Methods and apparatus for equipment connection, electronic equipment, storage media

Abstract

This application relates to the field of data processing technology and discloses a method for device connectivity detection. The method includes: obtaining the Internet Protocol (IP) addresses corresponding to multiple advertising records and the occurrence time of each advertising record, whereby the advertising records represent data records generated by devices reached by the advertised ads. Several device pairs are determined based on each IP address and occurrence time, and device connectivity features corresponding to each device pair are obtained. The device connectivity features are input into a preset prediction model to predict whether a device in each device pair is a connectivity device. This approach considers more comprehensive device connectivity features during device connectivity detection, improving the accuracy of predicting whether a device is a connectivity device. This application also discloses a device, electronic device, and storage medium for device connectivity detection.

Description

Technical Field

[0001] This application relates to the field of data processing technology, such as a method and apparatus for device interconnection, electronic devices, and storage media. Background Technology

[0002] With the advancement of technology and the emergence of "multi-screen" devices such as smartphones, tablets, computers, and internet TVs, discussions on multi-screen marketing are becoming increasingly frequent. A core argument is "multi-screen integration." Typically, an individual owns multiple devices across smartphones, tablets, computers, and internet TVs. Multi-screen integration helps determine which smart devices belong to the same person. It can help identify multiple devices belonging to the same consumer, providing them with a similar brand consumption experience. Multi-screen integration can help advertising platforms optimize their placement strategies, avoiding excessive ad exposure to the same person across different devices. Furthermore, multi-screen integration enables device-to-person calculations, helping advertisers understand how many people their ads on each device have truly and effectively reached.

[0003] In the process of implementing the embodiments of this disclosure, at least the following problems were found in the related art:

[0004] Related technologies consider few device connectivity features when performing device connectivity analysis, resulting in poor accuracy in predicting whether a device is a connectivity device. Summary of the Invention

[0005] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0006] This disclosure provides a method, apparatus, electronic device, and storage medium for device connectivity testing, which can improve the accuracy of determining whether a device to be predicted is a connectivity device.

[0007] In some embodiments, the method for device connectivity includes: obtaining the Internet Protocol (IP) addresses corresponding to multiple advertising records and the occurrence time of each advertising record, wherein the advertising records are used to characterize data records generated by devices reached by the advertised ads. Several device pairs are determined based on each IP address and each occurrence time, and device connectivity features corresponding to each device pair are obtained. The device connectivity features include the number of pairings of the device pair, the number of active days of the device, the number of exposures of the device, the number of devices associated with the connectivity IP address, the number of device pairings, whether the active IP address of the device is consistent with the connectivity IP address, the percentage of exposures of the device on the connectivity IP address, the percentage of active days of the device on the connectivity IP address, a first percentage of the number of exposures of the device on the connectivity IP address relative to the total number of exposures of the device, and a second percentage of the number of active days of the device on the connectivity IP address relative to the total number of active days of the device; the connectivity IP address is the IP address corresponding to the device pair; the active IP address is the IP address with the most exposures. The device connectivity features are input into a preset prediction model to predict whether the devices in each device pair are connectivity devices.

[0008] In some embodiments, obtaining the Internet Protocol (IP) addresses corresponding to each of the multiple advertising records and the occurrence time of each advertising record includes: obtaining advertising log data, wherein the advertising log data includes multiple advertising records; and extracting the Internet Protocol (IP) addresses corresponding to each of the advertising records and the occurrence time of each advertising record from the advertising log data.

[0009] In some embodiments, determining a plurality of device pairs based on each of the IP addresses and each of the occurrence times includes: pairing devices corresponding to advertising records whose occurrence times are within the same preset time period and whose IP addresses are the same, to obtain the device pairs.

[0010] In some embodiments, inputting the device connectivity features of each device into a preset prediction model to predict whether a device in each device pair is a connectivity device includes: inputting the device connectivity features of each device into the prediction model to obtain the device connectivity probability of each device pair; and determining whether a device in each device pair is a connectivity device based on the device connectivity probability.

[0011] In some embodiments, determining whether a device in a device pair is a connected device based on the device connection probability includes: determining that a device in a device pair is a connected device when the device connection probability is greater than or equal to a preset probability.

[0012] In some embodiments, determining whether a device in a device pair is a connected device based on the device connection probability includes: if the device connection probability is less than a preset probability, determining that the device in the device pair is not a connected device.

[0013] In some embodiments, the prediction model is obtained by: acquiring sample device pair features and corresponding sample labels, whereby the sample labels characterize whether the device pair corresponding to the sample device pair features is a connected device. The sample device pair features with the sample labels are then input into a preset model for training to obtain the prediction model.

[0014] In some embodiments, the device for device connectivity includes: a first acquisition module configured to acquire the Internet Protocol (IP) addresses corresponding to multiple advertising records and the occurrence time of each advertising record; the advertising records are used to characterize data records generated by devices reached by the delivered advertisements. A determination module configured to determine a plurality of device pairs based on each IP address and each occurrence time. A second acquisition module configured to acquire device connectivity features corresponding to each device pair. The device connectivity features include the number of pairings of the device pair, the number of active days of the device, the number of exposures of the device, the number of devices associated with the connectivity IP address, the number of pairings of the device, whether the active IP address of the device is consistent with the connectivity IP address, the percentage of exposures of the device on the connectivity IP address, the percentage of active days of the device on the connectivity IP address, a first percentage of the number of exposures of the device on the connectivity IP address relative to the total number of exposures of the device, and a second percentage of the number of active days of the device on the connectivity IP address relative to the total number of active days of the device. The connectivity IP address is the IP address corresponding to the device pair, and the active IP address is the IP address with the most exposures. The prediction module is configured to input the connectivity features of each device into a preset prediction model and predict whether the device in each device pair is a connectivity device.

[0015] In some embodiments, the electronic device includes a processor and a memory storing program instructions, the processor being configured to execute the above-described method for device connectivity when the program instructions are executed.

[0016] In some embodiments, the storage medium stores program instructions that, when executed, perform the above-described method for device connectivity.

[0017] The method, apparatus, electronic device, and storage medium for device connectivity provided in this disclosure can achieve the following technical effects: By considering multiple device connectivity features, such as the number of times devices are paired, the number of active days of a device, the number of times a device is exposed, the number of devices associated with a connectivity IP address, the number of paired devices, whether the active IP address of a device is consistent with the connectivity IP address, the percentage of exposures of a device on a connectivity IP address, the percentage of active days of a device on a connectivity IP address, the first percentage of exposures of a device on a connectivity IP address to the total number of exposures of the device, and the second percentage of active days of a device on a connectivity IP address to the total active days of the device, more comprehensive device connectivity features are considered when performing device connectivity, thus improving the accuracy of determining whether a device to be predicted is a connectivity device.

[0018] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0019] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein:

[0020] Figure 1 This is a schematic diagram of a method for device connection provided in an embodiment of this disclosure;

[0021] Figure 2 This is a schematic diagram of another method for device connection provided in an embodiment of this disclosure;

[0022] Figure 3 This is a schematic diagram of another method for device connection provided in an embodiment of this disclosure;

[0023] Figure 4 This is a schematic diagram of a method for obtaining a prediction model provided in an embodiment of this disclosure;

[0024] Figure 5 This is a schematic diagram of a device for enabling device connectivity provided in an embodiment of this disclosure;

[0025] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0026] To provide a more detailed understanding of the features and technical content of the embodiments of this disclosure, the implementation of the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this disclosure. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0027] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0028] Unless otherwise stated, the term "multiple" means two or more.

[0029] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0030] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0031] The term "correspondence" can refer to an association or binding relationship. The correspondence between A and B means that there is an association or binding relationship between A and B.

[0032] The technical solutions in the embodiments of the present invention can be applied to electronic devices such as computers or servers.

[0033] In this embodiment of the invention, data mining of advertising records yields various device connectivity features, such as the number of device pairings, the number of active days for a device, the number of times a device is exposed, the number of devices associated with a connectivity IP address, the number of device pairings, whether the active IP address of a device matches the connectivity IP address, the percentage of exposures of a device on a connectivity IP address, the percentage of active days of a device on a connectivity IP address, the first percentage of exposures of a device on a connectivity IP address relative to the total number of exposures of the device, and the second percentage of active days of a device on a connectivity IP address relative to the total active days of the device. These device connectivity features allow for the identification of connectivity relationships between devices, regardless of television media, television manufacturers, geographical location, or time, enabling more accurate prediction of whether devices in a device pair are connectivity devices.

[0034] Combination Figure 1 As shown in the embodiments of this disclosure, a method for device connection is provided, the method comprising:

[0035] In step S101, the electronic device obtains the Internet Protocol (IP) addresses corresponding to multiple advertising records and the occurrence time of each advertising record. Advertising records are used to represent data records generated by devices that have been reached by the delivered advertisements.

[0036] In step S102, the electronic device determines several device pairs based on each IP address and each occurrence time.

[0037] Step S103: The electronic device acquires the device connectivity features corresponding to each device pair. These features include the number of times devices are paired within the device pair, the number of active days for the device, the number of times the device is exposed, the number of devices associated with the connectivity IP address, the number of device pairs, whether the active IP address of the device matches the connectivity IP address, the percentage of exposures of the device on the connectivity IP address, the percentage of active days of the device on the connectivity IP address, the first percentage of the device's exposures on the connectivity IP address relative to the total number of device exposures, and the second percentage of the device's active days on the connectivity IP address relative to the total number of active days of the device. The connectivity IP address is the IP address corresponding to the device pair, and the active IP address is the IP address with the most exposures.

[0038] In step S104, the electronic device inputs the connection features of each device into a preset prediction model to predict whether the device in each device pair is a connection device.

[0039] The method for device connectivity provided in this disclosure considers multiple device connectivity features, including the number of times devices are paired, the number of active days of a device, the number of times a device is exposed, the number of devices associated with a connectivity IP address, the number of device pairings, whether the active IP address of a device is consistent with the connectivity IP address, the percentage of exposures of a device on a connectivity IP address, the percentage of active days of a device on a connectivity IP address, the first percentage of exposures of a device on a connectivity IP address relative to the total number of device exposures, and the second percentage of active days of a device on a connectivity IP address relative to the total number of active days of a device. This approach considers more comprehensive device connectivity features during device connectivity analysis, improving the accuracy of predicting whether a device is a connectivity device.

[0040] Furthermore, the electronic device obtains the Internet Protocol (IP) addresses corresponding to multiple advertising records and the occurrence time of each advertising record, including: the electronic device obtains advertising log data, which includes multiple advertising records. The IP address corresponding to each advertising record and the occurrence time of each advertising record are extracted from the advertising log data. In this way, because advertising log data is easily obtained, and by extracting the IP addresses and occurrence times corresponding to advertising records from the advertising log data, users can easily uncover the interconnectivity between devices, and it is not easily limited by television media, television manufacturers, geographical location, or time.

[0041] Furthermore, the electronic device determines several device pairs based on the IP address and occurrence time of each advertising record. This includes pairing devices corresponding to advertising records that occur within the same preset time period and have the same IP address to obtain device pairs.

[0042] In some embodiments, the devices corresponding to each advertising record include mobile phone 1, mobile phone 2, mobile phone 3, TV 1, TV 2, and TV 3. If the occurrence times of each advertising record are all within the same preset time period and their IP addresses are all the same, then mobile phone 1, mobile phone 2, mobile phone 3, TV 1, TV 2, and TV 3 are paired up to obtain device pairs. The IP address is then identified as the connection IP address. For example, the device pairs are "Mobile Phone 1-TV 1", "Mobile Phone 1-TV 2", "Mobile Phone 1-TV 3", "Mobile Phone 2-TV 1", "Mobile Phone 2-TV 2", "Mobile Phone 2-TV 3", "Mobile Phone 3-TV 1", "Mobile Phone 3-TV 2", or "Mobile Phone 3-TV 3", etc.

[0043] Combination Figure 2 As shown in the embodiments of this disclosure, a method for device connection is provided, the method comprising:

[0044] In step S201, the electronic device acquires advertising log data; the advertising log data includes multiple advertising records. Advertising records are used to characterize the data generated by devices that have been reached by the delivered advertisements.

[0045] In step S202, the electronic device extracts the Internet Protocol IP address corresponding to each advertising record and the occurrence time of each advertising record from the advertising log data.

[0046] In step S203, the electronic device pairs up the devices corresponding to the advertising records that occurred within the same preset time period and had the same IP address to obtain device pairs.

[0047] Step S204: The electronic device acquires the device connectivity features corresponding to each device pair. These features include the number of times devices are paired within the device pair, the number of active days for the device, the number of times the device is exposed, the number of devices associated with the connectivity IP address, the number of device pairs, whether the active IP address of the device matches the connectivity IP address, the percentage of exposures of the device on the connectivity IP address, the percentage of active days of the device on the connectivity IP address, the first percentage of the device's exposures on the connectivity IP address relative to the total number of device exposures, and the second percentage of the device's active days on the connectivity IP address relative to the total number of active days of the device. The connectivity IP address is the IP address corresponding to the device pair, and the active IP address is the IP address with the most exposures.

[0048] In step S205, the electronic device inputs the connection features of each device into a preset prediction model to predict whether the device in each device pair is a connection device.

[0049] The device pairing method provided in this disclosure utilizes data mining capabilities to extract device pair features from advertising log data, thereby obtaining the pairing relationship between devices. This method is not limited by television media, television manufacturers, region, or time, and can more accurately predict whether a device in a pair is a pairing device. Furthermore, by considering multiple device pairing features, it takes into account more comprehensive device pairing characteristics, improving the accuracy of predicting whether a device is a pairing device.

[0050] Optionally, the device connectivity feature includes the number of times the devices in a device pair are paired. The electronic device obtains the device connectivity feature corresponding to each device pair, including: when a device pair triggers a preset pairing condition on multiple preset time periods or multiple IP addresses, the number of triggers is counted to obtain the number of pairings of the device pair. The preset pairing condition is that the occurrence time is within the same preset time period and the IP address is the same.

[0051] Optionally, the device connectivity features include the number of active days of the devices in the device pair. The electronic device obtains the device connectivity features corresponding to each device pair, including: counting the number of active days of each device in the device pair within a preset time period.

[0052] Optionally, the device connection feature includes the number of times the device is exposed to the device. The electronic device acquires the device connection feature corresponding to each device pair, including: counting the number of times each device is exposed to the device pair within a preset time period.

[0053] Optionally, the device connectivity features include the number of devices associated with the connectivity IP address. The electronic device obtains the device connectivity features corresponding to each device, including: counting the number of devices that have been exposed on the connectivity IP address to obtain the number of devices associated with the connectivity IP address.

[0054] Optionally, the device connectivity feature includes the number of device pairs. The electronic device obtains the device connectivity feature corresponding to each device pair, including: counting the number of device pairs that include the device, and obtaining the number of pairs for each device. For example, if device 1 is paired with device 2 and device 3, then there are two device pairs that include device 1, and the number of pairs for device 1 is 2.

[0055] Optionally, the device connectivity feature includes whether the device's active IP address is consistent with the connectivity IP address. The electronic device obtains the device connectivity features corresponding to each device, including: determining the IP address that generates the most exposure for the device as the active IP address of the device, and determining whether the active IP address of the device is consistent with the connectivity IP address of the device.

[0056] Optionally, the device connectivity features include the percentage of times a device is exposed on a connectivity IP address. Electronic devices acquire the connectivity features of each device for their respective corresponding IP addresses, including: counting the number of times a device is exposed on a connectivity IP address and the total number of times that device is exposed on that connectivity IP address, and calculating Z1 = B1 / Z. 总 Obtain the percentage of times the device was exposed on the connected IP address. Where Z1 is the percentage of times the device was exposed on the connected IP address, B1 is the number of times the device was exposed on the connected IP address, and Z... 总 This represents the total number of times the IP address has been accessed.

[0057] Optionally, the device connectivity characteristics include the percentage of active days for the device on the connected IP address. Electronic devices acquire connectivity characteristics for each device, including: counting the number of active days for the device on the connected IP address and the total number of active days for the connected IP address, and calculating Z2 = H1 / H. 总 Obtain the percentage of days the device was active on the connected IP address. Where Z2 represents the percentage of days the device was active on the connected IP address, H1 represents the total number of days the device was active on the connected IP address, and H... 总 This represents the total number of active days for the connected IP address.

[0058] Optionally, the device connectivity feature includes the first proportion of the device's exposure count on the connectivity IP address to the device's total exposure count. The electronic device acquires the connectivity features for each device, including: counting the number of active days the device has on the connectivity IP address and the device's total active days, and calculating Z3 = B1 / S. 总 The percentage of device exposures on the connected IP address relative to the total device exposures is calculated. Specifically, Z3 represents the percentage of device exposures on the connected IP address relative to the total device exposures, B1 represents the number of device exposures on the connected IP address, and S... 总 This represents the total number of exposures for the device.

[0059] Optionally, the device connectivity characteristics include the second ratio of the number of days the device is active on the connected IP address to the total number of active days of the device. Electronic devices acquire the connectivity characteristics of each device for their respective corresponding devices, including: statistically analyzing the number of days the device is active on the connected IP address and the total number of active days of the device, and calculating Z4 = H1 / Y. 总 The second percentage of the device's active days on the connected IP address out of the device's total active days. Here, Z4 represents the second percentage of the device's active days on the connected IP address out of the device's total active days, H1 represents the device's active days on the connected IP address, and Y... 总 This represents the total number of active days for the device.

[0060] Furthermore, the electronic device inputs the connectivity features of each device into a preset prediction model to predict whether a device in each device pair is a connectivity device. This includes: the electronic device using the connectivity feature prediction model to obtain the connectivity probability of each device pair; and determining whether a device in each device pair is a connectivity device based on the connectivity probability.

[0061] Furthermore, the electronic device determines whether the device in the device pair is the successfully connected device based on the device connection probability, including: the electronic device determines that the device in the device pair is the successfully connected device when the device connection probability is greater than or equal to a preset probability. The preset probability is 0.5.

[0062] Optionally, the electronic device determines whether the paired device is a successful device based on the device success probability, including: if the device success probability is less than a preset probability, the electronic device determines that the paired device is not a successful device. The preset probability is 0.5.

[0063] In some embodiments, if the device connection probability is greater than or equal to 0.5, the device in the device pair is determined to be a connected device; or, if the device connection probability is less than 0.5, the device in the device pair is determined not to be a connected device.

[0064] Combination Figure 3 As shown in the embodiments of this disclosure, a method for device connection is provided, the method comprising:

[0065] In step S301, the electronic device obtains the Internet Protocol (IP) addresses corresponding to multiple advertising records and the occurrence time of each advertising record. The advertising records are used to represent the data records generated by devices that have been reached by the advertised ads.

[0066] In step S302, the electronic device determines several device pairs based on each IP address and each occurrence time.

[0067] Step S303: The electronic device acquires the device connectivity features corresponding to each device pair. These features include the number of times devices are paired within the device pair, the number of active days for the device, the number of times the device is exposed, the number of devices associated with the connectivity IP address, the number of device pairs, whether the active IP address of the device matches the connectivity IP address, the percentage of exposures of the device on the connectivity IP address, the percentage of active days of the device on the connectivity IP address, the first percentage of the device's exposures on the connectivity IP address relative to the total number of device exposures, and the second percentage of the device's active days on the connectivity IP address relative to the total number of active days of the device. The connectivity IP address is the IP address corresponding to the device pair, and the active IP address is the IP address with the most exposures.

[0068] In step S304, the electronic device uses the device connectivity feature prediction model to obtain the device connectivity probability of each device pair.

[0069] Step S305: The electronic device determines whether the device paired with each device is a successful device based on the success probability of each device.

[0070] The device connection method provided in this disclosure considers multiple device connection features, thus taking into account more comprehensive device connection features during the connection process and improving the accuracy of predicting whether a device is a connection device. Simultaneously, a preset prediction model is used to predict the device connection probability of a device pair, making it easier for users to determine whether a device in a device pair is a connection device.

[0071] Furthermore, the electronic device prediction model is obtained through the following methods: The electronic device acquires sample device pair features and corresponding sample labels, whereby the sample labels characterize whether the device pair corresponding to the sample device pair features is a connected device. The sample device pair features with sample labels are then input into a pre-defined model for training to obtain the prediction model. The pre-defined model is a tree model. For example, tree models include Random Forest, GBDT (Gradient Boosting Decision Tree), LightGBM (Light Gradient Boosting Machine), Xgboost (Extreme Gradient Boosting), or catboost (Categorical Features + Gradient Boosting) models, etc.

[0072] Furthermore, the sample device with sample labels is used to train the feature input preset model to obtain the prediction model, including: training the sample device with sample labels to train multiple preset models to obtain candidate models corresponding to each preset model; and using model fusion technology to fuse the candidate models to obtain the prediction model.

[0073] In some embodiments, a first candidate model is obtained by training a labeled sample device on a feature input random forest model; a second candidate model is obtained by training a labeled sample device on a feature input GBDT model; a third candidate model is obtained by training a labeled sample device on a feature input LightGBM model; a fourth candidate model is obtained by training a labeled sample device on a feature input xgboost model; and a fifth candidate model is obtained by training a labeled sample device on a feature input catboost model. Model fusion techniques are then used to fuse the first, second, third, fourth, and fifth candidate models to obtain a prediction model.

[0074] Furthermore, model fusion techniques include averaging, voting, or stacking fusion methods.

[0075] In some embodiments, the averaging method involves obtaining the average of the predicted probabilities output by each candidate model. Here, the predicted probability is the success probability.

[0076] In some embodiments, the voting method involves obtaining the judgment results predicted by each candidate model and determining the judgment result with the most votes as the judgment result of the prediction model. The judgment result refers to whether the device in the device pair is a connected device.

[0077] In some embodiments, the stacking fusion method involves obtaining the judgment results predicted by each candidate model, acquiring the sample labels of each predicted judgment result, and determining the predicted judgment results as training samples. The training samples with sample labels are then input into a simple model for training to obtain a prediction model. The simple model includes a tree model and a logistic regression model.

[0078] Combination Figure 4 As shown in the embodiments of this disclosure, a method for obtaining a prediction model is provided, the method comprising:

[0079] Step S401: The electronic device acquires the sample device pair features and the corresponding sample labels. The sample labels are used to characterize whether the device pair corresponding to the sample device pair features is a connected device.

[0080] In step S402, the electronic device trains multiple preset models by inputting the sample devices with sample labels to obtain alternative models corresponding to each preset model.

[0081] In step S403, the electronic device uses model fusion technology to fuse the candidate models to obtain a prediction model.

[0082] The method for obtaining a prediction model provided in this disclosure involves training multiple preset models to obtain multiple candidate models, and then using model fusion technology to fuse the candidate models to obtain a prediction model. This makes the prediction model more accurate and allows users to use the prediction model to predict whether the device in the device is a connected device.

[0083] Combination Figure 5 As shown in the figure, this disclosure provides an apparatus for device connectivity, comprising: a first acquisition module 501, a determination module 502, a second acquisition module 503, and a prediction module 504. The first acquisition module 501 is configured to acquire the Internet Protocol (IP) addresses corresponding to multiple advertising records and the occurrence time of each advertising record, and send the IP addresses and occurrence times corresponding to the advertising records to the determination module. Advertising records are used to characterize data records generated by devices reached by the advertised ads. The determination module 502 is configured to receive the IP addresses and occurrence times corresponding to the advertising records, determine several device pairs based on each IP address and occurrence time, and send the device pairs to the second acquisition module. The second acquisition module 503 is configured to acquire the device pairs sent by the determination module, acquire device connectivity features corresponding to each device pair, and send the device connectivity features to the prediction module. The device connectivity features include the number of pairings between devices in a device pair, the number of active days of the device, the number of exposures of the device, the number of devices associated with the connectivity IP address, the number of device pairings, whether the active IP address of the device matches the connectivity IP address, the percentage of exposures of the device on the connectivity IP address, the percentage of active days of the device on the connectivity IP address, the first percentage of exposures of the device on the connectivity IP address relative to the total number of exposures of the device, and the second percentage of active days of the device on the connectivity IP address relative to the total number of active days of the device. The connectivity IP address is the IP address corresponding to the device pair, and the active IP address is the IP address with the most exposures. The prediction module 504 is configured to receive the device connectivity features sent by the second acquisition module and input each device connectivity feature into a preset prediction model to predict whether the devices in each device pair are connectivity devices.

[0084] The device for device connectivity provided in this embodiment acquires the Internet Protocol (IP) addresses corresponding to multiple advertising records and the occurrence time of each advertising record through a first acquisition module. The advertising records represent data records generated by devices reached by the advertised ads. A determination module identifies several device pairs based on each IP address and occurrence time. A second acquisition module acquires the device connectivity features corresponding to each device pair. A prediction module inputs the device connectivity features into a preset prediction model to predict whether the devices in each device pair are connectivity devices. By considering various device connectivity features, such as the number of pairings of devices in a device pair, the number of active days of the device, the number of exposures of the device, the number of devices associated with the connectivity IP address, the number of device pairings, whether the active IP address of the device matches the connectivity IP address, the percentage of exposures of the device on the connectivity IP address, the percentage of active days of the device on the connectivity IP address, the first proportion of the number of exposures of the device on the connectivity IP address to the total number of device exposures, and the second proportion of the number of active days of the device on the connectivity IP address to the total number of active days of the device, more comprehensive device connectivity features are considered during device connectivity analysis, improving the accuracy of predicting whether a device is a connectivity device.

[0085] Furthermore, the first acquisition module is configured to acquire the Internet Protocol IP address corresponding to each of the multiple advertising records and the occurrence time of each advertising record by acquiring advertising log data, which includes multiple advertising records, and extracting the Internet Protocol IP address corresponding to each advertising record and the occurrence time of each advertising record from the advertising log data.

[0086] Furthermore, the determination module is configured to determine several device pairs based on each IP address and each occurrence time in the following way: pairing devices corresponding to advertising records that occur within the same preset time period and have the same IP address to obtain device pairs.

[0087] Furthermore, the prediction module is configured to input the device connectivity features of each device into a preset prediction model in the following way, and predict whether the device in each device pair is a connectivity device: input the device connectivity feature prediction model of each device to obtain the device connectivity probability of each device pair, and determine whether the device in each device pair is a connectivity device based on the device connectivity probability.

[0088] Furthermore, determining whether a device in a device pair is a successfully connected device based on the device connection probability includes: determining that a device in a device pair is a successfully connected device when the device connection probability is greater than or equal to a preset probability.

[0089] Furthermore, determining whether a device in a device pair is a successfully connected device based on the device connection probability includes: determining that a device in a device pair is not a successfully connected device if the device connection probability is less than a preset probability.

[0090] Furthermore, the device for device connectivity also includes a third acquisition module, which is configured to acquire the prediction model by: acquiring sample device pair features and corresponding sample labels, whereby the sample labels characterize whether the device pair corresponding to the sample device pair features is a connectivity device; and inputting the sample device pair features with sample labels into a preset model for training to obtain the prediction model.

[0091] Combination Figure 6 As shown, this disclosure provides an electronic device including a processor 600 and a memory 601. Optionally, the electronic device may further include a communication interface 602 and a bus 603. The processor 600, communication interface 602, and memory 601 can communicate with each other via the bus 603. The communication interface 602 can be used for information transmission. The processor 600 can call logical instructions in the memory 601 to execute the device connection method described in the above embodiment.

[0092] The electronic device provided in this disclosure considers a variety of device connectivity features, including the number of times the device is paired with another device, the number of active days of the device, the number of times the device is exposed, the number of devices associated with the connected IP address, the number of device pairings, whether the active IP address of the device is consistent with the connected IP address, the percentage of the number of times the device is exposed on the connected IP address, the percentage of the number of active days of the device on the connected IP address, the first percentage of the number of times the device is exposed on the connected IP address to the total number of device exposures, and the second percentage of the number of active days of the device on the connected IP address to the total number of active days of the device. This approach considers more comprehensive device connectivity features when performing device connectivity analysis, thereby improving the accuracy of predicting whether a device is a connected device.

[0093] Furthermore, the logic instructions in the aforementioned memory 601 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0094] Alternatively, the electronic device may include a computer, tablet computer, or server.

[0095] The memory 601, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 600 executes functional applications and data processing by running the program instructions / modules stored in the memory 601, thereby implementing the method for device connectivity described in the above embodiments.

[0096] The memory 601 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 601 may include high-speed random access memory and may also include non-volatile memory.

[0097] This disclosure provides a storage medium storing program instructions, which, when executed, perform the aforementioned method for device connectivity.

[0098] This disclosure provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions that, when executed by a computer, cause the computer to perform the aforementioned method for device connectivity.

[0099] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0100] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure. The aforementioned storage medium can be a non-transitory storage medium, including: a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media capable of storing program code; it can also be a transient storage medium.

[0101] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0102] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0103] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. Furthermore, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0104] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for connecting equipment, characterized in that, include: Obtain the Internet Protocol IP address corresponding to each of the multiple advertising records and the occurrence time of each advertising record; The advertising records are used to characterize the data records generated by devices that have been reached by the advertising; Several device pairs are determined based on the IP addresses and the times of occurrence. Obtain the device connectivity features corresponding to each device pair; the device connectivity features include the number of pairings of the device pair, the number of active days of the device, the number of exposures of the device, the number of devices associated with the connectivity IP address, the number of pairings of the device, whether the active IP address of the device is consistent with the connectivity IP address, the percentage of exposures of the device on the connectivity IP address, the percentage of active days of the device on the connectivity IP address, the first percentage of the number of exposures of the device on the connectivity IP address to the total number of exposures of the device, and the second percentage of the number of active days of the device on the connectivity IP address to the total number of active days of the device; the connectivity IP address is the IP address corresponding to the device pair; the active IP address is the IP address with the most exposures; Input the device connectivity features of each device into the prediction model to obtain the device connectivity probability of each device pair; Determine whether the device in each device pair is a successful device based on the success probability of each device; The prediction model is obtained in the following way: Obtain sample device pair features and corresponding sample labels for the sample device pair features; the sample labels are used to characterize whether the device pair corresponding to the sample device pair features is a connected device. The sample devices with sample labels are used to train multiple preset models by inputting features into them, thereby obtaining candidate models corresponding to each preset model. The model fusion technique is used to fuse the candidate models to obtain the prediction model; Model fusion techniques include averaging, voting, or stacking fusion methods.

2. The method according to claim 1, characterized in that, The step of obtaining the Internet Protocol (IP) addresses corresponding to multiple advertising records and the occurrence time of each advertising record includes: Obtain advertising log data; the advertising log data includes multiple advertising records; Extract the Internet Protocol IP address corresponding to each advertising record and the occurrence time of each advertising record from the advertising log data.

3. The method according to claim 1, characterized in that, Several device pairs are determined based on the IP addresses and the times of occurrence, including: Devices corresponding to advertising records that occur within the same preset time period and have the same IP address are paired up to obtain the device pairs.

4. The method according to claim 1, characterized in that, Determining whether the device in the device pair is a successful device based on the success probability of the device connection includes: If the probability of the device being connected is greater than or equal to a preset probability, then the device in the device pair is determined to be the connected device.

5. The method according to claim 1, characterized in that, Determining whether the device in the device pair is a successful device based on the success probability of the device connection includes: If the probability of a device being connected is less than a preset probability, then the device in the device pair is determined not to be a connected device.

6. A device for connecting equipment, characterized in that, include: The first acquisition module is configured to acquire the Internet Protocol IP address corresponding to each of the multiple advertising records and the occurrence time of each advertising record; The advertising records are used to characterize the data records generated by devices that have been reached by the advertising; The determination module is configured to determine several device pairs based on each of the IP addresses and each of the occurrence times; The second acquisition module is configured to acquire device connectivity features corresponding to each device pair; the device connectivity features include the number of pairings of the device pair, the number of active days of the device, the number of exposures of the device, the number of devices associated with the connectivity IP address, the number of pairings of the device, whether the active IP address of the device is consistent with the connectivity IP address, the percentage of exposures of the device on the connectivity IP address, the percentage of active days of the device on the connectivity IP address, the first percentage of the number of exposures of the device on the connectivity IP address to the total number of exposures of the device, and the second percentage of the number of active days of the device on the connectivity IP address to the total number of active days of the device; the connectivity IP address is the IP address corresponding to the device pair; the active IP address is the IP address with the most exposures; The prediction module is configured to input the connectivity features of each device into a preset prediction model and predict whether a device in each device pair is a connectivity device. Specifically, the prediction module is configured to input the connectivity features of each device into the preset prediction model and predict whether a device in each device pair is a connectivity device by: inputting the connectivity features of each device into the prediction model to obtain the connectivity probability of each device pair; and determining whether a device in each device pair is a connectivity device based on the connectivity probability. The prediction model is obtained in the following way: Obtain sample device pair features and corresponding sample labels for the sample device pair features; the sample labels are used to characterize whether the device pair corresponding to the sample device pair features is a connected device. The sample devices with sample labels are used to train multiple preset models by inputting features into them, thereby obtaining candidate models corresponding to each preset model. The model fusion technique is used to fuse the candidate models to obtain the prediction model; Model fusion techniques include averaging, voting, or stacking fusion methods.

7. An electronic device comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to execute, when running the program instructions, the method for device connectivity as described in any one of claims 1 to 5.

8. A storage medium storing program instructions, characterized in that, When the program instructions are executed, they perform the method for device connection as described in any one of claims 1 to 5.

Images