifiers into a first intermediate table after the filtering module filters out terminal identifier pairs with the same MAC address at the same time from the WiFi address table. The grouping module is configured to group terminal identifiers in the first intermediate table based on the location table and the terminal model table. Terminal identifiers with the same location information and terminal model at the same time are grouped together. For each group containing only one terminal identifier, the dual-SIM terminal containing that single terminal identifier is identified as a dual-SIM terminal with only one SIM card installed by the operator. For each group containing two terminal identifiers, the dual-SIM terminal containing both terminal identifiers is identified as a dual-SIM terminal with at least one SIM card installed by the operator. For each group containing more than two terminal identifiers, based on the traffic usage table, terminal identifiers whose traffic usage time overlaps with the other terminal identifiers in the same group are selected, and the dual-SIM terminal containing the selected terminal identifier is identified as a dual-SIM terminal with only one SIM card installed by the operator.

11. A computer device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the terminal identifier association determination method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the processor performs the terminal identifier association determination method according to any one of claims 1 to 9.

Images