Device association method and apparatus, electronic device, and storage medium

Abstract

The application provides a device association method and device, electronic equipment and storage medium, the method comprises the following steps: S100, in response to receiving a device association instruction, obtaining the basic data table in the target time period corresponding to the current time; S200, for TN i , obtaining m data corresponding to the mobile communication ID and TN i As a target data set, if the target data set is not null, execute S300, otherwise, execute S500; S300, for A i , obtaining the corresponding similarity set SA i ; S400, obtaining the maximum in SA i As the target similarity of A i , if MSA i ≥S0, establish the association relationship between the unencrypted mobile communication ID corresponding to MSA i And A i , and execute S500; otherwise, execute S500; S500, set i=i+1, if i≤n, execute S200. The application can accurately associate the mobile communication ID and the corresponding device ID.

Description

Technical Field

[0001] This invention relates to the field of data processing, and in particular to a device association method, apparatus, electronic device, and storage medium. Background Technology

[0002] In some application scenarios, it's necessary to accurately associate a user's mobile communication ID (such as a phone number) with its corresponding device ID, such as the mobile communication device ID. In reality, the number of available mobile communication IDs remains relatively constant. However, in actual applications, users may change devices without updating their mobile communication IDs. This can lead to a mismatch between the previously obtained mobile communication ID and its corresponding device ID, resulting in inaccurate data. Therefore, it's necessary to update the device ID corresponding to each mobile communication ID to find the accurate one. However, due to device version upgrades, device privacy protection, and other reasons, valid mobile communication IDs may not be obtainable; that is, the obtained mobile communication IDs may be encrypted. Therefore, in cases where only the device is updated without updating the mobile communication ID, it will be impossible to associate the mobile communication ID with the corresponding new device ID. Summary of the Invention

[0003] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows:

[0004] This invention provides a device association method, the method comprising the following steps:

[0005] S100, in response to receiving a device association command, obtain the basic data table for the target time period corresponding to the current time, wherein the i-th row of the basic data table includes (TN) i A i BF i ), TN i For the i-th encrypted mobile communication ID, A i For TN i Corresponding device ID ii BF i For A i The corresponding behavioral fingerprint set, BF i ={WF i AP i GW i GL i}, WF i For A i The corresponding list of Wi-Fi addresses, AP i For A i The corresponding list of installed apps, GW i For A i The corresponding gateway list, GLi For A i The corresponding Geohash grid position information, GL i Based on the obtained A i The corresponding location information is determined; the value of i ranges from 1 to n, where n is the number of rows in the basic data table;

[0006] S200, for TN i Obtain the mobile communication ID and TN from the original data table. i The corresponding m data points are used as the target dataset. If the target dataset is not null, execute S300; otherwise, execute S500. Each row of data in the original data table includes an unencrypted mobile communication ID, the device ID corresponding to the unencrypted mobile communication ID, and the behavior fingerprint corresponding to the device ID.

[0007] S300, for A i Obtain the corresponding similarity set SA i ={SA 1 i SA 2 i SA r i SA m i}, where SA r i For A i The similarity between SA and the m-th data in the target dataset r i =f(SWF) r i SAP r i SGW r i SGL r i ),SWF r i For A i The similarity between the corresponding list of Wi-Fi addresses and the list of Wi-Fi addresses corresponding to the r-th data point in the target dataset, where r ranges from 1 to m; SAP r i For A i The similarity between the corresponding list of installed apps and the list of installed apps corresponding to the r-th data point in the target dataset; SGW r i For A i The similarity between the corresponding gateway list and the gateway list corresponding to the r-th data in the target dataset; SBF i For A iThe corresponding behavioral fingerprint similarity set, SGL i ={SGL 1 i SGL 2 j , ..., SGL r i , ..., SGL m i}, SGL r i For A i The similarity between the corresponding Geohash grid location information and the Geohash grid location information corresponding to the m-th data in the target dataset; f() is the defined function expression;

[0008] S400, obtain MSA i =max{SA 1 i SA 2 i SA r i SA m i As A i Target similarity, if MSA i ≥S0, establish MSA i The corresponding unencrypted mobile communication ID and A i If the relationship between them is determined, then S500 is executed; otherwise, S500 is executed directly; S0 is to set the similarity threshold.

[0009] S500: Set i = i + 1. If i ≤ n, execute S200; otherwise, exit the current control program.

[0010] This invention also provides a device association apparatus, the apparatus comprising:

[0011] The data acquisition module is used to, in response to a received device association command, acquire a basic data table for the target time period corresponding to the current time, wherein the i-th row of the basic data table includes (TN) i A i BF i ), TN i For the i-th encrypted mobile communication ID, A i For TN i Corresponding device ID ii BF i For A i The corresponding behavioral fingerprint set, BF i ={WF i AP i GW i GLi}, WF i For A i The corresponding list of Wi-Fi addresses, AP i For A i The corresponding list of installed apps, GW i For A i The corresponding gateway list, GL i For A i The corresponding Geohash grid position information, GL i Based on the obtained A i The corresponding location information is determined; the value of i ranges from 1 to n, where n is the number of rows in the basic data table;

[0012] The data processing module is used to perform the following operations:

[0013] S10, for TN i Obtain the mobile communication ID and TN from the original data table. i The corresponding m data are used as the target dataset. If the target dataset is not null, execute S20; otherwise, execute S40. Each row of data in the original data table includes an unencrypted mobile communication ID, the device ID corresponding to the unencrypted mobile communication ID, and the behavior fingerprint corresponding to the device ID.

[0014] S20, for A i Obtain the corresponding similarity set SA i ={SA 1 i SA 2 i SA r i SA m i}, where SA r i For A i The similarity between SA and the m-th data in the target dataset r i =f(SWF) r i SAP r i SGW r i SGL r i ),SWF r i For A i The similarity between the corresponding list of Wi-Fi addresses and the list of Wi-Fi addresses corresponding to the r-th data point in the target dataset, where r ranges from 1 to m; SAP ri For A i The similarity between the corresponding list of installed apps and the list of installed apps corresponding to the r-th data point in the target dataset; SGW r i For A i The similarity between the corresponding gateway list and the gateway list corresponding to the r-th data in the target dataset; SBF i For A i The corresponding behavioral fingerprint similarity set, SGL i ={SGL 1 i SGL 2 j , ..., SGL r i , ..., SGL m i}, SGL r i For A i The similarity between the corresponding Geohash grid location information and the Geohash grid location information corresponding to the m-th data in the target dataset; f() is the defined function expression;

[0015] S30, Obtain MSA i =max{SA 1 i SA 2 i SA r i SA m i As A i Target similarity, if MSA i ≥S0, establish MSA i The corresponding unencrypted mobile communication ID and A i If the relationship between them is determined, then S40 is executed; otherwise, S40 is executed directly; S0 is to set the similarity threshold.

[0016] S40: Set i = i + 1. If i ≤ n, execute S10; otherwise, exit the current control program.

[0017] This invention also provides a non-transitory computer-readable storage medium storing at least one instruction or at least one program segment, characterized in that the at least one instruction or the at least one program segment is loaded and executed by a processor to implement the method described above.

[0018] This invention also provides an electronic device, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0019] The present invention has at least the following beneficial effects:

[0020] The device association method provided in this embodiment of the invention first obtains the corresponding data from the original data table as the target dataset based on the encrypted mobile communication ID corresponding to the data to be matched. Then, it obtains the similarity between the data to be matched and each target data from the perspectives of Wi-Fi address, APP installation, gateway, and device location. Then, it associates the device ID corresponding to the data to be matched with the mobile communication ID corresponding to the maximum similarity exceeding the set similarity threshold. In this way, it can quickly and accurately associate historical mobile communication IDs with the currently used device. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart of a device association method provided in an embodiment of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] 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 specified order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0025] The device association method provided in this embodiment of the invention can be applied to any terminal or server with data processing capabilities. When the terminal or server executes the device association method provided in this embodiment of the invention, it can execute independently or through cluster collaboration.

[0026] This invention provides a device association method, such as... Figure 1 As shown, the method may include the following steps:

[0027] S100, in response to receiving a device association command, obtain the basic data table for the target time period corresponding to the current time, wherein the i-th row of the basic data table includes (TN) i A i BF i ), TN i For the i-th encrypted mobile communication ID, A i For TN i Corresponding device ID ii BF i For A i The corresponding behavioral fingerprint set, BF i ={WF i AP i GW i GL i}, WF i For A i The corresponding list of Wi-Fi addresses, AP i For A i The corresponding list of installed apps, GW i For A i The corresponding gateway list, GL i For A i The corresponding Geohash grid position information, GL i Based on the obtained A i The corresponding location information is determined; the value of i ranges from 1 to n, where n is the number of rows in the basic data table.

[0028] In this embodiment of the invention, the target time period can be set based on actual needs. The duration of each target time period is fixed and may include p consecutively arranged time windows. The duration of the target time period is L = Δt * p, where Δt is the duration of each time window. Preferably, p = 30. The duration of each time window is fixed and can be divided in hours or days; this embodiment of the invention does not impose a specific limitation. Preferably, it can be divided in days, and the duration of each time window is one day, for example, from 0:00 to 24:00.

[0029] In this embodiment of the invention, the device may be a mobile communication device. The device ID may be a unique code used to distinguish different mobile communication devices. For example, the device ID may be any one or a combination of the IMEI, IMSI, and MAC address of the mobile communication device, or any one or a combination of the IMEI, IMSI, and MAC address of the mobile terminal that has been encrypted (e.g., MD5 encryption). This embodiment of the invention does not impose specific limitations.

[0030] In this embodiment of the invention, the mobile communication ID can be an ID installed on the corresponding device for communication, such as a SIM card number or mobile phone number. The encrypted mobile communication ID can be in a format that uses asterisks (*) to replace the middle four digits, such as 136****1234.

[0031] In this embodiment of the invention, the APP installation list is a list of APPs that have been installed on the device.

[0032] Those skilled in the art will know that obtaining the list of Wi-Fi addresses, the list of installed apps, and the list of gateways for each device is a prior art.

[0033] In this embodiment of the invention, the device's location information can be obtained through existing methods, and the initial location information obtained can be latitude and longitude coordinates. The obtained initial location information will be converted into a Geohash grid of a set number of bits. The specific conversion method can be existing technology, and the set number of bits can be set according to actual needs. Preferably, it can be an 8-bit Geohash.

[0034] Furthermore, in embodiments of the present invention, GL i ={GL 1 i GL 2 i GL 3 i}, GL 1 i GL 2 i GL 3 i These are the first, second, and third dwelling grid positions, respectively.

[0035] Among them, GL 1 i For A i The corresponding first dwell grid information set GLP 1 i ={GLP 1 i1 GLP 1 i2 GLP 1 ijGLP 1 ip The grid position corresponding to the highest word frequency in GLP is the grid position that appears most frequently. 1 ij For A i The corresponding grid position where the device stays for the longest time within a first set time range corresponding to the j-th time window. In this embodiment of the invention, the first set time range can be an evening period, such as the period between 6 pm and 7 am. GLP 1 ij This can be obtained based on the following steps:

[0036] S101, obtain A i The corresponding grid location information of the device within the j-th time window;

[0037] S102, Obtain the position belonging to the first set time range from the acquired grid position information, and use it as the first target grid position;

[0038] S103, Obtain the grid position with the longest dwell time from the first target grid position as the GLP. 1 ij .

[0039] In this embodiment of the invention, the dwell time can be the cumulative duration.

[0040] Among them, GL 2 i For A i The corresponding second dwell grid information set GLP 2 i ={GLP 2 i1 GLP 2 i2 GLP 2 ij GLP 2 ip The grid position corresponding to the highest word frequency in}, GLP 2 ij For A i The corresponding grid position where the device stays for the longest time within the second set time range corresponding to the j-th time window.

[0041] In this embodiment of the invention, the second set time range can be a nighttime period, such as the period between 7:00 AM and 6:00 PM. GLP 2 ij This can be obtained based on the following steps:

[0042] S110, obtain A iThe corresponding grid location information of the device within the j-th time window;

[0043] S112, Obtain the position belonging to the second set time range from the acquired grid position information, and use it as the second target grid position;

[0044] S114, Obtain the grid position with the longest dwell time from the second target grid position as the GLP. 2 ij .

[0045] Among them, GL 3 i Based on A i The corresponding third dwell grid information set GLP 3 i ={GLP 3 i1 GLP 3 i2 GLP 3 ij GLP 3 ip Confirmed, GLP 3 ij For A i The corresponding grid position where the device stays for a longer time than a preset dwell time threshold within the j-th time window, where j ranges from 1 to p.

[0046] In this embodiment of the invention, the preset stay duration threshold can be set based on actual needs, for example, it can be 8 hours. GLP 3 ij It can be obtained based on the following steps:

[0047] S120, obtain A i The corresponding grid location information of the device within the j-th time window;

[0048] S122, Obtain the dwell time for each grid location from the acquired grid location information to obtain a list of dwell times;

[0049] S124, retrieve the grid position with the longest dwell time from the dwell time list as the GLP. 3 ij .

[0050] In one embodiment of the present invention, GL 3 i GLP 3 i The grid position corresponding to the highest word frequency. In another embodiment of the invention, GL 3 i GLP 3i The grid positions corresponding to the first K word frequencies are the GLP values. 3 i The grid position of the middle word frequency in the first K positions is used as GL 3 i For example, K = 10.

[0051] S200, for TN i Obtain the mobile communication ID and TN from the original data table. i The corresponding m data are used as the target dataset. If the target dataset is not null, execute S300; otherwise, execute S500. Each row of data in the original data table includes an unencrypted mobile communication ID, the device ID corresponding to the unencrypted mobile communication ID, and the behavior fingerprint corresponding to the device ID.

[0052] In this embodiment of the invention, with TN i The corresponding data consists of the first 3 digits and the last 4 digits of the mobile communication ID corresponding to this data, which are respectively related to the TN. i The first 3 and last 4 digits are the same.

[0053] The advantage of S200 is that by setting the matching of mobile communication IDs as a filtering condition, it can reduce the amount of data processing associated with the device.

[0054] S300, for A i Obtain the corresponding similarity set SA i ={SA 1 i SA 2 i SA r i SA m i}, where SA r i For A i The similarity between SA and the m-th data in the target dataset r i =f(SWF) r i SAP r i SGW r i SGL r i ),SWF r i For A i The similarity between the corresponding list of Wi-Fi addresses and the list of Wi-Fi addresses corresponding to the r-th data point in the target dataset, where r ranges from 1 to m; SAP ri For A i The similarity between the corresponding list of installed apps and the list of installed apps corresponding to the r-th data point in the target dataset; SGW r i For A i The similarity between the corresponding gateway list and the gateway list corresponding to the r-th data in the target dataset; SBF i For A i The corresponding behavioral fingerprint similarity set, SGL i ={SGL 1 i SGL 2 j , ..., SGL r i , ..., SGL m i}, SGL r i For A i The similarity between the corresponding Geohash grid location information and the Geohash grid location information corresponding to the m-th data in the target dataset; f() is the defined function expression.

[0055] In this embodiment of the invention, SWF r i =(WF i ∩MWF r ) / (WF i ∪MWF r ), i.e., SWF r i For WF i and MWF r The number of identical Wi-Fi addresses and WF i and MWF r The ratio of the number of all Wi-Fi addresses contained in MWF r This is the list of Wi-Fi addresses corresponding to the r-th data in the target dataset.

[0056] Furthermore, in this embodiment of the invention, SAP r i =(AP i ∩MAP r ) / (AP i ∪MAP r SAP r i For AP i and MAP r The same number of app installations and AP i and MAP rThe ratio of the number of installed apps included in the MAP r This is the list of installed apps corresponding to the r-th data point in the target dataset.

[0057] Furthermore, in this embodiment of the invention, SGW r i =(GW) i ∩MGW r ) / (GW i ∪MGW r ), i.e., SGW r i For GW i and MGW r The same number of gateways and GW i and MGW r The ratio of the number of all gateways included in MGW r This is the list of gateways corresponding to the r-th data in the target dataset.

[0058] Furthermore, in this embodiment of the invention, SGL r i =[(GLP 1 ij ∩GLP 1 r )+(GLP 2 ij ∩GLP 2 r )+(GLP 3 ij ∩GLP 3 r )] / (GLP 1 ij ∪GLP 1 r ∪GLP 2 ij ∪GLP 2 r ∪GLP 3 ij ∪GLP 3 r GLP 1 r GLP 2 r and GLP 3 r These represent the first, second, and third stop grid positions corresponding to the r-th data point in the target dataset, respectively. (GLP) h ij ∩GLP h r GLPh ij and GLP h r GLP with the same number of grids 1 ij ∪GLP 1 r ∪GLP 2 ij ∪GLP 2 r ∪GLP 3 ij ∪GLP 3 r This indicates the number of grid cells contained in these grid locations, with h ranging from 1 to 3.

[0059] Furthermore, in one embodiment of the present invention, SA r i =(SWF) r i +SAP r i +SGW r i +SGL r i ) / 4.

[0060] Furthermore, in another embodiment of the present invention, SA r i =w1*SWF r i +w2*SAP r i +w3*SGW r i +w4*SGL r i w1 to w4 are preset coefficients, and w1 + w2 + w3 + w4 = 1. Compared with the previous embodiment, the data similarity in this embodiment considers the weight of the similarity of each dimension, which can be more accurate.

[0061] In one illustrative embodiment, w1 to w4 may be empirical values.

[0062] In another illustrative embodiment, w1 to w4 can be obtained through the following steps:

[0063] S301, obtain Q training samples, the s-th training sample includes (D1) s D2 s F s ), the first dataset D1 s =(WF1) s AP1 s GW1s GL1 s ), the second dataset D2 s =(WF2) s AP2 s GW2 s GL2 s WF1 s AP1 s GW1 s GL1 s These are the Wi-Fi address list, APP installation list, gateway list, and grid location information corresponding to the initial device ID of the s-th mobile communication ID, respectively. (WF2) s AP2 s GW2 s GL2 s These represent the Wi-Fi address list, APP installation list, gateway list, and grid location information corresponding to the current device ID corresponding to the s-th mobile communication ID. The initial device ID and the current device ID are different; the value of s ranges from 1 to Q; F s Let F be the label corresponding to the s-th training sample. s =1.

[0064] S302, input the current batch of training samples into the AI ​​model for training, and obtain the corresponding output result; in this embodiment of the invention, the output result is the similarity between the first dataset and the second dataset, and the specific calculation method of the similarity can be referred to the aforementioned S300.

[0065] S303: Based on the output results of all samples in the current batch and their corresponding labels, obtain the current loss function value and determine whether the current loss function value meets the preset model training termination condition. If it meets the condition, take w1 to w4 corresponding to the current model as the final w1 to w4. If it does not meet the condition, execute S304.

[0066] Those skilled in the art will know that the preset model training termination conditions can be set based on actual needs, for example, including the loss function being less than a preset first loss threshold or the loss function being less than a preset second loss threshold, and remaining unchanged, wherein the first loss threshold is less than the second loss threshold.

[0067] S304, calculate the partial derivative of the current loss function to obtain the current parameter tuning value, update the weight value corresponding to the AI ​​model based on the current parameter tuning value, and use the positive and negative sample data of the next batch as the current batch sample, then return to step S302.

[0068] In this embodiment of the invention, the AI ​​model can be an existing neural network model.

[0069] The values ​​w1 to w4 obtained by training an AI model are more accurate than empirical values.

[0070] S400, obtain MSA i =max{SA 1 i SA 2 i SA r i SA m i As A i Target similarity, if MSA i ≥S0, establish MSA i The corresponding unencrypted mobile communication ID and A i The relationship between them is determined, and S500 is executed; otherwise, S500 is executed directly; S0 is the set similarity threshold, which can be an empirical value, such as S0 = 0.85 to 0.95, preferably S0 = 0.9.

[0071] S500: Set i = i + 1. If i ≤ n, execute S200; otherwise, exit the current control program.

[0072] Furthermore, the S400 may also include:

[0073] Based on the established MSA i The corresponding unencrypted mobile communication ID and A i The relationships between them are used to update the corresponding data in the original data table.

[0074] The device association method provided in this embodiment of the invention first obtains the corresponding data from the original data table as the target dataset based on the encrypted mobile communication ID corresponding to the data to be matched. Then, it obtains the similarity between the data to be matched and each target data from the perspectives of Wi-Fi address, APP installation, gateway, and device location. Then, it associates the device ID corresponding to the data to be matched with the mobile communication ID corresponding to the maximum similarity exceeding the set similarity threshold. In this way, it can quickly and accurately associate historical mobile communication IDs with the currently used device.

[0075] Based on the same inventive concept, embodiments of the present invention also provide a device association apparatus, the apparatus comprising:

[0076] The data acquisition module is used to, in response to a received device association command, acquire a basic data table for the target time period corresponding to the current time, wherein the i-th row of the basic data table includes (TN) i A i BF i ), TN i For the i-th encrypted mobile communication ID, Ai For TN i Corresponding device ID ii BF i For A i The corresponding behavioral fingerprint set, BF i ={WF i AP i GW i GL i}, WF i For A i The corresponding list of Wi-Fi addresses, AP i For A i The corresponding list of installed apps, GW i For A i The corresponding gateway list, GL i For A i The corresponding Geohash grid position information, GL i Based on the obtained A i The corresponding location information is determined; the value of i ranges from 1 to n, where n is the number of rows in the basic data table;

[0077] The data processing module is used to perform the following operations:

[0078] S10, for TN i Obtain the mobile communication ID and TN from the original data table. i The corresponding m data are used as the target dataset. If the target dataset is not null, execute S20; otherwise, execute S40. Each row of data in the original data table includes an unencrypted mobile communication ID, the device ID corresponding to the unencrypted mobile communication ID, and the behavior fingerprint corresponding to the device ID.

[0079] S20, for A i Obtain the corresponding similarity set SA i ={SA 1 i SA 2 i SA r i SA m i}, where SA r i For A i The similarity between SA and the m-th data in the target dataset r i =f(SWF) r i SAP r i SGW ri SGL r i ),SWF r i For A i The similarity between the corresponding list of Wi-Fi addresses and the list of Wi-Fi addresses corresponding to the r-th data point in the target dataset, where r ranges from 1 to m; SAP r i For A i The similarity between the corresponding list of installed apps and the list of installed apps corresponding to the r-th data point in the target dataset; SGW r i For A i The similarity between the corresponding gateway list and the gateway list corresponding to the r-th data in the target dataset; SBF i For A i The corresponding behavioral fingerprint similarity set, SGL i ={SGL 1 i SGL 2 j , ..., SGL r i , ..., SGL m i}, SGL r i For A i The similarity between the corresponding Geohash grid location information and the Geohash grid location information corresponding to the m-th data in the target dataset; f() is the defined function expression;

[0080] S30, Obtain MSA i =max{SA 1 i SA 2 i SA r i SA m i As A i Target similarity, if MSA i ≥S0, establish MSA i The corresponding unencrypted mobile communication ID and A i If the relationship between them is determined, then S40 is executed; otherwise, S40 is executed directly; S0 is to set the similarity threshold.

[0081] S40: Set i = i + 1. If i ≤ n, execute S10; otherwise, exit the current control program.

[0082] Specific limitations regarding the device association mechanism can be found in the limitations of the device association method described above, and will not be repeated here. Each module in the aforementioned device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0083] Embodiments of the present invention also provide a non-transitory computer-readable storage medium that can be disposed in an electronic device to store at least one instruction or at least one program related to implementing a method in the method embodiments, wherein the at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiments.

[0084] Embodiments of the present invention also provide an electronic device, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0085] Embodiments of the present invention also provide a computer program product including program code, which, when the program product is run on an electronic device, causes the electronic device to perform the steps of the methods described above in various exemplary embodiments of the present invention.

[0086] While specific embodiments of the invention have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of the invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the invention. The scope of this invention is defined by the appended claims.

Claims

1. A device association method, characterized in that, The method includes the following steps: S100, in response to receiving a device association command, obtain the basic data table for the target time period corresponding to the current time, wherein the i-th row of the basic data table includes (TN) i A i BF i ), TN i For the i-th encrypted mobile communication ID, A i For TN i Corresponding device ID i BF i For A i The corresponding behavioral fingerprint set, BF i ={WF i AP i GW i GL i }, WF i For A i The corresponding list of Wi-Fi addresses, AP i For A i The corresponding list of installed apps, GW i For A i The corresponding gateway list, GL i For A i The corresponding Geohash grid position information, GL i Based on the obtained A i The corresponding location information is determined; the value of i ranges from 1 to n, where n is the number of rows in the basic data table; S200, for TN i Obtain the mobile communication ID and TN from the original data table. i The corresponding m data points are used as the target dataset. If the target dataset is not null, execute S300; otherwise, execute S500. Each row of data in the original data table includes an unencrypted mobile communication ID, the device ID corresponding to the unencrypted mobile communication ID, and the behavior fingerprint corresponding to the device ID. S300, for A i Obtain the corresponding similarity set SA i ={SA 1 i SA 2 i SA r i SA m i }, where SA r i For A i The similarity between SA and the r-th data in the target dataset r i =f(SWF) r i SAP r i SGW r i SGL r i ), SWF r i For A i The similarity between the corresponding list of Wi-Fi addresses and the list of Wi-Fi addresses corresponding to the r-th data in the target dataset, where r ranges from 1 to m; SAP r i For A i The similarity between the corresponding list of installed apps and the list of installed apps corresponding to the r-th data point in the target dataset; SGW r i For A i The similarity between the corresponding gateway list and the gateway list corresponding to the r-th data in the target dataset; SBF i For A i The corresponding behavioral fingerprint similarity set, SBF i ={SGL 1 i SGL 2 j , ..., SGL r i , ..., SGL m i }, SGL r i For A i The similarity between the corresponding Geohash grid location information and the Geohash grid location information corresponding to the r-th data in the target dataset; f() is the defined function expression; S400, obtain MSA i =max{SA 1 i SA 2 i SA r i SA m i As A i Target similarity, if MSA i ≥S0, establish MSA i The corresponding unencrypted mobile communication ID and A i If the relationship between them is determined, then S500 is executed; otherwise, S500 is executed directly; S0 is to set the similarity threshold. S500: Set i = i + 1. If i ≤ n, execute S200; otherwise, exit the current control program.

2. The method according to claim 1, characterized in that, SWF r i =(WF i ∩MWF r ) / (WF i ∪MWF r ), MWF r This is the list of Wi-Fi addresses corresponding to the r-th data in the target dataset.

3. The method according to claim 1, characterized in that, SAP r i =(AP i ∩MAP r ) / (AP i ∪MAP r ), MAP r This is the list of installed apps corresponding to the r-th data point in the target dataset.

4. The method according to claim 1, characterized in that, SGW r i =(GW i ∩MGW r ) / (GW i ∪MGW r MGW r This is the list of gateways corresponding to the r-th data in the target dataset.

5. The method according to claim 1, characterized in that, The target time period includes p consecutively arranged time windows, and the duration of the target time period L = Δt * p, where Δt is the duration of each time window; Among them, GL i ={GL 1 i GL 2 i GL 3 i }, GL 1 i GL 2 i GL 3 i These are the first stop grid position, the second stop grid position, and the third stop grid position, respectively. GL 1 i For A i The corresponding first dwell grid information set GLP 1 i ={GLP 1 i1 GLP 1 i2 GLP 1 ij GLP 1 ip The grid position corresponding to the highest word frequency in}, GLP 1 ij For A i The corresponding grid position where the device stays for the longest time within the first set time range corresponding to the j-th time window; GL 2 i For A i The corresponding second dwell grid information set GLP 2 i ={GLP 2 i1 GLP 2 i2 GLP 2 ij GLP 2 ip The grid position corresponding to the highest word frequency in}, GLP 2 ij For A i The corresponding grid position where the device stays for the longest time within the second set time range corresponding to the j-th time window; GL 3 i Based on A i The corresponding third dwell grid information set GLP 3 i ={GLP 3 i1 GLP 3 i2 GLP 3 ij GLP 3 ip Confirmed, GLP 3 ij For A i The corresponding grid position where the device stays for a longer time than a preset dwell time threshold within the j-th time window, where j ranges from 1 to p.

6. The method according to claim 5, characterized in that, SGL r i =[(GLP) 1 ij ∩GLP 1 r )+(GLP) 2 ij ∩GLP 2 r )+(GLP) 3 ij ∩GLP 3 r )] / (GLP 1 ij ∪GLP 1 r ∪GLP 2 ij ∪GLP 2 r ∪GLP 3 ij ∪GLP 3 r GLP 1 r GLP 2 r and GLP 3 r These are the first, second, and third dwell grid positions corresponding to the r-th data point in the target dataset, respectively.

7. The method according to claim 1, characterized in that, SA r i =w1*SWF r i + w2*SAP r i +w3*SGW r i +w4*SGL r i w1 to w4 are preset coefficients.

8. A device association apparatus, characterized in that, The device includes: The data acquisition module is used to, in response to a received device association command, acquire a basic data table for the target time period corresponding to the current time, wherein the i-th row of the basic data table includes (TN) i A i BF i ), TN i For the i-th encrypted mobile communication ID, A i For TN i Corresponding device ID i BF i For A i The corresponding behavioral fingerprint set, BF i ={WF i AP i GW i GL i }, WF i For A i The corresponding list of Wi-Fi addresses, AP i For A i The corresponding list of installed apps, GW i For A i The corresponding gateway list, GL i For A i The corresponding Geohash grid position information, GL i Based on the obtained A i The corresponding location information is determined; the value of i ranges from 1 to n, where n is the number of rows in the basic data table; The data processing module is used to perform the following operations: S10, for TN i Obtain the mobile communication ID and TN from the original data table. i The corresponding m data are used as the target dataset. If the target dataset is not null, execute S20; otherwise, execute S40. Each row of data in the original data table includes an unencrypted mobile communication ID, the device ID corresponding to the unencrypted mobile communication ID, and the behavior fingerprint corresponding to the device ID. S20, for A i Obtain the corresponding similarity set SA i ={SA 1 i SA 2 i SA r i SA m i }, where SA r i For A i The similarity between SA and the r-th data in the target dataset r i =f(SWF) r i SAP r i SGW r i SGL r i ), SWF r i For A i The similarity between the corresponding list of Wi-Fi addresses and the list of Wi-Fi addresses corresponding to the r-th data in the target dataset, where r ranges from 1 to m; SAP r i For A i The similarity between the corresponding list of installed apps and the list of installed apps corresponding to the r-th data point in the target dataset; SGW r i For A i The similarity between the corresponding gateway list and the gateway list corresponding to the r-th data in the target dataset; SBF i For A i The corresponding behavioral fingerprint similarity set, SBF i ={SGL 1 i SGL 2 j , ..., SGL r i , ..., SGL m i }, SGL r i For A i The similarity between the corresponding Geohash grid location information and the Geohash grid location information corresponding to the r-th data in the target dataset; f() is the defined function expression; S30, Obtain MSA i =max{SA 1 i SA 2 i SA r i SA m i As A i Target similarity, if MSA i ≥S0, establish MSA i The corresponding unencrypted mobile communication ID and A i If the relationship between them is determined, then S40 is executed; otherwise, S40 is executed directly; S0 is to set the similarity threshold. S40: Set i = i + 1. If i ≤ n, execute S10; otherwise, exit the current control program.

9. A non-transitory computer-readable storage medium, wherein the storage medium stores at least one instruction or at least one program segment, characterized in that, The at least one instruction or the at least one program segment is loaded and executed by the processor to implement the method as described in any one of claims 1-7.

10. An electronic device, characterized in that, Includes a processor and the non-transitory computer-readable storage medium as described in claim 9.

Images